linux/kernel/sched/fair.c

8357 lines
217 KiB
C
Raw Normal View History

/*
* Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH)
*
* Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
*
* Interactivity improvements by Mike Galbraith
* (C) 2007 Mike Galbraith <efault@gmx.de>
*
* Various enhancements by Dmitry Adamushko.
* (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com>
*
* Group scheduling enhancements by Srivatsa Vaddagiri
* Copyright IBM Corporation, 2007
* Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
*
* Scaled math optimizations by Thomas Gleixner
* Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
*
* Adaptive scheduling granularity, math enhancements by Peter Zijlstra
* Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
*/
#include <linux/latencytop.h>
#include <linux/sched.h>
#include <linux/cpumask.h>
sched/fair: Leverage the idle state info when choosing the "idlest" cpu The code in find_idlest_cpu() looks for the CPU with the smallest load. However, if multiple CPUs are idle, the first idle CPU is selected irrespective of the depth of its idle state. Among the idle CPUs we should pick the one with with the shallowest idle state, or the latest to have gone idle if all idle CPUs are in the same state. The later applies even when cpuidle is configured out. This patch doesn't cover the following issues: - The idle exit latency of a CPU might be larger than the time needed to migrate the waking task to an already running CPU with sufficient capacity, and therefore performance would benefit from task packing in such case (in most cases task packing is about power saving). - Some idle states have a non negligible and non abortable entry latency which needs to run to completion before the exit latency can start. A concurrent patch series is making this info available to the cpuidle core. Once available, the entry latency with the idle timestamp could determine when the exit latency may be effective. Those issues will be handled in due course. In the mean time, what is implemented here should improve things already compared to the current state of affairs. Based on an initial patch from Daniel Lezcano. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: linux-pm@vger.kernel.org Cc: linaro-kernel@lists.linaro.org Link: http://lkml.kernel.org/n/tip-@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-09-04 15:32:10 +00:00
#include <linux/cpuidle.h>
#include <linux/slab.h>
#include <linux/profile.h>
#include <linux/interrupt.h>
#include <linux/mempolicy.h>
#include <linux/migrate.h>
#include <linux/task_work.h>
#include <trace/events/sched.h>
#include "sched.h"
/*
* Targeted preemption latency for CPU-bound tasks:
* (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
*
* NOTE: this latency value is not the same as the concept of
* 'timeslice length' - timeslices in CFS are of variable length
* and have no persistent notion like in traditional, time-slice
* based scheduling concepts.
*
* (to see the precise effective timeslice length of your workload,
* run vmstat and monitor the context-switches (cs) field)
*/
unsigned int sysctl_sched_latency = 6000000ULL;
unsigned int normalized_sysctl_sched_latency = 6000000ULL;
/*
* The initial- and re-scaling of tunables is configurable
* (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus))
*
* Options are:
* SCHED_TUNABLESCALING_NONE - unscaled, always *1
* SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus)
* SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus
*/
enum sched_tunable_scaling sysctl_sched_tunable_scaling
= SCHED_TUNABLESCALING_LOG;
/*
* Minimal preemption granularity for CPU-bound tasks:
* (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
*/
unsigned int sysctl_sched_min_granularity = 750000ULL;
unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
/*
* is kept at sysctl_sched_latency / sysctl_sched_min_granularity
*/
static unsigned int sched_nr_latency = 8;
/*
* After fork, child runs first. If set to 0 (default) then
* parent will (try to) run first.
*/
unsigned int sysctl_sched_child_runs_first __read_mostly;
/*
* SCHED_OTHER wake-up granularity.
* (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
*
* This option delays the preemption effects of decoupled workloads
* and reduces their over-scheduling. Synchronous workloads will still
* have immediate wakeup/sleep latencies.
*/
unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;
const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
/*
* The exponential sliding window over which load is averaged for shares
* distribution.
* (default: 10msec)
*/
unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
#ifdef CONFIG_CFS_BANDWIDTH
/*
* Amount of runtime to allocate from global (tg) to local (per-cfs_rq) pool
* each time a cfs_rq requests quota.
*
* Note: in the case that the slice exceeds the runtime remaining (either due
* to consumption or the quota being specified to be smaller than the slice)
* we will always only issue the remaining available time.
*
* default: 5 msec, units: microseconds
*/
unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
#endif
static inline void update_load_add(struct load_weight *lw, unsigned long inc)
{
lw->weight += inc;
lw->inv_weight = 0;
}
static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
{
lw->weight -= dec;
lw->inv_weight = 0;
}
static inline void update_load_set(struct load_weight *lw, unsigned long w)
{
lw->weight = w;
lw->inv_weight = 0;
}
/*
* Increase the granularity value when there are more CPUs,
* because with more CPUs the 'effective latency' as visible
* to users decreases. But the relationship is not linear,
* so pick a second-best guess by going with the log2 of the
* number of CPUs.
*
* This idea comes from the SD scheduler of Con Kolivas:
*/
static unsigned int get_update_sysctl_factor(void)
{
unsigned int cpus = min_t(unsigned int, num_online_cpus(), 8);
unsigned int factor;
switch (sysctl_sched_tunable_scaling) {
case SCHED_TUNABLESCALING_NONE:
factor = 1;
break;
case SCHED_TUNABLESCALING_LINEAR:
factor = cpus;
break;
case SCHED_TUNABLESCALING_LOG:
default:
factor = 1 + ilog2(cpus);
break;
}
return factor;
}
static void update_sysctl(void)
{
unsigned int factor = get_update_sysctl_factor();
#define SET_SYSCTL(name) \
(sysctl_##name = (factor) * normalized_sysctl_##name)
SET_SYSCTL(sched_min_granularity);
SET_SYSCTL(sched_latency);
SET_SYSCTL(sched_wakeup_granularity);
#undef SET_SYSCTL
}
void sched_init_granularity(void)
{
update_sysctl();
}
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
#define WMULT_CONST (~0U)
#define WMULT_SHIFT 32
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
static void __update_inv_weight(struct load_weight *lw)
{
unsigned long w;
if (likely(lw->inv_weight))
return;
w = scale_load_down(lw->weight);
if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
lw->inv_weight = 1;
else if (unlikely(!w))
lw->inv_weight = WMULT_CONST;
else
lw->inv_weight = WMULT_CONST / w;
}
/*
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
* delta_exec * weight / lw.weight
* OR
* (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT
*
* Either weight := NICE_0_LOAD and lw \e prio_to_wmult[], in which case
* we're guaranteed shift stays positive because inv_weight is guaranteed to
* fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22.
*
* Or, weight =< lw.weight (because lw.weight is the runqueue weight), thus
* weight/lw.weight <= 1, and therefore our shift will also be positive.
*/
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw)
{
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
u64 fact = scale_load_down(weight);
int shift = WMULT_SHIFT;
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
__update_inv_weight(lw);
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
if (unlikely(fact >> 32)) {
while (fact >> 32) {
fact >>= 1;
shift--;
}
}
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
/* hint to use a 32x32->64 mul */
fact = (u64)(u32)fact * lw->inv_weight;
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
while (fact >> 32) {
fact >>= 1;
shift--;
}
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
return mul_u64_u32_shr(delta_exec, fact, shift);
}
const struct sched_class fair_sched_class;
/**************************************************************
* CFS operations on generic schedulable entities:
*/
#ifdef CONFIG_FAIR_GROUP_SCHED
/* cpu runqueue to which this cfs_rq is attached */
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
{
return cfs_rq->rq;
}
/* An entity is a task if it doesn't "own" a runqueue */
#define entity_is_task(se) (!se->my_q)
static inline struct task_struct *task_of(struct sched_entity *se)
{
#ifdef CONFIG_SCHED_DEBUG
WARN_ON_ONCE(!entity_is_task(se));
#endif
return container_of(se, struct task_struct, se);
}
/* Walk up scheduling entities hierarchy */
#define for_each_sched_entity(se) \
for (; se; se = se->parent)
static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
return p->se.cfs_rq;
}
/* runqueue on which this entity is (to be) queued */
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
return se->cfs_rq;
}
/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
return grp->my_q;
}
static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
if (!cfs_rq->on_list) {
/*
* Ensure we either appear before our parent (if already
* enqueued) or force our parent to appear after us when it is
* enqueued. The fact that we always enqueue bottom-up
* reduces this to two cases.
*/
if (cfs_rq->tg->parent &&
cfs_rq->tg->parent->cfs_rq[cpu_of(rq_of(cfs_rq))]->on_list) {
list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
&rq_of(cfs_rq)->leaf_cfs_rq_list);
} else {
list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
&rq_of(cfs_rq)->leaf_cfs_rq_list);
}
cfs_rq->on_list = 1;
}
}
static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
if (cfs_rq->on_list) {
list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
cfs_rq->on_list = 0;
}
}
/* Iterate thr' all leaf cfs_rq's on a runqueue */
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
/* Do the two (enqueued) entities belong to the same group ? */
static inline struct cfs_rq *
is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
if (se->cfs_rq == pse->cfs_rq)
return se->cfs_rq;
return NULL;
}
static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
return se->parent;
}
static void
find_matching_se(struct sched_entity **se, struct sched_entity **pse)
{
int se_depth, pse_depth;
/*
* preemption test can be made between sibling entities who are in the
* same cfs_rq i.e who have a common parent. Walk up the hierarchy of
* both tasks until we find their ancestors who are siblings of common
* parent.
*/
/* First walk up until both entities are at same depth */
se_depth = (*se)->depth;
pse_depth = (*pse)->depth;
while (se_depth > pse_depth) {
se_depth--;
*se = parent_entity(*se);
}
while (pse_depth > se_depth) {
pse_depth--;
*pse = parent_entity(*pse);
}
while (!is_same_group(*se, *pse)) {
*se = parent_entity(*se);
*pse = parent_entity(*pse);
}
}
#else /* !CONFIG_FAIR_GROUP_SCHED */
static inline struct task_struct *task_of(struct sched_entity *se)
{
return container_of(se, struct task_struct, se);
}
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
{
return container_of(cfs_rq, struct rq, cfs);
}
#define entity_is_task(se) 1
#define for_each_sched_entity(se) \
for (; se; se = NULL)
static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
return &task_rq(p)->cfs;
}
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
struct task_struct *p = task_of(se);
struct rq *rq = task_rq(p);
return &rq->cfs;
}
/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
return NULL;
}
static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
}
static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
}
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
return NULL;
}
static inline void
find_matching_se(struct sched_entity **se, struct sched_entity **pse)
{
}
#endif /* CONFIG_FAIR_GROUP_SCHED */
static __always_inline
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec);
/**************************************************************
* Scheduling class tree data structure manipulation methods:
*/
static inline u64 max_vruntime(u64 max_vruntime, u64 vruntime)
{
s64 delta = (s64)(vruntime - max_vruntime);
if (delta > 0)
max_vruntime = vruntime;
return max_vruntime;
}
static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
{
s64 delta = (s64)(vruntime - min_vruntime);
if (delta < 0)
min_vruntime = vruntime;
return min_vruntime;
}
static inline int entity_before(struct sched_entity *a,
struct sched_entity *b)
{
return (s64)(a->vruntime - b->vruntime) < 0;
}
static void update_min_vruntime(struct cfs_rq *cfs_rq)
{
u64 vruntime = cfs_rq->min_vruntime;
if (cfs_rq->curr)
vruntime = cfs_rq->curr->vruntime;
if (cfs_rq->rb_leftmost) {
struct sched_entity *se = rb_entry(cfs_rq->rb_leftmost,
struct sched_entity,
run_node);
if (!cfs_rq->curr)
vruntime = se->vruntime;
else
vruntime = min_vruntime(vruntime, se->vruntime);
}
/* ensure we never gain time by being placed backwards. */
cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
#ifndef CONFIG_64BIT
smp_wmb();
cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
#endif
}
/*
* Enqueue an entity into the rb-tree:
*/
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
struct rb_node *parent = NULL;
struct sched_entity *entry;
int leftmost = 1;
/*
* Find the right place in the rbtree:
*/
while (*link) {
parent = *link;
entry = rb_entry(parent, struct sched_entity, run_node);
/*
* We dont care about collisions. Nodes with
* the same key stay together.
*/
if (entity_before(se, entry)) {
link = &parent->rb_left;
} else {
link = &parent->rb_right;
leftmost = 0;
}
}
/*
* Maintain a cache of leftmost tree entries (it is frequently
* used):
*/
if (leftmost)
cfs_rq->rb_leftmost = &se->run_node;
rb_link_node(&se->run_node, parent, link);
rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
}
static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
if (cfs_rq->rb_leftmost == &se->run_node) {
struct rb_node *next_node;
next_node = rb_next(&se->run_node);
cfs_rq->rb_leftmost = next_node;
}
rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
}
struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *left = cfs_rq->rb_leftmost;
if (!left)
return NULL;
return rb_entry(left, struct sched_entity, run_node);
}
static struct sched_entity *__pick_next_entity(struct sched_entity *se)
{
struct rb_node *next = rb_next(&se->run_node);
if (!next)
return NULL;
return rb_entry(next, struct sched_entity, run_node);
}
#ifdef CONFIG_SCHED_DEBUG
struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
if (!last)
return NULL;
return rb_entry(last, struct sched_entity, run_node);
}
/**************************************************************
* Scheduling class statistics methods:
*/
int sched_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
unsigned int factor = get_update_sysctl_factor();
if (ret || !write)
return ret;
sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency,
sysctl_sched_min_granularity);
#define WRT_SYSCTL(name) \
(normalized_sysctl_##name = sysctl_##name / (factor))
WRT_SYSCTL(sched_min_granularity);
WRT_SYSCTL(sched_latency);
WRT_SYSCTL(sched_wakeup_granularity);
#undef WRT_SYSCTL
return 0;
}
#endif
/*
* delta /= w
*/
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se)
{
if (unlikely(se->load.weight != NICE_0_LOAD))
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
delta = __calc_delta(delta, NICE_0_LOAD, &se->load);
return delta;
}
/*
* The idea is to set a period in which each task runs once.
*
* When there are too many tasks (sched_nr_latency) we have to stretch
* this period because otherwise the slices get too small.
*
* p = (nr <= nl) ? l : l*nr/nl
*/
static u64 __sched_period(unsigned long nr_running)
{
if (unlikely(nr_running > sched_nr_latency))
return nr_running * sysctl_sched_min_granularity;
else
return sysctl_sched_latency;
}
/*
* We calculate the wall-time slice from the period by taking a part
* proportional to the weight.
*
* s = p*P[w/rw]
*/
static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq);
for_each_sched_entity(se) {
struct load_weight *load;
struct load_weight lw;
cfs_rq = cfs_rq_of(se);
load = &cfs_rq->load;
if (unlikely(!se->on_rq)) {
lw = cfs_rq->load;
update_load_add(&lw, se->load.weight);
load = &lw;
}
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
slice = __calc_delta(slice, se->load.weight, load);
}
return slice;
}
/*
* We calculate the vruntime slice of a to-be-inserted task.
*
* vs = s/w
*/
static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
return calc_delta_fair(sched_slice(cfs_rq, se), se);
}
sched: Set an initial value of runnable avg for new forked task We need to initialize the se.avg.{decay_count, load_avg_contrib} for a new forked task. Otherwise random values of above variables cause a mess when a new task is enqueued: enqueue_task_fair enqueue_entity enqueue_entity_load_avg and make fork balancing imbalance due to incorrect load_avg_contrib. Further more, Morten Rasmussen notice some tasks were not launched at once after created. So Paul and Peter suggest giving a start value for new task runnable avg time same as sched_slice(). PeterZ said: > So the 'problem' is that our running avg is a 'floating' average; ie. it > decays with time. Now we have to guess about the future of our newly > spawned task -- something that is nigh impossible seeing these CPU > vendors keep refusing to implement the crystal ball instruction. > > So there's two asymptotic cases we want to deal well with; 1) the case > where the newly spawned program will be 'nearly' idle for its lifetime; > and 2) the case where its cpu-bound. > > Since we have to guess, we'll go for worst case and assume its > cpu-bound; now we don't want to make the avg so heavy adjusting to the > near-idle case takes forever. We want to be able to quickly adjust and > lower our running avg. > > Now we also don't want to make our avg too light, such that it gets > decremented just for the new task not having had a chance to run yet -- > even if when it would run, it would be more cpu-bound than not. > > So what we do is we make the initial avg of the same duration as that we > guess it takes to run each task on the system at least once -- aka > sched_slice(). > > Of course we can defeat this with wakeup/fork bombs, but in the 'normal' > case it should be good enough. Paul also contributed most of the code comments in this commit. Signed-off-by: Alex Shi <alex.shi@intel.com> Reviewed-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Reviewed-by: Paul Turner <pjt@google.com> [peterz; added explanation of sched_slice() usage] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1371694737-29336-4-git-send-email-alex.shi@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-06-20 02:18:47 +00:00
#ifdef CONFIG_SMP
static int select_idle_sibling(struct task_struct *p, int cpu);
static unsigned long task_h_load(struct task_struct *p);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
/*
* We choose a half-life close to 1 scheduling period.
* Note: The tables below are dependent on this value.
*/
#define LOAD_AVG_PERIOD 32
#define LOAD_AVG_MAX 47742 /* maximum possible load avg */
#define LOAD_AVG_MAX_N 345 /* number of full periods to produce LOAD_MAX_AVG */
sched: Set an initial value of runnable avg for new forked task We need to initialize the se.avg.{decay_count, load_avg_contrib} for a new forked task. Otherwise random values of above variables cause a mess when a new task is enqueued: enqueue_task_fair enqueue_entity enqueue_entity_load_avg and make fork balancing imbalance due to incorrect load_avg_contrib. Further more, Morten Rasmussen notice some tasks were not launched at once after created. So Paul and Peter suggest giving a start value for new task runnable avg time same as sched_slice(). PeterZ said: > So the 'problem' is that our running avg is a 'floating' average; ie. it > decays with time. Now we have to guess about the future of our newly > spawned task -- something that is nigh impossible seeing these CPU > vendors keep refusing to implement the crystal ball instruction. > > So there's two asymptotic cases we want to deal well with; 1) the case > where the newly spawned program will be 'nearly' idle for its lifetime; > and 2) the case where its cpu-bound. > > Since we have to guess, we'll go for worst case and assume its > cpu-bound; now we don't want to make the avg so heavy adjusting to the > near-idle case takes forever. We want to be able to quickly adjust and > lower our running avg. > > Now we also don't want to make our avg too light, such that it gets > decremented just for the new task not having had a chance to run yet -- > even if when it would run, it would be more cpu-bound than not. > > So what we do is we make the initial avg of the same duration as that we > guess it takes to run each task on the system at least once -- aka > sched_slice(). > > Of course we can defeat this with wakeup/fork bombs, but in the 'normal' > case it should be good enough. Paul also contributed most of the code comments in this commit. Signed-off-by: Alex Shi <alex.shi@intel.com> Reviewed-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Reviewed-by: Paul Turner <pjt@google.com> [peterz; added explanation of sched_slice() usage] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1371694737-29336-4-git-send-email-alex.shi@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-06-20 02:18:47 +00:00
/* Give new sched_entity start runnable values to heavy its load in infant time */
void init_entity_runnable_average(struct sched_entity *se)
sched: Set an initial value of runnable avg for new forked task We need to initialize the se.avg.{decay_count, load_avg_contrib} for a new forked task. Otherwise random values of above variables cause a mess when a new task is enqueued: enqueue_task_fair enqueue_entity enqueue_entity_load_avg and make fork balancing imbalance due to incorrect load_avg_contrib. Further more, Morten Rasmussen notice some tasks were not launched at once after created. So Paul and Peter suggest giving a start value for new task runnable avg time same as sched_slice(). PeterZ said: > So the 'problem' is that our running avg is a 'floating' average; ie. it > decays with time. Now we have to guess about the future of our newly > spawned task -- something that is nigh impossible seeing these CPU > vendors keep refusing to implement the crystal ball instruction. > > So there's two asymptotic cases we want to deal well with; 1) the case > where the newly spawned program will be 'nearly' idle for its lifetime; > and 2) the case where its cpu-bound. > > Since we have to guess, we'll go for worst case and assume its > cpu-bound; now we don't want to make the avg so heavy adjusting to the > near-idle case takes forever. We want to be able to quickly adjust and > lower our running avg. > > Now we also don't want to make our avg too light, such that it gets > decremented just for the new task not having had a chance to run yet -- > even if when it would run, it would be more cpu-bound than not. > > So what we do is we make the initial avg of the same duration as that we > guess it takes to run each task on the system at least once -- aka > sched_slice(). > > Of course we can defeat this with wakeup/fork bombs, but in the 'normal' > case it should be good enough. Paul also contributed most of the code comments in this commit. Signed-off-by: Alex Shi <alex.shi@intel.com> Reviewed-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Reviewed-by: Paul Turner <pjt@google.com> [peterz; added explanation of sched_slice() usage] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1371694737-29336-4-git-send-email-alex.shi@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-06-20 02:18:47 +00:00
{
struct sched_avg *sa = &se->avg;
sched: Set an initial value of runnable avg for new forked task We need to initialize the se.avg.{decay_count, load_avg_contrib} for a new forked task. Otherwise random values of above variables cause a mess when a new task is enqueued: enqueue_task_fair enqueue_entity enqueue_entity_load_avg and make fork balancing imbalance due to incorrect load_avg_contrib. Further more, Morten Rasmussen notice some tasks were not launched at once after created. So Paul and Peter suggest giving a start value for new task runnable avg time same as sched_slice(). PeterZ said: > So the 'problem' is that our running avg is a 'floating' average; ie. it > decays with time. Now we have to guess about the future of our newly > spawned task -- something that is nigh impossible seeing these CPU > vendors keep refusing to implement the crystal ball instruction. > > So there's two asymptotic cases we want to deal well with; 1) the case > where the newly spawned program will be 'nearly' idle for its lifetime; > and 2) the case where its cpu-bound. > > Since we have to guess, we'll go for worst case and assume its > cpu-bound; now we don't want to make the avg so heavy adjusting to the > near-idle case takes forever. We want to be able to quickly adjust and > lower our running avg. > > Now we also don't want to make our avg too light, such that it gets > decremented just for the new task not having had a chance to run yet -- > even if when it would run, it would be more cpu-bound than not. > > So what we do is we make the initial avg of the same duration as that we > guess it takes to run each task on the system at least once -- aka > sched_slice(). > > Of course we can defeat this with wakeup/fork bombs, but in the 'normal' > case it should be good enough. Paul also contributed most of the code comments in this commit. Signed-off-by: Alex Shi <alex.shi@intel.com> Reviewed-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Reviewed-by: Paul Turner <pjt@google.com> [peterz; added explanation of sched_slice() usage] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1371694737-29336-4-git-send-email-alex.shi@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-06-20 02:18:47 +00:00
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
sa->last_update_time = 0;
/*
* sched_avg's period_contrib should be strictly less then 1024, so
* we give it 1023 to make sure it is almost a period (1024us), and
* will definitely be update (after enqueue).
*/
sa->period_contrib = 1023;
sa->load_avg = scale_load_down(se->load.weight);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
sa->util_avg = scale_load_down(SCHED_LOAD_SCALE);
sa->util_sum = LOAD_AVG_MAX;
/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
sched: Set an initial value of runnable avg for new forked task We need to initialize the se.avg.{decay_count, load_avg_contrib} for a new forked task. Otherwise random values of above variables cause a mess when a new task is enqueued: enqueue_task_fair enqueue_entity enqueue_entity_load_avg and make fork balancing imbalance due to incorrect load_avg_contrib. Further more, Morten Rasmussen notice some tasks were not launched at once after created. So Paul and Peter suggest giving a start value for new task runnable avg time same as sched_slice(). PeterZ said: > So the 'problem' is that our running avg is a 'floating' average; ie. it > decays with time. Now we have to guess about the future of our newly > spawned task -- something that is nigh impossible seeing these CPU > vendors keep refusing to implement the crystal ball instruction. > > So there's two asymptotic cases we want to deal well with; 1) the case > where the newly spawned program will be 'nearly' idle for its lifetime; > and 2) the case where its cpu-bound. > > Since we have to guess, we'll go for worst case and assume its > cpu-bound; now we don't want to make the avg so heavy adjusting to the > near-idle case takes forever. We want to be able to quickly adjust and > lower our running avg. > > Now we also don't want to make our avg too light, such that it gets > decremented just for the new task not having had a chance to run yet -- > even if when it would run, it would be more cpu-bound than not. > > So what we do is we make the initial avg of the same duration as that we > guess it takes to run each task on the system at least once -- aka > sched_slice(). > > Of course we can defeat this with wakeup/fork bombs, but in the 'normal' > case it should be good enough. Paul also contributed most of the code comments in this commit. Signed-off-by: Alex Shi <alex.shi@intel.com> Reviewed-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Reviewed-by: Paul Turner <pjt@google.com> [peterz; added explanation of sched_slice() usage] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1371694737-29336-4-git-send-email-alex.shi@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-06-20 02:18:47 +00:00
}
static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq);
sched: Set an initial value of runnable avg for new forked task We need to initialize the se.avg.{decay_count, load_avg_contrib} for a new forked task. Otherwise random values of above variables cause a mess when a new task is enqueued: enqueue_task_fair enqueue_entity enqueue_entity_load_avg and make fork balancing imbalance due to incorrect load_avg_contrib. Further more, Morten Rasmussen notice some tasks were not launched at once after created. So Paul and Peter suggest giving a start value for new task runnable avg time same as sched_slice(). PeterZ said: > So the 'problem' is that our running avg is a 'floating' average; ie. it > decays with time. Now we have to guess about the future of our newly > spawned task -- something that is nigh impossible seeing these CPU > vendors keep refusing to implement the crystal ball instruction. > > So there's two asymptotic cases we want to deal well with; 1) the case > where the newly spawned program will be 'nearly' idle for its lifetime; > and 2) the case where its cpu-bound. > > Since we have to guess, we'll go for worst case and assume its > cpu-bound; now we don't want to make the avg so heavy adjusting to the > near-idle case takes forever. We want to be able to quickly adjust and > lower our running avg. > > Now we also don't want to make our avg too light, such that it gets > decremented just for the new task not having had a chance to run yet -- > even if when it would run, it would be more cpu-bound than not. > > So what we do is we make the initial avg of the same duration as that we > guess it takes to run each task on the system at least once -- aka > sched_slice(). > > Of course we can defeat this with wakeup/fork bombs, but in the 'normal' > case it should be good enough. Paul also contributed most of the code comments in this commit. Signed-off-by: Alex Shi <alex.shi@intel.com> Reviewed-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Reviewed-by: Paul Turner <pjt@google.com> [peterz; added explanation of sched_slice() usage] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1371694737-29336-4-git-send-email-alex.shi@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-06-20 02:18:47 +00:00
#else
void init_entity_runnable_average(struct sched_entity *se)
sched: Set an initial value of runnable avg for new forked task We need to initialize the se.avg.{decay_count, load_avg_contrib} for a new forked task. Otherwise random values of above variables cause a mess when a new task is enqueued: enqueue_task_fair enqueue_entity enqueue_entity_load_avg and make fork balancing imbalance due to incorrect load_avg_contrib. Further more, Morten Rasmussen notice some tasks were not launched at once after created. So Paul and Peter suggest giving a start value for new task runnable avg time same as sched_slice(). PeterZ said: > So the 'problem' is that our running avg is a 'floating' average; ie. it > decays with time. Now we have to guess about the future of our newly > spawned task -- something that is nigh impossible seeing these CPU > vendors keep refusing to implement the crystal ball instruction. > > So there's two asymptotic cases we want to deal well with; 1) the case > where the newly spawned program will be 'nearly' idle for its lifetime; > and 2) the case where its cpu-bound. > > Since we have to guess, we'll go for worst case and assume its > cpu-bound; now we don't want to make the avg so heavy adjusting to the > near-idle case takes forever. We want to be able to quickly adjust and > lower our running avg. > > Now we also don't want to make our avg too light, such that it gets > decremented just for the new task not having had a chance to run yet -- > even if when it would run, it would be more cpu-bound than not. > > So what we do is we make the initial avg of the same duration as that we > guess it takes to run each task on the system at least once -- aka > sched_slice(). > > Of course we can defeat this with wakeup/fork bombs, but in the 'normal' > case it should be good enough. Paul also contributed most of the code comments in this commit. Signed-off-by: Alex Shi <alex.shi@intel.com> Reviewed-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Reviewed-by: Paul Turner <pjt@google.com> [peterz; added explanation of sched_slice() usage] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1371694737-29336-4-git-send-email-alex.shi@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-06-20 02:18:47 +00:00
{
}
#endif
/*
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
* Update the current task's runtime statistics.
*/
static void update_curr(struct cfs_rq *cfs_rq)
{
struct sched_entity *curr = cfs_rq->curr;
u64 now = rq_clock_task(rq_of(cfs_rq));
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
u64 delta_exec;
if (unlikely(!curr))
return;
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
delta_exec = now - curr->exec_start;
if (unlikely((s64)delta_exec <= 0))
return;
curr->exec_start = now;
sched: cpu accounting controller (V2) Commit cfb5285660aad4931b2ebbfa902ea48a37dfffa1 removed a useful feature for us, which provided a cpu accounting resource controller. This feature would be useful if someone wants to group tasks only for accounting purpose and doesnt really want to exercise any control over their cpu consumption. The patch below reintroduces the feature. It is based on Paul Menage's original patch (Commit 62d0df64065e7c135d0002f069444fbdfc64768f), with these differences: - Removed load average information. I felt it needs more thought (esp to deal with SMP and virtualized platforms) and can be added for 2.6.25 after more discussions. - Convert group cpu usage to be nanosecond accurate (as rest of the cfs stats are) and invoke cpuacct_charge() from the respective scheduler classes - Make accounting scalable on SMP systems by splitting the usage counter to be per-cpu - Move the code from kernel/cpu_acct.c to kernel/sched.c (since the code is not big enough to warrant a new file and also this rightly needs to live inside the scheduler. Also things like accessing rq->lock while reading cpu usage becomes easier if the code lived in kernel/sched.c) The patch also modifies the cpu controller not to provide the same accounting information. Tested-by: Balbir Singh <balbir@linux.vnet.ibm.com> Tested the patches on top of 2.6.24-rc3. The patches work fine. Ran some simple tests like cpuspin (spin on the cpu), ran several tasks in the same group and timed them. Compared their time stamps with cpuacct.usage. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-12-02 19:04:49 +00:00
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
schedstat_set(curr->statistics.exec_max,
max(delta_exec, curr->statistics.exec_max));
curr->sum_exec_runtime += delta_exec;
schedstat_add(cfs_rq, exec_clock, delta_exec);
curr->vruntime += calc_delta_fair(delta_exec, curr);
update_min_vruntime(cfs_rq);
sched: cpu accounting controller (V2) Commit cfb5285660aad4931b2ebbfa902ea48a37dfffa1 removed a useful feature for us, which provided a cpu accounting resource controller. This feature would be useful if someone wants to group tasks only for accounting purpose and doesnt really want to exercise any control over their cpu consumption. The patch below reintroduces the feature. It is based on Paul Menage's original patch (Commit 62d0df64065e7c135d0002f069444fbdfc64768f), with these differences: - Removed load average information. I felt it needs more thought (esp to deal with SMP and virtualized platforms) and can be added for 2.6.25 after more discussions. - Convert group cpu usage to be nanosecond accurate (as rest of the cfs stats are) and invoke cpuacct_charge() from the respective scheduler classes - Make accounting scalable on SMP systems by splitting the usage counter to be per-cpu - Move the code from kernel/cpu_acct.c to kernel/sched.c (since the code is not big enough to warrant a new file and also this rightly needs to live inside the scheduler. Also things like accessing rq->lock while reading cpu usage becomes easier if the code lived in kernel/sched.c) The patch also modifies the cpu controller not to provide the same accounting information. Tested-by: Balbir Singh <balbir@linux.vnet.ibm.com> Tested the patches on top of 2.6.24-rc3. The patches work fine. Ran some simple tests like cpuspin (spin on the cpu), ran several tasks in the same group and timed them. Compared their time stamps with cpuacct.usage. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-12-02 19:04:49 +00:00
if (entity_is_task(curr)) {
struct task_struct *curtask = task_of(curr);
trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime);
sched: cpu accounting controller (V2) Commit cfb5285660aad4931b2ebbfa902ea48a37dfffa1 removed a useful feature for us, which provided a cpu accounting resource controller. This feature would be useful if someone wants to group tasks only for accounting purpose and doesnt really want to exercise any control over their cpu consumption. The patch below reintroduces the feature. It is based on Paul Menage's original patch (Commit 62d0df64065e7c135d0002f069444fbdfc64768f), with these differences: - Removed load average information. I felt it needs more thought (esp to deal with SMP and virtualized platforms) and can be added for 2.6.25 after more discussions. - Convert group cpu usage to be nanosecond accurate (as rest of the cfs stats are) and invoke cpuacct_charge() from the respective scheduler classes - Make accounting scalable on SMP systems by splitting the usage counter to be per-cpu - Move the code from kernel/cpu_acct.c to kernel/sched.c (since the code is not big enough to warrant a new file and also this rightly needs to live inside the scheduler. Also things like accessing rq->lock while reading cpu usage becomes easier if the code lived in kernel/sched.c) The patch also modifies the cpu controller not to provide the same accounting information. Tested-by: Balbir Singh <balbir@linux.vnet.ibm.com> Tested the patches on top of 2.6.24-rc3. The patches work fine. Ran some simple tests like cpuspin (spin on the cpu), ran several tasks in the same group and timed them. Compared their time stamps with cpuacct.usage. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-12-02 19:04:49 +00:00
cpuacct_charge(curtask, delta_exec);
timers: fix itimer/many thread hang Overview This patch reworks the handling of POSIX CPU timers, including the ITIMER_PROF, ITIMER_VIRT timers and rlimit handling. It was put together with the help of Roland McGrath, the owner and original writer of this code. The problem we ran into, and the reason for this rework, has to do with using a profiling timer in a process with a large number of threads. It appears that the performance of the old implementation of run_posix_cpu_timers() was at least O(n*3) (where "n" is the number of threads in a process) or worse. Everything is fine with an increasing number of threads until the time taken for that routine to run becomes the same as or greater than the tick time, at which point things degrade rather quickly. This patch fixes bug 9906, "Weird hang with NPTL and SIGPROF." Code Changes This rework corrects the implementation of run_posix_cpu_timers() to make it run in constant time for a particular machine. (Performance may vary between one machine and another depending upon whether the kernel is built as single- or multiprocessor and, in the latter case, depending upon the number of running processors.) To do this, at each tick we now update fields in signal_struct as well as task_struct. The run_posix_cpu_timers() function uses those fields to make its decisions. We define a new structure, "task_cputime," to contain user, system and scheduler times and use these in appropriate places: struct task_cputime { cputime_t utime; cputime_t stime; unsigned long long sum_exec_runtime; }; This is included in the structure "thread_group_cputime," which is a new substructure of signal_struct and which varies for uniprocessor versus multiprocessor kernels. For uniprocessor kernels, it uses "task_cputime" as a simple substructure, while for multiprocessor kernels it is a pointer: struct thread_group_cputime { struct task_cputime totals; }; struct thread_group_cputime { struct task_cputime *totals; }; We also add a new task_cputime substructure directly to signal_struct, to cache the earliest expiration of process-wide timers, and task_cputime also replaces the it_*_expires fields of task_struct (used for earliest expiration of thread timers). The "thread_group_cputime" structure contains process-wide timers that are updated via account_user_time() and friends. In the non-SMP case the structure is a simple aggregator; unfortunately in the SMP case that simplicity was not achievable due to cache-line contention between CPUs (in one measured case performance was actually _worse_ on a 16-cpu system than the same test on a 4-cpu system, due to this contention). For SMP, the thread_group_cputime counters are maintained as a per-cpu structure allocated using alloc_percpu(). The timer functions update only the timer field in the structure corresponding to the running CPU, obtained using per_cpu_ptr(). We define a set of inline functions in sched.h that we use to maintain the thread_group_cputime structure and hide the differences between UP and SMP implementations from the rest of the kernel. The thread_group_cputime_init() function initializes the thread_group_cputime structure for the given task. The thread_group_cputime_alloc() is a no-op for UP; for SMP it calls the out-of-line function thread_group_cputime_alloc_smp() to allocate and fill in the per-cpu structures and fields. The thread_group_cputime_free() function, also a no-op for UP, in SMP frees the per-cpu structures. The thread_group_cputime_clone_thread() function (also a UP no-op) for SMP calls thread_group_cputime_alloc() if the per-cpu structures haven't yet been allocated. The thread_group_cputime() function fills the task_cputime structure it is passed with the contents of the thread_group_cputime fields; in UP it's that simple but in SMP it must also safely check that tsk->signal is non-NULL (if it is it just uses the appropriate fields of task_struct) and, if so, sums the per-cpu values for each online CPU. Finally, the three functions account_group_user_time(), account_group_system_time() and account_group_exec_runtime() are used by timer functions to update the respective fields of the thread_group_cputime structure. Non-SMP operation is trivial and will not be mentioned further. The per-cpu structure is always allocated when a task creates its first new thread, via a call to thread_group_cputime_clone_thread() from copy_signal(). It is freed at process exit via a call to thread_group_cputime_free() from cleanup_signal(). All functions that formerly summed utime/stime/sum_sched_runtime values from from all threads in the thread group now use thread_group_cputime() to snapshot the values in the thread_group_cputime structure or the values in the task structure itself if the per-cpu structure hasn't been allocated. Finally, the code in kernel/posix-cpu-timers.c has changed quite a bit. The run_posix_cpu_timers() function has been split into a fast path and a slow path; the former safely checks whether there are any expired thread timers and, if not, just returns, while the slow path does the heavy lifting. With the dedicated thread group fields, timers are no longer "rebalanced" and the process_timer_rebalance() function and related code has gone away. All summing loops are gone and all code that used them now uses the thread_group_cputime() inline. When process-wide timers are set, the new task_cputime structure in signal_struct is used to cache the earliest expiration; this is checked in the fast path. Performance The fix appears not to add significant overhead to existing operations. It generally performs the same as the current code except in two cases, one in which it performs slightly worse (Case 5 below) and one in which it performs very significantly better (Case 2 below). Overall it's a wash except in those two cases. I've since done somewhat more involved testing on a dual-core Opteron system. Case 1: With no itimer running, for a test with 100,000 threads, the fixed kernel took 1428.5 seconds, 513 seconds more than the unfixed system, all of which was spent in the system. There were twice as many voluntary context switches with the fix as without it. Case 2: With an itimer running at .01 second ticks and 4000 threads (the most an unmodified kernel can handle), the fixed kernel ran the test in eight percent of the time (5.8 seconds as opposed to 70 seconds) and had better tick accuracy (.012 seconds per tick as opposed to .023 seconds per tick). Case 3: A 4000-thread test with an initial timer tick of .01 second and an interval of 10,000 seconds (i.e. a timer that ticks only once) had very nearly the same performance in both cases: 6.3 seconds elapsed for the fixed kernel versus 5.5 seconds for the unfixed kernel. With fewer threads (eight in these tests), the Case 1 test ran in essentially the same time on both the modified and unmodified kernels (5.2 seconds versus 5.8 seconds). The Case 2 test ran in about the same time as well, 5.9 seconds versus 5.4 seconds but again with much better tick accuracy, .013 seconds per tick versus .025 seconds per tick for the unmodified kernel. Since the fix affected the rlimit code, I also tested soft and hard CPU limits. Case 4: With a hard CPU limit of 20 seconds and eight threads (and an itimer running), the modified kernel was very slightly favored in that while it killed the process in 19.997 seconds of CPU time (5.002 seconds of wall time), only .003 seconds of that was system time, the rest was user time. The unmodified kernel killed the process in 20.001 seconds of CPU (5.014 seconds of wall time) of which .016 seconds was system time. Really, though, the results were too close to call. The results were essentially the same with no itimer running. Case 5: With a soft limit of 20 seconds and a hard limit of 2000 seconds (where the hard limit would never be reached) and an itimer running, the modified kernel exhibited worse tick accuracy than the unmodified kernel: .050 seconds/tick versus .028 seconds/tick. Otherwise, performance was almost indistinguishable. With no itimer running this test exhibited virtually identical behavior and times in both cases. In times past I did some limited performance testing. those results are below. On a four-cpu Opteron system without this fix, a sixteen-thread test executed in 3569.991 seconds, of which user was 3568.435s and system was 1.556s. On the same system with the fix, user and elapsed time were about the same, but system time dropped to 0.007 seconds. Performance with eight, four and one thread were comparable. Interestingly, the timer ticks with the fix seemed more accurate: The sixteen-thread test with the fix received 149543 ticks for 0.024 seconds per tick, while the same test without the fix received 58720 for 0.061 seconds per tick. Both cases were configured for an interval of 0.01 seconds. Again, the other tests were comparable. Each thread in this test computed the primes up to 25,000,000. I also did a test with a large number of threads, 100,000 threads, which is impossible without the fix. In this case each thread computed the primes only up to 10,000 (to make the runtime manageable). System time dominated, at 1546.968 seconds out of a total 2176.906 seconds (giving a user time of 629.938s). It received 147651 ticks for 0.015 seconds per tick, still quite accurate. There is obviously no comparable test without the fix. Signed-off-by: Frank Mayhar <fmayhar@google.com> Cc: Roland McGrath <roland@redhat.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-12 16:54:39 +00:00
account_group_exec_runtime(curtask, delta_exec);
sched: cpu accounting controller (V2) Commit cfb5285660aad4931b2ebbfa902ea48a37dfffa1 removed a useful feature for us, which provided a cpu accounting resource controller. This feature would be useful if someone wants to group tasks only for accounting purpose and doesnt really want to exercise any control over their cpu consumption. The patch below reintroduces the feature. It is based on Paul Menage's original patch (Commit 62d0df64065e7c135d0002f069444fbdfc64768f), with these differences: - Removed load average information. I felt it needs more thought (esp to deal with SMP and virtualized platforms) and can be added for 2.6.25 after more discussions. - Convert group cpu usage to be nanosecond accurate (as rest of the cfs stats are) and invoke cpuacct_charge() from the respective scheduler classes - Make accounting scalable on SMP systems by splitting the usage counter to be per-cpu - Move the code from kernel/cpu_acct.c to kernel/sched.c (since the code is not big enough to warrant a new file and also this rightly needs to live inside the scheduler. Also things like accessing rq->lock while reading cpu usage becomes easier if the code lived in kernel/sched.c) The patch also modifies the cpu controller not to provide the same accounting information. Tested-by: Balbir Singh <balbir@linux.vnet.ibm.com> Tested the patches on top of 2.6.24-rc3. The patches work fine. Ran some simple tests like cpuspin (spin on the cpu), ran several tasks in the same group and timed them. Compared their time stamps with cpuacct.usage. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-12-02 19:04:49 +00:00
}
account_cfs_rq_runtime(cfs_rq, delta_exec);
}
sched/cputime: Fix clock_nanosleep()/clock_gettime() inconsistency Commit d670ec13178d0 "posix-cpu-timers: Cure SMP wobbles" fixes one glibc test case in cost of breaking another one. After that commit, calling clock_nanosleep(TIMER_ABSTIME, X) and then clock_gettime(&Y) can result of Y time being smaller than X time. Reproducer/tester can be found further below, it can be compiled and ran by: gcc -o tst-cpuclock2 tst-cpuclock2.c -pthread while ./tst-cpuclock2 ; do : ; done This reproducer, when running on a buggy kernel, will complain about "clock_gettime difference too small". Issue happens because on start in thread_group_cputimer() we initialize sum_exec_runtime of cputimer with threads runtime not yet accounted and then add the threads runtime to running cputimer again on scheduler tick, making it's sum_exec_runtime bigger than actual threads runtime. KOSAKI Motohiro posted a fix for this problem, but that patch was never applied: https://lkml.org/lkml/2013/5/26/191 . This patch takes different approach to cure the problem. It calls update_curr() when cputimer starts, that assure we will have updated stats of running threads and on the next schedule tick we will account only the runtime that elapsed from cputimer start. That also assure we have consistent state between cpu times of individual threads and cpu time of the process consisted by those threads. Full reproducer (tst-cpuclock2.c): #define _GNU_SOURCE #include <unistd.h> #include <sys/syscall.h> #include <stdio.h> #include <time.h> #include <pthread.h> #include <stdint.h> #include <inttypes.h> /* Parameters for the Linux kernel ABI for CPU clocks. */ #define CPUCLOCK_SCHED 2 #define MAKE_PROCESS_CPUCLOCK(pid, clock) \ ((~(clockid_t) (pid) << 3) | (clockid_t) (clock)) static pthread_barrier_t barrier; /* Help advance the clock. */ static void *chew_cpu(void *arg) { pthread_barrier_wait(&barrier); while (1) ; return NULL; } /* Don't use the glibc wrapper. */ static int do_nanosleep(int flags, const struct timespec *req) { clockid_t clock_id = MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED); return syscall(SYS_clock_nanosleep, clock_id, flags, req, NULL); } static int64_t tsdiff(const struct timespec *before, const struct timespec *after) { int64_t before_i = before->tv_sec * 1000000000ULL + before->tv_nsec; int64_t after_i = after->tv_sec * 1000000000ULL + after->tv_nsec; return after_i - before_i; } int main(void) { int result = 0; pthread_t th; pthread_barrier_init(&barrier, NULL, 2); if (pthread_create(&th, NULL, chew_cpu, NULL) != 0) { perror("pthread_create"); return 1; } pthread_barrier_wait(&barrier); /* The test. */ struct timespec before, after, sleeptimeabs; int64_t sleepdiff, diffabs; const struct timespec sleeptime = {.tv_sec = 0,.tv_nsec = 100000000 }; /* The relative nanosleep. Not sure why this is needed, but its presence seems to make it easier to reproduce the problem. */ if (do_nanosleep(0, &sleeptime) != 0) { perror("clock_nanosleep"); return 1; } /* Get the current time. */ if (clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &before) < 0) { perror("clock_gettime[2]"); return 1; } /* Compute the absolute sleep time based on the current time. */ uint64_t nsec = before.tv_nsec + sleeptime.tv_nsec; sleeptimeabs.tv_sec = before.tv_sec + nsec / 1000000000; sleeptimeabs.tv_nsec = nsec % 1000000000; /* Sleep for the computed time. */ if (do_nanosleep(TIMER_ABSTIME, &sleeptimeabs) != 0) { perror("absolute clock_nanosleep"); return 1; } /* Get the time after the sleep. */ if (clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &after) < 0) { perror("clock_gettime[3]"); return 1; } /* The time after sleep should always be equal to or after the absolute sleep time passed to clock_nanosleep. */ sleepdiff = tsdiff(&sleeptimeabs, &after); if (sleepdiff < 0) { printf("absolute clock_nanosleep woke too early: %" PRId64 "\n", sleepdiff); result = 1; printf("Before %llu.%09llu\n", before.tv_sec, before.tv_nsec); printf("After %llu.%09llu\n", after.tv_sec, after.tv_nsec); printf("Sleep %llu.%09llu\n", sleeptimeabs.tv_sec, sleeptimeabs.tv_nsec); } /* The difference between the timestamps taken before and after the clock_nanosleep call should be equal to or more than the duration of the sleep. */ diffabs = tsdiff(&before, &after); if (diffabs < sleeptime.tv_nsec) { printf("clock_gettime difference too small: %" PRId64 "\n", diffabs); result = 1; } pthread_cancel(th); return result; } Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20141112155843.GA24803@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-11-12 15:58:44 +00:00
static void update_curr_fair(struct rq *rq)
{
update_curr(cfs_rq_of(&rq->curr->se));
}
static inline void
update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
schedstat_set(se->statistics.wait_start, rq_clock(rq_of(cfs_rq)));
}
/*
* Task is being enqueued - update stats:
*/
static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
/*
* Are we enqueueing a waiting task? (for current tasks
* a dequeue/enqueue event is a NOP)
*/
if (se != cfs_rq->curr)
update_stats_wait_start(cfs_rq, se);
}
static void
update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max,
rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start));
schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1);
schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum +
rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
#ifdef CONFIG_SCHEDSTATS
if (entity_is_task(se)) {
trace_sched_stat_wait(task_of(se),
rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
}
#endif
schedstat_set(se->statistics.wait_start, 0);
}
static inline void
update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
/*
* Mark the end of the wait period if dequeueing a
* waiting task:
*/
if (se != cfs_rq->curr)
update_stats_wait_end(cfs_rq, se);
}
/*
* We are picking a new current task - update its stats:
*/
static inline void
update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
/*
* We are starting a new run period:
*/
se->exec_start = rq_clock_task(rq_of(cfs_rq));
}
/**************************************************
* Scheduling class queueing methods:
*/
#ifdef CONFIG_NUMA_BALANCING
/*
sched/numa: Set the scan rate proportional to the memory usage of the task being scanned The NUMA PTE scan rate is controlled with a combination of the numa_balancing_scan_period_min, numa_balancing_scan_period_max and numa_balancing_scan_size. This scan rate is independent of the size of the task and as an aside it is further complicated by the fact that numa_balancing_scan_size controls how many pages are marked pte_numa and not how much virtual memory is scanned. In combination, it is almost impossible to meaningfully tune the min and max scan periods and reasoning about performance is complex when the time to complete a full scan is is partially a function of the tasks memory size. This patch alters the semantic of the min and max tunables to be about tuning the length time it takes to complete a scan of a tasks occupied virtual address space. Conceptually this is a lot easier to understand. There is a "sanity" check to ensure the scan rate is never extremely fast based on the amount of virtual memory that should be scanned in a second. The default of 2.5G seems arbitrary but it is to have the maximum scan rate after the patch roughly match the maximum scan rate before the patch was applied. On a similar note, numa_scan_period is in milliseconds and not jiffies. Properly placed pages slow the scanning rate but adding 10 jiffies to numa_scan_period means that the rate scanning slows depends on HZ which is confusing. Get rid of the jiffies_to_msec conversion and treat it as ms. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1381141781-10992-18-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-07 10:28:55 +00:00
* Approximate time to scan a full NUMA task in ms. The task scan period is
* calculated based on the tasks virtual memory size and
* numa_balancing_scan_size.
*/
sched/numa: Set the scan rate proportional to the memory usage of the task being scanned The NUMA PTE scan rate is controlled with a combination of the numa_balancing_scan_period_min, numa_balancing_scan_period_max and numa_balancing_scan_size. This scan rate is independent of the size of the task and as an aside it is further complicated by the fact that numa_balancing_scan_size controls how many pages are marked pte_numa and not how much virtual memory is scanned. In combination, it is almost impossible to meaningfully tune the min and max scan periods and reasoning about performance is complex when the time to complete a full scan is is partially a function of the tasks memory size. This patch alters the semantic of the min and max tunables to be about tuning the length time it takes to complete a scan of a tasks occupied virtual address space. Conceptually this is a lot easier to understand. There is a "sanity" check to ensure the scan rate is never extremely fast based on the amount of virtual memory that should be scanned in a second. The default of 2.5G seems arbitrary but it is to have the maximum scan rate after the patch roughly match the maximum scan rate before the patch was applied. On a similar note, numa_scan_period is in milliseconds and not jiffies. Properly placed pages slow the scanning rate but adding 10 jiffies to numa_scan_period means that the rate scanning slows depends on HZ which is confusing. Get rid of the jiffies_to_msec conversion and treat it as ms. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1381141781-10992-18-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-07 10:28:55 +00:00
unsigned int sysctl_numa_balancing_scan_period_min = 1000;
unsigned int sysctl_numa_balancing_scan_period_max = 60000;
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
/* Portion of address space to scan in MB */
unsigned int sysctl_numa_balancing_scan_size = 256;
mm: sched: numa: Implement slow start for working set sampling Add a 1 second delay before starting to scan the working set of a task and starting to balance it amongst nodes. [ note that before the constant per task WSS sampling rate patch the initial scan would happen much later still, in effect that patch caused this regression. ] The theory is that short-run tasks benefit very little from NUMA placement: they come and go, and they better stick to the node they were started on. As tasks mature and rebalance to other CPUs and nodes, so does their NUMA placement have to change and so does it start to matter more and more. In practice this change fixes an observable kbuild regression: # [ a perf stat --null --repeat 10 test of ten bzImage builds to /dev/shm ] !NUMA: 45.291088843 seconds time elapsed ( +- 0.40% ) 45.154231752 seconds time elapsed ( +- 0.36% ) +NUMA, no slow start: 46.172308123 seconds time elapsed ( +- 0.30% ) 46.343168745 seconds time elapsed ( +- 0.25% ) +NUMA, 1 sec slow start: 45.224189155 seconds time elapsed ( +- 0.25% ) 45.160866532 seconds time elapsed ( +- 0.17% ) and it also fixes an observable perf bench (hackbench) regression: # perf stat --null --repeat 10 perf bench sched messaging -NUMA: -NUMA: 0.246225691 seconds time elapsed ( +- 1.31% ) +NUMA no slow start: 0.252620063 seconds time elapsed ( +- 1.13% ) +NUMA 1sec delay: 0.248076230 seconds time elapsed ( +- 1.35% ) The implementation is simple and straightforward, most of the patch deals with adding the /proc/sys/kernel/numa_balancing_scan_delay_ms tunable knob. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote the changelog, ran measurements, tuned the default. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:47 +00:00
/* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
unsigned int sysctl_numa_balancing_scan_delay = 1000;
sched/numa: Set the scan rate proportional to the memory usage of the task being scanned The NUMA PTE scan rate is controlled with a combination of the numa_balancing_scan_period_min, numa_balancing_scan_period_max and numa_balancing_scan_size. This scan rate is independent of the size of the task and as an aside it is further complicated by the fact that numa_balancing_scan_size controls how many pages are marked pte_numa and not how much virtual memory is scanned. In combination, it is almost impossible to meaningfully tune the min and max scan periods and reasoning about performance is complex when the time to complete a full scan is is partially a function of the tasks memory size. This patch alters the semantic of the min and max tunables to be about tuning the length time it takes to complete a scan of a tasks occupied virtual address space. Conceptually this is a lot easier to understand. There is a "sanity" check to ensure the scan rate is never extremely fast based on the amount of virtual memory that should be scanned in a second. The default of 2.5G seems arbitrary but it is to have the maximum scan rate after the patch roughly match the maximum scan rate before the patch was applied. On a similar note, numa_scan_period is in milliseconds and not jiffies. Properly placed pages slow the scanning rate but adding 10 jiffies to numa_scan_period means that the rate scanning slows depends on HZ which is confusing. Get rid of the jiffies_to_msec conversion and treat it as ms. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1381141781-10992-18-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-07 10:28:55 +00:00
static unsigned int task_nr_scan_windows(struct task_struct *p)
{
unsigned long rss = 0;
unsigned long nr_scan_pages;
/*
* Calculations based on RSS as non-present and empty pages are skipped
* by the PTE scanner and NUMA hinting faults should be trapped based
* on resident pages
*/
nr_scan_pages = sysctl_numa_balancing_scan_size << (20 - PAGE_SHIFT);
rss = get_mm_rss(p->mm);
if (!rss)
rss = nr_scan_pages;
rss = round_up(rss, nr_scan_pages);
return rss / nr_scan_pages;
}
/* For sanitys sake, never scan more PTEs than MAX_SCAN_WINDOW MB/sec. */
#define MAX_SCAN_WINDOW 2560
static unsigned int task_scan_min(struct task_struct *p)
{
unsigned int scan_size = READ_ONCE(sysctl_numa_balancing_scan_size);
sched/numa: Set the scan rate proportional to the memory usage of the task being scanned The NUMA PTE scan rate is controlled with a combination of the numa_balancing_scan_period_min, numa_balancing_scan_period_max and numa_balancing_scan_size. This scan rate is independent of the size of the task and as an aside it is further complicated by the fact that numa_balancing_scan_size controls how many pages are marked pte_numa and not how much virtual memory is scanned. In combination, it is almost impossible to meaningfully tune the min and max scan periods and reasoning about performance is complex when the time to complete a full scan is is partially a function of the tasks memory size. This patch alters the semantic of the min and max tunables to be about tuning the length time it takes to complete a scan of a tasks occupied virtual address space. Conceptually this is a lot easier to understand. There is a "sanity" check to ensure the scan rate is never extremely fast based on the amount of virtual memory that should be scanned in a second. The default of 2.5G seems arbitrary but it is to have the maximum scan rate after the patch roughly match the maximum scan rate before the patch was applied. On a similar note, numa_scan_period is in milliseconds and not jiffies. Properly placed pages slow the scanning rate but adding 10 jiffies to numa_scan_period means that the rate scanning slows depends on HZ which is confusing. Get rid of the jiffies_to_msec conversion and treat it as ms. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1381141781-10992-18-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-07 10:28:55 +00:00
unsigned int scan, floor;
unsigned int windows = 1;
sched/fair: Fix division by zero sysctl_numa_balancing_scan_size File /proc/sys/kernel/numa_balancing_scan_size_mb allows writing of zero. This bash command reproduces problem: $ while :; do echo 0 > /proc/sys/kernel/numa_balancing_scan_size_mb; \ echo 256 > /proc/sys/kernel/numa_balancing_scan_size_mb; done divide error: 0000 [#1] SMP Modules linked in: CPU: 0 PID: 24112 Comm: bash Not tainted 3.17.0+ #8 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88013c852600 ti: ffff880037a68000 task.ti: ffff880037a68000 RIP: 0010:[<ffffffff81074191>] [<ffffffff81074191>] task_scan_min+0x21/0x50 RSP: 0000:ffff880037a6bce0 EFLAGS: 00010246 RAX: 0000000000000a00 RBX: 00000000000003e8 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88013c852600 RBP: ffff880037a6bcf0 R08: 0000000000000001 R09: 0000000000015c90 R10: ffff880239bf6c00 R11: 0000000000000016 R12: 0000000000003fff R13: ffff88013c852600 R14: ffffea0008d1b000 R15: 0000000000000003 FS: 00007f12bb048700(0000) GS:ffff88007da00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000001505678 CR3: 0000000234770000 CR4: 00000000000006f0 Stack: ffff88013c852600 0000000000003fff ffff880037a6bd18 ffffffff810741d1 ffff88013c852600 0000000000003fff 000000000002bfff ffff880037a6bda8 ffffffff81077ef7 ffffea0008a56d40 0000000000000001 0000000000000001 Call Trace: [<ffffffff810741d1>] task_scan_max+0x11/0x40 [<ffffffff81077ef7>] task_numa_fault+0x1f7/0xae0 [<ffffffff8115a896>] ? migrate_misplaced_page+0x276/0x300 [<ffffffff81134a4d>] handle_mm_fault+0x62d/0xba0 [<ffffffff8103e2f1>] __do_page_fault+0x191/0x510 [<ffffffff81030122>] ? native_smp_send_reschedule+0x42/0x60 [<ffffffff8106dc00>] ? check_preempt_curr+0x80/0xa0 [<ffffffff8107092c>] ? wake_up_new_task+0x11c/0x1a0 [<ffffffff8104887d>] ? do_fork+0x14d/0x340 [<ffffffff811799bb>] ? get_unused_fd_flags+0x2b/0x30 [<ffffffff811799df>] ? __fd_install+0x1f/0x60 [<ffffffff8103e67c>] do_page_fault+0xc/0x10 [<ffffffff8150d322>] page_fault+0x22/0x30 RIP [<ffffffff81074191>] task_scan_min+0x21/0x50 RSP <ffff880037a6bce0> ---[ end trace 9a826d16936c04de ]--- Also fix race in task_scan_min (it depends on compiler behaviour). Signed-off-by: Kirill Tkhai <ktkhai@parallels.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Dario Faggioli <raistlin@linux.it> Cc: David Rientjes <rientjes@google.com> Cc: Jens Axboe <axboe@fb.com> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Rik van Riel <riel@redhat.com> Link: http://lkml.kernel.org/r/1413455977.24793.78.camel@tkhai Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-10-16 10:39:37 +00:00
if (scan_size < MAX_SCAN_WINDOW)
windows = MAX_SCAN_WINDOW / scan_size;
sched/numa: Set the scan rate proportional to the memory usage of the task being scanned The NUMA PTE scan rate is controlled with a combination of the numa_balancing_scan_period_min, numa_balancing_scan_period_max and numa_balancing_scan_size. This scan rate is independent of the size of the task and as an aside it is further complicated by the fact that numa_balancing_scan_size controls how many pages are marked pte_numa and not how much virtual memory is scanned. In combination, it is almost impossible to meaningfully tune the min and max scan periods and reasoning about performance is complex when the time to complete a full scan is is partially a function of the tasks memory size. This patch alters the semantic of the min and max tunables to be about tuning the length time it takes to complete a scan of a tasks occupied virtual address space. Conceptually this is a lot easier to understand. There is a "sanity" check to ensure the scan rate is never extremely fast based on the amount of virtual memory that should be scanned in a second. The default of 2.5G seems arbitrary but it is to have the maximum scan rate after the patch roughly match the maximum scan rate before the patch was applied. On a similar note, numa_scan_period is in milliseconds and not jiffies. Properly placed pages slow the scanning rate but adding 10 jiffies to numa_scan_period means that the rate scanning slows depends on HZ which is confusing. Get rid of the jiffies_to_msec conversion and treat it as ms. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1381141781-10992-18-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-07 10:28:55 +00:00
floor = 1000 / windows;
scan = sysctl_numa_balancing_scan_period_min / task_nr_scan_windows(p);
return max_t(unsigned int, floor, scan);
}
static unsigned int task_scan_max(struct task_struct *p)
{
unsigned int smin = task_scan_min(p);
unsigned int smax;
/* Watch for min being lower than max due to floor calculations */
smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p);
return max(smin, smax);
}
static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
{
rq->nr_numa_running += (p->numa_preferred_nid != -1);
rq->nr_preferred_running += (p->numa_preferred_nid == task_node(p));
}
static void account_numa_dequeue(struct rq *rq, struct task_struct *p)
{
rq->nr_numa_running -= (p->numa_preferred_nid != -1);
rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p));
}
struct numa_group {
atomic_t refcount;
spinlock_t lock; /* nr_tasks, tasks */
int nr_tasks;
pid_t gid;
struct rcu_head rcu;
nodemask_t active_nodes;
unsigned long total_faults;
sched/numa: Normalize faults_cpu stats and weigh by CPU use Tracing the code that decides the active nodes has made it abundantly clear that the naive implementation of the faults_from code has issues. Specifically, the garbage collector in some workloads will access orders of magnitudes more memory than the threads that do all the active work. This resulted in the node with the garbage collector being marked the only active node in the group. This issue is avoided if we weigh the statistics by CPU use of each task in the numa group, instead of by how many faults each thread has occurred. To achieve this, we normalize the number of faults to the fraction of faults that occurred on each node, and then multiply that fraction by the fraction of CPU time the task has used since the last time task_numa_placement was invoked. This way the nodes in the active node mask will be the ones where the tasks from the numa group are most actively running, and the influence of eg. the garbage collector and other do-little threads is properly minimized. On a 4 node system, using CPU use statistics calculated over a longer interval results in about 1% fewer page migrations with two 32-warehouse specjbb runs on a 4 node system, and about 5% fewer page migrations, as well as 1% better throughput, with two 8-warehouse specjbb runs, as compared with the shorter term statistics kept by the scheduler. Signed-off-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Chegu Vinod <chegu_vinod@hp.com> Link: http://lkml.kernel.org/r/1390860228-21539-7-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-01-27 22:03:45 +00:00
/*
* Faults_cpu is used to decide whether memory should move
* towards the CPU. As a consequence, these stats are weighted
* more by CPU use than by memory faults.
*/
unsigned long *faults_cpu;
unsigned long faults[0];
};
/* Shared or private faults. */
#define NR_NUMA_HINT_FAULT_TYPES 2
/* Memory and CPU locality */
#define NR_NUMA_HINT_FAULT_STATS (NR_NUMA_HINT_FAULT_TYPES * 2)
/* Averaged statistics, and temporary buffers. */
#define NR_NUMA_HINT_FAULT_BUCKETS (NR_NUMA_HINT_FAULT_STATS * 2)
pid_t task_numa_group_id(struct task_struct *p)
{
return p->numa_group ? p->numa_group->gid : 0;
}
/*
* The averaged statistics, shared & private, memory & cpu,
* occupy the first half of the array. The second half of the
* array is for current counters, which are averaged into the
* first set by task_numa_placement.
*/
static inline int task_faults_idx(enum numa_faults_stats s, int nid, int priv)
{
return NR_NUMA_HINT_FAULT_TYPES * (s * nr_node_ids + nid) + priv;
}
static inline unsigned long task_faults(struct task_struct *p, int nid)
{
if (!p->numa_faults)
return 0;
return p->numa_faults[task_faults_idx(NUMA_MEM, nid, 0)] +
p->numa_faults[task_faults_idx(NUMA_MEM, nid, 1)];
}
static inline unsigned long group_faults(struct task_struct *p, int nid)
{
if (!p->numa_group)
return 0;
return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] +
p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)];
}
static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
{
return group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 0)] +
group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)];
}
sched/numa: Calculate node scores in complex NUMA topologies In order to do task placement on systems with complex NUMA topologies, it is necessary to count the faults on nodes nearby the node that is being examined for a potential move. In case of a system with a backplane interconnect, we are dealing with groups of NUMA nodes; each of the nodes within a group is the same number of hops away from nodes in other groups in the system. Optimal placement on this topology is achieved by counting all nearby nodes equally. When comparing nodes A and B at distance N, nearby nodes are those at distances smaller than N from nodes A or B. Placement strategy on a system with a glueless mesh NUMA topology needs to be different, because there are no natural groups of nodes determined by the hardware. Instead, when dealing with two nodes A and B at distance N, N >= 2, there will be intermediate nodes at distance < N from both nodes A and B. Good placement can be achieved by right shifting the faults on nearby nodes by the number of hops from the node being scored. In this context, a nearby node is any node less than the maximum distance in the system away from the node. Those nodes are skipped for efficiency reasons, there is no real policy reason to do so. Placement policy on directly connected NUMA systems is not affected. Signed-off-by: Rik van Riel <riel@redhat.com> Tested-by: Chegu Vinod <chegu_vinod@hp.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: mgorman@suse.de Cc: chegu_vinod@hp.com Link: http://lkml.kernel.org/r/1413530994-9732-5-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-10-17 07:29:52 +00:00
/* Handle placement on systems where not all nodes are directly connected. */
static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
int maxdist, bool task)
{
unsigned long score = 0;
int node;
/*
* All nodes are directly connected, and the same distance
* from each other. No need for fancy placement algorithms.
*/
if (sched_numa_topology_type == NUMA_DIRECT)
return 0;
/*
* This code is called for each node, introducing N^2 complexity,
* which should be ok given the number of nodes rarely exceeds 8.
*/
for_each_online_node(node) {
unsigned long faults;
int dist = node_distance(nid, node);
/*
* The furthest away nodes in the system are not interesting
* for placement; nid was already counted.
*/
if (dist == sched_max_numa_distance || node == nid)
continue;
/*
* On systems with a backplane NUMA topology, compare groups
* of nodes, and move tasks towards the group with the most
* memory accesses. When comparing two nodes at distance
* "hoplimit", only nodes closer by than "hoplimit" are part
* of each group. Skip other nodes.
*/
if (sched_numa_topology_type == NUMA_BACKPLANE &&
dist > maxdist)
continue;
/* Add up the faults from nearby nodes. */
if (task)
faults = task_faults(p, node);
else
faults = group_faults(p, node);
/*
* On systems with a glueless mesh NUMA topology, there are
* no fixed "groups of nodes". Instead, nodes that are not
* directly connected bounce traffic through intermediate
* nodes; a numa_group can occupy any set of nodes.
* The further away a node is, the less the faults count.
* This seems to result in good task placement.
*/
if (sched_numa_topology_type == NUMA_GLUELESS_MESH) {
faults *= (sched_max_numa_distance - dist);
faults /= (sched_max_numa_distance - LOCAL_DISTANCE);
}
score += faults;
}
return score;
}
/*
* These return the fraction of accesses done by a particular task, or
* task group, on a particular numa node. The group weight is given a
* larger multiplier, in order to group tasks together that are almost
* evenly spread out between numa nodes.
*/
static inline unsigned long task_weight(struct task_struct *p, int nid,
int dist)
{
unsigned long faults, total_faults;
if (!p->numa_faults)
return 0;
total_faults = p->total_numa_faults;
if (!total_faults)
return 0;
faults = task_faults(p, nid);
sched/numa: Calculate node scores in complex NUMA topologies In order to do task placement on systems with complex NUMA topologies, it is necessary to count the faults on nodes nearby the node that is being examined for a potential move. In case of a system with a backplane interconnect, we are dealing with groups of NUMA nodes; each of the nodes within a group is the same number of hops away from nodes in other groups in the system. Optimal placement on this topology is achieved by counting all nearby nodes equally. When comparing nodes A and B at distance N, nearby nodes are those at distances smaller than N from nodes A or B. Placement strategy on a system with a glueless mesh NUMA topology needs to be different, because there are no natural groups of nodes determined by the hardware. Instead, when dealing with two nodes A and B at distance N, N >= 2, there will be intermediate nodes at distance < N from both nodes A and B. Good placement can be achieved by right shifting the faults on nearby nodes by the number of hops from the node being scored. In this context, a nearby node is any node less than the maximum distance in the system away from the node. Those nodes are skipped for efficiency reasons, there is no real policy reason to do so. Placement policy on directly connected NUMA systems is not affected. Signed-off-by: Rik van Riel <riel@redhat.com> Tested-by: Chegu Vinod <chegu_vinod@hp.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: mgorman@suse.de Cc: chegu_vinod@hp.com Link: http://lkml.kernel.org/r/1413530994-9732-5-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-10-17 07:29:52 +00:00
faults += score_nearby_nodes(p, nid, dist, true);
return 1000 * faults / total_faults;
}
static inline unsigned long group_weight(struct task_struct *p, int nid,
int dist)
{
unsigned long faults, total_faults;
if (!p->numa_group)
return 0;
total_faults = p->numa_group->total_faults;
if (!total_faults)
return 0;
faults = group_faults(p, nid);
sched/numa: Calculate node scores in complex NUMA topologies In order to do task placement on systems with complex NUMA topologies, it is necessary to count the faults on nodes nearby the node that is being examined for a potential move. In case of a system with a backplane interconnect, we are dealing with groups of NUMA nodes; each of the nodes within a group is the same number of hops away from nodes in other groups in the system. Optimal placement on this topology is achieved by counting all nearby nodes equally. When comparing nodes A and B at distance N, nearby nodes are those at distances smaller than N from nodes A or B. Placement strategy on a system with a glueless mesh NUMA topology needs to be different, because there are no natural groups of nodes determined by the hardware. Instead, when dealing with two nodes A and B at distance N, N >= 2, there will be intermediate nodes at distance < N from both nodes A and B. Good placement can be achieved by right shifting the faults on nearby nodes by the number of hops from the node being scored. In this context, a nearby node is any node less than the maximum distance in the system away from the node. Those nodes are skipped for efficiency reasons, there is no real policy reason to do so. Placement policy on directly connected NUMA systems is not affected. Signed-off-by: Rik van Riel <riel@redhat.com> Tested-by: Chegu Vinod <chegu_vinod@hp.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: mgorman@suse.de Cc: chegu_vinod@hp.com Link: http://lkml.kernel.org/r/1413530994-9732-5-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-10-17 07:29:52 +00:00
faults += score_nearby_nodes(p, nid, dist, false);
return 1000 * faults / total_faults;
}
bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
int src_nid, int dst_cpu)
{
struct numa_group *ng = p->numa_group;
int dst_nid = cpu_to_node(dst_cpu);
int last_cpupid, this_cpupid;
this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
/*
* Multi-stage node selection is used in conjunction with a periodic
* migration fault to build a temporal task<->page relation. By using
* a two-stage filter we remove short/unlikely relations.
*
* Using P(p) ~ n_p / n_t as per frequentist probability, we can equate
* a task's usage of a particular page (n_p) per total usage of this
* page (n_t) (in a given time-span) to a probability.
*
* Our periodic faults will sample this probability and getting the
* same result twice in a row, given these samples are fully
* independent, is then given by P(n)^2, provided our sample period
* is sufficiently short compared to the usage pattern.
*
* This quadric squishes small probabilities, making it less likely we
* act on an unlikely task<->page relation.
*/
last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
if (!cpupid_pid_unset(last_cpupid) &&
cpupid_to_nid(last_cpupid) != dst_nid)
return false;
/* Always allow migrate on private faults */
if (cpupid_match_pid(p, last_cpupid))
return true;
/* A shared fault, but p->numa_group has not been set up yet. */
if (!ng)
return true;
/*
* Do not migrate if the destination is not a node that
* is actively used by this numa group.
*/
if (!node_isset(dst_nid, ng->active_nodes))
return false;
/*
* Source is a node that is not actively used by this
* numa group, while the destination is. Migrate.
*/
if (!node_isset(src_nid, ng->active_nodes))
return true;
/*
* Both source and destination are nodes in active
* use by this numa group. Maximize memory bandwidth
* by migrating from more heavily used groups, to less
* heavily used ones, spreading the load around.
* Use a 1/4 hysteresis to avoid spurious page movement.
*/
return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4);
}
static unsigned long weighted_cpuload(const int cpu);
static unsigned long source_load(int cpu, int type);
static unsigned long target_load(int cpu, int type);
static unsigned long capacity_of(int cpu);
static long effective_load(struct task_group *tg, int cpu, long wl, long wg);
/* Cached statistics for all CPUs within a node */
struct numa_stats {
unsigned long nr_running;
unsigned long load;
/* Total compute capacity of CPUs on a node */
unsigned long compute_capacity;
/* Approximate capacity in terms of runnable tasks on a node */
unsigned long task_capacity;
int has_free_capacity;
};
/*
* XXX borrowed from update_sg_lb_stats
*/
static void update_numa_stats(struct numa_stats *ns, int nid)
{
int smt, cpu, cpus = 0;
unsigned long capacity;
memset(ns, 0, sizeof(*ns));
for_each_cpu(cpu, cpumask_of_node(nid)) {
struct rq *rq = cpu_rq(cpu);
ns->nr_running += rq->nr_running;
ns->load += weighted_cpuload(cpu);
ns->compute_capacity += capacity_of(cpu);
cpus++;
}
/*
* If we raced with hotplug and there are no CPUs left in our mask
* the @ns structure is NULL'ed and task_numa_compare() will
* not find this node attractive.
*
* We'll either bail at !has_free_capacity, or we'll detect a huge
* imbalance and bail there.
*/
if (!cpus)
return;
/* smt := ceil(cpus / capacity), assumes: 1 < smt_power < 2 */
smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity);
capacity = cpus / smt; /* cores */
ns->task_capacity = min_t(unsigned, capacity,
DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE));
ns->has_free_capacity = (ns->nr_running < ns->task_capacity);
}
struct task_numa_env {
struct task_struct *p;
int src_cpu, src_nid;
int dst_cpu, dst_nid;
struct numa_stats src_stats, dst_stats;
int imbalance_pct;
int dist;
struct task_struct *best_task;
long best_imp;
int best_cpu;
};
static void task_numa_assign(struct task_numa_env *env,
struct task_struct *p, long imp)
{
if (env->best_task)
put_task_struct(env->best_task);
if (p)
get_task_struct(p);
env->best_task = p;
env->best_imp = imp;
env->best_cpu = env->dst_cpu;
}
static bool load_too_imbalanced(long src_load, long dst_load,
struct task_numa_env *env)
{
long imb, old_imb;
long orig_src_load, orig_dst_load;
long src_capacity, dst_capacity;
/*
* The load is corrected for the CPU capacity available on each node.
*
* src_load dst_load
* ------------ vs ---------
* src_capacity dst_capacity
*/
src_capacity = env->src_stats.compute_capacity;
dst_capacity = env->dst_stats.compute_capacity;
/* We care about the slope of the imbalance, not the direction. */
if (dst_load < src_load)
swap(dst_load, src_load);
/* Is the difference below the threshold? */
imb = dst_load * src_capacity * 100 -
src_load * dst_capacity * env->imbalance_pct;
if (imb <= 0)
return false;
/*
* The imbalance is above the allowed threshold.
* Compare it with the old imbalance.
*/
orig_src_load = env->src_stats.load;
orig_dst_load = env->dst_stats.load;
if (orig_dst_load < orig_src_load)
swap(orig_dst_load, orig_src_load);
old_imb = orig_dst_load * src_capacity * 100 -
orig_src_load * dst_capacity * env->imbalance_pct;
/* Would this change make things worse? */
return (imb > old_imb);
}
/*
* This checks if the overall compute and NUMA accesses of the system would
* be improved if the source tasks was migrated to the target dst_cpu taking
* into account that it might be best if task running on the dst_cpu should
* be exchanged with the source task
*/
static void task_numa_compare(struct task_numa_env *env,
long taskimp, long groupimp)
{
struct rq *src_rq = cpu_rq(env->src_cpu);
struct rq *dst_rq = cpu_rq(env->dst_cpu);
struct task_struct *cur;
long src_load, dst_load;
long load;
long imp = env->p->numa_group ? groupimp : taskimp;
sched/numa: Examine a task move when examining a task swap Running "perf bench numa mem -0 -m -P 1000 -p 8 -t 20" on a 4 node system results in 160 runnable threads on a system with 80 CPU threads. Once a process has nearly converged, with 39 threads on one node and 1 thread on another node, the remaining thread will be unable to migrate to its preferred node through a task swap. However, a simple task move would make the workload converge, witout causing an imbalance. Test for this unlikely occurrence, and attempt a task move to the preferred nid when it happens. # Running main, "perf bench numa mem -p 8 -t 20 -0 -m -P 1000" ### # 160 tasks will execute (on 4 nodes, 80 CPUs): # -1x 0MB global shared mem operations # -1x 1000MB process shared mem operations # -1x 0MB thread local mem operations ### ### # # 0.0% [0.2 mins] 0/0 1/1 36/2 0/0 [36/3 ] l: 0-0 ( 0) {0-2} # 0.0% [0.3 mins] 43/3 37/2 39/2 41/3 [ 6/10] l: 0-1 ( 1) {1-2} # 0.0% [0.4 mins] 42/3 38/2 40/2 40/2 [ 4/9 ] l: 1-2 ( 1) [50.0%] {1-2} # 0.0% [0.6 mins] 41/3 39/2 40/2 40/2 [ 2/9 ] l: 2-4 ( 2) [50.0%] {1-2} # 0.0% [0.7 mins] 40/2 40/2 40/2 40/2 [ 0/8 ] l: 3-5 ( 2) [40.0%] ( 41.8s converged) Without this patch, this same perf bench numa mem run had to rely on the scheduler load balancer to first balance out the load (moving a random task), before a task swap could complete the NUMA convergence. The load balancer does not normally take action unless the load difference exceeds 25%. Convergence times of over half an hour have been observed without this patch. With this patch, the NUMA balancing code will simply migrate the task, if that does not cause an imbalance. Also skip examining a CPU in detail if the improvement on that CPU is no more than the best we already have. Signed-off-by: Rik van Riel <riel@redhat.com> Cc: chegu_vinod@hp.com Cc: mgorman@suse.de Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/n/tip-ggthh0rnh0yua6o5o3p6cr1o@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-23 15:46:16 +00:00
long moveimp = imp;
int dist = env->dist;
rcu_read_lock();
sched/numa: Fix unsafe get_task_struct() in task_numa_assign() Unlocked access to dst_rq->curr in task_numa_compare() is racy. If curr task is exiting this may be a reason of use-after-free: task_numa_compare() do_exit() ... current->flags |= PF_EXITING; ... release_task() ... ~~delayed_put_task_struct()~~ ... schedule() rcu_read_lock() ... cur = ACCESS_ONCE(dst_rq->curr) ... ... rq->curr = next; ... context_switch() ... finish_task_switch() ... put_task_struct() ... __put_task_struct() ... free_task_struct() task_numa_assign() ... get_task_struct() ... As noted by Oleg: <<The lockless get_task_struct(tsk) is only safe if tsk == current and didn't pass exit_notify(), or if this tsk was found on a rcu protected list (say, for_each_process() or find_task_by_vpid()). IOW, it is only safe if release_task() was not called before we take rcu_read_lock(), in this case we can rely on the fact that delayed_put_pid() can not drop the (potentially) last reference until rcu_read_unlock(). And as Kirill pointed out task_numa_compare()->task_numa_assign() path does get_task_struct(dst_rq->curr) and this is not safe. The task_struct itself can't go away, but rcu_read_lock() can't save us from the final put_task_struct() in finish_task_switch(); this reference goes away without rcu gp>> The patch provides simple check of PF_EXITING flag. If it's not set, this guarantees that call_rcu() of delayed_put_task_struct() callback hasn't happened yet, so we can safely do get_task_struct() in task_numa_assign(). Locked dst_rq->lock protects from concurrency with the last schedule(). Reusing or unmapping of cur's memory may happen without it. Suggested-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Kirill Tkhai <ktkhai@parallels.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1413962231.19914.130.camel@tkhai Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-10-22 07:17:11 +00:00
raw_spin_lock_irq(&dst_rq->lock);
cur = dst_rq->curr;
/*
* No need to move the exiting task, and this ensures that ->curr
* wasn't reaped and thus get_task_struct() in task_numa_assign()
* is safe under RCU read lock.
* Note that rcu_read_lock() itself can't protect from the final
* put_task_struct() after the last schedule().
*/
if ((cur->flags & PF_EXITING) || is_idle_task(cur))
cur = NULL;
sched/numa: Fix unsafe get_task_struct() in task_numa_assign() Unlocked access to dst_rq->curr in task_numa_compare() is racy. If curr task is exiting this may be a reason of use-after-free: task_numa_compare() do_exit() ... current->flags |= PF_EXITING; ... release_task() ... ~~delayed_put_task_struct()~~ ... schedule() rcu_read_lock() ... cur = ACCESS_ONCE(dst_rq->curr) ... ... rq->curr = next; ... context_switch() ... finish_task_switch() ... put_task_struct() ... __put_task_struct() ... free_task_struct() task_numa_assign() ... get_task_struct() ... As noted by Oleg: <<The lockless get_task_struct(tsk) is only safe if tsk == current and didn't pass exit_notify(), or if this tsk was found on a rcu protected list (say, for_each_process() or find_task_by_vpid()). IOW, it is only safe if release_task() was not called before we take rcu_read_lock(), in this case we can rely on the fact that delayed_put_pid() can not drop the (potentially) last reference until rcu_read_unlock(). And as Kirill pointed out task_numa_compare()->task_numa_assign() path does get_task_struct(dst_rq->curr) and this is not safe. The task_struct itself can't go away, but rcu_read_lock() can't save us from the final put_task_struct() in finish_task_switch(); this reference goes away without rcu gp>> The patch provides simple check of PF_EXITING flag. If it's not set, this guarantees that call_rcu() of delayed_put_task_struct() callback hasn't happened yet, so we can safely do get_task_struct() in task_numa_assign(). Locked dst_rq->lock protects from concurrency with the last schedule(). Reusing or unmapping of cur's memory may happen without it. Suggested-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Kirill Tkhai <ktkhai@parallels.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1413962231.19914.130.camel@tkhai Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-10-22 07:17:11 +00:00
raw_spin_unlock_irq(&dst_rq->lock);
/*
* Because we have preemption enabled we can get migrated around and
* end try selecting ourselves (current == env->p) as a swap candidate.
*/
if (cur == env->p)
goto unlock;
/*
* "imp" is the fault differential for the source task between the
* source and destination node. Calculate the total differential for
* the source task and potential destination task. The more negative
* the value is, the more rmeote accesses that would be expected to
* be incurred if the tasks were swapped.
*/
if (cur) {
/* Skip this swap candidate if cannot move to the source cpu */
if (!cpumask_test_cpu(env->src_cpu, tsk_cpus_allowed(cur)))
goto unlock;
/*
* If dst and source tasks are in the same NUMA group, or not
* in any group then look only at task weights.
*/
if (cur->numa_group == env->p->numa_group) {
imp = taskimp + task_weight(cur, env->src_nid, dist) -
task_weight(cur, env->dst_nid, dist);
/*
* Add some hysteresis to prevent swapping the
* tasks within a group over tiny differences.
*/
if (cur->numa_group)
imp -= imp/16;
} else {
/*
* Compare the group weights. If a task is all by
* itself (not part of a group), use the task weight
* instead.
*/
if (cur->numa_group)
imp += group_weight(cur, env->src_nid, dist) -
group_weight(cur, env->dst_nid, dist);
else
imp += task_weight(cur, env->src_nid, dist) -
task_weight(cur, env->dst_nid, dist);
}
}
sched/numa: Examine a task move when examining a task swap Running "perf bench numa mem -0 -m -P 1000 -p 8 -t 20" on a 4 node system results in 160 runnable threads on a system with 80 CPU threads. Once a process has nearly converged, with 39 threads on one node and 1 thread on another node, the remaining thread will be unable to migrate to its preferred node through a task swap. However, a simple task move would make the workload converge, witout causing an imbalance. Test for this unlikely occurrence, and attempt a task move to the preferred nid when it happens. # Running main, "perf bench numa mem -p 8 -t 20 -0 -m -P 1000" ### # 160 tasks will execute (on 4 nodes, 80 CPUs): # -1x 0MB global shared mem operations # -1x 1000MB process shared mem operations # -1x 0MB thread local mem operations ### ### # # 0.0% [0.2 mins] 0/0 1/1 36/2 0/0 [36/3 ] l: 0-0 ( 0) {0-2} # 0.0% [0.3 mins] 43/3 37/2 39/2 41/3 [ 6/10] l: 0-1 ( 1) {1-2} # 0.0% [0.4 mins] 42/3 38/2 40/2 40/2 [ 4/9 ] l: 1-2 ( 1) [50.0%] {1-2} # 0.0% [0.6 mins] 41/3 39/2 40/2 40/2 [ 2/9 ] l: 2-4 ( 2) [50.0%] {1-2} # 0.0% [0.7 mins] 40/2 40/2 40/2 40/2 [ 0/8 ] l: 3-5 ( 2) [40.0%] ( 41.8s converged) Without this patch, this same perf bench numa mem run had to rely on the scheduler load balancer to first balance out the load (moving a random task), before a task swap could complete the NUMA convergence. The load balancer does not normally take action unless the load difference exceeds 25%. Convergence times of over half an hour have been observed without this patch. With this patch, the NUMA balancing code will simply migrate the task, if that does not cause an imbalance. Also skip examining a CPU in detail if the improvement on that CPU is no more than the best we already have. Signed-off-by: Rik van Riel <riel@redhat.com> Cc: chegu_vinod@hp.com Cc: mgorman@suse.de Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/n/tip-ggthh0rnh0yua6o5o3p6cr1o@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-23 15:46:16 +00:00
if (imp <= env->best_imp && moveimp <= env->best_imp)
goto unlock;
if (!cur) {
/* Is there capacity at our destination? */
if (env->src_stats.nr_running <= env->src_stats.task_capacity &&
!env->dst_stats.has_free_capacity)
goto unlock;
goto balance;
}
/* Balance doesn't matter much if we're running a task per cpu */
sched/numa: Examine a task move when examining a task swap Running "perf bench numa mem -0 -m -P 1000 -p 8 -t 20" on a 4 node system results in 160 runnable threads on a system with 80 CPU threads. Once a process has nearly converged, with 39 threads on one node and 1 thread on another node, the remaining thread will be unable to migrate to its preferred node through a task swap. However, a simple task move would make the workload converge, witout causing an imbalance. Test for this unlikely occurrence, and attempt a task move to the preferred nid when it happens. # Running main, "perf bench numa mem -p 8 -t 20 -0 -m -P 1000" ### # 160 tasks will execute (on 4 nodes, 80 CPUs): # -1x 0MB global shared mem operations # -1x 1000MB process shared mem operations # -1x 0MB thread local mem operations ### ### # # 0.0% [0.2 mins] 0/0 1/1 36/2 0/0 [36/3 ] l: 0-0 ( 0) {0-2} # 0.0% [0.3 mins] 43/3 37/2 39/2 41/3 [ 6/10] l: 0-1 ( 1) {1-2} # 0.0% [0.4 mins] 42/3 38/2 40/2 40/2 [ 4/9 ] l: 1-2 ( 1) [50.0%] {1-2} # 0.0% [0.6 mins] 41/3 39/2 40/2 40/2 [ 2/9 ] l: 2-4 ( 2) [50.0%] {1-2} # 0.0% [0.7 mins] 40/2 40/2 40/2 40/2 [ 0/8 ] l: 3-5 ( 2) [40.0%] ( 41.8s converged) Without this patch, this same perf bench numa mem run had to rely on the scheduler load balancer to first balance out the load (moving a random task), before a task swap could complete the NUMA convergence. The load balancer does not normally take action unless the load difference exceeds 25%. Convergence times of over half an hour have been observed without this patch. With this patch, the NUMA balancing code will simply migrate the task, if that does not cause an imbalance. Also skip examining a CPU in detail if the improvement on that CPU is no more than the best we already have. Signed-off-by: Rik van Riel <riel@redhat.com> Cc: chegu_vinod@hp.com Cc: mgorman@suse.de Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/n/tip-ggthh0rnh0yua6o5o3p6cr1o@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-23 15:46:16 +00:00
if (imp > env->best_imp && src_rq->nr_running == 1 &&
dst_rq->nr_running == 1)
goto assign;
/*
* In the overloaded case, try and keep the load balanced.
*/
balance:
load = task_h_load(env->p);
dst_load = env->dst_stats.load + load;
src_load = env->src_stats.load - load;
sched/numa: Examine a task move when examining a task swap Running "perf bench numa mem -0 -m -P 1000 -p 8 -t 20" on a 4 node system results in 160 runnable threads on a system with 80 CPU threads. Once a process has nearly converged, with 39 threads on one node and 1 thread on another node, the remaining thread will be unable to migrate to its preferred node through a task swap. However, a simple task move would make the workload converge, witout causing an imbalance. Test for this unlikely occurrence, and attempt a task move to the preferred nid when it happens. # Running main, "perf bench numa mem -p 8 -t 20 -0 -m -P 1000" ### # 160 tasks will execute (on 4 nodes, 80 CPUs): # -1x 0MB global shared mem operations # -1x 1000MB process shared mem operations # -1x 0MB thread local mem operations ### ### # # 0.0% [0.2 mins] 0/0 1/1 36/2 0/0 [36/3 ] l: 0-0 ( 0) {0-2} # 0.0% [0.3 mins] 43/3 37/2 39/2 41/3 [ 6/10] l: 0-1 ( 1) {1-2} # 0.0% [0.4 mins] 42/3 38/2 40/2 40/2 [ 4/9 ] l: 1-2 ( 1) [50.0%] {1-2} # 0.0% [0.6 mins] 41/3 39/2 40/2 40/2 [ 2/9 ] l: 2-4 ( 2) [50.0%] {1-2} # 0.0% [0.7 mins] 40/2 40/2 40/2 40/2 [ 0/8 ] l: 3-5 ( 2) [40.0%] ( 41.8s converged) Without this patch, this same perf bench numa mem run had to rely on the scheduler load balancer to first balance out the load (moving a random task), before a task swap could complete the NUMA convergence. The load balancer does not normally take action unless the load difference exceeds 25%. Convergence times of over half an hour have been observed without this patch. With this patch, the NUMA balancing code will simply migrate the task, if that does not cause an imbalance. Also skip examining a CPU in detail if the improvement on that CPU is no more than the best we already have. Signed-off-by: Rik van Riel <riel@redhat.com> Cc: chegu_vinod@hp.com Cc: mgorman@suse.de Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/n/tip-ggthh0rnh0yua6o5o3p6cr1o@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-23 15:46:16 +00:00
if (moveimp > imp && moveimp > env->best_imp) {
/*
* If the improvement from just moving env->p direction is
* better than swapping tasks around, check if a move is
* possible. Store a slightly smaller score than moveimp,
* so an actually idle CPU will win.
*/
if (!load_too_imbalanced(src_load, dst_load, env)) {
imp = moveimp - 1;
cur = NULL;
goto assign;
}
}
if (imp <= env->best_imp)
goto unlock;
if (cur) {
load = task_h_load(cur);
dst_load -= load;
src_load += load;
}
if (load_too_imbalanced(src_load, dst_load, env))
goto unlock;
/*
* One idle CPU per node is evaluated for a task numa move.
* Call select_idle_sibling to maybe find a better one.
*/
if (!cur)
env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
assign:
task_numa_assign(env, cur, imp);
unlock:
rcu_read_unlock();
}
static void task_numa_find_cpu(struct task_numa_env *env,
long taskimp, long groupimp)
{
int cpu;
for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
/* Skip this CPU if the source task cannot migrate */
if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(env->p)))
continue;
env->dst_cpu = cpu;
task_numa_compare(env, taskimp, groupimp);
}
}
sched/numa: Only consider less busy nodes as numa balancing destinations Changeset a43455a1d572 ("sched/numa: Ensure task_numa_migrate() checks the preferred node") fixes an issue where workloads would never converge on a fully loaded (or overloaded) system. However, it introduces a regression on less than fully loaded systems, where workloads converge on a few NUMA nodes, instead of properly staying spread out across the whole system. This leads to a reduction in available memory bandwidth, and usable CPU cache, with predictable performance problems. The root cause appears to be an interaction between the load balancer and NUMA balancing, where the short term load represented by the load balancer differs from the long term load the NUMA balancing code would like to base its decisions on. Simply reverting a43455a1d572 would re-introduce the non-convergence of workloads on fully loaded systems, so that is not a good option. As an aside, the check done before a43455a1d572 only applied to a task's preferred node, not to other candidate nodes in the system, so the converge-on-too-few-nodes problem still happens, just to a lesser degree. Instead, try to compensate for the impedance mismatch between the load balancer and NUMA balancing by only ever considering a lesser loaded node as a destination for NUMA balancing, regardless of whether the task is trying to move to the preferred node, or to another node. This patch also addresses the issue that a system with a single runnable thread would never migrate that thread to near its memory, introduced by 095bebf61a46 ("sched/numa: Do not move past the balance point if unbalanced"). A test where the main thread creates a large memory area, and spawns a worker thread to iterate over the memory (placed on another node by select_task_rq_fair), after which the main thread goes to sleep and waits for the worker thread to loop over all the memory now sees the worker thread migrated to where the memory is, instead of having all the memory migrated over like before. Jirka has run a number of performance tests on several systems: single instance SpecJBB 2005 performance is 7-15% higher on a 4 node system, with higher gains on systems with more cores per socket. Multi-instance SpecJBB 2005 (one per node), linpack, and stream see little or no changes with the revert of 095bebf61a46 and this patch. Reported-by: Artem Bityutski <dedekind1@gmail.com> Reported-by: Jirka Hladky <jhladky@redhat.com> Tested-by: Jirka Hladky <jhladky@redhat.com> Tested-by: Artem Bityutskiy <dedekind1@gmail.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150528095249.3083ade0@annuminas.surriel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-28 13:52:49 +00:00
/* Only move tasks to a NUMA node less busy than the current node. */
static bool numa_has_capacity(struct task_numa_env *env)
{
struct numa_stats *src = &env->src_stats;
struct numa_stats *dst = &env->dst_stats;
if (src->has_free_capacity && !dst->has_free_capacity)
return false;
/*
* Only consider a task move if the source has a higher load
* than the destination, corrected for CPU capacity on each node.
*
* src->load dst->load
* --------------------- vs ---------------------
* src->compute_capacity dst->compute_capacity
*/
if (src->load * dst->compute_capacity * env->imbalance_pct >
dst->load * src->compute_capacity * 100)
sched/numa: Only consider less busy nodes as numa balancing destinations Changeset a43455a1d572 ("sched/numa: Ensure task_numa_migrate() checks the preferred node") fixes an issue where workloads would never converge on a fully loaded (or overloaded) system. However, it introduces a regression on less than fully loaded systems, where workloads converge on a few NUMA nodes, instead of properly staying spread out across the whole system. This leads to a reduction in available memory bandwidth, and usable CPU cache, with predictable performance problems. The root cause appears to be an interaction between the load balancer and NUMA balancing, where the short term load represented by the load balancer differs from the long term load the NUMA balancing code would like to base its decisions on. Simply reverting a43455a1d572 would re-introduce the non-convergence of workloads on fully loaded systems, so that is not a good option. As an aside, the check done before a43455a1d572 only applied to a task's preferred node, not to other candidate nodes in the system, so the converge-on-too-few-nodes problem still happens, just to a lesser degree. Instead, try to compensate for the impedance mismatch between the load balancer and NUMA balancing by only ever considering a lesser loaded node as a destination for NUMA balancing, regardless of whether the task is trying to move to the preferred node, or to another node. This patch also addresses the issue that a system with a single runnable thread would never migrate that thread to near its memory, introduced by 095bebf61a46 ("sched/numa: Do not move past the balance point if unbalanced"). A test where the main thread creates a large memory area, and spawns a worker thread to iterate over the memory (placed on another node by select_task_rq_fair), after which the main thread goes to sleep and waits for the worker thread to loop over all the memory now sees the worker thread migrated to where the memory is, instead of having all the memory migrated over like before. Jirka has run a number of performance tests on several systems: single instance SpecJBB 2005 performance is 7-15% higher on a 4 node system, with higher gains on systems with more cores per socket. Multi-instance SpecJBB 2005 (one per node), linpack, and stream see little or no changes with the revert of 095bebf61a46 and this patch. Reported-by: Artem Bityutski <dedekind1@gmail.com> Reported-by: Jirka Hladky <jhladky@redhat.com> Tested-by: Jirka Hladky <jhladky@redhat.com> Tested-by: Artem Bityutskiy <dedekind1@gmail.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150528095249.3083ade0@annuminas.surriel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-28 13:52:49 +00:00
return true;
return false;
}
static int task_numa_migrate(struct task_struct *p)
{
struct task_numa_env env = {
.p = p,
.src_cpu = task_cpu(p),
.src_nid = task_node(p),
.imbalance_pct = 112,
.best_task = NULL,
.best_imp = 0,
.best_cpu = -1
};
struct sched_domain *sd;
unsigned long taskweight, groupweight;
int nid, ret, dist;
long taskimp, groupimp;
/*
* Pick the lowest SD_NUMA domain, as that would have the smallest
* imbalance and would be the first to start moving tasks about.
*
* And we want to avoid any moving of tasks about, as that would create
* random movement of tasks -- counter the numa conditions we're trying
* to satisfy here.
*/
rcu_read_lock();
sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu));
if (sd)
env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2;
rcu_read_unlock();
/*
* Cpusets can break the scheduler domain tree into smaller
* balance domains, some of which do not cross NUMA boundaries.
* Tasks that are "trapped" in such domains cannot be migrated
* elsewhere, so there is no point in (re)trying.
*/
if (unlikely(!sd)) {
p->numa_preferred_nid = task_node(p);
return -EINVAL;
}
env.dst_nid = p->numa_preferred_nid;
dist = env.dist = node_distance(env.src_nid, env.dst_nid);
taskweight = task_weight(p, env.src_nid, dist);
groupweight = group_weight(p, env.src_nid, dist);
update_numa_stats(&env.src_stats, env.src_nid);
taskimp = task_weight(p, env.dst_nid, dist) - taskweight;
groupimp = group_weight(p, env.dst_nid, dist) - groupweight;
update_numa_stats(&env.dst_stats, env.dst_nid);
/* Try to find a spot on the preferred nid. */
sched/numa: Only consider less busy nodes as numa balancing destinations Changeset a43455a1d572 ("sched/numa: Ensure task_numa_migrate() checks the preferred node") fixes an issue where workloads would never converge on a fully loaded (or overloaded) system. However, it introduces a regression on less than fully loaded systems, where workloads converge on a few NUMA nodes, instead of properly staying spread out across the whole system. This leads to a reduction in available memory bandwidth, and usable CPU cache, with predictable performance problems. The root cause appears to be an interaction between the load balancer and NUMA balancing, where the short term load represented by the load balancer differs from the long term load the NUMA balancing code would like to base its decisions on. Simply reverting a43455a1d572 would re-introduce the non-convergence of workloads on fully loaded systems, so that is not a good option. As an aside, the check done before a43455a1d572 only applied to a task's preferred node, not to other candidate nodes in the system, so the converge-on-too-few-nodes problem still happens, just to a lesser degree. Instead, try to compensate for the impedance mismatch between the load balancer and NUMA balancing by only ever considering a lesser loaded node as a destination for NUMA balancing, regardless of whether the task is trying to move to the preferred node, or to another node. This patch also addresses the issue that a system with a single runnable thread would never migrate that thread to near its memory, introduced by 095bebf61a46 ("sched/numa: Do not move past the balance point if unbalanced"). A test where the main thread creates a large memory area, and spawns a worker thread to iterate over the memory (placed on another node by select_task_rq_fair), after which the main thread goes to sleep and waits for the worker thread to loop over all the memory now sees the worker thread migrated to where the memory is, instead of having all the memory migrated over like before. Jirka has run a number of performance tests on several systems: single instance SpecJBB 2005 performance is 7-15% higher on a 4 node system, with higher gains on systems with more cores per socket. Multi-instance SpecJBB 2005 (one per node), linpack, and stream see little or no changes with the revert of 095bebf61a46 and this patch. Reported-by: Artem Bityutski <dedekind1@gmail.com> Reported-by: Jirka Hladky <jhladky@redhat.com> Tested-by: Jirka Hladky <jhladky@redhat.com> Tested-by: Artem Bityutskiy <dedekind1@gmail.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150528095249.3083ade0@annuminas.surriel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-28 13:52:49 +00:00
if (numa_has_capacity(&env))
task_numa_find_cpu(&env, taskimp, groupimp);
/*
* Look at other nodes in these cases:
* - there is no space available on the preferred_nid
* - the task is part of a numa_group that is interleaved across
* multiple NUMA nodes; in order to better consolidate the group,
* we need to check other locations.
*/
if (env.best_cpu == -1 || (p->numa_group &&
nodes_weight(p->numa_group->active_nodes) > 1)) {
for_each_online_node(nid) {
if (nid == env.src_nid || nid == p->numa_preferred_nid)
continue;
dist = node_distance(env.src_nid, env.dst_nid);
sched/numa: Calculate node scores in complex NUMA topologies In order to do task placement on systems with complex NUMA topologies, it is necessary to count the faults on nodes nearby the node that is being examined for a potential move. In case of a system with a backplane interconnect, we are dealing with groups of NUMA nodes; each of the nodes within a group is the same number of hops away from nodes in other groups in the system. Optimal placement on this topology is achieved by counting all nearby nodes equally. When comparing nodes A and B at distance N, nearby nodes are those at distances smaller than N from nodes A or B. Placement strategy on a system with a glueless mesh NUMA topology needs to be different, because there are no natural groups of nodes determined by the hardware. Instead, when dealing with two nodes A and B at distance N, N >= 2, there will be intermediate nodes at distance < N from both nodes A and B. Good placement can be achieved by right shifting the faults on nearby nodes by the number of hops from the node being scored. In this context, a nearby node is any node less than the maximum distance in the system away from the node. Those nodes are skipped for efficiency reasons, there is no real policy reason to do so. Placement policy on directly connected NUMA systems is not affected. Signed-off-by: Rik van Riel <riel@redhat.com> Tested-by: Chegu Vinod <chegu_vinod@hp.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: mgorman@suse.de Cc: chegu_vinod@hp.com Link: http://lkml.kernel.org/r/1413530994-9732-5-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-10-17 07:29:52 +00:00
if (sched_numa_topology_type == NUMA_BACKPLANE &&
dist != env.dist) {
taskweight = task_weight(p, env.src_nid, dist);
groupweight = group_weight(p, env.src_nid, dist);
}
/* Only consider nodes where both task and groups benefit */
taskimp = task_weight(p, nid, dist) - taskweight;
groupimp = group_weight(p, nid, dist) - groupweight;
if (taskimp < 0 && groupimp < 0)
continue;
env.dist = dist;
env.dst_nid = nid;
update_numa_stats(&env.dst_stats, env.dst_nid);
sched/numa: Only consider less busy nodes as numa balancing destinations Changeset a43455a1d572 ("sched/numa: Ensure task_numa_migrate() checks the preferred node") fixes an issue where workloads would never converge on a fully loaded (or overloaded) system. However, it introduces a regression on less than fully loaded systems, where workloads converge on a few NUMA nodes, instead of properly staying spread out across the whole system. This leads to a reduction in available memory bandwidth, and usable CPU cache, with predictable performance problems. The root cause appears to be an interaction between the load balancer and NUMA balancing, where the short term load represented by the load balancer differs from the long term load the NUMA balancing code would like to base its decisions on. Simply reverting a43455a1d572 would re-introduce the non-convergence of workloads on fully loaded systems, so that is not a good option. As an aside, the check done before a43455a1d572 only applied to a task's preferred node, not to other candidate nodes in the system, so the converge-on-too-few-nodes problem still happens, just to a lesser degree. Instead, try to compensate for the impedance mismatch between the load balancer and NUMA balancing by only ever considering a lesser loaded node as a destination for NUMA balancing, regardless of whether the task is trying to move to the preferred node, or to another node. This patch also addresses the issue that a system with a single runnable thread would never migrate that thread to near its memory, introduced by 095bebf61a46 ("sched/numa: Do not move past the balance point if unbalanced"). A test where the main thread creates a large memory area, and spawns a worker thread to iterate over the memory (placed on another node by select_task_rq_fair), after which the main thread goes to sleep and waits for the worker thread to loop over all the memory now sees the worker thread migrated to where the memory is, instead of having all the memory migrated over like before. Jirka has run a number of performance tests on several systems: single instance SpecJBB 2005 performance is 7-15% higher on a 4 node system, with higher gains on systems with more cores per socket. Multi-instance SpecJBB 2005 (one per node), linpack, and stream see little or no changes with the revert of 095bebf61a46 and this patch. Reported-by: Artem Bityutski <dedekind1@gmail.com> Reported-by: Jirka Hladky <jhladky@redhat.com> Tested-by: Jirka Hladky <jhladky@redhat.com> Tested-by: Artem Bityutskiy <dedekind1@gmail.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150528095249.3083ade0@annuminas.surriel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-28 13:52:49 +00:00
if (numa_has_capacity(&env))
task_numa_find_cpu(&env, taskimp, groupimp);
}
}
/*
* If the task is part of a workload that spans multiple NUMA nodes,
* and is migrating into one of the workload's active nodes, remember
* this node as the task's preferred numa node, so the workload can
* settle down.
* A task that migrated to a second choice node will be better off
* trying for a better one later. Do not set the preferred node here.
*/
if (p->numa_group) {
if (env.best_cpu == -1)
nid = env.src_nid;
else
nid = env.dst_nid;
if (node_isset(nid, p->numa_group->active_nodes))
sched_setnuma(p, env.dst_nid);
}
/* No better CPU than the current one was found. */
if (env.best_cpu == -1)
return -EAGAIN;
/*
* Reset the scan period if the task is being rescheduled on an
* alternative node to recheck if the tasks is now properly placed.
*/
p->numa_scan_period = task_scan_min(p);
if (env.best_task == NULL) {
sched: add tracepoints related to NUMA task migration This patch adds three tracepoints o trace_sched_move_numa when a task is moved to a node o trace_sched_swap_numa when a task is swapped with another task o trace_sched_stick_numa when a numa-related migration fails The tracepoints allow the NUMA scheduler activity to be monitored and the following high-level metrics can be calculated o NUMA migrated stuck nr trace_sched_stick_numa o NUMA migrated idle nr trace_sched_move_numa o NUMA migrated swapped nr trace_sched_swap_numa o NUMA local swapped trace_sched_swap_numa src_nid == dst_nid (should never happen) o NUMA remote swapped trace_sched_swap_numa src_nid != dst_nid (should == NUMA migrated swapped) o NUMA group swapped trace_sched_swap_numa src_ngid == dst_ngid Maybe a small number of these are acceptable but a high number would be a major surprise. It would be even worse if bounces are frequent. o NUMA avg task migs. Average number of migrations for tasks o NUMA stddev task mig Self-explanatory o NUMA max task migs. Maximum number of migrations for a single task In general the intent of the tracepoints is to help diagnose problems where automatic NUMA balancing appears to be doing an excessive amount of useless work. [akpm@linux-foundation.org: remove semicolon-after-if, repair coding-style] Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Alex Thorlton <athorlton@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-21 23:51:03 +00:00
ret = migrate_task_to(p, env.best_cpu);
if (ret != 0)
trace_sched_stick_numa(p, env.src_cpu, env.best_cpu);
return ret;
}
ret = migrate_swap(p, env.best_task);
sched: add tracepoints related to NUMA task migration This patch adds three tracepoints o trace_sched_move_numa when a task is moved to a node o trace_sched_swap_numa when a task is swapped with another task o trace_sched_stick_numa when a numa-related migration fails The tracepoints allow the NUMA scheduler activity to be monitored and the following high-level metrics can be calculated o NUMA migrated stuck nr trace_sched_stick_numa o NUMA migrated idle nr trace_sched_move_numa o NUMA migrated swapped nr trace_sched_swap_numa o NUMA local swapped trace_sched_swap_numa src_nid == dst_nid (should never happen) o NUMA remote swapped trace_sched_swap_numa src_nid != dst_nid (should == NUMA migrated swapped) o NUMA group swapped trace_sched_swap_numa src_ngid == dst_ngid Maybe a small number of these are acceptable but a high number would be a major surprise. It would be even worse if bounces are frequent. o NUMA avg task migs. Average number of migrations for tasks o NUMA stddev task mig Self-explanatory o NUMA max task migs. Maximum number of migrations for a single task In general the intent of the tracepoints is to help diagnose problems where automatic NUMA balancing appears to be doing an excessive amount of useless work. [akpm@linux-foundation.org: remove semicolon-after-if, repair coding-style] Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Alex Thorlton <athorlton@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-21 23:51:03 +00:00
if (ret != 0)
trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
put_task_struct(env.best_task);
return ret;
}
/* Attempt to migrate a task to a CPU on the preferred node. */
static void numa_migrate_preferred(struct task_struct *p)
{
unsigned long interval = HZ;
/* This task has no NUMA fault statistics yet */
if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
return;
/* Periodically retry migrating the task to the preferred node */
interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16);
p->numa_migrate_retry = jiffies + interval;
/* Success if task is already running on preferred CPU */
if (task_node(p) == p->numa_preferred_nid)
return;
/* Otherwise, try migrate to a CPU on the preferred node */
task_numa_migrate(p);
}
/*
* Find the nodes on which the workload is actively running. We do this by
* tracking the nodes from which NUMA hinting faults are triggered. This can
* be different from the set of nodes where the workload's memory is currently
* located.
*
* The bitmask is used to make smarter decisions on when to do NUMA page
* migrations, To prevent flip-flopping, and excessive page migrations, nodes
* are added when they cause over 6/16 of the maximum number of faults, but
* only removed when they drop below 3/16.
*/
static void update_numa_active_node_mask(struct numa_group *numa_group)
{
unsigned long faults, max_faults = 0;
int nid;
for_each_online_node(nid) {
faults = group_faults_cpu(numa_group, nid);
if (faults > max_faults)
max_faults = faults;
}
for_each_online_node(nid) {
faults = group_faults_cpu(numa_group, nid);
if (!node_isset(nid, numa_group->active_nodes)) {
if (faults > max_faults * 6 / 16)
node_set(nid, numa_group->active_nodes);
} else if (faults < max_faults * 3 / 16)
node_clear(nid, numa_group->active_nodes);
}
}
/*
* When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS
* increments. The more local the fault statistics are, the higher the scan
* period will be for the next scan window. If local/(local+remote) ratio is
* below NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS)
* the scan period will decrease. Aim for 70% local accesses.
*/
#define NUMA_PERIOD_SLOTS 10
#define NUMA_PERIOD_THRESHOLD 7
/*
* Increase the scan period (slow down scanning) if the majority of
* our memory is already on our local node, or if the majority of
* the page accesses are shared with other processes.
* Otherwise, decrease the scan period.
*/
static void update_task_scan_period(struct task_struct *p,
unsigned long shared, unsigned long private)
{
unsigned int period_slot;
int ratio;
int diff;
unsigned long remote = p->numa_faults_locality[0];
unsigned long local = p->numa_faults_locality[1];
/*
* If there were no record hinting faults then either the task is
* completely idle or all activity is areas that are not of interest
mm: numa: slow PTE scan rate if migration failures occur Dave Chinner reported the following on https://lkml.org/lkml/2015/3/1/226 Across the board the 4.0-rc1 numbers are much slower, and the degradation is far worse when using the large memory footprint configs. Perf points straight at the cause - this is from 4.0-rc1 on the "-o bhash=101073" config: - 56.07% 56.07% [kernel] [k] default_send_IPI_mask_sequence_phys - default_send_IPI_mask_sequence_phys - 99.99% physflat_send_IPI_mask - 99.37% native_send_call_func_ipi smp_call_function_many - native_flush_tlb_others - 99.85% flush_tlb_page ptep_clear_flush try_to_unmap_one rmap_walk try_to_unmap migrate_pages migrate_misplaced_page - handle_mm_fault - 99.73% __do_page_fault trace_do_page_fault do_async_page_fault + async_page_fault 0.63% native_send_call_func_single_ipi generic_exec_single smp_call_function_single This is showing excessive migration activity even though excessive migrations are meant to get throttled. Normally, the scan rate is tuned on a per-task basis depending on the locality of faults. However, if migrations fail for any reason then the PTE scanner may scan faster if the faults continue to be remote. This means there is higher system CPU overhead and fault trapping at exactly the time we know that migrations cannot happen. This patch tracks when migration failures occur and slows the PTE scanner. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Dave Chinner <david@fromorbit.com> Tested-by: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-03-25 22:55:42 +00:00
* to automatic numa balancing. Related to that, if there were failed
* migration then it implies we are migrating too quickly or the local
* node is overloaded. In either case, scan slower
*/
mm: numa: slow PTE scan rate if migration failures occur Dave Chinner reported the following on https://lkml.org/lkml/2015/3/1/226 Across the board the 4.0-rc1 numbers are much slower, and the degradation is far worse when using the large memory footprint configs. Perf points straight at the cause - this is from 4.0-rc1 on the "-o bhash=101073" config: - 56.07% 56.07% [kernel] [k] default_send_IPI_mask_sequence_phys - default_send_IPI_mask_sequence_phys - 99.99% physflat_send_IPI_mask - 99.37% native_send_call_func_ipi smp_call_function_many - native_flush_tlb_others - 99.85% flush_tlb_page ptep_clear_flush try_to_unmap_one rmap_walk try_to_unmap migrate_pages migrate_misplaced_page - handle_mm_fault - 99.73% __do_page_fault trace_do_page_fault do_async_page_fault + async_page_fault 0.63% native_send_call_func_single_ipi generic_exec_single smp_call_function_single This is showing excessive migration activity even though excessive migrations are meant to get throttled. Normally, the scan rate is tuned on a per-task basis depending on the locality of faults. However, if migrations fail for any reason then the PTE scanner may scan faster if the faults continue to be remote. This means there is higher system CPU overhead and fault trapping at exactly the time we know that migrations cannot happen. This patch tracks when migration failures occur and slows the PTE scanner. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Dave Chinner <david@fromorbit.com> Tested-by: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-03-25 22:55:42 +00:00
if (local + shared == 0 || p->numa_faults_locality[2]) {
p->numa_scan_period = min(p->numa_scan_period_max,
p->numa_scan_period << 1);
p->mm->numa_next_scan = jiffies +
msecs_to_jiffies(p->numa_scan_period);
return;
}
/*
* Prepare to scale scan period relative to the current period.
* == NUMA_PERIOD_THRESHOLD scan period stays the same
* < NUMA_PERIOD_THRESHOLD scan period decreases (scan faster)
* >= NUMA_PERIOD_THRESHOLD scan period increases (scan slower)
*/
period_slot = DIV_ROUND_UP(p->numa_scan_period, NUMA_PERIOD_SLOTS);
ratio = (local * NUMA_PERIOD_SLOTS) / (local + remote);
if (ratio >= NUMA_PERIOD_THRESHOLD) {
int slot = ratio - NUMA_PERIOD_THRESHOLD;
if (!slot)
slot = 1;
diff = slot * period_slot;
} else {
diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot;
/*
* Scale scan rate increases based on sharing. There is an
* inverse relationship between the degree of sharing and
* the adjustment made to the scanning period. Broadly
* speaking the intent is that there is little point
* scanning faster if shared accesses dominate as it may
* simply bounce migrations uselessly
*/
sched/fair: Care divide error in update_task_scan_period() While offling node by hot removing memory, the following divide error occurs: divide error: 0000 [#1] SMP [...] Call Trace: [...] handle_mm_fault [...] ? try_to_wake_up [...] ? wake_up_state [...] __do_page_fault [...] ? do_futex [...] ? put_prev_entity [...] ? __switch_to [...] do_page_fault [...] page_fault [...] RIP [<ffffffff810a7081>] task_numa_fault RSP <ffff88084eb2bcb0> The issue occurs as follows: 1. When page fault occurs and page is allocated from node 1, task_struct->numa_faults_buffer_memory[] of node 1 is incremented and p->numa_faults_locality[] is also incremented as follows: o numa_faults_buffer_memory[] o numa_faults_locality[] NR_NUMA_HINT_FAULT_TYPES | 0 | 1 | ---------------------------------- ---------------------- node 0 | 0 | 0 | remote | 0 | node 1 | 0 | 1 | locale | 1 | ---------------------------------- ---------------------- 2. node 1 is offlined by hot removing memory. 3. When page fault occurs, fault_types[] is calculated by using p->numa_faults_buffer_memory[] of all online nodes in task_numa_placement(). But node 1 was offline by step 2. So the fault_types[] is calculated by using only p->numa_faults_buffer_memory[] of node 0. So both of fault_types[] are set to 0. 4. The values(0) of fault_types[] pass to update_task_scan_period(). 5. numa_faults_locality[1] is set to 1. So the following division is calculated. static void update_task_scan_period(struct task_struct *p, unsigned long shared, unsigned long private){ ... ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared)); } 6. But both of private and shared are set to 0. So divide error occurs here. The divide error is rare case because the trigger is node offline. This patch always increments denominator for avoiding divide error. Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/54475703.8000505@jp.fujitsu.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-10-22 07:04:35 +00:00
ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared + 1));
diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
}
p->numa_scan_period = clamp(p->numa_scan_period + diff,
task_scan_min(p), task_scan_max(p));
memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
}
sched/numa: Normalize faults_cpu stats and weigh by CPU use Tracing the code that decides the active nodes has made it abundantly clear that the naive implementation of the faults_from code has issues. Specifically, the garbage collector in some workloads will access orders of magnitudes more memory than the threads that do all the active work. This resulted in the node with the garbage collector being marked the only active node in the group. This issue is avoided if we weigh the statistics by CPU use of each task in the numa group, instead of by how many faults each thread has occurred. To achieve this, we normalize the number of faults to the fraction of faults that occurred on each node, and then multiply that fraction by the fraction of CPU time the task has used since the last time task_numa_placement was invoked. This way the nodes in the active node mask will be the ones where the tasks from the numa group are most actively running, and the influence of eg. the garbage collector and other do-little threads is properly minimized. On a 4 node system, using CPU use statistics calculated over a longer interval results in about 1% fewer page migrations with two 32-warehouse specjbb runs on a 4 node system, and about 5% fewer page migrations, as well as 1% better throughput, with two 8-warehouse specjbb runs, as compared with the shorter term statistics kept by the scheduler. Signed-off-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Chegu Vinod <chegu_vinod@hp.com> Link: http://lkml.kernel.org/r/1390860228-21539-7-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-01-27 22:03:45 +00:00
/*
* Get the fraction of time the task has been running since the last
* NUMA placement cycle. The scheduler keeps similar statistics, but
* decays those on a 32ms period, which is orders of magnitude off
* from the dozens-of-seconds NUMA balancing period. Use the scheduler
* stats only if the task is so new there are no NUMA statistics yet.
*/
static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
{
u64 runtime, delta, now;
/* Use the start of this time slice to avoid calculations. */
now = p->se.exec_start;
runtime = p->se.sum_exec_runtime;
if (p->last_task_numa_placement) {
delta = runtime - p->last_sum_exec_runtime;
*period = now - p->last_task_numa_placement;
} else {
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
delta = p->se.avg.load_sum / p->se.load.weight;
*period = LOAD_AVG_MAX;
sched/numa: Normalize faults_cpu stats and weigh by CPU use Tracing the code that decides the active nodes has made it abundantly clear that the naive implementation of the faults_from code has issues. Specifically, the garbage collector in some workloads will access orders of magnitudes more memory than the threads that do all the active work. This resulted in the node with the garbage collector being marked the only active node in the group. This issue is avoided if we weigh the statistics by CPU use of each task in the numa group, instead of by how many faults each thread has occurred. To achieve this, we normalize the number of faults to the fraction of faults that occurred on each node, and then multiply that fraction by the fraction of CPU time the task has used since the last time task_numa_placement was invoked. This way the nodes in the active node mask will be the ones where the tasks from the numa group are most actively running, and the influence of eg. the garbage collector and other do-little threads is properly minimized. On a 4 node system, using CPU use statistics calculated over a longer interval results in about 1% fewer page migrations with two 32-warehouse specjbb runs on a 4 node system, and about 5% fewer page migrations, as well as 1% better throughput, with two 8-warehouse specjbb runs, as compared with the shorter term statistics kept by the scheduler. Signed-off-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Chegu Vinod <chegu_vinod@hp.com> Link: http://lkml.kernel.org/r/1390860228-21539-7-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-01-27 22:03:45 +00:00
}
p->last_sum_exec_runtime = runtime;
p->last_task_numa_placement = now;
return delta;
}
/*
* Determine the preferred nid for a task in a numa_group. This needs to
* be done in a way that produces consistent results with group_weight,
* otherwise workloads might not converge.
*/
static int preferred_group_nid(struct task_struct *p, int nid)
{
nodemask_t nodes;
int dist;
/* Direct connections between all NUMA nodes. */
if (sched_numa_topology_type == NUMA_DIRECT)
return nid;
/*
* On a system with glueless mesh NUMA topology, group_weight
* scores nodes according to the number of NUMA hinting faults on
* both the node itself, and on nearby nodes.
*/
if (sched_numa_topology_type == NUMA_GLUELESS_MESH) {
unsigned long score, max_score = 0;
int node, max_node = nid;
dist = sched_max_numa_distance;
for_each_online_node(node) {
score = group_weight(p, node, dist);
if (score > max_score) {
max_score = score;
max_node = node;
}
}
return max_node;
}
/*
* Finding the preferred nid in a system with NUMA backplane
* interconnect topology is more involved. The goal is to locate
* tasks from numa_groups near each other in the system, and
* untangle workloads from different sides of the system. This requires
* searching down the hierarchy of node groups, recursively searching
* inside the highest scoring group of nodes. The nodemask tricks
* keep the complexity of the search down.
*/
nodes = node_online_map;
for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) {
unsigned long max_faults = 0;
2015-01-23 08:25:38 +00:00
nodemask_t max_group = NODE_MASK_NONE;
int a, b;
/* Are there nodes at this distance from each other? */
if (!find_numa_distance(dist))
continue;
for_each_node_mask(a, nodes) {
unsigned long faults = 0;
nodemask_t this_group;
nodes_clear(this_group);
/* Sum group's NUMA faults; includes a==b case. */
for_each_node_mask(b, nodes) {
if (node_distance(a, b) < dist) {
faults += group_faults(p, b);
node_set(b, this_group);
node_clear(b, nodes);
}
}
/* Remember the top group. */
if (faults > max_faults) {
max_faults = faults;
max_group = this_group;
/*
* subtle: at the smallest distance there is
* just one node left in each "group", the
* winner is the preferred nid.
*/
nid = a;
}
}
/* Next round, evaluate the nodes within max_group. */
if (!max_faults)
break;
nodes = max_group;
}
return nid;
}
static void task_numa_placement(struct task_struct *p)
{
int seq, nid, max_nid = -1, max_group_nid = -1;
unsigned long max_faults = 0, max_group_faults = 0;
unsigned long fault_types[2] = { 0, 0 };
sched/numa: Normalize faults_cpu stats and weigh by CPU use Tracing the code that decides the active nodes has made it abundantly clear that the naive implementation of the faults_from code has issues. Specifically, the garbage collector in some workloads will access orders of magnitudes more memory than the threads that do all the active work. This resulted in the node with the garbage collector being marked the only active node in the group. This issue is avoided if we weigh the statistics by CPU use of each task in the numa group, instead of by how many faults each thread has occurred. To achieve this, we normalize the number of faults to the fraction of faults that occurred on each node, and then multiply that fraction by the fraction of CPU time the task has used since the last time task_numa_placement was invoked. This way the nodes in the active node mask will be the ones where the tasks from the numa group are most actively running, and the influence of eg. the garbage collector and other do-little threads is properly minimized. On a 4 node system, using CPU use statistics calculated over a longer interval results in about 1% fewer page migrations with two 32-warehouse specjbb runs on a 4 node system, and about 5% fewer page migrations, as well as 1% better throughput, with two 8-warehouse specjbb runs, as compared with the shorter term statistics kept by the scheduler. Signed-off-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Chegu Vinod <chegu_vinod@hp.com> Link: http://lkml.kernel.org/r/1390860228-21539-7-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-01-27 22:03:45 +00:00
unsigned long total_faults;
u64 runtime, period;
spinlock_t *group_lock = NULL;
/*
* The p->mm->numa_scan_seq field gets updated without
* exclusive access. Use READ_ONCE() here to ensure
* that the field is read in a single access:
*/
seq = READ_ONCE(p->mm->numa_scan_seq);
if (p->numa_scan_seq == seq)
return;
p->numa_scan_seq = seq;
sched/numa: Set the scan rate proportional to the memory usage of the task being scanned The NUMA PTE scan rate is controlled with a combination of the numa_balancing_scan_period_min, numa_balancing_scan_period_max and numa_balancing_scan_size. This scan rate is independent of the size of the task and as an aside it is further complicated by the fact that numa_balancing_scan_size controls how many pages are marked pte_numa and not how much virtual memory is scanned. In combination, it is almost impossible to meaningfully tune the min and max scan periods and reasoning about performance is complex when the time to complete a full scan is is partially a function of the tasks memory size. This patch alters the semantic of the min and max tunables to be about tuning the length time it takes to complete a scan of a tasks occupied virtual address space. Conceptually this is a lot easier to understand. There is a "sanity" check to ensure the scan rate is never extremely fast based on the amount of virtual memory that should be scanned in a second. The default of 2.5G seems arbitrary but it is to have the maximum scan rate after the patch roughly match the maximum scan rate before the patch was applied. On a similar note, numa_scan_period is in milliseconds and not jiffies. Properly placed pages slow the scanning rate but adding 10 jiffies to numa_scan_period means that the rate scanning slows depends on HZ which is confusing. Get rid of the jiffies_to_msec conversion and treat it as ms. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1381141781-10992-18-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-07 10:28:55 +00:00
p->numa_scan_period_max = task_scan_max(p);
sched/numa: Normalize faults_cpu stats and weigh by CPU use Tracing the code that decides the active nodes has made it abundantly clear that the naive implementation of the faults_from code has issues. Specifically, the garbage collector in some workloads will access orders of magnitudes more memory than the threads that do all the active work. This resulted in the node with the garbage collector being marked the only active node in the group. This issue is avoided if we weigh the statistics by CPU use of each task in the numa group, instead of by how many faults each thread has occurred. To achieve this, we normalize the number of faults to the fraction of faults that occurred on each node, and then multiply that fraction by the fraction of CPU time the task has used since the last time task_numa_placement was invoked. This way the nodes in the active node mask will be the ones where the tasks from the numa group are most actively running, and the influence of eg. the garbage collector and other do-little threads is properly minimized. On a 4 node system, using CPU use statistics calculated over a longer interval results in about 1% fewer page migrations with two 32-warehouse specjbb runs on a 4 node system, and about 5% fewer page migrations, as well as 1% better throughput, with two 8-warehouse specjbb runs, as compared with the shorter term statistics kept by the scheduler. Signed-off-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Chegu Vinod <chegu_vinod@hp.com> Link: http://lkml.kernel.org/r/1390860228-21539-7-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-01-27 22:03:45 +00:00
total_faults = p->numa_faults_locality[0] +
p->numa_faults_locality[1];
runtime = numa_get_avg_runtime(p, &period);
/* If the task is part of a group prevent parallel updates to group stats */
if (p->numa_group) {
group_lock = &p->numa_group->lock;
spin_lock_irq(group_lock);
}
/* Find the node with the highest number of faults */
for_each_online_node(nid) {
/* Keep track of the offsets in numa_faults array */
int mem_idx, membuf_idx, cpu_idx, cpubuf_idx;
unsigned long faults = 0, group_faults = 0;
int priv;
for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) {
sched/numa: Normalize faults_cpu stats and weigh by CPU use Tracing the code that decides the active nodes has made it abundantly clear that the naive implementation of the faults_from code has issues. Specifically, the garbage collector in some workloads will access orders of magnitudes more memory than the threads that do all the active work. This resulted in the node with the garbage collector being marked the only active node in the group. This issue is avoided if we weigh the statistics by CPU use of each task in the numa group, instead of by how many faults each thread has occurred. To achieve this, we normalize the number of faults to the fraction of faults that occurred on each node, and then multiply that fraction by the fraction of CPU time the task has used since the last time task_numa_placement was invoked. This way the nodes in the active node mask will be the ones where the tasks from the numa group are most actively running, and the influence of eg. the garbage collector and other do-little threads is properly minimized. On a 4 node system, using CPU use statistics calculated over a longer interval results in about 1% fewer page migrations with two 32-warehouse specjbb runs on a 4 node system, and about 5% fewer page migrations, as well as 1% better throughput, with two 8-warehouse specjbb runs, as compared with the shorter term statistics kept by the scheduler. Signed-off-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Chegu Vinod <chegu_vinod@hp.com> Link: http://lkml.kernel.org/r/1390860228-21539-7-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-01-27 22:03:45 +00:00
long diff, f_diff, f_weight;
mem_idx = task_faults_idx(NUMA_MEM, nid, priv);
membuf_idx = task_faults_idx(NUMA_MEMBUF, nid, priv);
cpu_idx = task_faults_idx(NUMA_CPU, nid, priv);
cpubuf_idx = task_faults_idx(NUMA_CPUBUF, nid, priv);
/* Decay existing window, copy faults since last scan */
diff = p->numa_faults[membuf_idx] - p->numa_faults[mem_idx] / 2;
fault_types[priv] += p->numa_faults[membuf_idx];
p->numa_faults[membuf_idx] = 0;
sched/numa: Normalize faults_cpu stats and weigh by CPU use Tracing the code that decides the active nodes has made it abundantly clear that the naive implementation of the faults_from code has issues. Specifically, the garbage collector in some workloads will access orders of magnitudes more memory than the threads that do all the active work. This resulted in the node with the garbage collector being marked the only active node in the group. This issue is avoided if we weigh the statistics by CPU use of each task in the numa group, instead of by how many faults each thread has occurred. To achieve this, we normalize the number of faults to the fraction of faults that occurred on each node, and then multiply that fraction by the fraction of CPU time the task has used since the last time task_numa_placement was invoked. This way the nodes in the active node mask will be the ones where the tasks from the numa group are most actively running, and the influence of eg. the garbage collector and other do-little threads is properly minimized. On a 4 node system, using CPU use statistics calculated over a longer interval results in about 1% fewer page migrations with two 32-warehouse specjbb runs on a 4 node system, and about 5% fewer page migrations, as well as 1% better throughput, with two 8-warehouse specjbb runs, as compared with the shorter term statistics kept by the scheduler. Signed-off-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Chegu Vinod <chegu_vinod@hp.com> Link: http://lkml.kernel.org/r/1390860228-21539-7-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-01-27 22:03:45 +00:00
/*
* Normalize the faults_from, so all tasks in a group
* count according to CPU use, instead of by the raw
* number of faults. Tasks with little runtime have
* little over-all impact on throughput, and thus their
* faults are less important.
*/
f_weight = div64_u64(runtime << 16, period + 1);
f_weight = (f_weight * p->numa_faults[cpubuf_idx]) /
sched/numa: Normalize faults_cpu stats and weigh by CPU use Tracing the code that decides the active nodes has made it abundantly clear that the naive implementation of the faults_from code has issues. Specifically, the garbage collector in some workloads will access orders of magnitudes more memory than the threads that do all the active work. This resulted in the node with the garbage collector being marked the only active node in the group. This issue is avoided if we weigh the statistics by CPU use of each task in the numa group, instead of by how many faults each thread has occurred. To achieve this, we normalize the number of faults to the fraction of faults that occurred on each node, and then multiply that fraction by the fraction of CPU time the task has used since the last time task_numa_placement was invoked. This way the nodes in the active node mask will be the ones where the tasks from the numa group are most actively running, and the influence of eg. the garbage collector and other do-little threads is properly minimized. On a 4 node system, using CPU use statistics calculated over a longer interval results in about 1% fewer page migrations with two 32-warehouse specjbb runs on a 4 node system, and about 5% fewer page migrations, as well as 1% better throughput, with two 8-warehouse specjbb runs, as compared with the shorter term statistics kept by the scheduler. Signed-off-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Chegu Vinod <chegu_vinod@hp.com> Link: http://lkml.kernel.org/r/1390860228-21539-7-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-01-27 22:03:45 +00:00
(total_faults + 1);
f_diff = f_weight - p->numa_faults[cpu_idx] / 2;
p->numa_faults[cpubuf_idx] = 0;
p->numa_faults[mem_idx] += diff;
p->numa_faults[cpu_idx] += f_diff;
faults += p->numa_faults[mem_idx];
p->total_numa_faults += diff;
if (p->numa_group) {
/*
* safe because we can only change our own group
*
* mem_idx represents the offset for a given
* nid and priv in a specific region because it
* is at the beginning of the numa_faults array.
*/
p->numa_group->faults[mem_idx] += diff;
p->numa_group->faults_cpu[mem_idx] += f_diff;
p->numa_group->total_faults += diff;
group_faults += p->numa_group->faults[mem_idx];
}
}
if (faults > max_faults) {
max_faults = faults;
max_nid = nid;
}
if (group_faults > max_group_faults) {
max_group_faults = group_faults;
max_group_nid = nid;
}
}
update_task_scan_period(p, fault_types[0], fault_types[1]);
if (p->numa_group) {
update_numa_active_node_mask(p->numa_group);
spin_unlock_irq(group_lock);
max_nid = preferred_group_nid(p, max_group_nid);
}
if (max_faults) {
/* Set the new preferred node */
if (max_nid != p->numa_preferred_nid)
sched_setnuma(p, max_nid);
if (task_node(p) != p->numa_preferred_nid)
numa_migrate_preferred(p);
}
}
static inline int get_numa_group(struct numa_group *grp)
{
return atomic_inc_not_zero(&grp->refcount);
}
static inline void put_numa_group(struct numa_group *grp)
{
if (atomic_dec_and_test(&grp->refcount))
kfree_rcu(grp, rcu);
}
static void task_numa_group(struct task_struct *p, int cpupid, int flags,
int *priv)
{
struct numa_group *grp, *my_grp;
struct task_struct *tsk;
bool join = false;
int cpu = cpupid_to_cpu(cpupid);
int i;
if (unlikely(!p->numa_group)) {
unsigned int size = sizeof(struct numa_group) +
4*nr_node_ids*sizeof(unsigned long);
grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
if (!grp)
return;
atomic_set(&grp->refcount, 1);
spin_lock_init(&grp->lock);
grp->gid = p->pid;
/* Second half of the array tracks nids where faults happen */
grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES *
nr_node_ids;
node_set(task_node(current), grp->active_nodes);
for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
grp->faults[i] = p->numa_faults[i];
grp->total_faults = p->total_numa_faults;
grp->nr_tasks++;
rcu_assign_pointer(p->numa_group, grp);
}
rcu_read_lock();
tsk = READ_ONCE(cpu_rq(cpu)->curr);
if (!cpupid_match_pid(tsk, cpupid))
goto no_join;
grp = rcu_dereference(tsk->numa_group);
if (!grp)
goto no_join;
my_grp = p->numa_group;
if (grp == my_grp)
goto no_join;
/*
* Only join the other group if its bigger; if we're the bigger group,
* the other task will join us.
*/
if (my_grp->nr_tasks > grp->nr_tasks)
goto no_join;
/*
* Tie-break on the grp address.
*/
if (my_grp->nr_tasks == grp->nr_tasks && my_grp > grp)
goto no_join;
/* Always join threads in the same process. */
if (tsk->mm == current->mm)
join = true;
/* Simple filter to avoid false positives due to PID collisions */
if (flags & TNF_SHARED)
join = true;
/* Update priv based on whether false sharing was detected */
*priv = !join;
if (join && !get_numa_group(grp))
goto no_join;
rcu_read_unlock();
if (!join)
return;
BUG_ON(irqs_disabled());
double_lock_irq(&my_grp->lock, &grp->lock);
for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) {
my_grp->faults[i] -= p->numa_faults[i];
grp->faults[i] += p->numa_faults[i];
}
my_grp->total_faults -= p->total_numa_faults;
grp->total_faults += p->total_numa_faults;
my_grp->nr_tasks--;
grp->nr_tasks++;
spin_unlock(&my_grp->lock);
spin_unlock_irq(&grp->lock);
rcu_assign_pointer(p->numa_group, grp);
put_numa_group(my_grp);
return;
no_join:
rcu_read_unlock();
return;
}
void task_numa_free(struct task_struct *p)
{
struct numa_group *grp = p->numa_group;
void *numa_faults = p->numa_faults;
unsigned long flags;
int i;
if (grp) {
spin_lock_irqsave(&grp->lock, flags);
for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
grp->faults[i] -= p->numa_faults[i];
grp->total_faults -= p->total_numa_faults;
grp->nr_tasks--;
spin_unlock_irqrestore(&grp->lock, flags);
RCU_INIT_POINTER(p->numa_group, NULL);
put_numa_group(grp);
}
p->numa_faults = NULL;
kfree(numa_faults);
}
/*
* Got a PROT_NONE fault for a page on @node.
*/
void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
{
struct task_struct *p = current;
bool migrated = flags & TNF_MIGRATED;
int cpu_node = task_node(current);
int local = !!(flags & TNF_FAULT_LOCAL);
int priv;
if (!static_branch_likely(&sched_numa_balancing))
return;
/* for example, ksmd faulting in a user's mm */
if (!p->mm)
return;
/* Allocate buffer to track faults on a per-node basis */
if (unlikely(!p->numa_faults)) {
int size = sizeof(*p->numa_faults) *
NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids;
p->numa_faults = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
if (!p->numa_faults)
return;
p->total_numa_faults = 0;
memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
}
/*
* First accesses are treated as private, otherwise consider accesses
* to be private if the accessing pid has not changed
*/
if (unlikely(last_cpupid == (-1 & LAST_CPUPID_MASK))) {
priv = 1;
} else {
priv = cpupid_match_pid(p, last_cpupid);
if (!priv && !(flags & TNF_NO_GROUP))
task_numa_group(p, last_cpupid, flags, &priv);
}
/*
* If a workload spans multiple NUMA nodes, a shared fault that
* occurs wholly within the set of nodes that the workload is
* actively using should be counted as local. This allows the
* scan rate to slow down when a workload has settled down.
*/
if (!priv && !local && p->numa_group &&
node_isset(cpu_node, p->numa_group->active_nodes) &&
node_isset(mem_node, p->numa_group->active_nodes))
local = 1;
task_numa_placement(p);
/*
* Retry task to preferred node migration periodically, in case it
* case it previously failed, or the scheduler moved us.
*/
if (time_after(jiffies, p->numa_migrate_retry))
numa_migrate_preferred(p);
if (migrated)
p->numa_pages_migrated += pages;
mm: numa: slow PTE scan rate if migration failures occur Dave Chinner reported the following on https://lkml.org/lkml/2015/3/1/226 Across the board the 4.0-rc1 numbers are much slower, and the degradation is far worse when using the large memory footprint configs. Perf points straight at the cause - this is from 4.0-rc1 on the "-o bhash=101073" config: - 56.07% 56.07% [kernel] [k] default_send_IPI_mask_sequence_phys - default_send_IPI_mask_sequence_phys - 99.99% physflat_send_IPI_mask - 99.37% native_send_call_func_ipi smp_call_function_many - native_flush_tlb_others - 99.85% flush_tlb_page ptep_clear_flush try_to_unmap_one rmap_walk try_to_unmap migrate_pages migrate_misplaced_page - handle_mm_fault - 99.73% __do_page_fault trace_do_page_fault do_async_page_fault + async_page_fault 0.63% native_send_call_func_single_ipi generic_exec_single smp_call_function_single This is showing excessive migration activity even though excessive migrations are meant to get throttled. Normally, the scan rate is tuned on a per-task basis depending on the locality of faults. However, if migrations fail for any reason then the PTE scanner may scan faster if the faults continue to be remote. This means there is higher system CPU overhead and fault trapping at exactly the time we know that migrations cannot happen. This patch tracks when migration failures occur and slows the PTE scanner. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Dave Chinner <david@fromorbit.com> Tested-by: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-03-25 22:55:42 +00:00
if (flags & TNF_MIGRATE_FAIL)
p->numa_faults_locality[2] += pages;
p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages;
p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages;
p->numa_faults_locality[local] += pages;
}
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
static void reset_ptenuma_scan(struct task_struct *p)
{
/*
* We only did a read acquisition of the mmap sem, so
* p->mm->numa_scan_seq is written to without exclusive access
* and the update is not guaranteed to be atomic. That's not
* much of an issue though, since this is just used for
* statistical sampling. Use READ_ONCE/WRITE_ONCE, which are not
* expensive, to avoid any form of compiler optimizations:
*/
WRITE_ONCE(p->mm->numa_scan_seq, READ_ONCE(p->mm->numa_scan_seq) + 1);
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
p->mm->numa_scan_offset = 0;
}
/*
* The expensive part of numa migration is done from task_work context.
* Triggered from task_tick_numa().
*/
void task_numa_work(struct callback_head *work)
{
unsigned long migrate, next_scan, now = jiffies;
struct task_struct *p = current;
struct mm_struct *mm = p->mm;
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
struct vm_area_struct *vma;
unsigned long start, end;
sched/numa: Set the scan rate proportional to the memory usage of the task being scanned The NUMA PTE scan rate is controlled with a combination of the numa_balancing_scan_period_min, numa_balancing_scan_period_max and numa_balancing_scan_size. This scan rate is independent of the size of the task and as an aside it is further complicated by the fact that numa_balancing_scan_size controls how many pages are marked pte_numa and not how much virtual memory is scanned. In combination, it is almost impossible to meaningfully tune the min and max scan periods and reasoning about performance is complex when the time to complete a full scan is is partially a function of the tasks memory size. This patch alters the semantic of the min and max tunables to be about tuning the length time it takes to complete a scan of a tasks occupied virtual address space. Conceptually this is a lot easier to understand. There is a "sanity" check to ensure the scan rate is never extremely fast based on the amount of virtual memory that should be scanned in a second. The default of 2.5G seems arbitrary but it is to have the maximum scan rate after the patch roughly match the maximum scan rate before the patch was applied. On a similar note, numa_scan_period is in milliseconds and not jiffies. Properly placed pages slow the scanning rate but adding 10 jiffies to numa_scan_period means that the rate scanning slows depends on HZ which is confusing. Get rid of the jiffies_to_msec conversion and treat it as ms. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1381141781-10992-18-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-07 10:28:55 +00:00
unsigned long nr_pte_updates = 0;
long pages;
WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));
work->next = work; /* protect against double add */
/*
* Who cares about NUMA placement when they're dying.
*
* NOTE: make sure not to dereference p->mm before this check,
* exit_task_work() happens _after_ exit_mm() so we could be called
* without p->mm even though we still had it when we enqueued this
* work.
*/
if (p->flags & PF_EXITING)
return;
if (!mm->numa_next_scan) {
mm->numa_next_scan = now +
msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
}
/*
* Enforce maximal scan/migration frequency..
*/
migrate = mm->numa_next_scan;
if (time_before(now, migrate))
return;
sched/numa: Set the scan rate proportional to the memory usage of the task being scanned The NUMA PTE scan rate is controlled with a combination of the numa_balancing_scan_period_min, numa_balancing_scan_period_max and numa_balancing_scan_size. This scan rate is independent of the size of the task and as an aside it is further complicated by the fact that numa_balancing_scan_size controls how many pages are marked pte_numa and not how much virtual memory is scanned. In combination, it is almost impossible to meaningfully tune the min and max scan periods and reasoning about performance is complex when the time to complete a full scan is is partially a function of the tasks memory size. This patch alters the semantic of the min and max tunables to be about tuning the length time it takes to complete a scan of a tasks occupied virtual address space. Conceptually this is a lot easier to understand. There is a "sanity" check to ensure the scan rate is never extremely fast based on the amount of virtual memory that should be scanned in a second. The default of 2.5G seems arbitrary but it is to have the maximum scan rate after the patch roughly match the maximum scan rate before the patch was applied. On a similar note, numa_scan_period is in milliseconds and not jiffies. Properly placed pages slow the scanning rate but adding 10 jiffies to numa_scan_period means that the rate scanning slows depends on HZ which is confusing. Get rid of the jiffies_to_msec conversion and treat it as ms. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1381141781-10992-18-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-07 10:28:55 +00:00
if (p->numa_scan_period == 0) {
p->numa_scan_period_max = task_scan_max(p);
p->numa_scan_period = task_scan_min(p);
}
next_scan = now + msecs_to_jiffies(p->numa_scan_period);
if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
return;
sched/numa: Mitigate chance that same task always updates PTEs With a trace_printk("working\n"); right after the cmpxchg in task_numa_work() we can see that of a 4 thread process, its always the same task winning the race and doing the protection change. This is a problem since the task doing the protection change has a penalty for taking faults -- it is busy when marking the PTEs. If its always the same task the ->numa_faults[] get severely skewed. Avoid this by delaying the task doing the protection change such that it is unlikely to win the privilege again. Before: root@interlagos:~# grep "thread 0/.*working" /debug/tracing/trace | tail -15 thread 0/0-3232 [022] .... 212.787402: task_numa_work: working thread 0/0-3232 [022] .... 212.888473: task_numa_work: working thread 0/0-3232 [022] .... 212.989538: task_numa_work: working thread 0/0-3232 [022] .... 213.090602: task_numa_work: working thread 0/0-3232 [022] .... 213.191667: task_numa_work: working thread 0/0-3232 [022] .... 213.292734: task_numa_work: working thread 0/0-3232 [022] .... 213.393804: task_numa_work: working thread 0/0-3232 [022] .... 213.494869: task_numa_work: working thread 0/0-3232 [022] .... 213.596937: task_numa_work: working thread 0/0-3232 [022] .... 213.699000: task_numa_work: working thread 0/0-3232 [022] .... 213.801067: task_numa_work: working thread 0/0-3232 [022] .... 213.903155: task_numa_work: working thread 0/0-3232 [022] .... 214.005201: task_numa_work: working thread 0/0-3232 [022] .... 214.107266: task_numa_work: working thread 0/0-3232 [022] .... 214.209342: task_numa_work: working After: root@interlagos:~# grep "thread 0/.*working" /debug/tracing/trace | tail -15 thread 0/0-3253 [005] .... 136.865051: task_numa_work: working thread 0/2-3255 [026] .... 136.965134: task_numa_work: working thread 0/3-3256 [024] .... 137.065217: task_numa_work: working thread 0/3-3256 [024] .... 137.165302: task_numa_work: working thread 0/3-3256 [024] .... 137.265382: task_numa_work: working thread 0/0-3253 [004] .... 137.366465: task_numa_work: working thread 0/2-3255 [026] .... 137.466549: task_numa_work: working thread 0/0-3253 [004] .... 137.566629: task_numa_work: working thread 0/0-3253 [004] .... 137.666711: task_numa_work: working thread 0/1-3254 [028] .... 137.766799: task_numa_work: working thread 0/0-3253 [004] .... 137.866876: task_numa_work: working thread 0/2-3255 [026] .... 137.966960: task_numa_work: working thread 0/1-3254 [028] .... 138.067041: task_numa_work: working thread 0/2-3255 [026] .... 138.167123: task_numa_work: working thread 0/3-3256 [024] .... 138.267207: task_numa_work: working Signed-off-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1381141781-10992-14-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-07 10:28:51 +00:00
/*
* Delay this task enough that another task of this mm will likely win
* the next time around.
*/
p->node_stamp += 2 * TICK_NSEC;
start = mm->numa_scan_offset;
pages = sysctl_numa_balancing_scan_size;
pages <<= 20 - PAGE_SHIFT; /* MB in pages */
if (!pages)
return;
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
down_read(&mm->mmap_sem);
vma = find_vma(mm, start);
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
if (!vma) {
reset_ptenuma_scan(p);
start = 0;
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
vma = mm->mmap;
}
for (; vma; vma = vma->vm_next) {
if (!vma_migratable(vma) || !vma_policy_mof(vma) ||
sched, numa: do not hint for NUMA balancing on VM_MIXEDMAP mappings Jovi Zhangwei reported the following problem Below kernel vm bug can be triggered by tcpdump which mmaped a lot of pages with GFP_COMP flag. [Mon May 25 05:29:33 2015] page:ffffea0015414000 count:66 mapcount:1 mapping: (null) index:0x0 [Mon May 25 05:29:33 2015] flags: 0x20047580004000(head) [Mon May 25 05:29:33 2015] page dumped because: VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page)) [Mon May 25 05:29:33 2015] ------------[ cut here ]------------ [Mon May 25 05:29:33 2015] kernel BUG at mm/migrate.c:1661! [Mon May 25 05:29:33 2015] invalid opcode: 0000 [#1] SMP In this case it was triggered by running tcpdump but it's not necessary reproducible on all systems. sudo tcpdump -i bond0.100 'tcp port 4242' -c 100000000000 -w 4242.pcap Compound pages cannot be migrated and it was not expected that such pages be marked for NUMA balancing. This did not take into account that drivers such as net/packet/af_packet.c may insert compound pages into userspace with vm_insert_page. This patch tells the NUMA balancing protection scanner to skip all VM_MIXEDMAP mappings which avoids the possibility that compound pages are marked for migration. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Jovi Zhangwei <jovi@cloudflare.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-10 18:15:00 +00:00
is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) {
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
continue;
}
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
/*
* Shared library pages mapped by multiple processes are not
* migrated as it is expected they are cache replicated. Avoid
* hinting faults in read-only file-backed mappings or the vdso
* as migrating the pages will be of marginal benefit.
*/
if (!vma->vm_mm ||
(vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ)))
continue;
/*
* Skip inaccessible VMAs to avoid any confusion between
* PROT_NONE and NUMA hinting ptes
*/
if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
continue;
do {
start = max(start, vma->vm_start);
end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
end = min(end, vma->vm_end);
sched/numa: Set the scan rate proportional to the memory usage of the task being scanned The NUMA PTE scan rate is controlled with a combination of the numa_balancing_scan_period_min, numa_balancing_scan_period_max and numa_balancing_scan_size. This scan rate is independent of the size of the task and as an aside it is further complicated by the fact that numa_balancing_scan_size controls how many pages are marked pte_numa and not how much virtual memory is scanned. In combination, it is almost impossible to meaningfully tune the min and max scan periods and reasoning about performance is complex when the time to complete a full scan is is partially a function of the tasks memory size. This patch alters the semantic of the min and max tunables to be about tuning the length time it takes to complete a scan of a tasks occupied virtual address space. Conceptually this is a lot easier to understand. There is a "sanity" check to ensure the scan rate is never extremely fast based on the amount of virtual memory that should be scanned in a second. The default of 2.5G seems arbitrary but it is to have the maximum scan rate after the patch roughly match the maximum scan rate before the patch was applied. On a similar note, numa_scan_period is in milliseconds and not jiffies. Properly placed pages slow the scanning rate but adding 10 jiffies to numa_scan_period means that the rate scanning slows depends on HZ which is confusing. Get rid of the jiffies_to_msec conversion and treat it as ms. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1381141781-10992-18-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-07 10:28:55 +00:00
nr_pte_updates += change_prot_numa(vma, start, end);
/*
* Scan sysctl_numa_balancing_scan_size but ensure that
* at least one PTE is updated so that unused virtual
* address space is quickly skipped.
*/
if (nr_pte_updates)
pages -= (end - start) >> PAGE_SHIFT;
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
start = end;
if (pages <= 0)
goto out;
cond_resched();
} while (end != vma->vm_end);
}
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
out:
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
/*
* It is possible to reach the end of the VMA list but the last few
* VMAs are not guaranteed to the vma_migratable. If they are not, we
* would find the !migratable VMA on the next scan but not reset the
* scanner to the start so check it now.
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
*/
if (vma)
mm->numa_scan_offset = start;
mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Previously, to probe the working set of a task, we'd use a very simple and crude method: mark all of its address space PROT_NONE. That method has various (obvious) disadvantages: - it samples the working set at dissimilar rates, giving some tasks a sampling quality advantage over others. - creates performance problems for tasks with very large working sets - over-samples processes with large address spaces but which only very rarely execute Improve that method by keeping a rotating offset into the address space that marks the current position of the scan, and advance it by a constant rate (in a CPU cycles execution proportional manner). If the offset reaches the last mapped address of the mm then it then it starts over at the first address. The per-task nature of the working set sampling functionality in this tree allows such constant rate, per task, execution-weight proportional sampling of the working set, with an adaptive sampling interval/frequency that goes from once per 100ms up to just once per 8 seconds. The current sampling volume is 256 MB per interval. As tasks mature and converge their working set, so does the sampling rate slow down to just a trickle, 256 MB per 8 seconds of CPU time executed. This, beyond being adaptive, also rate-limits rarely executing systems and does not over-sample on overloaded systems. [ In AutoNUMA speak, this patch deals with the effective sampling rate of the 'hinting page fault'. AutoNUMA's scanning is currently rate-limited, but it is also fundamentally single-threaded, executing in the knuma_scand kernel thread, so the limit in AutoNUMA is global and does not scale up with the number of CPUs, nor does it scan tasks in an execution proportional manner. So the idea of rate-limiting the scanning was first implemented in the AutoNUMA tree via a global rate limit. This patch goes beyond that by implementing an execution rate proportional working set sampling rate that is not implemented via a single global scanning daemon. ] [ Dan Carpenter pointed out a possible NULL pointer dereference in the first version of this patch. ] Based-on-idea-by: Andrea Arcangeli <aarcange@redhat.com> Bug-Found-By: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote changelog and fixed bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:45 +00:00
else
reset_ptenuma_scan(p);
up_read(&mm->mmap_sem);
}
/*
* Drive the periodic memory faults..
*/
void task_tick_numa(struct rq *rq, struct task_struct *curr)
{
struct callback_head *work = &curr->numa_work;
u64 period, now;
/*
* We don't care about NUMA placement if we don't have memory.
*/
if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work)
return;
/*
* Using runtime rather than walltime has the dual advantage that
* we (mostly) drive the selection from busy threads and that the
* task needs to have done some actual work before we bother with
* NUMA placement.
*/
now = curr->se.sum_exec_runtime;
period = (u64)curr->numa_scan_period * NSEC_PER_MSEC;
if (now - curr->node_stamp > period) {
mm: sched: numa: Implement slow start for working set sampling Add a 1 second delay before starting to scan the working set of a task and starting to balance it amongst nodes. [ note that before the constant per task WSS sampling rate patch the initial scan would happen much later still, in effect that patch caused this regression. ] The theory is that short-run tasks benefit very little from NUMA placement: they come and go, and they better stick to the node they were started on. As tasks mature and rebalance to other CPUs and nodes, so does their NUMA placement have to change and so does it start to matter more and more. In practice this change fixes an observable kbuild regression: # [ a perf stat --null --repeat 10 test of ten bzImage builds to /dev/shm ] !NUMA: 45.291088843 seconds time elapsed ( +- 0.40% ) 45.154231752 seconds time elapsed ( +- 0.36% ) +NUMA, no slow start: 46.172308123 seconds time elapsed ( +- 0.30% ) 46.343168745 seconds time elapsed ( +- 0.25% ) +NUMA, 1 sec slow start: 45.224189155 seconds time elapsed ( +- 0.25% ) 45.160866532 seconds time elapsed ( +- 0.17% ) and it also fixes an observable perf bench (hackbench) regression: # perf stat --null --repeat 10 perf bench sched messaging -NUMA: -NUMA: 0.246225691 seconds time elapsed ( +- 1.31% ) +NUMA no slow start: 0.252620063 seconds time elapsed ( +- 1.13% ) +NUMA 1sec delay: 0.248076230 seconds time elapsed ( +- 1.35% ) The implementation is simple and straightforward, most of the patch deals with adding the /proc/sys/kernel/numa_balancing_scan_delay_ms tunable knob. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> [ Wrote the changelog, ran measurements, tuned the default. ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com>
2012-10-25 12:16:47 +00:00
if (!curr->node_stamp)
sched/numa: Set the scan rate proportional to the memory usage of the task being scanned The NUMA PTE scan rate is controlled with a combination of the numa_balancing_scan_period_min, numa_balancing_scan_period_max and numa_balancing_scan_size. This scan rate is independent of the size of the task and as an aside it is further complicated by the fact that numa_balancing_scan_size controls how many pages are marked pte_numa and not how much virtual memory is scanned. In combination, it is almost impossible to meaningfully tune the min and max scan periods and reasoning about performance is complex when the time to complete a full scan is is partially a function of the tasks memory size. This patch alters the semantic of the min and max tunables to be about tuning the length time it takes to complete a scan of a tasks occupied virtual address space. Conceptually this is a lot easier to understand. There is a "sanity" check to ensure the scan rate is never extremely fast based on the amount of virtual memory that should be scanned in a second. The default of 2.5G seems arbitrary but it is to have the maximum scan rate after the patch roughly match the maximum scan rate before the patch was applied. On a similar note, numa_scan_period is in milliseconds and not jiffies. Properly placed pages slow the scanning rate but adding 10 jiffies to numa_scan_period means that the rate scanning slows depends on HZ which is confusing. Get rid of the jiffies_to_msec conversion and treat it as ms. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1381141781-10992-18-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-07 10:28:55 +00:00
curr->numa_scan_period = task_scan_min(curr);
sched/numa: Mitigate chance that same task always updates PTEs With a trace_printk("working\n"); right after the cmpxchg in task_numa_work() we can see that of a 4 thread process, its always the same task winning the race and doing the protection change. This is a problem since the task doing the protection change has a penalty for taking faults -- it is busy when marking the PTEs. If its always the same task the ->numa_faults[] get severely skewed. Avoid this by delaying the task doing the protection change such that it is unlikely to win the privilege again. Before: root@interlagos:~# grep "thread 0/.*working" /debug/tracing/trace | tail -15 thread 0/0-3232 [022] .... 212.787402: task_numa_work: working thread 0/0-3232 [022] .... 212.888473: task_numa_work: working thread 0/0-3232 [022] .... 212.989538: task_numa_work: working thread 0/0-3232 [022] .... 213.090602: task_numa_work: working thread 0/0-3232 [022] .... 213.191667: task_numa_work: working thread 0/0-3232 [022] .... 213.292734: task_numa_work: working thread 0/0-3232 [022] .... 213.393804: task_numa_work: working thread 0/0-3232 [022] .... 213.494869: task_numa_work: working thread 0/0-3232 [022] .... 213.596937: task_numa_work: working thread 0/0-3232 [022] .... 213.699000: task_numa_work: working thread 0/0-3232 [022] .... 213.801067: task_numa_work: working thread 0/0-3232 [022] .... 213.903155: task_numa_work: working thread 0/0-3232 [022] .... 214.005201: task_numa_work: working thread 0/0-3232 [022] .... 214.107266: task_numa_work: working thread 0/0-3232 [022] .... 214.209342: task_numa_work: working After: root@interlagos:~# grep "thread 0/.*working" /debug/tracing/trace | tail -15 thread 0/0-3253 [005] .... 136.865051: task_numa_work: working thread 0/2-3255 [026] .... 136.965134: task_numa_work: working thread 0/3-3256 [024] .... 137.065217: task_numa_work: working thread 0/3-3256 [024] .... 137.165302: task_numa_work: working thread 0/3-3256 [024] .... 137.265382: task_numa_work: working thread 0/0-3253 [004] .... 137.366465: task_numa_work: working thread 0/2-3255 [026] .... 137.466549: task_numa_work: working thread 0/0-3253 [004] .... 137.566629: task_numa_work: working thread 0/0-3253 [004] .... 137.666711: task_numa_work: working thread 0/1-3254 [028] .... 137.766799: task_numa_work: working thread 0/0-3253 [004] .... 137.866876: task_numa_work: working thread 0/2-3255 [026] .... 137.966960: task_numa_work: working thread 0/1-3254 [028] .... 138.067041: task_numa_work: working thread 0/2-3255 [026] .... 138.167123: task_numa_work: working thread 0/3-3256 [024] .... 138.267207: task_numa_work: working Signed-off-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1381141781-10992-14-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-07 10:28:51 +00:00
curr->node_stamp += period;
if (!time_before(jiffies, curr->mm->numa_next_scan)) {
init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */
task_work_add(curr, work, true);
}
}
}
#else
static void task_tick_numa(struct rq *rq, struct task_struct *curr)
{
}
static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p)
{
}
static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p)
{
}
#endif /* CONFIG_NUMA_BALANCING */
static void
account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
update_load_add(&cfs_rq->load, se->load.weight);
if (!parent_entity(se))
update_load_add(&rq_of(cfs_rq)->load, se->load.weight);
#ifdef CONFIG_SMP
if (entity_is_task(se)) {
struct rq *rq = rq_of(cfs_rq);
account_numa_enqueue(rq, task_of(se));
list_add(&se->group_node, &rq->cfs_tasks);
}
#endif
cfs_rq->nr_running++;
}
static void
account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
update_load_sub(&cfs_rq->load, se->load.weight);
if (!parent_entity(se))
update_load_sub(&rq_of(cfs_rq)->load, se->load.weight);
if (entity_is_task(se)) {
account_numa_dequeue(rq_of(cfs_rq), task_of(se));
list_del_init(&se->group_node);
}
cfs_rq->nr_running--;
}
#ifdef CONFIG_FAIR_GROUP_SCHED
# ifdef CONFIG_SMP
static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
{
long tg_weight;
/*
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
* Use this CPU's real-time load instead of the last load contribution
* as the updating of the contribution is delayed, and we will use the
* the real-time load to calc the share. See update_tg_load_avg().
*/
tg_weight = atomic_long_read(&tg->load_avg);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
tg_weight -= cfs_rq->tg_load_avg_contrib;
tg_weight += cfs_rq_load_avg(cfs_rq);
return tg_weight;
}
static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
long tg_weight, load, shares;
tg_weight = calc_tg_weight(tg, cfs_rq);
load = cfs_rq_load_avg(cfs_rq);
shares = (tg->shares * load);
if (tg_weight)
shares /= tg_weight;
if (shares < MIN_SHARES)
shares = MIN_SHARES;
if (shares > tg->shares)
shares = tg->shares;
return shares;
}
# else /* CONFIG_SMP */
static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
return tg->shares;
}
# endif /* CONFIG_SMP */
static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
unsigned long weight)
{
if (se->on_rq) {
/* commit outstanding execution time */
if (cfs_rq->curr == se)
update_curr(cfs_rq);
account_entity_dequeue(cfs_rq, se);
}
update_load_set(&se->load, weight);
if (se->on_rq)
account_entity_enqueue(cfs_rq, se);
}
static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
static void update_cfs_shares(struct cfs_rq *cfs_rq)
{
struct task_group *tg;
struct sched_entity *se;
long shares;
tg = cfs_rq->tg;
se = tg->se[cpu_of(rq_of(cfs_rq))];
if (!se || throttled_hierarchy(cfs_rq))
return;
#ifndef CONFIG_SMP
if (likely(se->load.weight == tg->shares))
return;
#endif
shares = calc_cfs_shares(cfs_rq, tg);
reweight_entity(cfs_rq_of(se), se, shares);
}
#else /* CONFIG_FAIR_GROUP_SCHED */
static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
{
}
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_SMP
sched: Make __update_entity_runnable_avg() fast __update_entity_runnable_avg forms the core of maintaining an entity's runnable load average. In this function we charge the accumulated run-time since last update and handle appropriate decay. In some cases, e.g. a waking task, this time interval may be much larger than our period unit. Fortunately we can exploit some properties of our series to perform decay for a blocked update in constant time and account the contribution for a running update in essentially-constant* time. [*]: For any running entity they should be performing updates at the tick which gives us a soft limit of 1 jiffy between updates, and we can compute up to a 32 jiffy update in a single pass. C program to generate the magic constants in the arrays: #include <math.h> #include <stdio.h> #define N 32 #define WMULT_SHIFT 32 const long WMULT_CONST = ((1UL << N) - 1); double y; long runnable_avg_yN_inv[N]; void calc_mult_inv() { int i; double yn = 0; printf("inverses\n"); for (i = 0; i < N; i++) { yn = (double)WMULT_CONST * pow(y, i); runnable_avg_yN_inv[i] = yn; printf("%2d: 0x%8lx\n", i, runnable_avg_yN_inv[i]); } printf("\n"); } long mult_inv(long c, int n) { return (c * runnable_avg_yN_inv[n]) >> WMULT_SHIFT; } void calc_yn_sum(int n) { int i; double sum = 0, sum_fl = 0, diff = 0; /* * We take the floored sum to ensure the sum of partial sums is never * larger than the actual sum. */ printf("sum y^n\n"); printf(" %8s %8s %8s\n", "exact", "floor", "error"); for (i = 1; i <= n; i++) { sum = (y * sum + y * 1024); sum_fl = floor(y * sum_fl+ y * 1024); printf("%2d: %8.0f %8.0f %8.0f\n", i, sum, sum_fl, sum_fl - sum); } printf("\n"); } void calc_conv(long n) { long old_n; int i = -1; printf("convergence (LOAD_AVG_MAX, LOAD_AVG_MAX_N)\n"); do { old_n = n; n = mult_inv(n, 1) + 1024; i++; } while (n != old_n); printf("%d> %ld\n", i - 1, n); printf("\n"); } void main() { y = pow(0.5, 1/(double)N); calc_mult_inv(); calc_conv(1024); calc_yn_sum(N); } [ Compile with -lm ] Signed-off-by: Paul Turner <pjt@google.com> Reviewed-by: Ben Segall <bsegall@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20120823141507.277808946@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-10-04 11:18:32 +00:00
/* Precomputed fixed inverse multiplies for multiplication by y^n */
static const u32 runnable_avg_yN_inv[] = {
0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6,
0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85,
0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581,
0xad583ee9, 0xa9a15ab4, 0xa5fed6a9, 0xa2704302, 0x9ef5325f, 0x9b8d39b9,
0x9837f050, 0x94f4efa8, 0x91c3d373, 0x8ea4398a, 0x8b95c1e3, 0x88980e80,
0x85aac367, 0x82cd8698,
};
/*
* Precomputed \Sum y^k { 1<=k<=n }. These are floor(true_value) to prevent
* over-estimates when re-combining.
*/
static const u32 runnable_avg_yN_sum[] = {
0, 1002, 1982, 2941, 3880, 4798, 5697, 6576, 7437, 8279, 9103,
9909,10698,11470,12226,12966,13690,14398,15091,15769,16433,17082,
17718,18340,18949,19545,20128,20698,21256,21802,22336,22859,23371,
};
/*
* Approximate:
* val * y^n, where y^32 ~= 0.5 (~1 scheduling period)
*/
static __always_inline u64 decay_load(u64 val, u64 n)
{
sched: Make __update_entity_runnable_avg() fast __update_entity_runnable_avg forms the core of maintaining an entity's runnable load average. In this function we charge the accumulated run-time since last update and handle appropriate decay. In some cases, e.g. a waking task, this time interval may be much larger than our period unit. Fortunately we can exploit some properties of our series to perform decay for a blocked update in constant time and account the contribution for a running update in essentially-constant* time. [*]: For any running entity they should be performing updates at the tick which gives us a soft limit of 1 jiffy between updates, and we can compute up to a 32 jiffy update in a single pass. C program to generate the magic constants in the arrays: #include <math.h> #include <stdio.h> #define N 32 #define WMULT_SHIFT 32 const long WMULT_CONST = ((1UL << N) - 1); double y; long runnable_avg_yN_inv[N]; void calc_mult_inv() { int i; double yn = 0; printf("inverses\n"); for (i = 0; i < N; i++) { yn = (double)WMULT_CONST * pow(y, i); runnable_avg_yN_inv[i] = yn; printf("%2d: 0x%8lx\n", i, runnable_avg_yN_inv[i]); } printf("\n"); } long mult_inv(long c, int n) { return (c * runnable_avg_yN_inv[n]) >> WMULT_SHIFT; } void calc_yn_sum(int n) { int i; double sum = 0, sum_fl = 0, diff = 0; /* * We take the floored sum to ensure the sum of partial sums is never * larger than the actual sum. */ printf("sum y^n\n"); printf(" %8s %8s %8s\n", "exact", "floor", "error"); for (i = 1; i <= n; i++) { sum = (y * sum + y * 1024); sum_fl = floor(y * sum_fl+ y * 1024); printf("%2d: %8.0f %8.0f %8.0f\n", i, sum, sum_fl, sum_fl - sum); } printf("\n"); } void calc_conv(long n) { long old_n; int i = -1; printf("convergence (LOAD_AVG_MAX, LOAD_AVG_MAX_N)\n"); do { old_n = n; n = mult_inv(n, 1) + 1024; i++; } while (n != old_n); printf("%d> %ld\n", i - 1, n); printf("\n"); } void main() { y = pow(0.5, 1/(double)N); calc_mult_inv(); calc_conv(1024); calc_yn_sum(N); } [ Compile with -lm ] Signed-off-by: Paul Turner <pjt@google.com> Reviewed-by: Ben Segall <bsegall@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20120823141507.277808946@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-10-04 11:18:32 +00:00
unsigned int local_n;
if (!n)
return val;
else if (unlikely(n > LOAD_AVG_PERIOD * 63))
return 0;
/* after bounds checking we can collapse to 32-bit */
local_n = n;
/*
* As y^PERIOD = 1/2, we can combine
* y^n = 1/2^(n/PERIOD) * y^(n%PERIOD)
* With a look-up table which covers y^n (n<PERIOD)
sched: Make __update_entity_runnable_avg() fast __update_entity_runnable_avg forms the core of maintaining an entity's runnable load average. In this function we charge the accumulated run-time since last update and handle appropriate decay. In some cases, e.g. a waking task, this time interval may be much larger than our period unit. Fortunately we can exploit some properties of our series to perform decay for a blocked update in constant time and account the contribution for a running update in essentially-constant* time. [*]: For any running entity they should be performing updates at the tick which gives us a soft limit of 1 jiffy between updates, and we can compute up to a 32 jiffy update in a single pass. C program to generate the magic constants in the arrays: #include <math.h> #include <stdio.h> #define N 32 #define WMULT_SHIFT 32 const long WMULT_CONST = ((1UL << N) - 1); double y; long runnable_avg_yN_inv[N]; void calc_mult_inv() { int i; double yn = 0; printf("inverses\n"); for (i = 0; i < N; i++) { yn = (double)WMULT_CONST * pow(y, i); runnable_avg_yN_inv[i] = yn; printf("%2d: 0x%8lx\n", i, runnable_avg_yN_inv[i]); } printf("\n"); } long mult_inv(long c, int n) { return (c * runnable_avg_yN_inv[n]) >> WMULT_SHIFT; } void calc_yn_sum(int n) { int i; double sum = 0, sum_fl = 0, diff = 0; /* * We take the floored sum to ensure the sum of partial sums is never * larger than the actual sum. */ printf("sum y^n\n"); printf(" %8s %8s %8s\n", "exact", "floor", "error"); for (i = 1; i <= n; i++) { sum = (y * sum + y * 1024); sum_fl = floor(y * sum_fl+ y * 1024); printf("%2d: %8.0f %8.0f %8.0f\n", i, sum, sum_fl, sum_fl - sum); } printf("\n"); } void calc_conv(long n) { long old_n; int i = -1; printf("convergence (LOAD_AVG_MAX, LOAD_AVG_MAX_N)\n"); do { old_n = n; n = mult_inv(n, 1) + 1024; i++; } while (n != old_n); printf("%d> %ld\n", i - 1, n); printf("\n"); } void main() { y = pow(0.5, 1/(double)N); calc_mult_inv(); calc_conv(1024); calc_yn_sum(N); } [ Compile with -lm ] Signed-off-by: Paul Turner <pjt@google.com> Reviewed-by: Ben Segall <bsegall@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20120823141507.277808946@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-10-04 11:18:32 +00:00
*
* To achieve constant time decay_load.
*/
if (unlikely(local_n >= LOAD_AVG_PERIOD)) {
val >>= local_n / LOAD_AVG_PERIOD;
local_n %= LOAD_AVG_PERIOD;
}
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32);
return val;
sched: Make __update_entity_runnable_avg() fast __update_entity_runnable_avg forms the core of maintaining an entity's runnable load average. In this function we charge the accumulated run-time since last update and handle appropriate decay. In some cases, e.g. a waking task, this time interval may be much larger than our period unit. Fortunately we can exploit some properties of our series to perform decay for a blocked update in constant time and account the contribution for a running update in essentially-constant* time. [*]: For any running entity they should be performing updates at the tick which gives us a soft limit of 1 jiffy between updates, and we can compute up to a 32 jiffy update in a single pass. C program to generate the magic constants in the arrays: #include <math.h> #include <stdio.h> #define N 32 #define WMULT_SHIFT 32 const long WMULT_CONST = ((1UL << N) - 1); double y; long runnable_avg_yN_inv[N]; void calc_mult_inv() { int i; double yn = 0; printf("inverses\n"); for (i = 0; i < N; i++) { yn = (double)WMULT_CONST * pow(y, i); runnable_avg_yN_inv[i] = yn; printf("%2d: 0x%8lx\n", i, runnable_avg_yN_inv[i]); } printf("\n"); } long mult_inv(long c, int n) { return (c * runnable_avg_yN_inv[n]) >> WMULT_SHIFT; } void calc_yn_sum(int n) { int i; double sum = 0, sum_fl = 0, diff = 0; /* * We take the floored sum to ensure the sum of partial sums is never * larger than the actual sum. */ printf("sum y^n\n"); printf(" %8s %8s %8s\n", "exact", "floor", "error"); for (i = 1; i <= n; i++) { sum = (y * sum + y * 1024); sum_fl = floor(y * sum_fl+ y * 1024); printf("%2d: %8.0f %8.0f %8.0f\n", i, sum, sum_fl, sum_fl - sum); } printf("\n"); } void calc_conv(long n) { long old_n; int i = -1; printf("convergence (LOAD_AVG_MAX, LOAD_AVG_MAX_N)\n"); do { old_n = n; n = mult_inv(n, 1) + 1024; i++; } while (n != old_n); printf("%d> %ld\n", i - 1, n); printf("\n"); } void main() { y = pow(0.5, 1/(double)N); calc_mult_inv(); calc_conv(1024); calc_yn_sum(N); } [ Compile with -lm ] Signed-off-by: Paul Turner <pjt@google.com> Reviewed-by: Ben Segall <bsegall@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20120823141507.277808946@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-10-04 11:18:32 +00:00
}
/*
* For updates fully spanning n periods, the contribution to runnable
* average will be: \Sum 1024*y^n
*
* We can compute this reasonably efficiently by combining:
* y^PERIOD = 1/2 with precomputed \Sum 1024*y^n {for n <PERIOD}
*/
static u32 __compute_runnable_contrib(u64 n)
{
u32 contrib = 0;
if (likely(n <= LOAD_AVG_PERIOD))
return runnable_avg_yN_sum[n];
else if (unlikely(n >= LOAD_AVG_MAX_N))
return LOAD_AVG_MAX;
/* Compute \Sum k^n combining precomputed values for k^i, \Sum k^j */
do {
contrib /= 2; /* y^LOAD_AVG_PERIOD = 1/2 */
contrib += runnable_avg_yN_sum[LOAD_AVG_PERIOD];
n -= LOAD_AVG_PERIOD;
} while (n > LOAD_AVG_PERIOD);
contrib = decay_load(contrib, n);
return contrib + runnable_avg_yN_sum[n];
}
#define scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
/*
* We can represent the historical contribution to runnable average as the
* coefficients of a geometric series. To do this we sub-divide our runnable
* history into segments of approximately 1ms (1024us); label the segment that
* occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
*
* [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
* p0 p1 p2
* (now) (~1ms ago) (~2ms ago)
*
* Let u_i denote the fraction of p_i that the entity was runnable.
*
* We then designate the fractions u_i as our co-efficients, yielding the
* following representation of historical load:
* u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
*
* We choose y based on the with of a reasonably scheduling period, fixing:
* y^32 = 0.5
*
* This means that the contribution to load ~32ms ago (u_32) will be weighted
* approximately half as much as the contribution to load within the last ms
* (u_0).
*
* When a period "rolls over" and we have new u_0`, multiplying the previous
* sum again by y is sufficient to update:
* load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
* = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
*/
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
static __always_inline int
__update_load_avg(u64 now, int cpu, struct sched_avg *sa,
unsigned long weight, int running, struct cfs_rq *cfs_rq)
{
u64 delta, scaled_delta, periods;
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
u32 contrib;
int delta_w, scaled_delta_w, decayed = 0;
sched: Make sched entity usage tracking scale-invariant Apply frequency scale-invariance correction factor to usage tracking. Each segment of the running_avg_sum geometric series is now scaled by the current frequency so the utilization_avg_contrib of each entity will be invariant with frequency scaling. As a result, utilization_load_avg which is the sum of utilization_avg_contrib, becomes invariant too. So the usage level that is returned by get_cpu_usage(), stays relative to the max frequency as the cpu_capacity which is is compared against. Then, we want the keep the load tracking values in a 32-bit type, which implies that the max value of {runnable|running}_avg_sum must be lower than 2^32/88761=48388 (88761 is the max weigth of a task). As LOAD_AVG_MAX = 47742, arch_scale_freq_capacity() must return a value less than (48388/47742) << SCHED_CAPACITY_SHIFT = 1037 (SCHED_SCALE_CAPACITY = 1024). So we define the range to [0..SCHED_SCALE_CAPACITY] in order to avoid overflow. Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com> Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Paul Turner <pjt@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Morten.Rasmussen@arm.com Cc: Paul Turner <pjt@google.com> Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425455186-13451-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-03-04 07:46:26 +00:00
unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
delta = now - sa->last_update_time;
/*
* This should only happen when time goes backwards, which it
* unfortunately does during sched clock init when we swap over to TSC.
*/
if ((s64)delta < 0) {
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
sa->last_update_time = now;
return 0;
}
/*
* Use 1024ns as the unit of measurement since it's a reasonable
* approximation of 1us and fast to compute.
*/
delta >>= 10;
if (!delta)
return 0;
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
sa->last_update_time = now;
/* delta_w is the amount already accumulated against our next period */
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
delta_w = sa->period_contrib;
if (delta + delta_w >= 1024) {
decayed = 1;
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
/* how much left for next period will start over, we don't know yet */
sa->period_contrib = 0;
/*
* Now that we know we're crossing a period boundary, figure
* out how much from delta we need to complete the current
* period and accrue it.
*/
delta_w = 1024 - delta_w;
scaled_delta_w = scale(delta_w, scale_freq);
if (weight) {
sa->load_sum += weight * scaled_delta_w;
if (cfs_rq) {
cfs_rq->runnable_load_sum +=
weight * scaled_delta_w;
}
}
sched: Add sched_avg::utilization_avg_contrib Add new statistics which reflect the average time a task is running on the CPU and the sum of these running time of the tasks on a runqueue. The latter is named utilization_load_avg. This patch is based on the usage metric that was proposed in the 1st versions of the per-entity load tracking patchset by Paul Turner <pjt@google.com> but that has be removed afterwards. This version differs from the original one in the sense that it's not linked to task_group. The rq's utilization_load_avg will be used to check if a rq is overloaded or not instead of trying to compute how many tasks a group of CPUs can handle. Rename runnable_avg_period into avg_period as it is now used with both runnable_avg_sum and running_avg_sum. Add some descriptions of the variables to explain their differences. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Paul Turner <pjt@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Morten.Rasmussen@arm.com Cc: Paul Turner <pjt@google.com> Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-2-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:04 +00:00
if (running)
sa->util_sum += scaled_delta_w;
sched: Make __update_entity_runnable_avg() fast __update_entity_runnable_avg forms the core of maintaining an entity's runnable load average. In this function we charge the accumulated run-time since last update and handle appropriate decay. In some cases, e.g. a waking task, this time interval may be much larger than our period unit. Fortunately we can exploit some properties of our series to perform decay for a blocked update in constant time and account the contribution for a running update in essentially-constant* time. [*]: For any running entity they should be performing updates at the tick which gives us a soft limit of 1 jiffy between updates, and we can compute up to a 32 jiffy update in a single pass. C program to generate the magic constants in the arrays: #include <math.h> #include <stdio.h> #define N 32 #define WMULT_SHIFT 32 const long WMULT_CONST = ((1UL << N) - 1); double y; long runnable_avg_yN_inv[N]; void calc_mult_inv() { int i; double yn = 0; printf("inverses\n"); for (i = 0; i < N; i++) { yn = (double)WMULT_CONST * pow(y, i); runnable_avg_yN_inv[i] = yn; printf("%2d: 0x%8lx\n", i, runnable_avg_yN_inv[i]); } printf("\n"); } long mult_inv(long c, int n) { return (c * runnable_avg_yN_inv[n]) >> WMULT_SHIFT; } void calc_yn_sum(int n) { int i; double sum = 0, sum_fl = 0, diff = 0; /* * We take the floored sum to ensure the sum of partial sums is never * larger than the actual sum. */ printf("sum y^n\n"); printf(" %8s %8s %8s\n", "exact", "floor", "error"); for (i = 1; i <= n; i++) { sum = (y * sum + y * 1024); sum_fl = floor(y * sum_fl+ y * 1024); printf("%2d: %8.0f %8.0f %8.0f\n", i, sum, sum_fl, sum_fl - sum); } printf("\n"); } void calc_conv(long n) { long old_n; int i = -1; printf("convergence (LOAD_AVG_MAX, LOAD_AVG_MAX_N)\n"); do { old_n = n; n = mult_inv(n, 1) + 1024; i++; } while (n != old_n); printf("%d> %ld\n", i - 1, n); printf("\n"); } void main() { y = pow(0.5, 1/(double)N); calc_mult_inv(); calc_conv(1024); calc_yn_sum(N); } [ Compile with -lm ] Signed-off-by: Paul Turner <pjt@google.com> Reviewed-by: Ben Segall <bsegall@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20120823141507.277808946@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-10-04 11:18:32 +00:00
delta -= delta_w;
/* Figure out how many additional periods this update spans */
periods = delta / 1024;
delta %= 1024;
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
sa->load_sum = decay_load(sa->load_sum, periods + 1);
if (cfs_rq) {
cfs_rq->runnable_load_sum =
decay_load(cfs_rq->runnable_load_sum, periods + 1);
}
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
sa->util_sum = decay_load((u64)(sa->util_sum), periods + 1);
sched: Make __update_entity_runnable_avg() fast __update_entity_runnable_avg forms the core of maintaining an entity's runnable load average. In this function we charge the accumulated run-time since last update and handle appropriate decay. In some cases, e.g. a waking task, this time interval may be much larger than our period unit. Fortunately we can exploit some properties of our series to perform decay for a blocked update in constant time and account the contribution for a running update in essentially-constant* time. [*]: For any running entity they should be performing updates at the tick which gives us a soft limit of 1 jiffy between updates, and we can compute up to a 32 jiffy update in a single pass. C program to generate the magic constants in the arrays: #include <math.h> #include <stdio.h> #define N 32 #define WMULT_SHIFT 32 const long WMULT_CONST = ((1UL << N) - 1); double y; long runnable_avg_yN_inv[N]; void calc_mult_inv() { int i; double yn = 0; printf("inverses\n"); for (i = 0; i < N; i++) { yn = (double)WMULT_CONST * pow(y, i); runnable_avg_yN_inv[i] = yn; printf("%2d: 0x%8lx\n", i, runnable_avg_yN_inv[i]); } printf("\n"); } long mult_inv(long c, int n) { return (c * runnable_avg_yN_inv[n]) >> WMULT_SHIFT; } void calc_yn_sum(int n) { int i; double sum = 0, sum_fl = 0, diff = 0; /* * We take the floored sum to ensure the sum of partial sums is never * larger than the actual sum. */ printf("sum y^n\n"); printf(" %8s %8s %8s\n", "exact", "floor", "error"); for (i = 1; i <= n; i++) { sum = (y * sum + y * 1024); sum_fl = floor(y * sum_fl+ y * 1024); printf("%2d: %8.0f %8.0f %8.0f\n", i, sum, sum_fl, sum_fl - sum); } printf("\n"); } void calc_conv(long n) { long old_n; int i = -1; printf("convergence (LOAD_AVG_MAX, LOAD_AVG_MAX_N)\n"); do { old_n = n; n = mult_inv(n, 1) + 1024; i++; } while (n != old_n); printf("%d> %ld\n", i - 1, n); printf("\n"); } void main() { y = pow(0.5, 1/(double)N); calc_mult_inv(); calc_conv(1024); calc_yn_sum(N); } [ Compile with -lm ] Signed-off-by: Paul Turner <pjt@google.com> Reviewed-by: Ben Segall <bsegall@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20120823141507.277808946@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-10-04 11:18:32 +00:00
/* Efficiently calculate \sum (1..n_period) 1024*y^i */
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
contrib = __compute_runnable_contrib(periods);
contrib = scale(contrib, scale_freq);
if (weight) {
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
sa->load_sum += weight * contrib;
if (cfs_rq)
cfs_rq->runnable_load_sum += weight * contrib;
}
sched: Add sched_avg::utilization_avg_contrib Add new statistics which reflect the average time a task is running on the CPU and the sum of these running time of the tasks on a runqueue. The latter is named utilization_load_avg. This patch is based on the usage metric that was proposed in the 1st versions of the per-entity load tracking patchset by Paul Turner <pjt@google.com> but that has be removed afterwards. This version differs from the original one in the sense that it's not linked to task_group. The rq's utilization_load_avg will be used to check if a rq is overloaded or not instead of trying to compute how many tasks a group of CPUs can handle. Rename runnable_avg_period into avg_period as it is now used with both runnable_avg_sum and running_avg_sum. Add some descriptions of the variables to explain their differences. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Paul Turner <pjt@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Morten.Rasmussen@arm.com Cc: Paul Turner <pjt@google.com> Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-2-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:04 +00:00
if (running)
sa->util_sum += contrib;
}
/* Remainder of delta accrued against u_0` */
scaled_delta = scale(delta, scale_freq);
if (weight) {
sa->load_sum += weight * scaled_delta;
if (cfs_rq)
cfs_rq->runnable_load_sum += weight * scaled_delta;
}
sched: Add sched_avg::utilization_avg_contrib Add new statistics which reflect the average time a task is running on the CPU and the sum of these running time of the tasks on a runqueue. The latter is named utilization_load_avg. This patch is based on the usage metric that was proposed in the 1st versions of the per-entity load tracking patchset by Paul Turner <pjt@google.com> but that has be removed afterwards. This version differs from the original one in the sense that it's not linked to task_group. The rq's utilization_load_avg will be used to check if a rq is overloaded or not instead of trying to compute how many tasks a group of CPUs can handle. Rename runnable_avg_period into avg_period as it is now used with both runnable_avg_sum and running_avg_sum. Add some descriptions of the variables to explain their differences. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Paul Turner <pjt@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Morten.Rasmussen@arm.com Cc: Paul Turner <pjt@google.com> Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-2-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:04 +00:00
if (running)
sa->util_sum += scaled_delta;
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
sa->period_contrib += delta;
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
if (decayed) {
sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX);
if (cfs_rq) {
cfs_rq->runnable_load_avg =
div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
}
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
sa->util_avg = (sa->util_sum << SCHED_LOAD_SHIFT) / LOAD_AVG_MAX;
}
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
return decayed;
}
#ifdef CONFIG_FAIR_GROUP_SCHED
/*
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
* Updating tg's load_avg is necessary before update_cfs_share (which is done)
* and effective_load (which is not done because it is too costly).
*/
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
{
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
if (force || abs(delta) > cfs_rq->tg_load_avg_contrib / 64) {
atomic_long_add(delta, &cfs_rq->tg->load_avg);
cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg;
}
}
#else /* CONFIG_FAIR_GROUP_SCHED */
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
#endif /* CONFIG_FAIR_GROUP_SCHED */
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
/* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
{
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
struct sched_avg *sa = &cfs_rq->avg;
int decayed;
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
if (atomic_long_read(&cfs_rq->removed_load_avg)) {
long r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
sa->load_avg = max_t(long, sa->load_avg - r, 0);
sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
}
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
if (atomic_long_read(&cfs_rq->removed_util_avg)) {
long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
sa->util_avg = max_t(long, sa->util_avg - r, 0);
sa->util_sum = max_t(s32, sa->util_sum -
((r * LOAD_AVG_MAX) >> SCHED_LOAD_SHIFT), 0);
}
sched: Add sched_avg::utilization_avg_contrib Add new statistics which reflect the average time a task is running on the CPU and the sum of these running time of the tasks on a runqueue. The latter is named utilization_load_avg. This patch is based on the usage metric that was proposed in the 1st versions of the per-entity load tracking patchset by Paul Turner <pjt@google.com> but that has be removed afterwards. This version differs from the original one in the sense that it's not linked to task_group. The rq's utilization_load_avg will be used to check if a rq is overloaded or not instead of trying to compute how many tasks a group of CPUs can handle. Rename runnable_avg_period into avg_period as it is now used with both runnable_avg_sum and running_avg_sum. Add some descriptions of the variables to explain their differences. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Paul Turner <pjt@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Morten.Rasmussen@arm.com Cc: Paul Turner <pjt@google.com> Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-2-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:04 +00:00
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
scale_load_down(cfs_rq->load.weight), cfs_rq->curr != NULL, cfs_rq);
sched: Add sched_avg::utilization_avg_contrib Add new statistics which reflect the average time a task is running on the CPU and the sum of these running time of the tasks on a runqueue. The latter is named utilization_load_avg. This patch is based on the usage metric that was proposed in the 1st versions of the per-entity load tracking patchset by Paul Turner <pjt@google.com> but that has be removed afterwards. This version differs from the original one in the sense that it's not linked to task_group. The rq's utilization_load_avg will be used to check if a rq is overloaded or not instead of trying to compute how many tasks a group of CPUs can handle. Rename runnable_avg_period into avg_period as it is now used with both runnable_avg_sum and running_avg_sum. Add some descriptions of the variables to explain their differences. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Paul Turner <pjt@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Morten.Rasmussen@arm.com Cc: Paul Turner <pjt@google.com> Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-2-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:04 +00:00
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
#ifndef CONFIG_64BIT
smp_wmb();
cfs_rq->load_last_update_time_copy = sa->last_update_time;
#endif
sched: Add sched_avg::utilization_avg_contrib Add new statistics which reflect the average time a task is running on the CPU and the sum of these running time of the tasks on a runqueue. The latter is named utilization_load_avg. This patch is based on the usage metric that was proposed in the 1st versions of the per-entity load tracking patchset by Paul Turner <pjt@google.com> but that has be removed afterwards. This version differs from the original one in the sense that it's not linked to task_group. The rq's utilization_load_avg will be used to check if a rq is overloaded or not instead of trying to compute how many tasks a group of CPUs can handle. Rename runnable_avg_period into avg_period as it is now used with both runnable_avg_sum and running_avg_sum. Add some descriptions of the variables to explain their differences. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Paul Turner <pjt@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Morten.Rasmussen@arm.com Cc: Paul Turner <pjt@google.com> Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-2-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:04 +00:00
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
return decayed;
}
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
/* Update task and its cfs_rq load average */
static inline void update_load_avg(struct sched_entity *se, int update_tg)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
u64 now = cfs_rq_clock_task(cfs_rq);
int cpu = cpu_of(rq_of(cfs_rq));
/*
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
* Track task load average for carrying it to new CPU after migrated, and
* track group sched_entity load average for task_h_load calc in migration
*/
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
__update_load_avg(now, cpu, &se->avg,
se->on_rq * scale_load_down(se->load.weight),
cfs_rq->curr == se, NULL);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
update_tg_load_avg(cfs_rq, 0);
}
static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
if (!sched_feat(ATTACH_AGE_LOAD))
goto skip_aging;
sched/fair: Fix switched_to_fair()'s per entity load tracking Where switched_from_fair() will remove the entity's load from the runqueue, switched_to_fair() does not currently add it back. This means that when a task leaves the fair class for a short duration; say because of PI; we loose its load contribution. This can ripple forward and disturb the load tracking because other operations (enqueue, dequeue) assume its factored in. Only once the runqueue empties will the load tracking recover. When we add it back in, age the per entity average to match up with the runqueue age. This has the obvious problem that if the task leaves the fair class for a significant time, the load will age to 0. Employ the normal migration rule for inter-runqueue moves in task_move_group_fair(). Again, there is the obvious problem of the task migrating while not in the fair class. The alternative solution would be to to omit the chunk in attach_entity_load_avg(), which would effectively reset the timestamp and use whatever avg there was. Signed-off-by: Byungchul Park <byungchul.park@lge.com> [ Rewrote the changelog and comments. ] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: yuyang.du@intel.com Link: http://lkml.kernel.org/r/1440069720-27038-5-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-08-20 11:21:59 +00:00
/*
* If we got migrated (either between CPUs or between cgroups) we'll
* have aged the average right before clearing @last_update_time.
*/
if (se->avg.last_update_time) {
__update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
&se->avg, 0, 0, NULL);
/*
* XXX: we could have just aged the entire load away if we've been
* absent from the fair class for too long.
*/
}
skip_aging:
se->avg.last_update_time = cfs_rq->avg.last_update_time;
cfs_rq->avg.load_avg += se->avg.load_avg;
cfs_rq->avg.load_sum += se->avg.load_sum;
cfs_rq->avg.util_avg += se->avg.util_avg;
cfs_rq->avg.util_sum += se->avg.util_sum;
}
static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
__update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
&se->avg, se->on_rq * scale_load_down(se->load.weight),
cfs_rq->curr == se, NULL);
cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
cfs_rq->avg.load_sum = max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0);
cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
cfs_rq->avg.util_sum = max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0);
}
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
/* Add the load generated by se into cfs_rq's load average */
static inline void
enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
struct sched_avg *sa = &se->avg;
u64 now = cfs_rq_clock_task(cfs_rq);
int migrated, decayed;
migrated = !sa->last_update_time;
if (!migrated) {
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
__update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
se->on_rq * scale_load_down(se->load.weight),
cfs_rq->curr == se, NULL);
}
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
decayed = update_cfs_rq_load_avg(now, cfs_rq);
cfs_rq->runnable_load_avg += sa->load_avg;
cfs_rq->runnable_load_sum += sa->load_sum;
if (migrated)
attach_entity_load_avg(cfs_rq, se);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
if (decayed || migrated)
update_tg_load_avg(cfs_rq, 0);
}
/* Remove the runnable load generated by se from cfs_rq's runnable load average */
static inline void
dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
update_load_avg(se, 1);
cfs_rq->runnable_load_avg =
max_t(long, cfs_rq->runnable_load_avg - se->avg.load_avg, 0);
cfs_rq->runnable_load_sum =
max_t(s64, cfs_rq->runnable_load_sum - se->avg.load_sum, 0);
}
/*
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
* Task first catches up with cfs_rq, and then subtract
* itself from the cfs_rq (task must be off the queue now).
*/
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
void remove_entity_load_avg(struct sched_entity *se)
{
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
struct cfs_rq *cfs_rq = cfs_rq_of(se);
u64 last_update_time;
#ifndef CONFIG_64BIT
u64 last_update_time_copy;
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
do {
last_update_time_copy = cfs_rq->load_last_update_time_copy;
smp_rmb();
last_update_time = cfs_rq->avg.last_update_time;
} while (last_update_time != last_update_time_copy);
#else
last_update_time = cfs_rq->avg.last_update_time;
#endif
__update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg);
atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg);
}
sched: Fix wrong rq's runnable_avg update with rt tasks The current update of the rq's load can be erroneous when RT tasks are involved. The update of the load of a rq that becomes idle, is done only if the avg_idle is less than sysctl_sched_migration_cost. If RT tasks and short idle duration alternate, the runnable_avg will not be updated correctly and the time will be accounted as idle time when a CFS task wakes up. A new idle_enter function is called when the next task is the idle function so the elapsed time will be accounted as run time in the load of the rq, whatever the average idle time is. The function update_rq_runnable_avg is removed from idle_balance. When a RT task is scheduled on an idle CPU, the update of the rq's load is not done when the rq exit idle state because CFS's functions are not called. Then, the idle_balance, which is called just before entering the idle function, updates the rq's load and makes the assumption that the elapsed time since the last update, was only running time. As a consequence, the rq's load of a CPU that only runs a periodic RT task, is close to LOAD_AVG_MAX whatever the running duration of the RT task is. A new idle_exit function is called when the prev task is the idle function so the elapsed time will be accounted as idle time in the rq's load. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: linaro-kernel@lists.linaro.org Cc: peterz@infradead.org Cc: pjt@google.com Cc: fweisbec@gmail.com Cc: efault@gmx.de Link: http://lkml.kernel.org/r/1366302867-5055-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-04-18 16:34:26 +00:00
/*
* Update the rq's load with the elapsed running time before entering
* idle. if the last scheduled task is not a CFS task, idle_enter will
* be the only way to update the runnable statistic.
*/
void idle_enter_fair(struct rq *this_rq)
{
}
/*
* Update the rq's load with the elapsed idle time before a task is
* scheduled. if the newly scheduled task is not a CFS task, idle_exit will
* be the only way to update the runnable statistic.
*/
void idle_exit_fair(struct rq *this_rq)
{
}
static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq)
{
return cfs_rq->runnable_load_avg;
}
static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
{
return cfs_rq->avg.load_avg;
}
static int idle_balance(struct rq *this_rq);
#else /* CONFIG_SMP */
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
static inline void update_load_avg(struct sched_entity *se, int update_tg) {}
static inline void
enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
static inline void
dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
static inline void remove_entity_load_avg(struct sched_entity *se) {}
static inline void
attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
static inline void
detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
static inline int idle_balance(struct rq *rq)
{
return 0;
}
#endif /* CONFIG_SMP */
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHEDSTATS
struct task_struct *tsk = NULL;
if (entity_is_task(se))
tsk = task_of(se);
if (se->statistics.sleep_start) {
u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.sleep_start;
if ((s64)delta < 0)
delta = 0;
if (unlikely(delta > se->statistics.sleep_max))
se->statistics.sleep_max = delta;
se->statistics.sleep_start = 0;
se->statistics.sum_sleep_runtime += delta;
if (tsk) {
account_scheduler_latency(tsk, delta >> 10, 1);
trace_sched_stat_sleep(tsk, delta);
}
}
if (se->statistics.block_start) {
u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.block_start;
if ((s64)delta < 0)
delta = 0;
if (unlikely(delta > se->statistics.block_max))
se->statistics.block_max = delta;
se->statistics.block_start = 0;
se->statistics.sum_sleep_runtime += delta;
if (tsk) {
if (tsk->in_iowait) {
se->statistics.iowait_sum += delta;
se->statistics.iowait_count++;
trace_sched_stat_iowait(tsk, delta);
}
trace_sched_stat_blocked(tsk, delta);
/*
* Blocking time is in units of nanosecs, so shift by
* 20 to get a milliseconds-range estimation of the
* amount of time that the task spent sleeping:
*/
if (unlikely(prof_on == SLEEP_PROFILING)) {
profile_hits(SLEEP_PROFILING,
(void *)get_wchan(tsk),
delta >> 20);
}
account_scheduler_latency(tsk, delta >> 10, 0);
}
}
#endif
}
static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHED_DEBUG
s64 d = se->vruntime - cfs_rq->min_vruntime;
if (d < 0)
d = -d;
if (d > 3*sysctl_sched_latency)
schedstat_inc(cfs_rq, nr_spread_over);
#endif
}
static void
place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
{
u64 vruntime = cfs_rq->min_vruntime;
/*
* The 'current' period is already promised to the current tasks,
* however the extra weight of the new task will slow them down a
* little, place the new task so that it fits in the slot that
* stays open at the end.
*/
if (initial && sched_feat(START_DEBIT))
vruntime += sched_vslice(cfs_rq, se);
/* sleeps up to a single latency don't count. */
if (!initial) {
unsigned long thresh = sysctl_sched_latency;
/*
* Halve their sleep time's effect, to allow
* for a gentler effect of sleepers:
*/
if (sched_feat(GENTLE_FAIR_SLEEPERS))
thresh >>= 1;
vruntime -= thresh;
}
/* ensure we never gain time by being placed backwards. */
se->vruntime = max_vruntime(se->vruntime, vruntime);
}
static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
static void
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
/*
* Update the normalized vruntime before updating min_vruntime
* through calling update_curr().
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
*/
if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING))
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
se->vruntime += cfs_rq->min_vruntime;
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
enqueue_entity_load_avg(cfs_rq, se);
account_entity_enqueue(cfs_rq, se);
update_cfs_shares(cfs_rq);
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
if (flags & ENQUEUE_WAKEUP) {
place_entity(cfs_rq, se, 0);
enqueue_sleeper(cfs_rq, se);
}
update_stats_enqueue(cfs_rq, se);
check_spread(cfs_rq, se);
if (se != cfs_rq->curr)
__enqueue_entity(cfs_rq, se);
se->on_rq = 1;
if (cfs_rq->nr_running == 1) {
list_add_leaf_cfs_rq(cfs_rq);
check_enqueue_throttle(cfs_rq);
}
}
static void __clear_buddies_last(struct sched_entity *se)
{
for_each_sched_entity(se) {
struct cfs_rq *cfs_rq = cfs_rq_of(se);
if (cfs_rq->last != se)
break;
cfs_rq->last = NULL;
}
}
static void __clear_buddies_next(struct sched_entity *se)
{
for_each_sched_entity(se) {
struct cfs_rq *cfs_rq = cfs_rq_of(se);
if (cfs_rq->next != se)
break;
cfs_rq->next = NULL;
}
}
static void __clear_buddies_skip(struct sched_entity *se)
{
for_each_sched_entity(se) {
struct cfs_rq *cfs_rq = cfs_rq_of(se);
if (cfs_rq->skip != se)
break;
cfs_rq->skip = NULL;
}
}
static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
if (cfs_rq->last == se)
__clear_buddies_last(se);
if (cfs_rq->next == se)
__clear_buddies_next(se);
if (cfs_rq->skip == se)
__clear_buddies_skip(se);
}
static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
sched: Return unused runtime on group dequeue When a local cfs_rq blocks we return the majority of its remaining quota to the global bandwidth pool for use by other runqueues. We do this only when the quota is current and there is more than min_cfs_rq_quota [1ms by default] of runtime remaining on the rq. In the case where there are throttled runqueues and we have sufficient bandwidth to meter out a slice, a second timer is kicked off to handle this delivery, unthrottling where appropriate. Using a 'worst case' antagonist which executes on each cpu for 1ms before moving onto the next on a fairly large machine: no quota generations: 197.47 ms /cgroup/a/cpuacct.usage 199.46 ms /cgroup/a/cpuacct.usage 205.46 ms /cgroup/a/cpuacct.usage 198.46 ms /cgroup/a/cpuacct.usage 208.39 ms /cgroup/a/cpuacct.usage Since we are allowed to use "stale" quota our usage is effectively bounded by the rate of input into the global pool and performance is relatively stable. with quota generations [1s increments]: 119.58 ms /cgroup/a/cpuacct.usage 119.65 ms /cgroup/a/cpuacct.usage 119.64 ms /cgroup/a/cpuacct.usage 119.63 ms /cgroup/a/cpuacct.usage 119.60 ms /cgroup/a/cpuacct.usage The large deficit here is due to quota generations (/intentionally/) preventing us from now using previously stranded slack quota. The cost is that this quota becomes unavailable. with quota generations and quota return: 200.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 198.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 200.06 ms /cgroup/a/cpuacct.usage By returning unused quota we're able to both stably consume our desired quota and prevent unintentional overages due to the abuse of slack quota from previous quota periods (especially on a large machine). Signed-off-by: Paul Turner <pjt@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110721184758.306848658@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-07-21 16:43:41 +00:00
static void
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
dequeue_entity_load_avg(cfs_rq, se);
update_stats_dequeue(cfs_rq, se);
if (flags & DEQUEUE_SLEEP) {
#ifdef CONFIG_SCHEDSTATS
if (entity_is_task(se)) {
struct task_struct *tsk = task_of(se);
if (tsk->state & TASK_INTERRUPTIBLE)
se->statistics.sleep_start = rq_clock(rq_of(cfs_rq));
if (tsk->state & TASK_UNINTERRUPTIBLE)
se->statistics.block_start = rq_clock(rq_of(cfs_rq));
}
#endif
}
clear_buddies(cfs_rq, se);
if (se != cfs_rq->curr)
__dequeue_entity(cfs_rq, se);
se->on_rq = 0;
account_entity_dequeue(cfs_rq, se);
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
/*
* Normalize the entity after updating the min_vruntime because the
* update can refer to the ->curr item and we need to reflect this
* movement in our normalized position.
*/
if (!(flags & DEQUEUE_SLEEP))
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
se->vruntime -= cfs_rq->min_vruntime;
sched: Return unused runtime on group dequeue When a local cfs_rq blocks we return the majority of its remaining quota to the global bandwidth pool for use by other runqueues. We do this only when the quota is current and there is more than min_cfs_rq_quota [1ms by default] of runtime remaining on the rq. In the case where there are throttled runqueues and we have sufficient bandwidth to meter out a slice, a second timer is kicked off to handle this delivery, unthrottling where appropriate. Using a 'worst case' antagonist which executes on each cpu for 1ms before moving onto the next on a fairly large machine: no quota generations: 197.47 ms /cgroup/a/cpuacct.usage 199.46 ms /cgroup/a/cpuacct.usage 205.46 ms /cgroup/a/cpuacct.usage 198.46 ms /cgroup/a/cpuacct.usage 208.39 ms /cgroup/a/cpuacct.usage Since we are allowed to use "stale" quota our usage is effectively bounded by the rate of input into the global pool and performance is relatively stable. with quota generations [1s increments]: 119.58 ms /cgroup/a/cpuacct.usage 119.65 ms /cgroup/a/cpuacct.usage 119.64 ms /cgroup/a/cpuacct.usage 119.63 ms /cgroup/a/cpuacct.usage 119.60 ms /cgroup/a/cpuacct.usage The large deficit here is due to quota generations (/intentionally/) preventing us from now using previously stranded slack quota. The cost is that this quota becomes unavailable. with quota generations and quota return: 200.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 198.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 200.06 ms /cgroup/a/cpuacct.usage By returning unused quota we're able to both stably consume our desired quota and prevent unintentional overages due to the abuse of slack quota from previous quota periods (especially on a large machine). Signed-off-by: Paul Turner <pjt@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110721184758.306848658@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-07-21 16:43:41 +00:00
/* return excess runtime on last dequeue */
return_cfs_rq_runtime(cfs_rq);
update_min_vruntime(cfs_rq);
update_cfs_shares(cfs_rq);
}
/*
* Preempt the current task with a newly woken task if needed:
*/
static void
check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
unsigned long ideal_runtime, delta_exec;
struct sched_entity *se;
s64 delta;
ideal_runtime = sched_slice(cfs_rq, curr);
delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
if (delta_exec > ideal_runtime) {
resched_curr(rq_of(cfs_rq));
/*
* The current task ran long enough, ensure it doesn't get
* re-elected due to buddy favours.
*/
clear_buddies(cfs_rq, curr);
sched: Strengthen buddies and mitigate buddy induced latencies This patch restores the effectiveness of LAST_BUDDY in preventing pgsql+oltp from collapsing due to wakeup preemption. It also switches LAST_BUDDY to exclusively do what it does best, namely mitigate the effects of aggressive wakeup preemption, which improves vmark throughput markedly, and restores mysql+oltp scalability. Since buddies are about scalability, enable them beginning at the point where we begin expanding sched_latency, namely sched_nr_latency. Previously, buddies were cleared aggressively, which seriously reduced their effectiveness. Not clearing aggressively however, produces a small drop in mysql+oltp throughput immediately after peak, indicating that LAST_BUDDY is actually doing some harm. This is right at the point where X on the desktop in competition with another load wants low latency service. Ergo, do not enable until we need to scale. To mitigate latency induced by buddies, or by a task just missing wakeup preemption, check latency at tick time. Last hunk prevents buddies from stymieing BALANCE_NEWIDLE via CACHE_HOT_BUDDY. Supporting performance tests: tip = v2.6.32-rc5-1497-ga525b32 tipx = NO_GENTLE_FAIR_SLEEPERS NEXT_BUDDY granularity knobs = 31 knobs + 31 buddies tip+x = NO_GENTLE_FAIR_SLEEPERS granularity knobs = 31 knobs (Three run averages except where noted.) vmark: ------ tip 108466 messages per second tip+ 125307 messages per second tip+x 125335 messages per second tipx 117781 messages per second 2.6.31.3 122729 messages per second mysql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 9949.89 18690.20 34801.24 34460.04 32682.88 30765.97 28305.27 25059.64 19548.08 tip+ 10013.90 18526.84 34900.38 34420.14 33069.83 32083.40 30578.30 28010.71 25605.47 tipx 9698.71 18002.70 34477.56 33420.01 32634.30 31657.27 29932.67 26827.52 21487.18 2.6.31.3 8243.11 18784.20 34404.83 33148.38 31900.32 31161.90 29663.81 25995.94 18058.86 pgsql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 13686.37 26609.25 51934.28 51347.81 49479.51 45312.65 36691.91 26851.57 24145.35 tip+ (1x) 13907.85 27135.87 52951.98 52514.04 51742.52 50705.43 49947.97 48374.19 46227.94 tip+x 13906.78 27065.81 52951.19 52542.59 52176.11 51815.94 50838.90 49439.46 46891.00 tipx 13742.46 26769.81 52351.99 51891.73 51320.79 50938.98 50248.65 48908.70 46553.84 2.6.31.3 13815.35 26906.46 52683.34 52061.31 51937.10 51376.80 50474.28 49394.47 47003.25 Signed-off-by: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-23 21:09:22 +00:00
return;
}
/*
* Ensure that a task that missed wakeup preemption by a
* narrow margin doesn't have to wait for a full slice.
* This also mitigates buddy induced latencies under load.
*/
if (delta_exec < sysctl_sched_min_granularity)
return;
se = __pick_first_entity(cfs_rq);
delta = curr->vruntime - se->vruntime;
sched: Strengthen buddies and mitigate buddy induced latencies This patch restores the effectiveness of LAST_BUDDY in preventing pgsql+oltp from collapsing due to wakeup preemption. It also switches LAST_BUDDY to exclusively do what it does best, namely mitigate the effects of aggressive wakeup preemption, which improves vmark throughput markedly, and restores mysql+oltp scalability. Since buddies are about scalability, enable them beginning at the point where we begin expanding sched_latency, namely sched_nr_latency. Previously, buddies were cleared aggressively, which seriously reduced their effectiveness. Not clearing aggressively however, produces a small drop in mysql+oltp throughput immediately after peak, indicating that LAST_BUDDY is actually doing some harm. This is right at the point where X on the desktop in competition with another load wants low latency service. Ergo, do not enable until we need to scale. To mitigate latency induced by buddies, or by a task just missing wakeup preemption, check latency at tick time. Last hunk prevents buddies from stymieing BALANCE_NEWIDLE via CACHE_HOT_BUDDY. Supporting performance tests: tip = v2.6.32-rc5-1497-ga525b32 tipx = NO_GENTLE_FAIR_SLEEPERS NEXT_BUDDY granularity knobs = 31 knobs + 31 buddies tip+x = NO_GENTLE_FAIR_SLEEPERS granularity knobs = 31 knobs (Three run averages except where noted.) vmark: ------ tip 108466 messages per second tip+ 125307 messages per second tip+x 125335 messages per second tipx 117781 messages per second 2.6.31.3 122729 messages per second mysql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 9949.89 18690.20 34801.24 34460.04 32682.88 30765.97 28305.27 25059.64 19548.08 tip+ 10013.90 18526.84 34900.38 34420.14 33069.83 32083.40 30578.30 28010.71 25605.47 tipx 9698.71 18002.70 34477.56 33420.01 32634.30 31657.27 29932.67 26827.52 21487.18 2.6.31.3 8243.11 18784.20 34404.83 33148.38 31900.32 31161.90 29663.81 25995.94 18058.86 pgsql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 13686.37 26609.25 51934.28 51347.81 49479.51 45312.65 36691.91 26851.57 24145.35 tip+ (1x) 13907.85 27135.87 52951.98 52514.04 51742.52 50705.43 49947.97 48374.19 46227.94 tip+x 13906.78 27065.81 52951.19 52542.59 52176.11 51815.94 50838.90 49439.46 46891.00 tipx 13742.46 26769.81 52351.99 51891.73 51320.79 50938.98 50248.65 48908.70 46553.84 2.6.31.3 13815.35 26906.46 52683.34 52061.31 51937.10 51376.80 50474.28 49394.47 47003.25 Signed-off-by: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-23 21:09:22 +00:00
if (delta < 0)
return;
if (delta > ideal_runtime)
resched_curr(rq_of(cfs_rq));
}
static void
set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
/* 'current' is not kept within the tree. */
if (se->on_rq) {
/*
* Any task has to be enqueued before it get to execute on
* a CPU. So account for the time it spent waiting on the
* runqueue.
*/
update_stats_wait_end(cfs_rq, se);
__dequeue_entity(cfs_rq, se);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
update_load_avg(se, 1);
}
update_stats_curr_start(cfs_rq, se);
cfs_rq->curr = se;
#ifdef CONFIG_SCHEDSTATS
/*
* Track our maximum slice length, if the CPU's load is at
* least twice that of our own weight (i.e. dont track it
* when there are only lesser-weight tasks around):
*/
if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
se->statistics.slice_max = max(se->statistics.slice_max,
se->sum_exec_runtime - se->prev_sum_exec_runtime);
}
#endif
se->prev_sum_exec_runtime = se->sum_exec_runtime;
}
static int
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
/*
* Pick the next process, keeping these things in mind, in this order:
* 1) keep things fair between processes/task groups
* 2) pick the "next" process, since someone really wants that to run
* 3) pick the "last" process, for cache locality
* 4) do not run the "skip" process, if something else is available
*/
static struct sched_entity *
pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
struct sched_entity *left = __pick_first_entity(cfs_rq);
struct sched_entity *se;
/*
* If curr is set we have to see if its left of the leftmost entity
* still in the tree, provided there was anything in the tree at all.
*/
if (!left || (curr && entity_before(curr, left)))
left = curr;
se = left; /* ideally we run the leftmost entity */
/*
* Avoid running the skip buddy, if running something else can
* be done without getting too unfair.
*/
if (cfs_rq->skip == se) {
struct sched_entity *second;
if (se == curr) {
second = __pick_first_entity(cfs_rq);
} else {
second = __pick_next_entity(se);
if (!second || (curr && entity_before(curr, second)))
second = curr;
}
if (second && wakeup_preempt_entity(second, left) < 1)
se = second;
}
sched: Strengthen buddies and mitigate buddy induced latencies This patch restores the effectiveness of LAST_BUDDY in preventing pgsql+oltp from collapsing due to wakeup preemption. It also switches LAST_BUDDY to exclusively do what it does best, namely mitigate the effects of aggressive wakeup preemption, which improves vmark throughput markedly, and restores mysql+oltp scalability. Since buddies are about scalability, enable them beginning at the point where we begin expanding sched_latency, namely sched_nr_latency. Previously, buddies were cleared aggressively, which seriously reduced their effectiveness. Not clearing aggressively however, produces a small drop in mysql+oltp throughput immediately after peak, indicating that LAST_BUDDY is actually doing some harm. This is right at the point where X on the desktop in competition with another load wants low latency service. Ergo, do not enable until we need to scale. To mitigate latency induced by buddies, or by a task just missing wakeup preemption, check latency at tick time. Last hunk prevents buddies from stymieing BALANCE_NEWIDLE via CACHE_HOT_BUDDY. Supporting performance tests: tip = v2.6.32-rc5-1497-ga525b32 tipx = NO_GENTLE_FAIR_SLEEPERS NEXT_BUDDY granularity knobs = 31 knobs + 31 buddies tip+x = NO_GENTLE_FAIR_SLEEPERS granularity knobs = 31 knobs (Three run averages except where noted.) vmark: ------ tip 108466 messages per second tip+ 125307 messages per second tip+x 125335 messages per second tipx 117781 messages per second 2.6.31.3 122729 messages per second mysql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 9949.89 18690.20 34801.24 34460.04 32682.88 30765.97 28305.27 25059.64 19548.08 tip+ 10013.90 18526.84 34900.38 34420.14 33069.83 32083.40 30578.30 28010.71 25605.47 tipx 9698.71 18002.70 34477.56 33420.01 32634.30 31657.27 29932.67 26827.52 21487.18 2.6.31.3 8243.11 18784.20 34404.83 33148.38 31900.32 31161.90 29663.81 25995.94 18058.86 pgsql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 13686.37 26609.25 51934.28 51347.81 49479.51 45312.65 36691.91 26851.57 24145.35 tip+ (1x) 13907.85 27135.87 52951.98 52514.04 51742.52 50705.43 49947.97 48374.19 46227.94 tip+x 13906.78 27065.81 52951.19 52542.59 52176.11 51815.94 50838.90 49439.46 46891.00 tipx 13742.46 26769.81 52351.99 51891.73 51320.79 50938.98 50248.65 48908.70 46553.84 2.6.31.3 13815.35 26906.46 52683.34 52061.31 51937.10 51376.80 50474.28 49394.47 47003.25 Signed-off-by: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-23 21:09:22 +00:00
/*
* Prefer last buddy, try to return the CPU to a preempted task.
*/
if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
se = cfs_rq->last;
/*
* Someone really wants this to run. If it's not unfair, run it.
*/
if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
se = cfs_rq->next;
sched: Strengthen buddies and mitigate buddy induced latencies This patch restores the effectiveness of LAST_BUDDY in preventing pgsql+oltp from collapsing due to wakeup preemption. It also switches LAST_BUDDY to exclusively do what it does best, namely mitigate the effects of aggressive wakeup preemption, which improves vmark throughput markedly, and restores mysql+oltp scalability. Since buddies are about scalability, enable them beginning at the point where we begin expanding sched_latency, namely sched_nr_latency. Previously, buddies were cleared aggressively, which seriously reduced their effectiveness. Not clearing aggressively however, produces a small drop in mysql+oltp throughput immediately after peak, indicating that LAST_BUDDY is actually doing some harm. This is right at the point where X on the desktop in competition with another load wants low latency service. Ergo, do not enable until we need to scale. To mitigate latency induced by buddies, or by a task just missing wakeup preemption, check latency at tick time. Last hunk prevents buddies from stymieing BALANCE_NEWIDLE via CACHE_HOT_BUDDY. Supporting performance tests: tip = v2.6.32-rc5-1497-ga525b32 tipx = NO_GENTLE_FAIR_SLEEPERS NEXT_BUDDY granularity knobs = 31 knobs + 31 buddies tip+x = NO_GENTLE_FAIR_SLEEPERS granularity knobs = 31 knobs (Three run averages except where noted.) vmark: ------ tip 108466 messages per second tip+ 125307 messages per second tip+x 125335 messages per second tipx 117781 messages per second 2.6.31.3 122729 messages per second mysql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 9949.89 18690.20 34801.24 34460.04 32682.88 30765.97 28305.27 25059.64 19548.08 tip+ 10013.90 18526.84 34900.38 34420.14 33069.83 32083.40 30578.30 28010.71 25605.47 tipx 9698.71 18002.70 34477.56 33420.01 32634.30 31657.27 29932.67 26827.52 21487.18 2.6.31.3 8243.11 18784.20 34404.83 33148.38 31900.32 31161.90 29663.81 25995.94 18058.86 pgsql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 13686.37 26609.25 51934.28 51347.81 49479.51 45312.65 36691.91 26851.57 24145.35 tip+ (1x) 13907.85 27135.87 52951.98 52514.04 51742.52 50705.43 49947.97 48374.19 46227.94 tip+x 13906.78 27065.81 52951.19 52542.59 52176.11 51815.94 50838.90 49439.46 46891.00 tipx 13742.46 26769.81 52351.99 51891.73 51320.79 50938.98 50248.65 48908.70 46553.84 2.6.31.3 13815.35 26906.46 52683.34 52061.31 51937.10 51376.80 50474.28 49394.47 47003.25 Signed-off-by: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-23 21:09:22 +00:00
clear_buddies(cfs_rq, se);
return se;
}
static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
{
/*
* If still on the runqueue then deactivate_task()
* was not called and update_curr() has to be done:
*/
if (prev->on_rq)
update_curr(cfs_rq);
/* throttle cfs_rqs exceeding runtime */
check_cfs_rq_runtime(cfs_rq);
check_spread(cfs_rq, prev);
if (prev->on_rq) {
update_stats_wait_start(cfs_rq, prev);
/* Put 'current' back into the tree. */
__enqueue_entity(cfs_rq, prev);
/* in !on_rq case, update occurred at dequeue */
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
update_load_avg(prev, 0);
}
cfs_rq->curr = NULL;
}
static void
entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
{
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
/*
* Ensure that runnable average is periodically updated.
*/
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
update_load_avg(curr, 1);
update_cfs_shares(cfs_rq);
#ifdef CONFIG_SCHED_HRTICK
/*
* queued ticks are scheduled to match the slice, so don't bother
* validating it and just reschedule.
*/
if (queued) {
resched_curr(rq_of(cfs_rq));
return;
}
/*
* don't let the period tick interfere with the hrtick preemption
*/
if (!sched_feat(DOUBLE_TICK) &&
hrtimer_active(&rq_of(cfs_rq)->hrtick_timer))
return;
#endif
if (cfs_rq->nr_running > 1)
check_preempt_tick(cfs_rq, curr);
}
/**************************************************
* CFS bandwidth control machinery
*/
#ifdef CONFIG_CFS_BANDWIDTH
#ifdef HAVE_JUMP_LABEL
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 07:31:31 +00:00
static struct static_key __cfs_bandwidth_used;
static inline bool cfs_bandwidth_used(void)
{
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 07:31:31 +00:00
return static_key_false(&__cfs_bandwidth_used);
}
void cfs_bandwidth_usage_inc(void)
{
static_key_slow_inc(&__cfs_bandwidth_used);
}
void cfs_bandwidth_usage_dec(void)
{
static_key_slow_dec(&__cfs_bandwidth_used);
}
#else /* HAVE_JUMP_LABEL */
static bool cfs_bandwidth_used(void)
{
return true;
}
void cfs_bandwidth_usage_inc(void) {}
void cfs_bandwidth_usage_dec(void) {}
#endif /* HAVE_JUMP_LABEL */
/*
* default period for cfs group bandwidth.
* default: 0.1s, units: nanoseconds
*/
static inline u64 default_cfs_period(void)
{
return 100000000ULL;
}
static inline u64 sched_cfs_bandwidth_slice(void)
{
return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC;
}
/*
* Replenish runtime according to assigned quota and update expiration time.
* We use sched_clock_cpu directly instead of rq->clock to avoid adding
* additional synchronization around rq->lock.
*
* requires cfs_b->lock
*/
void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
{
u64 now;
if (cfs_b->quota == RUNTIME_INF)
return;
now = sched_clock_cpu(smp_processor_id());
cfs_b->runtime = cfs_b->quota;
cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period);
}
static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
{
return &tg->cfs_bandwidth;
}
/* rq->task_clock normalized against any time this cfs_rq has spent throttled */
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
{
if (unlikely(cfs_rq->throttle_count))
return cfs_rq->throttled_clock_task;
return rq_clock_task(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time;
}
/* returns 0 on failure to allocate runtime */
static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
struct task_group *tg = cfs_rq->tg;
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
u64 amount = 0, min_amount, expires;
/* note: this is a positive sum as runtime_remaining <= 0 */
min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
raw_spin_lock(&cfs_b->lock);
if (cfs_b->quota == RUNTIME_INF)
amount = min_amount;
else {
sched: Cleanup bandwidth timers Roman reported a 3 cpu lockup scenario involving __start_cfs_bandwidth(). The more I look at that code the more I'm convinced its crack, that entire __start_cfs_bandwidth() thing is brain melting, we don't need to cancel a timer before starting it, *hrtimer_start*() will happily remove the timer for you if its still enqueued. Removing that, removes a big part of the problem, no more ugly cancel loop to get stuck in. So now, if I understand things right, the entire reason you have this cfs_b->lock guarded ->timer_active nonsense is to make sure we don't accidentally lose the timer. It appears to me that it should be possible to guarantee that same by unconditionally (re)starting the timer when !queued. Because regardless what hrtimer::function will return, if we beat it to (re)enqueue the timer, it doesn't matter. Now, because hrtimers don't come with any serialization guarantees we must ensure both handler and (re)start loop serialize their access to the hrtimer to avoid both trying to forward the timer at the same time. Update the rt bandwidth timer to match. This effectively reverts: 09dc4ab03936 ("sched/fair: Fix tg_set_cfs_bandwidth() deadlock on rq->lock"). Reported-by: Roman Gushchin <klamm@yandex-team.ru> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Ben Segall <bsegall@google.com> Cc: Paul Turner <pjt@google.com> Link: http://lkml.kernel.org/r/20150415095011.804589208@infradead.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-04-15 09:41:57 +00:00
start_cfs_bandwidth(cfs_b);
if (cfs_b->runtime > 0) {
amount = min(cfs_b->runtime, min_amount);
cfs_b->runtime -= amount;
cfs_b->idle = 0;
}
}
expires = cfs_b->runtime_expires;
raw_spin_unlock(&cfs_b->lock);
cfs_rq->runtime_remaining += amount;
/*
* we may have advanced our local expiration to account for allowed
* spread between our sched_clock and the one on which runtime was
* issued.
*/
if ((s64)(expires - cfs_rq->runtime_expires) > 0)
cfs_rq->runtime_expires = expires;
return cfs_rq->runtime_remaining > 0;
}
/*
* Note: This depends on the synchronization provided by sched_clock and the
* fact that rq->clock snapshots this value.
*/
static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
/* if the deadline is ahead of our clock, nothing to do */
if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0))
return;
if (cfs_rq->runtime_remaining < 0)
return;
/*
* If the local deadline has passed we have to consider the
* possibility that our sched_clock is 'fast' and the global deadline
* has not truly expired.
*
* Fortunately we can check determine whether this the case by checking
* whether the global deadline has advanced. It is valid to compare
* cfs_b->runtime_expires without any locks since we only care about
* exact equality, so a partial write will still work.
*/
if (cfs_rq->runtime_expires != cfs_b->runtime_expires) {
/* extend local deadline, drift is bounded above by 2 ticks */
cfs_rq->runtime_expires += TICK_NSEC;
} else {
/* global deadline is ahead, expiration has passed */
cfs_rq->runtime_remaining = 0;
}
}
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
{
/* dock delta_exec before expiring quota (as it could span periods) */
cfs_rq->runtime_remaining -= delta_exec;
expire_cfs_rq_runtime(cfs_rq);
if (likely(cfs_rq->runtime_remaining > 0))
return;
/*
* if we're unable to extend our runtime we resched so that the active
* hierarchy can be throttled
*/
if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr))
resched_curr(rq_of(cfs_rq));
}
static __always_inline
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
{
if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled)
return;
__account_cfs_rq_runtime(cfs_rq, delta_exec);
}
static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
{
return cfs_bandwidth_used() && cfs_rq->throttled;
}
/* check whether cfs_rq, or any parent, is throttled */
static inline int throttled_hierarchy(struct cfs_rq *cfs_rq)
{
return cfs_bandwidth_used() && cfs_rq->throttle_count;
}
/*
* Ensure that neither of the group entities corresponding to src_cpu or
* dest_cpu are members of a throttled hierarchy when performing group
* load-balance operations.
*/
static inline int throttled_lb_pair(struct task_group *tg,
int src_cpu, int dest_cpu)
{
struct cfs_rq *src_cfs_rq, *dest_cfs_rq;
src_cfs_rq = tg->cfs_rq[src_cpu];
dest_cfs_rq = tg->cfs_rq[dest_cpu];
return throttled_hierarchy(src_cfs_rq) ||
throttled_hierarchy(dest_cfs_rq);
}
/* updated child weight may affect parent so we have to do this bottom up */
static int tg_unthrottle_up(struct task_group *tg, void *data)
{
struct rq *rq = data;
struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
cfs_rq->throttle_count--;
#ifdef CONFIG_SMP
if (!cfs_rq->throttle_count) {
/* adjust cfs_rq_clock_task() */
cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
cfs_rq->throttled_clock_task;
}
#endif
return 0;
}
static int tg_throttle_down(struct task_group *tg, void *data)
{
struct rq *rq = data;
struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
/* group is entering throttled state, stop time */
if (!cfs_rq->throttle_count)
cfs_rq->throttled_clock_task = rq_clock_task(rq);
cfs_rq->throttle_count++;
return 0;
}
static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
{
struct rq *rq = rq_of(cfs_rq);
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
struct sched_entity *se;
long task_delta, dequeue = 1;
sched: Cleanup bandwidth timers Roman reported a 3 cpu lockup scenario involving __start_cfs_bandwidth(). The more I look at that code the more I'm convinced its crack, that entire __start_cfs_bandwidth() thing is brain melting, we don't need to cancel a timer before starting it, *hrtimer_start*() will happily remove the timer for you if its still enqueued. Removing that, removes a big part of the problem, no more ugly cancel loop to get stuck in. So now, if I understand things right, the entire reason you have this cfs_b->lock guarded ->timer_active nonsense is to make sure we don't accidentally lose the timer. It appears to me that it should be possible to guarantee that same by unconditionally (re)starting the timer when !queued. Because regardless what hrtimer::function will return, if we beat it to (re)enqueue the timer, it doesn't matter. Now, because hrtimers don't come with any serialization guarantees we must ensure both handler and (re)start loop serialize their access to the hrtimer to avoid both trying to forward the timer at the same time. Update the rt bandwidth timer to match. This effectively reverts: 09dc4ab03936 ("sched/fair: Fix tg_set_cfs_bandwidth() deadlock on rq->lock"). Reported-by: Roman Gushchin <klamm@yandex-team.ru> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Ben Segall <bsegall@google.com> Cc: Paul Turner <pjt@google.com> Link: http://lkml.kernel.org/r/20150415095011.804589208@infradead.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-04-15 09:41:57 +00:00
bool empty;
se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
/* freeze hierarchy runnable averages while throttled */
rcu_read_lock();
walk_tg_tree_from(cfs_rq->tg, tg_throttle_down, tg_nop, (void *)rq);
rcu_read_unlock();
task_delta = cfs_rq->h_nr_running;
for_each_sched_entity(se) {
struct cfs_rq *qcfs_rq = cfs_rq_of(se);
/* throttled entity or throttle-on-deactivate */
if (!se->on_rq)
break;
if (dequeue)
dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
qcfs_rq->h_nr_running -= task_delta;
if (qcfs_rq->load.weight)
dequeue = 0;
}
if (!se)
sub_nr_running(rq, task_delta);
cfs_rq->throttled = 1;
cfs_rq->throttled_clock = rq_clock(rq);
raw_spin_lock(&cfs_b->lock);
empty = list_empty(&cfs_b->throttled_cfs_rq);
sched: Cleanup bandwidth timers Roman reported a 3 cpu lockup scenario involving __start_cfs_bandwidth(). The more I look at that code the more I'm convinced its crack, that entire __start_cfs_bandwidth() thing is brain melting, we don't need to cancel a timer before starting it, *hrtimer_start*() will happily remove the timer for you if its still enqueued. Removing that, removes a big part of the problem, no more ugly cancel loop to get stuck in. So now, if I understand things right, the entire reason you have this cfs_b->lock guarded ->timer_active nonsense is to make sure we don't accidentally lose the timer. It appears to me that it should be possible to guarantee that same by unconditionally (re)starting the timer when !queued. Because regardless what hrtimer::function will return, if we beat it to (re)enqueue the timer, it doesn't matter. Now, because hrtimers don't come with any serialization guarantees we must ensure both handler and (re)start loop serialize their access to the hrtimer to avoid both trying to forward the timer at the same time. Update the rt bandwidth timer to match. This effectively reverts: 09dc4ab03936 ("sched/fair: Fix tg_set_cfs_bandwidth() deadlock on rq->lock"). Reported-by: Roman Gushchin <klamm@yandex-team.ru> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Ben Segall <bsegall@google.com> Cc: Paul Turner <pjt@google.com> Link: http://lkml.kernel.org/r/20150415095011.804589208@infradead.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-04-15 09:41:57 +00:00
/*
* Add to the _head_ of the list, so that an already-started
* distribute_cfs_runtime will not see us
*/
list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
sched: Cleanup bandwidth timers Roman reported a 3 cpu lockup scenario involving __start_cfs_bandwidth(). The more I look at that code the more I'm convinced its crack, that entire __start_cfs_bandwidth() thing is brain melting, we don't need to cancel a timer before starting it, *hrtimer_start*() will happily remove the timer for you if its still enqueued. Removing that, removes a big part of the problem, no more ugly cancel loop to get stuck in. So now, if I understand things right, the entire reason you have this cfs_b->lock guarded ->timer_active nonsense is to make sure we don't accidentally lose the timer. It appears to me that it should be possible to guarantee that same by unconditionally (re)starting the timer when !queued. Because regardless what hrtimer::function will return, if we beat it to (re)enqueue the timer, it doesn't matter. Now, because hrtimers don't come with any serialization guarantees we must ensure both handler and (re)start loop serialize their access to the hrtimer to avoid both trying to forward the timer at the same time. Update the rt bandwidth timer to match. This effectively reverts: 09dc4ab03936 ("sched/fair: Fix tg_set_cfs_bandwidth() deadlock on rq->lock"). Reported-by: Roman Gushchin <klamm@yandex-team.ru> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Ben Segall <bsegall@google.com> Cc: Paul Turner <pjt@google.com> Link: http://lkml.kernel.org/r/20150415095011.804589208@infradead.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-04-15 09:41:57 +00:00
/*
* If we're the first throttled task, make sure the bandwidth
* timer is running.
*/
if (empty)
start_cfs_bandwidth(cfs_b);
raw_spin_unlock(&cfs_b->lock);
}
void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
{
struct rq *rq = rq_of(cfs_rq);
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
struct sched_entity *se;
int enqueue = 1;
long task_delta;
se = cfs_rq->tg->se[cpu_of(rq)];
cfs_rq->throttled = 0;
update_rq_clock(rq);
raw_spin_lock(&cfs_b->lock);
cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock;
list_del_rcu(&cfs_rq->throttled_list);
raw_spin_unlock(&cfs_b->lock);
/* update hierarchical throttle state */
walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq);
if (!cfs_rq->load.weight)
return;
task_delta = cfs_rq->h_nr_running;
for_each_sched_entity(se) {
if (se->on_rq)
enqueue = 0;
cfs_rq = cfs_rq_of(se);
if (enqueue)
enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
cfs_rq->h_nr_running += task_delta;
if (cfs_rq_throttled(cfs_rq))
break;
}
if (!se)
add_nr_running(rq, task_delta);
/* determine whether we need to wake up potentially idle cpu */
if (rq->curr == rq->idle && rq->cfs.nr_running)
resched_curr(rq);
}
static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
u64 remaining, u64 expires)
{
struct cfs_rq *cfs_rq;
u64 runtime;
u64 starting_runtime = remaining;
rcu_read_lock();
list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
throttled_list) {
struct rq *rq = rq_of(cfs_rq);
raw_spin_lock(&rq->lock);
if (!cfs_rq_throttled(cfs_rq))
goto next;
runtime = -cfs_rq->runtime_remaining + 1;
if (runtime > remaining)
runtime = remaining;
remaining -= runtime;
cfs_rq->runtime_remaining += runtime;
cfs_rq->runtime_expires = expires;
/* we check whether we're throttled above */
if (cfs_rq->runtime_remaining > 0)
unthrottle_cfs_rq(cfs_rq);
next:
raw_spin_unlock(&rq->lock);
if (!remaining)
break;
}
rcu_read_unlock();
return starting_runtime - remaining;
}
/*
* Responsible for refilling a task_group's bandwidth and unthrottling its
* cfs_rqs as appropriate. If there has been no activity within the last
* period the timer is deactivated until scheduling resumes; cfs_b->idle is
* used to track this state.
*/
static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
{
u64 runtime, runtime_expires;
int throttled;
/* no need to continue the timer with no bandwidth constraint */
if (cfs_b->quota == RUNTIME_INF)
goto out_deactivate;
throttled = !list_empty(&cfs_b->throttled_cfs_rq);
cfs_b->nr_periods += overrun;
/*
* idle depends on !throttled (for the case of a large deficit), and if
* we're going inactive then everything else can be deferred
*/
if (cfs_b->idle && !throttled)
goto out_deactivate;
__refill_cfs_bandwidth_runtime(cfs_b);
if (!throttled) {
/* mark as potentially idle for the upcoming period */
cfs_b->idle = 1;
return 0;
}
/* account preceding periods in which throttling occurred */
cfs_b->nr_throttled += overrun;
runtime_expires = cfs_b->runtime_expires;
/*
* This check is repeated as we are holding onto the new bandwidth while
* we unthrottle. This can potentially race with an unthrottled group
* trying to acquire new bandwidth from the global pool. This can result
* in us over-using our runtime if it is all used during this loop, but
* only by limited amounts in that extreme case.
*/
while (throttled && cfs_b->runtime > 0) {
runtime = cfs_b->runtime;
raw_spin_unlock(&cfs_b->lock);
/* we can't nest cfs_b->lock while distributing bandwidth */
runtime = distribute_cfs_runtime(cfs_b, runtime,
runtime_expires);
raw_spin_lock(&cfs_b->lock);
throttled = !list_empty(&cfs_b->throttled_cfs_rq);
cfs_b->runtime -= min(runtime, cfs_b->runtime);
}
/*
* While we are ensured activity in the period following an
* unthrottle, this also covers the case in which the new bandwidth is
* insufficient to cover the existing bandwidth deficit. (Forcing the
* timer to remain active while there are any throttled entities.)
*/
cfs_b->idle = 0;
return 0;
out_deactivate:
return 1;
}
sched: Return unused runtime on group dequeue When a local cfs_rq blocks we return the majority of its remaining quota to the global bandwidth pool for use by other runqueues. We do this only when the quota is current and there is more than min_cfs_rq_quota [1ms by default] of runtime remaining on the rq. In the case where there are throttled runqueues and we have sufficient bandwidth to meter out a slice, a second timer is kicked off to handle this delivery, unthrottling where appropriate. Using a 'worst case' antagonist which executes on each cpu for 1ms before moving onto the next on a fairly large machine: no quota generations: 197.47 ms /cgroup/a/cpuacct.usage 199.46 ms /cgroup/a/cpuacct.usage 205.46 ms /cgroup/a/cpuacct.usage 198.46 ms /cgroup/a/cpuacct.usage 208.39 ms /cgroup/a/cpuacct.usage Since we are allowed to use "stale" quota our usage is effectively bounded by the rate of input into the global pool and performance is relatively stable. with quota generations [1s increments]: 119.58 ms /cgroup/a/cpuacct.usage 119.65 ms /cgroup/a/cpuacct.usage 119.64 ms /cgroup/a/cpuacct.usage 119.63 ms /cgroup/a/cpuacct.usage 119.60 ms /cgroup/a/cpuacct.usage The large deficit here is due to quota generations (/intentionally/) preventing us from now using previously stranded slack quota. The cost is that this quota becomes unavailable. with quota generations and quota return: 200.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 198.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 200.06 ms /cgroup/a/cpuacct.usage By returning unused quota we're able to both stably consume our desired quota and prevent unintentional overages due to the abuse of slack quota from previous quota periods (especially on a large machine). Signed-off-by: Paul Turner <pjt@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110721184758.306848658@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-07-21 16:43:41 +00:00
/* a cfs_rq won't donate quota below this amount */
static const u64 min_cfs_rq_runtime = 1 * NSEC_PER_MSEC;
/* minimum remaining period time to redistribute slack quota */
static const u64 min_bandwidth_expiration = 2 * NSEC_PER_MSEC;
/* how long we wait to gather additional slack before distributing */
static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC;
/*
* Are we near the end of the current quota period?
*
* Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the
* hrtimer base being cleared by hrtimer_start. In the case of
* migrate_hrtimers, base is never cleared, so we are fine.
*/
sched: Return unused runtime on group dequeue When a local cfs_rq blocks we return the majority of its remaining quota to the global bandwidth pool for use by other runqueues. We do this only when the quota is current and there is more than min_cfs_rq_quota [1ms by default] of runtime remaining on the rq. In the case where there are throttled runqueues and we have sufficient bandwidth to meter out a slice, a second timer is kicked off to handle this delivery, unthrottling where appropriate. Using a 'worst case' antagonist which executes on each cpu for 1ms before moving onto the next on a fairly large machine: no quota generations: 197.47 ms /cgroup/a/cpuacct.usage 199.46 ms /cgroup/a/cpuacct.usage 205.46 ms /cgroup/a/cpuacct.usage 198.46 ms /cgroup/a/cpuacct.usage 208.39 ms /cgroup/a/cpuacct.usage Since we are allowed to use "stale" quota our usage is effectively bounded by the rate of input into the global pool and performance is relatively stable. with quota generations [1s increments]: 119.58 ms /cgroup/a/cpuacct.usage 119.65 ms /cgroup/a/cpuacct.usage 119.64 ms /cgroup/a/cpuacct.usage 119.63 ms /cgroup/a/cpuacct.usage 119.60 ms /cgroup/a/cpuacct.usage The large deficit here is due to quota generations (/intentionally/) preventing us from now using previously stranded slack quota. The cost is that this quota becomes unavailable. with quota generations and quota return: 200.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 198.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 200.06 ms /cgroup/a/cpuacct.usage By returning unused quota we're able to both stably consume our desired quota and prevent unintentional overages due to the abuse of slack quota from previous quota periods (especially on a large machine). Signed-off-by: Paul Turner <pjt@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110721184758.306848658@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-07-21 16:43:41 +00:00
static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
{
struct hrtimer *refresh_timer = &cfs_b->period_timer;
u64 remaining;
/* if the call-back is running a quota refresh is already occurring */
if (hrtimer_callback_running(refresh_timer))
return 1;
/* is a quota refresh about to occur? */
remaining = ktime_to_ns(hrtimer_expires_remaining(refresh_timer));
if (remaining < min_expire)
return 1;
return 0;
}
static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b)
{
u64 min_left = cfs_bandwidth_slack_period + min_bandwidth_expiration;
/* if there's a quota refresh soon don't bother with slack */
if (runtime_refresh_within(cfs_b, min_left))
return;
sched,perf: Fix periodic timers In the below two commits (see Fixes) we have periodic timers that can stop themselves when they're no longer required, but need to be (re)-started when their idle condition changes. Further complications is that we want the timer handler to always do the forward such that it will always correctly deal with the overruns, and we do not want to race such that the handler has already decided to stop, but the (external) restart sees the timer still active and we end up with a 'lost' timer. The problem with the current code is that the re-start can come before the callback does the forward, at which point the forward from the callback will WARN about forwarding an enqueued timer. Now, conceptually its easy to detect if you're before or after the fwd by comparing the expiration time against the current time. Of course, that's expensive (and racy) because we don't have the current time. Alternatively one could cache this state inside the timer, but then everybody pays the overhead of maintaining this extra state, and that is undesired. The only other option that I could see is the external timer_active variable, which I tried to kill before. I would love a nicer interface for this seemingly simple 'problem' but alas. Fixes: 272325c4821f ("perf: Fix mux_interval hrtimer wreckage") Fixes: 77a4d1a1b9a1 ("sched: Cleanup bandwidth timers") Cc: pjt@google.com Cc: tglx@linutronix.de Cc: klamm@yandex-team.ru Cc: mingo@kernel.org Cc: bsegall@google.com Cc: hpa@zytor.com Cc: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150514102311.GX21418@twins.programming.kicks-ass.net
2015-05-14 10:23:11 +00:00
hrtimer_start(&cfs_b->slack_timer,
ns_to_ktime(cfs_bandwidth_slack_period),
HRTIMER_MODE_REL);
sched: Return unused runtime on group dequeue When a local cfs_rq blocks we return the majority of its remaining quota to the global bandwidth pool for use by other runqueues. We do this only when the quota is current and there is more than min_cfs_rq_quota [1ms by default] of runtime remaining on the rq. In the case where there are throttled runqueues and we have sufficient bandwidth to meter out a slice, a second timer is kicked off to handle this delivery, unthrottling where appropriate. Using a 'worst case' antagonist which executes on each cpu for 1ms before moving onto the next on a fairly large machine: no quota generations: 197.47 ms /cgroup/a/cpuacct.usage 199.46 ms /cgroup/a/cpuacct.usage 205.46 ms /cgroup/a/cpuacct.usage 198.46 ms /cgroup/a/cpuacct.usage 208.39 ms /cgroup/a/cpuacct.usage Since we are allowed to use "stale" quota our usage is effectively bounded by the rate of input into the global pool and performance is relatively stable. with quota generations [1s increments]: 119.58 ms /cgroup/a/cpuacct.usage 119.65 ms /cgroup/a/cpuacct.usage 119.64 ms /cgroup/a/cpuacct.usage 119.63 ms /cgroup/a/cpuacct.usage 119.60 ms /cgroup/a/cpuacct.usage The large deficit here is due to quota generations (/intentionally/) preventing us from now using previously stranded slack quota. The cost is that this quota becomes unavailable. with quota generations and quota return: 200.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 198.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 200.06 ms /cgroup/a/cpuacct.usage By returning unused quota we're able to both stably consume our desired quota and prevent unintentional overages due to the abuse of slack quota from previous quota periods (especially on a large machine). Signed-off-by: Paul Turner <pjt@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110721184758.306848658@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-07-21 16:43:41 +00:00
}
/* we know any runtime found here is valid as update_curr() precedes return */
static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
s64 slack_runtime = cfs_rq->runtime_remaining - min_cfs_rq_runtime;
if (slack_runtime <= 0)
return;
raw_spin_lock(&cfs_b->lock);
if (cfs_b->quota != RUNTIME_INF &&
cfs_rq->runtime_expires == cfs_b->runtime_expires) {
cfs_b->runtime += slack_runtime;
/* we are under rq->lock, defer unthrottling using a timer */
if (cfs_b->runtime > sched_cfs_bandwidth_slice() &&
!list_empty(&cfs_b->throttled_cfs_rq))
start_cfs_slack_bandwidth(cfs_b);
}
raw_spin_unlock(&cfs_b->lock);
/* even if it's not valid for return we don't want to try again */
cfs_rq->runtime_remaining -= slack_runtime;
}
static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
if (!cfs_bandwidth_used())
return;
if (!cfs_rq->runtime_enabled || cfs_rq->nr_running)
sched: Return unused runtime on group dequeue When a local cfs_rq blocks we return the majority of its remaining quota to the global bandwidth pool for use by other runqueues. We do this only when the quota is current and there is more than min_cfs_rq_quota [1ms by default] of runtime remaining on the rq. In the case where there are throttled runqueues and we have sufficient bandwidth to meter out a slice, a second timer is kicked off to handle this delivery, unthrottling where appropriate. Using a 'worst case' antagonist which executes on each cpu for 1ms before moving onto the next on a fairly large machine: no quota generations: 197.47 ms /cgroup/a/cpuacct.usage 199.46 ms /cgroup/a/cpuacct.usage 205.46 ms /cgroup/a/cpuacct.usage 198.46 ms /cgroup/a/cpuacct.usage 208.39 ms /cgroup/a/cpuacct.usage Since we are allowed to use "stale" quota our usage is effectively bounded by the rate of input into the global pool and performance is relatively stable. with quota generations [1s increments]: 119.58 ms /cgroup/a/cpuacct.usage 119.65 ms /cgroup/a/cpuacct.usage 119.64 ms /cgroup/a/cpuacct.usage 119.63 ms /cgroup/a/cpuacct.usage 119.60 ms /cgroup/a/cpuacct.usage The large deficit here is due to quota generations (/intentionally/) preventing us from now using previously stranded slack quota. The cost is that this quota becomes unavailable. with quota generations and quota return: 200.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 198.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 200.06 ms /cgroup/a/cpuacct.usage By returning unused quota we're able to both stably consume our desired quota and prevent unintentional overages due to the abuse of slack quota from previous quota periods (especially on a large machine). Signed-off-by: Paul Turner <pjt@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110721184758.306848658@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-07-21 16:43:41 +00:00
return;
__return_cfs_rq_runtime(cfs_rq);
}
/*
* This is done with a timer (instead of inline with bandwidth return) since
* it's necessary to juggle rq->locks to unthrottle their respective cfs_rqs.
*/
static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
{
u64 runtime = 0, slice = sched_cfs_bandwidth_slice();
u64 expires;
/* confirm we're still not at a refresh boundary */
raw_spin_lock(&cfs_b->lock);
if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
raw_spin_unlock(&cfs_b->lock);
sched: Return unused runtime on group dequeue When a local cfs_rq blocks we return the majority of its remaining quota to the global bandwidth pool for use by other runqueues. We do this only when the quota is current and there is more than min_cfs_rq_quota [1ms by default] of runtime remaining on the rq. In the case where there are throttled runqueues and we have sufficient bandwidth to meter out a slice, a second timer is kicked off to handle this delivery, unthrottling where appropriate. Using a 'worst case' antagonist which executes on each cpu for 1ms before moving onto the next on a fairly large machine: no quota generations: 197.47 ms /cgroup/a/cpuacct.usage 199.46 ms /cgroup/a/cpuacct.usage 205.46 ms /cgroup/a/cpuacct.usage 198.46 ms /cgroup/a/cpuacct.usage 208.39 ms /cgroup/a/cpuacct.usage Since we are allowed to use "stale" quota our usage is effectively bounded by the rate of input into the global pool and performance is relatively stable. with quota generations [1s increments]: 119.58 ms /cgroup/a/cpuacct.usage 119.65 ms /cgroup/a/cpuacct.usage 119.64 ms /cgroup/a/cpuacct.usage 119.63 ms /cgroup/a/cpuacct.usage 119.60 ms /cgroup/a/cpuacct.usage The large deficit here is due to quota generations (/intentionally/) preventing us from now using previously stranded slack quota. The cost is that this quota becomes unavailable. with quota generations and quota return: 200.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 198.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 200.06 ms /cgroup/a/cpuacct.usage By returning unused quota we're able to both stably consume our desired quota and prevent unintentional overages due to the abuse of slack quota from previous quota periods (especially on a large machine). Signed-off-by: Paul Turner <pjt@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110721184758.306848658@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-07-21 16:43:41 +00:00
return;
}
sched: Return unused runtime on group dequeue When a local cfs_rq blocks we return the majority of its remaining quota to the global bandwidth pool for use by other runqueues. We do this only when the quota is current and there is more than min_cfs_rq_quota [1ms by default] of runtime remaining on the rq. In the case where there are throttled runqueues and we have sufficient bandwidth to meter out a slice, a second timer is kicked off to handle this delivery, unthrottling where appropriate. Using a 'worst case' antagonist which executes on each cpu for 1ms before moving onto the next on a fairly large machine: no quota generations: 197.47 ms /cgroup/a/cpuacct.usage 199.46 ms /cgroup/a/cpuacct.usage 205.46 ms /cgroup/a/cpuacct.usage 198.46 ms /cgroup/a/cpuacct.usage 208.39 ms /cgroup/a/cpuacct.usage Since we are allowed to use "stale" quota our usage is effectively bounded by the rate of input into the global pool and performance is relatively stable. with quota generations [1s increments]: 119.58 ms /cgroup/a/cpuacct.usage 119.65 ms /cgroup/a/cpuacct.usage 119.64 ms /cgroup/a/cpuacct.usage 119.63 ms /cgroup/a/cpuacct.usage 119.60 ms /cgroup/a/cpuacct.usage The large deficit here is due to quota generations (/intentionally/) preventing us from now using previously stranded slack quota. The cost is that this quota becomes unavailable. with quota generations and quota return: 200.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 198.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 200.06 ms /cgroup/a/cpuacct.usage By returning unused quota we're able to both stably consume our desired quota and prevent unintentional overages due to the abuse of slack quota from previous quota periods (especially on a large machine). Signed-off-by: Paul Turner <pjt@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110721184758.306848658@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-07-21 16:43:41 +00:00
if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice)
sched: Return unused runtime on group dequeue When a local cfs_rq blocks we return the majority of its remaining quota to the global bandwidth pool for use by other runqueues. We do this only when the quota is current and there is more than min_cfs_rq_quota [1ms by default] of runtime remaining on the rq. In the case where there are throttled runqueues and we have sufficient bandwidth to meter out a slice, a second timer is kicked off to handle this delivery, unthrottling where appropriate. Using a 'worst case' antagonist which executes on each cpu for 1ms before moving onto the next on a fairly large machine: no quota generations: 197.47 ms /cgroup/a/cpuacct.usage 199.46 ms /cgroup/a/cpuacct.usage 205.46 ms /cgroup/a/cpuacct.usage 198.46 ms /cgroup/a/cpuacct.usage 208.39 ms /cgroup/a/cpuacct.usage Since we are allowed to use "stale" quota our usage is effectively bounded by the rate of input into the global pool and performance is relatively stable. with quota generations [1s increments]: 119.58 ms /cgroup/a/cpuacct.usage 119.65 ms /cgroup/a/cpuacct.usage 119.64 ms /cgroup/a/cpuacct.usage 119.63 ms /cgroup/a/cpuacct.usage 119.60 ms /cgroup/a/cpuacct.usage The large deficit here is due to quota generations (/intentionally/) preventing us from now using previously stranded slack quota. The cost is that this quota becomes unavailable. with quota generations and quota return: 200.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 198.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 200.06 ms /cgroup/a/cpuacct.usage By returning unused quota we're able to both stably consume our desired quota and prevent unintentional overages due to the abuse of slack quota from previous quota periods (especially on a large machine). Signed-off-by: Paul Turner <pjt@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110721184758.306848658@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-07-21 16:43:41 +00:00
runtime = cfs_b->runtime;
sched: Return unused runtime on group dequeue When a local cfs_rq blocks we return the majority of its remaining quota to the global bandwidth pool for use by other runqueues. We do this only when the quota is current and there is more than min_cfs_rq_quota [1ms by default] of runtime remaining on the rq. In the case where there are throttled runqueues and we have sufficient bandwidth to meter out a slice, a second timer is kicked off to handle this delivery, unthrottling where appropriate. Using a 'worst case' antagonist which executes on each cpu for 1ms before moving onto the next on a fairly large machine: no quota generations: 197.47 ms /cgroup/a/cpuacct.usage 199.46 ms /cgroup/a/cpuacct.usage 205.46 ms /cgroup/a/cpuacct.usage 198.46 ms /cgroup/a/cpuacct.usage 208.39 ms /cgroup/a/cpuacct.usage Since we are allowed to use "stale" quota our usage is effectively bounded by the rate of input into the global pool and performance is relatively stable. with quota generations [1s increments]: 119.58 ms /cgroup/a/cpuacct.usage 119.65 ms /cgroup/a/cpuacct.usage 119.64 ms /cgroup/a/cpuacct.usage 119.63 ms /cgroup/a/cpuacct.usage 119.60 ms /cgroup/a/cpuacct.usage The large deficit here is due to quota generations (/intentionally/) preventing us from now using previously stranded slack quota. The cost is that this quota becomes unavailable. with quota generations and quota return: 200.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 198.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 200.06 ms /cgroup/a/cpuacct.usage By returning unused quota we're able to both stably consume our desired quota and prevent unintentional overages due to the abuse of slack quota from previous quota periods (especially on a large machine). Signed-off-by: Paul Turner <pjt@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110721184758.306848658@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-07-21 16:43:41 +00:00
expires = cfs_b->runtime_expires;
raw_spin_unlock(&cfs_b->lock);
if (!runtime)
return;
runtime = distribute_cfs_runtime(cfs_b, runtime, expires);
raw_spin_lock(&cfs_b->lock);
if (expires == cfs_b->runtime_expires)
cfs_b->runtime -= min(runtime, cfs_b->runtime);
sched: Return unused runtime on group dequeue When a local cfs_rq blocks we return the majority of its remaining quota to the global bandwidth pool for use by other runqueues. We do this only when the quota is current and there is more than min_cfs_rq_quota [1ms by default] of runtime remaining on the rq. In the case where there are throttled runqueues and we have sufficient bandwidth to meter out a slice, a second timer is kicked off to handle this delivery, unthrottling where appropriate. Using a 'worst case' antagonist which executes on each cpu for 1ms before moving onto the next on a fairly large machine: no quota generations: 197.47 ms /cgroup/a/cpuacct.usage 199.46 ms /cgroup/a/cpuacct.usage 205.46 ms /cgroup/a/cpuacct.usage 198.46 ms /cgroup/a/cpuacct.usage 208.39 ms /cgroup/a/cpuacct.usage Since we are allowed to use "stale" quota our usage is effectively bounded by the rate of input into the global pool and performance is relatively stable. with quota generations [1s increments]: 119.58 ms /cgroup/a/cpuacct.usage 119.65 ms /cgroup/a/cpuacct.usage 119.64 ms /cgroup/a/cpuacct.usage 119.63 ms /cgroup/a/cpuacct.usage 119.60 ms /cgroup/a/cpuacct.usage The large deficit here is due to quota generations (/intentionally/) preventing us from now using previously stranded slack quota. The cost is that this quota becomes unavailable. with quota generations and quota return: 200.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 198.09 ms /cgroup/a/cpuacct.usage 200.09 ms /cgroup/a/cpuacct.usage 200.06 ms /cgroup/a/cpuacct.usage By returning unused quota we're able to both stably consume our desired quota and prevent unintentional overages due to the abuse of slack quota from previous quota periods (especially on a large machine). Signed-off-by: Paul Turner <pjt@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110721184758.306848658@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-07-21 16:43:41 +00:00
raw_spin_unlock(&cfs_b->lock);
}
/*
* When a group wakes up we want to make sure that its quota is not already
* expired/exceeded, otherwise it may be allowed to steal additional ticks of
* runtime as update_curr() throttling can not not trigger until it's on-rq.
*/
static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
{
if (!cfs_bandwidth_used())
return;
/* an active group must be handled by the update_curr()->put() path */
if (!cfs_rq->runtime_enabled || cfs_rq->curr)
return;
/* ensure the group is not already throttled */
if (cfs_rq_throttled(cfs_rq))
return;
/* update runtime allocation */
account_cfs_rq_runtime(cfs_rq, 0);
if (cfs_rq->runtime_remaining <= 0)
throttle_cfs_rq(cfs_rq);
}
/* conditionally throttle active cfs_rq's from put_prev_entity() */
static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
if (!cfs_bandwidth_used())
return false;
if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0))
return false;
/*
* it's possible for a throttled entity to be forced into a running
* state (e.g. set_curr_task), in this case we're finished.
*/
if (cfs_rq_throttled(cfs_rq))
return true;
throttle_cfs_rq(cfs_rq);
return true;
}
static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
{
struct cfs_bandwidth *cfs_b =
container_of(timer, struct cfs_bandwidth, slack_timer);
sched: Cleanup bandwidth timers Roman reported a 3 cpu lockup scenario involving __start_cfs_bandwidth(). The more I look at that code the more I'm convinced its crack, that entire __start_cfs_bandwidth() thing is brain melting, we don't need to cancel a timer before starting it, *hrtimer_start*() will happily remove the timer for you if its still enqueued. Removing that, removes a big part of the problem, no more ugly cancel loop to get stuck in. So now, if I understand things right, the entire reason you have this cfs_b->lock guarded ->timer_active nonsense is to make sure we don't accidentally lose the timer. It appears to me that it should be possible to guarantee that same by unconditionally (re)starting the timer when !queued. Because regardless what hrtimer::function will return, if we beat it to (re)enqueue the timer, it doesn't matter. Now, because hrtimers don't come with any serialization guarantees we must ensure both handler and (re)start loop serialize their access to the hrtimer to avoid both trying to forward the timer at the same time. Update the rt bandwidth timer to match. This effectively reverts: 09dc4ab03936 ("sched/fair: Fix tg_set_cfs_bandwidth() deadlock on rq->lock"). Reported-by: Roman Gushchin <klamm@yandex-team.ru> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Ben Segall <bsegall@google.com> Cc: Paul Turner <pjt@google.com> Link: http://lkml.kernel.org/r/20150415095011.804589208@infradead.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-04-15 09:41:57 +00:00
do_sched_cfs_slack_timer(cfs_b);
return HRTIMER_NORESTART;
}
static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
{
struct cfs_bandwidth *cfs_b =
container_of(timer, struct cfs_bandwidth, period_timer);
int overrun;
int idle = 0;
raw_spin_lock(&cfs_b->lock);
for (;;) {
sched: Cleanup bandwidth timers Roman reported a 3 cpu lockup scenario involving __start_cfs_bandwidth(). The more I look at that code the more I'm convinced its crack, that entire __start_cfs_bandwidth() thing is brain melting, we don't need to cancel a timer before starting it, *hrtimer_start*() will happily remove the timer for you if its still enqueued. Removing that, removes a big part of the problem, no more ugly cancel loop to get stuck in. So now, if I understand things right, the entire reason you have this cfs_b->lock guarded ->timer_active nonsense is to make sure we don't accidentally lose the timer. It appears to me that it should be possible to guarantee that same by unconditionally (re)starting the timer when !queued. Because regardless what hrtimer::function will return, if we beat it to (re)enqueue the timer, it doesn't matter. Now, because hrtimers don't come with any serialization guarantees we must ensure both handler and (re)start loop serialize their access to the hrtimer to avoid both trying to forward the timer at the same time. Update the rt bandwidth timer to match. This effectively reverts: 09dc4ab03936 ("sched/fair: Fix tg_set_cfs_bandwidth() deadlock on rq->lock"). Reported-by: Roman Gushchin <klamm@yandex-team.ru> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Ben Segall <bsegall@google.com> Cc: Paul Turner <pjt@google.com> Link: http://lkml.kernel.org/r/20150415095011.804589208@infradead.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-04-15 09:41:57 +00:00
overrun = hrtimer_forward_now(timer, cfs_b->period);
if (!overrun)
break;
idle = do_sched_cfs_period_timer(cfs_b, overrun);
}
sched,perf: Fix periodic timers In the below two commits (see Fixes) we have periodic timers that can stop themselves when they're no longer required, but need to be (re)-started when their idle condition changes. Further complications is that we want the timer handler to always do the forward such that it will always correctly deal with the overruns, and we do not want to race such that the handler has already decided to stop, but the (external) restart sees the timer still active and we end up with a 'lost' timer. The problem with the current code is that the re-start can come before the callback does the forward, at which point the forward from the callback will WARN about forwarding an enqueued timer. Now, conceptually its easy to detect if you're before or after the fwd by comparing the expiration time against the current time. Of course, that's expensive (and racy) because we don't have the current time. Alternatively one could cache this state inside the timer, but then everybody pays the overhead of maintaining this extra state, and that is undesired. The only other option that I could see is the external timer_active variable, which I tried to kill before. I would love a nicer interface for this seemingly simple 'problem' but alas. Fixes: 272325c4821f ("perf: Fix mux_interval hrtimer wreckage") Fixes: 77a4d1a1b9a1 ("sched: Cleanup bandwidth timers") Cc: pjt@google.com Cc: tglx@linutronix.de Cc: klamm@yandex-team.ru Cc: mingo@kernel.org Cc: bsegall@google.com Cc: hpa@zytor.com Cc: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150514102311.GX21418@twins.programming.kicks-ass.net
2015-05-14 10:23:11 +00:00
if (idle)
cfs_b->period_active = 0;
raw_spin_unlock(&cfs_b->lock);
return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
}
void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
raw_spin_lock_init(&cfs_b->lock);
cfs_b->runtime = 0;
cfs_b->quota = RUNTIME_INF;
cfs_b->period = ns_to_ktime(default_cfs_period());
INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
sched,perf: Fix periodic timers In the below two commits (see Fixes) we have periodic timers that can stop themselves when they're no longer required, but need to be (re)-started when their idle condition changes. Further complications is that we want the timer handler to always do the forward such that it will always correctly deal with the overruns, and we do not want to race such that the handler has already decided to stop, but the (external) restart sees the timer still active and we end up with a 'lost' timer. The problem with the current code is that the re-start can come before the callback does the forward, at which point the forward from the callback will WARN about forwarding an enqueued timer. Now, conceptually its easy to detect if you're before or after the fwd by comparing the expiration time against the current time. Of course, that's expensive (and racy) because we don't have the current time. Alternatively one could cache this state inside the timer, but then everybody pays the overhead of maintaining this extra state, and that is undesired. The only other option that I could see is the external timer_active variable, which I tried to kill before. I would love a nicer interface for this seemingly simple 'problem' but alas. Fixes: 272325c4821f ("perf: Fix mux_interval hrtimer wreckage") Fixes: 77a4d1a1b9a1 ("sched: Cleanup bandwidth timers") Cc: pjt@google.com Cc: tglx@linutronix.de Cc: klamm@yandex-team.ru Cc: mingo@kernel.org Cc: bsegall@google.com Cc: hpa@zytor.com Cc: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150514102311.GX21418@twins.programming.kicks-ass.net
2015-05-14 10:23:11 +00:00
hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
cfs_b->period_timer.function = sched_cfs_period_timer;
hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
cfs_b->slack_timer.function = sched_cfs_slack_timer;
}
static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
cfs_rq->runtime_enabled = 0;
INIT_LIST_HEAD(&cfs_rq->throttled_list);
}
sched: Cleanup bandwidth timers Roman reported a 3 cpu lockup scenario involving __start_cfs_bandwidth(). The more I look at that code the more I'm convinced its crack, that entire __start_cfs_bandwidth() thing is brain melting, we don't need to cancel a timer before starting it, *hrtimer_start*() will happily remove the timer for you if its still enqueued. Removing that, removes a big part of the problem, no more ugly cancel loop to get stuck in. So now, if I understand things right, the entire reason you have this cfs_b->lock guarded ->timer_active nonsense is to make sure we don't accidentally lose the timer. It appears to me that it should be possible to guarantee that same by unconditionally (re)starting the timer when !queued. Because regardless what hrtimer::function will return, if we beat it to (re)enqueue the timer, it doesn't matter. Now, because hrtimers don't come with any serialization guarantees we must ensure both handler and (re)start loop serialize their access to the hrtimer to avoid both trying to forward the timer at the same time. Update the rt bandwidth timer to match. This effectively reverts: 09dc4ab03936 ("sched/fair: Fix tg_set_cfs_bandwidth() deadlock on rq->lock"). Reported-by: Roman Gushchin <klamm@yandex-team.ru> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Ben Segall <bsegall@google.com> Cc: Paul Turner <pjt@google.com> Link: http://lkml.kernel.org/r/20150415095011.804589208@infradead.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-04-15 09:41:57 +00:00
void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
sched,perf: Fix periodic timers In the below two commits (see Fixes) we have periodic timers that can stop themselves when they're no longer required, but need to be (re)-started when their idle condition changes. Further complications is that we want the timer handler to always do the forward such that it will always correctly deal with the overruns, and we do not want to race such that the handler has already decided to stop, but the (external) restart sees the timer still active and we end up with a 'lost' timer. The problem with the current code is that the re-start can come before the callback does the forward, at which point the forward from the callback will WARN about forwarding an enqueued timer. Now, conceptually its easy to detect if you're before or after the fwd by comparing the expiration time against the current time. Of course, that's expensive (and racy) because we don't have the current time. Alternatively one could cache this state inside the timer, but then everybody pays the overhead of maintaining this extra state, and that is undesired. The only other option that I could see is the external timer_active variable, which I tried to kill before. I would love a nicer interface for this seemingly simple 'problem' but alas. Fixes: 272325c4821f ("perf: Fix mux_interval hrtimer wreckage") Fixes: 77a4d1a1b9a1 ("sched: Cleanup bandwidth timers") Cc: pjt@google.com Cc: tglx@linutronix.de Cc: klamm@yandex-team.ru Cc: mingo@kernel.org Cc: bsegall@google.com Cc: hpa@zytor.com Cc: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150514102311.GX21418@twins.programming.kicks-ass.net
2015-05-14 10:23:11 +00:00
lockdep_assert_held(&cfs_b->lock);
sched,perf: Fix periodic timers In the below two commits (see Fixes) we have periodic timers that can stop themselves when they're no longer required, but need to be (re)-started when their idle condition changes. Further complications is that we want the timer handler to always do the forward such that it will always correctly deal with the overruns, and we do not want to race such that the handler has already decided to stop, but the (external) restart sees the timer still active and we end up with a 'lost' timer. The problem with the current code is that the re-start can come before the callback does the forward, at which point the forward from the callback will WARN about forwarding an enqueued timer. Now, conceptually its easy to detect if you're before or after the fwd by comparing the expiration time against the current time. Of course, that's expensive (and racy) because we don't have the current time. Alternatively one could cache this state inside the timer, but then everybody pays the overhead of maintaining this extra state, and that is undesired. The only other option that I could see is the external timer_active variable, which I tried to kill before. I would love a nicer interface for this seemingly simple 'problem' but alas. Fixes: 272325c4821f ("perf: Fix mux_interval hrtimer wreckage") Fixes: 77a4d1a1b9a1 ("sched: Cleanup bandwidth timers") Cc: pjt@google.com Cc: tglx@linutronix.de Cc: klamm@yandex-team.ru Cc: mingo@kernel.org Cc: bsegall@google.com Cc: hpa@zytor.com Cc: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150514102311.GX21418@twins.programming.kicks-ass.net
2015-05-14 10:23:11 +00:00
if (!cfs_b->period_active) {
cfs_b->period_active = 1;
hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
}
}
static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
sched/fair: Fix RCU stall upon -ENOMEM in sched_create_group() When alloc_fair_sched_group() in sched_create_group() fails, free_sched_group() is called, and free_fair_sched_group() is called by free_sched_group(). Since destroy_cfs_bandwidth() is called by free_fair_sched_group() without calling init_cfs_bandwidth(), RCU stall occurs at hrtimer_cancel(): INFO: rcu_sched self-detected stall on CPU { 1} (t=60000 jiffies g=13074 c=13073 q=0) Task dump for CPU 1: (fprintd) R running task 0 6249 1 0x00000088 ... Call Trace: <IRQ> [<ffffffff81094988>] sched_show_task+0xa8/0x110 [<ffffffff81097acd>] dump_cpu_task+0x3d/0x50 [<ffffffff810c3a80>] rcu_dump_cpu_stacks+0x90/0xd0 [<ffffffff810c7751>] rcu_check_callbacks+0x491/0x700 [<ffffffff810cbf2b>] update_process_times+0x4b/0x80 [<ffffffff810db046>] tick_sched_handle.isra.20+0x36/0x50 [<ffffffff810db0a2>] tick_sched_timer+0x42/0x70 [<ffffffff810ccb19>] __run_hrtimer+0x69/0x1a0 [<ffffffff810db060>] ? tick_sched_handle.isra.20+0x50/0x50 [<ffffffff810ccedf>] hrtimer_interrupt+0xef/0x230 [<ffffffff810452cb>] local_apic_timer_interrupt+0x3b/0x70 [<ffffffff8164a465>] smp_apic_timer_interrupt+0x45/0x60 [<ffffffff816485bd>] apic_timer_interrupt+0x6d/0x80 <EOI> [<ffffffff810cc588>] ? lock_hrtimer_base.isra.23+0x18/0x50 [<ffffffff81193cf1>] ? __kmalloc+0x211/0x230 [<ffffffff810cc9d2>] hrtimer_try_to_cancel+0x22/0xd0 [<ffffffff81193cf1>] ? __kmalloc+0x211/0x230 [<ffffffff810ccaa2>] hrtimer_cancel+0x22/0x30 [<ffffffff810a3cb5>] free_fair_sched_group+0x25/0xd0 [<ffffffff8108df46>] free_sched_group+0x16/0x40 [<ffffffff810971bb>] sched_create_group+0x4b/0x80 [<ffffffff810aa383>] sched_autogroup_create_attach+0x43/0x1c0 [<ffffffff8107dc9c>] sys_setsid+0x7c/0x110 [<ffffffff81647729>] system_call_fastpath+0x12/0x17 Check whether init_cfs_bandwidth() was called before calling destroy_cfs_bandwidth(). Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> [ Move the check into destroy_cfs_bandwidth() to aid compilability. ] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Paul Turner <pjt@google.com> Cc: Ben Segall <bsegall@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/201412252210.GCC30204.SOMVFFOtQJFLOH@I-love.SAKURA.ne.jp Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-12-25 06:51:21 +00:00
/* init_cfs_bandwidth() was not called */
if (!cfs_b->throttled_cfs_rq.next)
return;
hrtimer_cancel(&cfs_b->period_timer);
hrtimer_cancel(&cfs_b->slack_timer);
}
sched/fair: Disable runtime_enabled on dying rq We kill rq->rd on the CPU_DOWN_PREPARE stage: cpuset_cpu_inactive -> cpuset_update_active_cpus -> partition_sched_domains -> -> cpu_attach_domain -> rq_attach_root -> set_rq_offline This unthrottles all throttled cfs_rqs. But the cpu is still able to call schedule() till take_cpu_down->__cpu_disable() is called from stop_machine. This case the tasks from just unthrottled cfs_rqs are pickable in a standard scheduler way, and they are picked by dying cpu. The cfs_rqs becomes throttled again, and migrate_tasks() in migration_call skips their tasks (one more unthrottle in migrate_tasks()->CPU_DYING does not happen, because rq->rd is already NULL). Patch sets runtime_enabled to zero. This guarantees, the runtime is not accounted, and the cfs_rqs won't exceed given cfs_rq->runtime_remaining = 1, and tasks will be pickable in migrate_tasks(). runtime_enabled is recalculated again when rq becomes online again. Ben Segall also noticed, we always enable runtime in tg_set_cfs_bandwidth(). Actually, we should do that for online cpus only. To prevent races with unthrottle_offline_cfs_rqs() we take get_online_cpus() lock. Reviewed-by: Ben Segall <bsegall@google.com> Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Kirill Tkhai <ktkhai@parallels.com> CC: Konstantin Khorenko <khorenko@parallels.com> CC: Paul Turner <pjt@google.com> CC: Mike Galbraith <umgwanakikbuti@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1403684382.3462.42.camel@tkhai Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-25 08:19:42 +00:00
static void __maybe_unused update_runtime_enabled(struct rq *rq)
{
struct cfs_rq *cfs_rq;
for_each_leaf_cfs_rq(rq, cfs_rq) {
struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth;
raw_spin_lock(&cfs_b->lock);
cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF;
raw_spin_unlock(&cfs_b->lock);
}
}
static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
{
struct cfs_rq *cfs_rq;
for_each_leaf_cfs_rq(rq, cfs_rq) {
if (!cfs_rq->runtime_enabled)
continue;
/*
* clock_task is not advancing so we just need to make sure
* there's some valid quota amount
*/
cfs_rq->runtime_remaining = 1;
sched/fair: Disable runtime_enabled on dying rq We kill rq->rd on the CPU_DOWN_PREPARE stage: cpuset_cpu_inactive -> cpuset_update_active_cpus -> partition_sched_domains -> -> cpu_attach_domain -> rq_attach_root -> set_rq_offline This unthrottles all throttled cfs_rqs. But the cpu is still able to call schedule() till take_cpu_down->__cpu_disable() is called from stop_machine. This case the tasks from just unthrottled cfs_rqs are pickable in a standard scheduler way, and they are picked by dying cpu. The cfs_rqs becomes throttled again, and migrate_tasks() in migration_call skips their tasks (one more unthrottle in migrate_tasks()->CPU_DYING does not happen, because rq->rd is already NULL). Patch sets runtime_enabled to zero. This guarantees, the runtime is not accounted, and the cfs_rqs won't exceed given cfs_rq->runtime_remaining = 1, and tasks will be pickable in migrate_tasks(). runtime_enabled is recalculated again when rq becomes online again. Ben Segall also noticed, we always enable runtime in tg_set_cfs_bandwidth(). Actually, we should do that for online cpus only. To prevent races with unthrottle_offline_cfs_rqs() we take get_online_cpus() lock. Reviewed-by: Ben Segall <bsegall@google.com> Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Kirill Tkhai <ktkhai@parallels.com> CC: Konstantin Khorenko <khorenko@parallels.com> CC: Paul Turner <pjt@google.com> CC: Mike Galbraith <umgwanakikbuti@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1403684382.3462.42.camel@tkhai Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-25 08:19:42 +00:00
/*
* Offline rq is schedulable till cpu is completely disabled
* in take_cpu_down(), so we prevent new cfs throttling here.
*/
cfs_rq->runtime_enabled = 0;
if (cfs_rq_throttled(cfs_rq))
unthrottle_cfs_rq(cfs_rq);
}
}
#else /* CONFIG_CFS_BANDWIDTH */
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
{
return rq_clock_task(rq_of(cfs_rq));
}
sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com Cc: Paul Turner <pjt@google.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-18 17:27:06 +00:00
static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {}
static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; }
static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
{
return 0;
}
static inline int throttled_hierarchy(struct cfs_rq *cfs_rq)
{
return 0;
}
static inline int throttled_lb_pair(struct task_group *tg,
int src_cpu, int dest_cpu)
{
return 0;
}
void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
#ifdef CONFIG_FAIR_GROUP_SCHED
static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
#endif
static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
{
return NULL;
}
static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
sched/fair: Disable runtime_enabled on dying rq We kill rq->rd on the CPU_DOWN_PREPARE stage: cpuset_cpu_inactive -> cpuset_update_active_cpus -> partition_sched_domains -> -> cpu_attach_domain -> rq_attach_root -> set_rq_offline This unthrottles all throttled cfs_rqs. But the cpu is still able to call schedule() till take_cpu_down->__cpu_disable() is called from stop_machine. This case the tasks from just unthrottled cfs_rqs are pickable in a standard scheduler way, and they are picked by dying cpu. The cfs_rqs becomes throttled again, and migrate_tasks() in migration_call skips their tasks (one more unthrottle in migrate_tasks()->CPU_DYING does not happen, because rq->rd is already NULL). Patch sets runtime_enabled to zero. This guarantees, the runtime is not accounted, and the cfs_rqs won't exceed given cfs_rq->runtime_remaining = 1, and tasks will be pickable in migrate_tasks(). runtime_enabled is recalculated again when rq becomes online again. Ben Segall also noticed, we always enable runtime in tg_set_cfs_bandwidth(). Actually, we should do that for online cpus only. To prevent races with unthrottle_offline_cfs_rqs() we take get_online_cpus() lock. Reviewed-by: Ben Segall <bsegall@google.com> Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Kirill Tkhai <ktkhai@parallels.com> CC: Konstantin Khorenko <khorenko@parallels.com> CC: Paul Turner <pjt@google.com> CC: Mike Galbraith <umgwanakikbuti@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1403684382.3462.42.camel@tkhai Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-25 08:19:42 +00:00
static inline void update_runtime_enabled(struct rq *rq) {}
static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
#endif /* CONFIG_CFS_BANDWIDTH */
/**************************************************
* CFS operations on tasks:
*/
#ifdef CONFIG_SCHED_HRTICK
static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
WARN_ON(task_rq(p) != rq);
sched: Save some hrtick_start_fair cycles hrtick_start_fair() shows up in profiles even when disabled. v3.0.6 taskset -c 3 pipe-test PerfTop: 997 irqs/sec kernel:89.5% exact: 0.0% [1000Hz cycles], (all, CPU: 3) ------------------------------------------------------------------------------------------------ Virgin Patched samples pcnt function samples pcnt function _______ _____ ___________________________ _______ _____ ___________________________ 2880.00 10.2% __schedule 3136.00 11.3% __schedule 1634.00 5.8% pipe_read 1615.00 5.8% pipe_read 1458.00 5.2% system_call 1534.00 5.5% system_call 1382.00 4.9% _raw_spin_lock_irqsave 1412.00 5.1% _raw_spin_lock_irqsave 1202.00 4.3% pipe_write 1255.00 4.5% copy_user_generic_string 1164.00 4.1% copy_user_generic_string 1241.00 4.5% __switch_to 1097.00 3.9% __switch_to 929.00 3.3% mutex_lock 872.00 3.1% mutex_lock 846.00 3.0% mutex_unlock 687.00 2.4% mutex_unlock 804.00 2.9% pipe_write 682.00 2.4% native_sched_clock 713.00 2.6% native_sched_clock 643.00 2.3% system_call_after_swapgs 653.00 2.3% _raw_spin_unlock_irqrestore 617.00 2.2% sched_clock_local 633.00 2.3% fsnotify 612.00 2.2% fsnotify 605.00 2.2% sched_clock_local 596.00 2.1% _raw_spin_unlock_irqrestore 593.00 2.1% system_call_after_swapgs 542.00 1.9% sysret_check 559.00 2.0% sysret_check 467.00 1.7% fget_light 472.00 1.7% fget_light 462.00 1.6% finish_task_switch 461.00 1.7% finish_task_switch 437.00 1.5% vfs_write 442.00 1.6% vfs_write 431.00 1.5% do_sync_write 428.00 1.5% do_sync_write 413.00 1.5% select_task_rq_fair 404.00 1.5% _raw_spin_lock_irq 386.00 1.4% update_curr 402.00 1.4% update_curr 385.00 1.4% rw_verify_area 389.00 1.4% do_sync_read 377.00 1.3% _raw_spin_lock_irq 378.00 1.4% vfs_read 369.00 1.3% do_sync_read 340.00 1.2% pipe_iov_copy_from_user 360.00 1.3% vfs_read 316.00 1.1% __wake_up_sync_key * 342.00 1.2% hrtick_start_fair 313.00 1.1% __wake_up_common Signed-off-by: Mike Galbraith <efault@gmx.de> [ fixed !CONFIG_SCHED_HRTICK borkage ] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1321971607.6855.17.camel@marge.simson.net Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-11-22 14:20:07 +00:00
if (cfs_rq->nr_running > 1) {
u64 slice = sched_slice(cfs_rq, se);
u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime;
s64 delta = slice - ran;
if (delta < 0) {
if (rq->curr == p)
resched_curr(rq);
return;
}
sched, x86: clean up hrtick implementation random uvesafb failures were reported against Gentoo: http://bugs.gentoo.org/show_bug.cgi?id=222799 and Mihai Moldovan bisected it back to: > 8f4d37ec073c17e2d4aa8851df5837d798606d6f is first bad commit > commit 8f4d37ec073c17e2d4aa8851df5837d798606d6f > Author: Peter Zijlstra <a.p.zijlstra@chello.nl> > Date: Fri Jan 25 21:08:29 2008 +0100 > > sched: high-res preemption tick Linus suspected it to be hrtick + vm86 interaction and observed: > Btw, Peter, Ingo: I think that commit is doing bad things. They aren't > _incorrect_ per se, but they are definitely bad. > > Why? > > Using random _TIF_WORK_MASK flags is really impolite for doing > "scheduling" work. There's a reason that arch/x86/kernel/entry_32.S > special-cases the _TIF_NEED_RESCHED flag: we don't want to exit out of > vm86 mode unnecessarily. > > See the "work_notifysig_v86" label, and how it does that > "save_v86_state()" thing etc etc. Right, I never liked having to fiddle with those TIF flags. Initially I needed it because the hrtimer base lock could not nest in the rq lock. That however is fixed these days. Currently the only reason left to fiddle with the TIF flags is remote wakeups. We cannot program a remote cpu's hrtimer. I've been thinking about using the new and improved IPI function call stuff to implement hrtimer_start_on(). However that does require that smp_call_function_single(.wait=0) works from interrupt context - /me looks at the latest series from Jens - Yes that does seem to be supported, good. Here's a stab at cleaning this stuff up ... Mihai reported test success as well. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Tested-by: Mihai Moldovan <ionic@ionic.de> Cc: Michal Januszewski <spock@gentoo.org> Cc: Antonino Daplas <adaplas@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-18 16:01:23 +00:00
hrtick_start(rq, delta);
}
}
/*
* called from enqueue/dequeue and updates the hrtick when the
* current task is from our class and nr_running is low enough
* to matter.
*/
static void hrtick_update(struct rq *rq)
{
struct task_struct *curr = rq->curr;
sched: Save some hrtick_start_fair cycles hrtick_start_fair() shows up in profiles even when disabled. v3.0.6 taskset -c 3 pipe-test PerfTop: 997 irqs/sec kernel:89.5% exact: 0.0% [1000Hz cycles], (all, CPU: 3) ------------------------------------------------------------------------------------------------ Virgin Patched samples pcnt function samples pcnt function _______ _____ ___________________________ _______ _____ ___________________________ 2880.00 10.2% __schedule 3136.00 11.3% __schedule 1634.00 5.8% pipe_read 1615.00 5.8% pipe_read 1458.00 5.2% system_call 1534.00 5.5% system_call 1382.00 4.9% _raw_spin_lock_irqsave 1412.00 5.1% _raw_spin_lock_irqsave 1202.00 4.3% pipe_write 1255.00 4.5% copy_user_generic_string 1164.00 4.1% copy_user_generic_string 1241.00 4.5% __switch_to 1097.00 3.9% __switch_to 929.00 3.3% mutex_lock 872.00 3.1% mutex_lock 846.00 3.0% mutex_unlock 687.00 2.4% mutex_unlock 804.00 2.9% pipe_write 682.00 2.4% native_sched_clock 713.00 2.6% native_sched_clock 643.00 2.3% system_call_after_swapgs 653.00 2.3% _raw_spin_unlock_irqrestore 617.00 2.2% sched_clock_local 633.00 2.3% fsnotify 612.00 2.2% fsnotify 605.00 2.2% sched_clock_local 596.00 2.1% _raw_spin_unlock_irqrestore 593.00 2.1% system_call_after_swapgs 542.00 1.9% sysret_check 559.00 2.0% sysret_check 467.00 1.7% fget_light 472.00 1.7% fget_light 462.00 1.6% finish_task_switch 461.00 1.7% finish_task_switch 437.00 1.5% vfs_write 442.00 1.6% vfs_write 431.00 1.5% do_sync_write 428.00 1.5% do_sync_write 413.00 1.5% select_task_rq_fair 404.00 1.5% _raw_spin_lock_irq 386.00 1.4% update_curr 402.00 1.4% update_curr 385.00 1.4% rw_verify_area 389.00 1.4% do_sync_read 377.00 1.3% _raw_spin_lock_irq 378.00 1.4% vfs_read 369.00 1.3% do_sync_read 340.00 1.2% pipe_iov_copy_from_user 360.00 1.3% vfs_read 316.00 1.1% __wake_up_sync_key * 342.00 1.2% hrtick_start_fair 313.00 1.1% __wake_up_common Signed-off-by: Mike Galbraith <efault@gmx.de> [ fixed !CONFIG_SCHED_HRTICK borkage ] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1321971607.6855.17.camel@marge.simson.net Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-11-22 14:20:07 +00:00
if (!hrtick_enabled(rq) || curr->sched_class != &fair_sched_class)
return;
if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency)
hrtick_start_fair(rq, curr);
}
#else /* !CONFIG_SCHED_HRTICK */
static inline void
hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
}
static inline void hrtick_update(struct rq *rq)
{
}
#endif
/*
* The enqueue_task method is called before nr_running is
* increased. Here we update the fair scheduling stats and
* then put the task into the rbtree:
*/
static void
enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
for_each_sched_entity(se) {
if (se->on_rq)
break;
cfs_rq = cfs_rq_of(se);
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
enqueue_entity(cfs_rq, se, flags);
/*
* end evaluation on encountering a throttled cfs_rq
*
* note: in the case of encountering a throttled cfs_rq we will
* post the final h_nr_running increment below.
*/
if (cfs_rq_throttled(cfs_rq))
break;
cfs_rq->h_nr_running++;
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
flags = ENQUEUE_WAKEUP;
}
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
cfs_rq->h_nr_running++;
if (cfs_rq_throttled(cfs_rq))
break;
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
update_load_avg(se, 1);
update_cfs_shares(cfs_rq);
}
if (!se)
add_nr_running(rq, 1);
hrtick_update(rq);
}
sched: Next buddy hint on sleep and preempt path When a task in a taskgroup sleeps, pick_next_task starts all the way back at the root and picks the task/taskgroup with the min vruntime across all runnable tasks. But when there are many frequently sleeping tasks across different taskgroups, it makes better sense to stay with same taskgroup for its slice period (or until all tasks in the taskgroup sleeps) instead of switching cross taskgroup on each sleep after a short runtime. This helps specifically where taskgroups corresponds to a process with multiple threads. The change reduces the number of CR3 switches in this case. Example: Two taskgroups with 2 threads each which are running for 2ms and sleeping for 1ms. Looking at sched:sched_switch shows: BEFORE: taskgroup_1 threads [5004, 5005], taskgroup_2 threads [5016, 5017] cpu-soaker-5004 [003] 3683.391089 cpu-soaker-5016 [003] 3683.393106 cpu-soaker-5005 [003] 3683.395119 cpu-soaker-5017 [003] 3683.397130 cpu-soaker-5004 [003] 3683.399143 cpu-soaker-5016 [003] 3683.401155 cpu-soaker-5005 [003] 3683.403168 cpu-soaker-5017 [003] 3683.405170 AFTER: taskgroup_1 threads [21890, 21891], taskgroup_2 threads [21934, 21935] cpu-soaker-21890 [003] 865.895494 cpu-soaker-21935 [003] 865.897506 cpu-soaker-21934 [003] 865.899520 cpu-soaker-21935 [003] 865.901532 cpu-soaker-21934 [003] 865.903543 cpu-soaker-21935 [003] 865.905546 cpu-soaker-21891 [003] 865.907548 cpu-soaker-21890 [003] 865.909560 cpu-soaker-21891 [003] 865.911571 cpu-soaker-21890 [003] 865.913582 cpu-soaker-21891 [003] 865.915594 cpu-soaker-21934 [003] 865.917606 Similar problem is there when there are multiple taskgroups and say a task A preempts currently running task B of taskgroup_1. On schedule, pick_next_task can pick an unrelated task on taskgroup_2. Here it would be better to give some preference to task B on pick_next_task. A simple (may be extreme case) benchmark I tried was tbench with 2 tbench client processes with 2 threads each running on a single CPU. Avg throughput across 5 50 sec runs was: BEFORE: 105.84 MB/sec AFTER: 112.42 MB/sec Signed-off-by: Venkatesh Pallipadi <venki@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1302802253-25760-1-git-send-email-venki@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-14 17:30:53 +00:00
static void set_next_buddy(struct sched_entity *se);
/*
* The dequeue_task method is called before nr_running is
* decreased. We remove the task from the rbtree and
* update the fair scheduling stats:
*/
static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
sched: Next buddy hint on sleep and preempt path When a task in a taskgroup sleeps, pick_next_task starts all the way back at the root and picks the task/taskgroup with the min vruntime across all runnable tasks. But when there are many frequently sleeping tasks across different taskgroups, it makes better sense to stay with same taskgroup for its slice period (or until all tasks in the taskgroup sleeps) instead of switching cross taskgroup on each sleep after a short runtime. This helps specifically where taskgroups corresponds to a process with multiple threads. The change reduces the number of CR3 switches in this case. Example: Two taskgroups with 2 threads each which are running for 2ms and sleeping for 1ms. Looking at sched:sched_switch shows: BEFORE: taskgroup_1 threads [5004, 5005], taskgroup_2 threads [5016, 5017] cpu-soaker-5004 [003] 3683.391089 cpu-soaker-5016 [003] 3683.393106 cpu-soaker-5005 [003] 3683.395119 cpu-soaker-5017 [003] 3683.397130 cpu-soaker-5004 [003] 3683.399143 cpu-soaker-5016 [003] 3683.401155 cpu-soaker-5005 [003] 3683.403168 cpu-soaker-5017 [003] 3683.405170 AFTER: taskgroup_1 threads [21890, 21891], taskgroup_2 threads [21934, 21935] cpu-soaker-21890 [003] 865.895494 cpu-soaker-21935 [003] 865.897506 cpu-soaker-21934 [003] 865.899520 cpu-soaker-21935 [003] 865.901532 cpu-soaker-21934 [003] 865.903543 cpu-soaker-21935 [003] 865.905546 cpu-soaker-21891 [003] 865.907548 cpu-soaker-21890 [003] 865.909560 cpu-soaker-21891 [003] 865.911571 cpu-soaker-21890 [003] 865.913582 cpu-soaker-21891 [003] 865.915594 cpu-soaker-21934 [003] 865.917606 Similar problem is there when there are multiple taskgroups and say a task A preempts currently running task B of taskgroup_1. On schedule, pick_next_task can pick an unrelated task on taskgroup_2. Here it would be better to give some preference to task B on pick_next_task. A simple (may be extreme case) benchmark I tried was tbench with 2 tbench client processes with 2 threads each running on a single CPU. Avg throughput across 5 50 sec runs was: BEFORE: 105.84 MB/sec AFTER: 112.42 MB/sec Signed-off-by: Venkatesh Pallipadi <venki@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1302802253-25760-1-git-send-email-venki@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-14 17:30:53 +00:00
int task_sleep = flags & DEQUEUE_SLEEP;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
dequeue_entity(cfs_rq, se, flags);
/*
* end evaluation on encountering a throttled cfs_rq
*
* note: in the case of encountering a throttled cfs_rq we will
* post the final h_nr_running decrement below.
*/
if (cfs_rq_throttled(cfs_rq))
break;
cfs_rq->h_nr_running--;
/* Don't dequeue parent if it has other entities besides us */
sched: Next buddy hint on sleep and preempt path When a task in a taskgroup sleeps, pick_next_task starts all the way back at the root and picks the task/taskgroup with the min vruntime across all runnable tasks. But when there are many frequently sleeping tasks across different taskgroups, it makes better sense to stay with same taskgroup for its slice period (or until all tasks in the taskgroup sleeps) instead of switching cross taskgroup on each sleep after a short runtime. This helps specifically where taskgroups corresponds to a process with multiple threads. The change reduces the number of CR3 switches in this case. Example: Two taskgroups with 2 threads each which are running for 2ms and sleeping for 1ms. Looking at sched:sched_switch shows: BEFORE: taskgroup_1 threads [5004, 5005], taskgroup_2 threads [5016, 5017] cpu-soaker-5004 [003] 3683.391089 cpu-soaker-5016 [003] 3683.393106 cpu-soaker-5005 [003] 3683.395119 cpu-soaker-5017 [003] 3683.397130 cpu-soaker-5004 [003] 3683.399143 cpu-soaker-5016 [003] 3683.401155 cpu-soaker-5005 [003] 3683.403168 cpu-soaker-5017 [003] 3683.405170 AFTER: taskgroup_1 threads [21890, 21891], taskgroup_2 threads [21934, 21935] cpu-soaker-21890 [003] 865.895494 cpu-soaker-21935 [003] 865.897506 cpu-soaker-21934 [003] 865.899520 cpu-soaker-21935 [003] 865.901532 cpu-soaker-21934 [003] 865.903543 cpu-soaker-21935 [003] 865.905546 cpu-soaker-21891 [003] 865.907548 cpu-soaker-21890 [003] 865.909560 cpu-soaker-21891 [003] 865.911571 cpu-soaker-21890 [003] 865.913582 cpu-soaker-21891 [003] 865.915594 cpu-soaker-21934 [003] 865.917606 Similar problem is there when there are multiple taskgroups and say a task A preempts currently running task B of taskgroup_1. On schedule, pick_next_task can pick an unrelated task on taskgroup_2. Here it would be better to give some preference to task B on pick_next_task. A simple (may be extreme case) benchmark I tried was tbench with 2 tbench client processes with 2 threads each running on a single CPU. Avg throughput across 5 50 sec runs was: BEFORE: 105.84 MB/sec AFTER: 112.42 MB/sec Signed-off-by: Venkatesh Pallipadi <venki@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1302802253-25760-1-git-send-email-venki@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-14 17:30:53 +00:00
if (cfs_rq->load.weight) {
/*
* Bias pick_next to pick a task from this cfs_rq, as
* p is sleeping when it is within its sched_slice.
*/
if (task_sleep && parent_entity(se))
set_next_buddy(parent_entity(se));
/* avoid re-evaluating load for this entity */
se = parent_entity(se);
break;
sched: Next buddy hint on sleep and preempt path When a task in a taskgroup sleeps, pick_next_task starts all the way back at the root and picks the task/taskgroup with the min vruntime across all runnable tasks. But when there are many frequently sleeping tasks across different taskgroups, it makes better sense to stay with same taskgroup for its slice period (or until all tasks in the taskgroup sleeps) instead of switching cross taskgroup on each sleep after a short runtime. This helps specifically where taskgroups corresponds to a process with multiple threads. The change reduces the number of CR3 switches in this case. Example: Two taskgroups with 2 threads each which are running for 2ms and sleeping for 1ms. Looking at sched:sched_switch shows: BEFORE: taskgroup_1 threads [5004, 5005], taskgroup_2 threads [5016, 5017] cpu-soaker-5004 [003] 3683.391089 cpu-soaker-5016 [003] 3683.393106 cpu-soaker-5005 [003] 3683.395119 cpu-soaker-5017 [003] 3683.397130 cpu-soaker-5004 [003] 3683.399143 cpu-soaker-5016 [003] 3683.401155 cpu-soaker-5005 [003] 3683.403168 cpu-soaker-5017 [003] 3683.405170 AFTER: taskgroup_1 threads [21890, 21891], taskgroup_2 threads [21934, 21935] cpu-soaker-21890 [003] 865.895494 cpu-soaker-21935 [003] 865.897506 cpu-soaker-21934 [003] 865.899520 cpu-soaker-21935 [003] 865.901532 cpu-soaker-21934 [003] 865.903543 cpu-soaker-21935 [003] 865.905546 cpu-soaker-21891 [003] 865.907548 cpu-soaker-21890 [003] 865.909560 cpu-soaker-21891 [003] 865.911571 cpu-soaker-21890 [003] 865.913582 cpu-soaker-21891 [003] 865.915594 cpu-soaker-21934 [003] 865.917606 Similar problem is there when there are multiple taskgroups and say a task A preempts currently running task B of taskgroup_1. On schedule, pick_next_task can pick an unrelated task on taskgroup_2. Here it would be better to give some preference to task B on pick_next_task. A simple (may be extreme case) benchmark I tried was tbench with 2 tbench client processes with 2 threads each running on a single CPU. Avg throughput across 5 50 sec runs was: BEFORE: 105.84 MB/sec AFTER: 112.42 MB/sec Signed-off-by: Venkatesh Pallipadi <venki@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1302802253-25760-1-git-send-email-venki@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-14 17:30:53 +00:00
}
flags |= DEQUEUE_SLEEP;
}
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
cfs_rq->h_nr_running--;
if (cfs_rq_throttled(cfs_rq))
break;
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
update_load_avg(se, 1);
update_cfs_shares(cfs_rq);
}
if (!se)
sub_nr_running(rq, 1);
hrtick_update(rq);
}
#ifdef CONFIG_SMP
/*
* per rq 'load' arrray crap; XXX kill this.
*/
/*
* The exact cpuload at various idx values, calculated at every tick would be
* load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
*
* If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
* on nth tick when cpu may be busy, then we have:
* load = ((2^idx - 1) / 2^idx)^(n-1) * load
* load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
*
* decay_load_missed() below does efficient calculation of
* load = ((2^idx - 1) / 2^idx)^(n-1) * load
* avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
*
* The calculation is approximated on a 128 point scale.
* degrade_zero_ticks is the number of ticks after which load at any
* particular idx is approximated to be zero.
* degrade_factor is a precomputed table, a row for each load idx.
* Each column corresponds to degradation factor for a power of two ticks,
* based on 128 point scale.
* Example:
* row 2, col 3 (=12) says that the degradation at load idx 2 after
* 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
*
* With this power of 2 load factors, we can degrade the load n times
* by looking at 1 bits in n and doing as many mult/shift instead of
* n mult/shifts needed by the exact degradation.
*/
#define DEGRADE_SHIFT 7
static const unsigned char
degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
static const unsigned char
degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
{0, 0, 0, 0, 0, 0, 0, 0},
{64, 32, 8, 0, 0, 0, 0, 0},
{96, 72, 40, 12, 1, 0, 0},
{112, 98, 75, 43, 15, 1, 0},
{120, 112, 98, 76, 45, 16, 2} };
/*
* Update cpu_load for any missed ticks, due to tickless idle. The backlog
* would be when CPU is idle and so we just decay the old load without
* adding any new load.
*/
static unsigned long
decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
{
int j = 0;
if (!missed_updates)
return load;
if (missed_updates >= degrade_zero_ticks[idx])
return 0;
if (idx == 1)
return load >> missed_updates;
while (missed_updates) {
if (missed_updates % 2)
load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT;
missed_updates >>= 1;
j++;
}
return load;
}
/*
* Update rq->cpu_load[] statistics. This function is usually called every
* scheduler tick (TICK_NSEC). With tickless idle this will not be called
* every tick. We fix it up based on jiffies.
*/
static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
unsigned long pending_updates)
{
int i, scale;
this_rq->nr_load_updates++;
/* Update our load: */
this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
unsigned long old_load, new_load;
/* scale is effectively 1 << i now, and >> i divides by scale */
old_load = this_rq->cpu_load[i];
old_load = decay_load_missed(old_load, pending_updates - 1, i);
new_load = this_load;
/*
* Round up the averaging division if load is increasing. This
* prevents us from getting stuck on 9 if the load is 10, for
* example.
*/
if (new_load > old_load)
new_load += scale - 1;
this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
}
sched_avg_update(this_rq);
}
/* Used instead of source_load when we know the type == 0 */
static unsigned long weighted_cpuload(const int cpu)
{
return cfs_rq_runnable_load_avg(&cpu_rq(cpu)->cfs);
}
#ifdef CONFIG_NO_HZ_COMMON
/*
* There is no sane way to deal with nohz on smp when using jiffies because the
* cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
* causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
*
* Therefore we cannot use the delta approach from the regular tick since that
* would seriously skew the load calculation. However we'll make do for those
* updates happening while idle (nohz_idle_balance) or coming out of idle
* (tick_nohz_idle_exit).
*
* This means we might still be one tick off for nohz periods.
*/
/*
* Called from nohz_idle_balance() to update the load ratings before doing the
* idle balance.
*/
static void update_idle_cpu_load(struct rq *this_rq)
{
unsigned long curr_jiffies = READ_ONCE(jiffies);
unsigned long load = weighted_cpuload(cpu_of(this_rq));
unsigned long pending_updates;
/*
* bail if there's load or we're actually up-to-date.
*/
if (load || curr_jiffies == this_rq->last_load_update_tick)
return;
pending_updates = curr_jiffies - this_rq->last_load_update_tick;
this_rq->last_load_update_tick = curr_jiffies;
__update_cpu_load(this_rq, load, pending_updates);
}
/*
* Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
*/
void update_cpu_load_nohz(void)
{
struct rq *this_rq = this_rq();
unsigned long curr_jiffies = READ_ONCE(jiffies);
unsigned long pending_updates;
if (curr_jiffies == this_rq->last_load_update_tick)
return;
raw_spin_lock(&this_rq->lock);
pending_updates = curr_jiffies - this_rq->last_load_update_tick;
if (pending_updates) {
this_rq->last_load_update_tick = curr_jiffies;
/*
* We were idle, this means load 0, the current load might be
* !0 due to remote wakeups and the sort.
*/
__update_cpu_load(this_rq, 0, pending_updates);
}
raw_spin_unlock(&this_rq->lock);
}
#endif /* CONFIG_NO_HZ */
/*
* Called from scheduler_tick()
*/
void update_cpu_load_active(struct rq *this_rq)
{
unsigned long load = weighted_cpuload(cpu_of(this_rq));
/*
* See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
*/
this_rq->last_load_update_tick = jiffies;
__update_cpu_load(this_rq, load, 1);
}
/*
* Return a low guess at the load of a migration-source cpu weighted
* according to the scheduling class and "nice" value.
*
* We want to under-estimate the load of migration sources, to
* balance conservatively.
*/
static unsigned long source_load(int cpu, int type)
{
struct rq *rq = cpu_rq(cpu);
unsigned long total = weighted_cpuload(cpu);
if (type == 0 || !sched_feat(LB_BIAS))
return total;
return min(rq->cpu_load[type-1], total);
}
/*
* Return a high guess at the load of a migration-target cpu weighted
* according to the scheduling class and "nice" value.
*/
static unsigned long target_load(int cpu, int type)
{
struct rq *rq = cpu_rq(cpu);
unsigned long total = weighted_cpuload(cpu);
if (type == 0 || !sched_feat(LB_BIAS))
return total;
return max(rq->cpu_load[type-1], total);
}
static unsigned long capacity_of(int cpu)
{
return cpu_rq(cpu)->cpu_capacity;
}
static unsigned long capacity_orig_of(int cpu)
{
return cpu_rq(cpu)->cpu_capacity_orig;
}
static unsigned long cpu_avg_load_per_task(int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long nr_running = READ_ONCE(rq->cfs.h_nr_running);
unsigned long load_avg = weighted_cpuload(cpu);
if (nr_running)
return load_avg / nr_running;
return 0;
}
sched: Implement smarter wake-affine logic The wake-affine scheduler feature is currently always trying to pull the wakee close to the waker. In theory this should be beneficial if the waker's CPU caches hot data for the wakee, and it's also beneficial in the extreme ping-pong high context switch rate case. Testing shows it can benefit hackbench up to 15%. However, the feature is somewhat blind, from which some workloads such as pgbench suffer. It's also time-consuming algorithmically. Testing shows it can damage pgbench up to 50% - far more than the benefit it brings in the best case. So wake-affine should be smarter and it should realize when to stop its thankless effort at trying to find a suitable CPU to wake on. This patch introduces 'wakee_flips', which will be increased each time the task flips (switches) its wakee target. So a high 'wakee_flips' value means the task has more than one wakee, and the bigger the number, the higher the wakeup frequency. Now when making the decision on whether to pull or not, pay attention to the wakee with a high 'wakee_flips', pulling such a task may benefit the wakee. Also imply that the waker will face cruel competition later, it could be very cruel or very fast depends on the story behind 'wakee_flips', waker therefore suffers. Furthermore, if waker also has a high 'wakee_flips', that implies that multiple tasks rely on it, then waker's higher latency will damage all of them, so pulling wakee seems to be a bad deal. Thus, when 'waker->wakee_flips / wakee->wakee_flips' becomes higher and higher, the cost of pulling seems to be worse and worse. The patch therefore helps the wake-affine feature to stop its pulling work when: wakee->wakee_flips > factor && waker->wakee_flips > (factor * wakee->wakee_flips) The 'factor' here is the number of CPUs in the current CPU's NUMA node, so a bigger node will lead to more pulling since the trial becomes more severe. After applying the patch, pgbench shows up to 40% improvements and no regressions. Tested with 12 cpu x86 server and tip 3.10.0-rc7. The percentages in the final column highlight the areas with the biggest wins, all other areas improved as well: pgbench base smart | db_size | clients | tps | | tps | +---------+---------+-------+ +-------+ | 22 MB | 1 | 10598 | | 10796 | | 22 MB | 2 | 21257 | | 21336 | | 22 MB | 4 | 41386 | | 41622 | | 22 MB | 8 | 51253 | | 57932 | | 22 MB | 12 | 48570 | | 54000 | | 22 MB | 16 | 46748 | | 55982 | +19.75% | 22 MB | 24 | 44346 | | 55847 | +25.93% | 22 MB | 32 | 43460 | | 54614 | +25.66% | 7484 MB | 1 | 8951 | | 9193 | | 7484 MB | 2 | 19233 | | 19240 | | 7484 MB | 4 | 37239 | | 37302 | | 7484 MB | 8 | 46087 | | 50018 | | 7484 MB | 12 | 42054 | | 48763 | | 7484 MB | 16 | 40765 | | 51633 | +26.66% | 7484 MB | 24 | 37651 | | 52377 | +39.11% | 7484 MB | 32 | 37056 | | 51108 | +37.92% | 15 GB | 1 | 8845 | | 9104 | | 15 GB | 2 | 19094 | | 19162 | | 15 GB | 4 | 36979 | | 36983 | | 15 GB | 8 | 46087 | | 49977 | | 15 GB | 12 | 41901 | | 48591 | | 15 GB | 16 | 40147 | | 50651 | +26.16% | 15 GB | 24 | 37250 | | 52365 | +40.58% | 15 GB | 32 | 36470 | | 50015 | +37.14% Signed-off-by: Michael Wang <wangyun@linux.vnet.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/51D50057.9000809@linux.vnet.ibm.com [ Improved the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-04 04:55:51 +00:00
static void record_wakee(struct task_struct *p)
{
/*
* Rough decay (wiping) for cost saving, don't worry
* about the boundary, really active task won't care
* about the loss.
*/
if (time_after(jiffies, current->wakee_flip_decay_ts + HZ)) {
current->wakee_flips >>= 1;
sched: Implement smarter wake-affine logic The wake-affine scheduler feature is currently always trying to pull the wakee close to the waker. In theory this should be beneficial if the waker's CPU caches hot data for the wakee, and it's also beneficial in the extreme ping-pong high context switch rate case. Testing shows it can benefit hackbench up to 15%. However, the feature is somewhat blind, from which some workloads such as pgbench suffer. It's also time-consuming algorithmically. Testing shows it can damage pgbench up to 50% - far more than the benefit it brings in the best case. So wake-affine should be smarter and it should realize when to stop its thankless effort at trying to find a suitable CPU to wake on. This patch introduces 'wakee_flips', which will be increased each time the task flips (switches) its wakee target. So a high 'wakee_flips' value means the task has more than one wakee, and the bigger the number, the higher the wakeup frequency. Now when making the decision on whether to pull or not, pay attention to the wakee with a high 'wakee_flips', pulling such a task may benefit the wakee. Also imply that the waker will face cruel competition later, it could be very cruel or very fast depends on the story behind 'wakee_flips', waker therefore suffers. Furthermore, if waker also has a high 'wakee_flips', that implies that multiple tasks rely on it, then waker's higher latency will damage all of them, so pulling wakee seems to be a bad deal. Thus, when 'waker->wakee_flips / wakee->wakee_flips' becomes higher and higher, the cost of pulling seems to be worse and worse. The patch therefore helps the wake-affine feature to stop its pulling work when: wakee->wakee_flips > factor && waker->wakee_flips > (factor * wakee->wakee_flips) The 'factor' here is the number of CPUs in the current CPU's NUMA node, so a bigger node will lead to more pulling since the trial becomes more severe. After applying the patch, pgbench shows up to 40% improvements and no regressions. Tested with 12 cpu x86 server and tip 3.10.0-rc7. The percentages in the final column highlight the areas with the biggest wins, all other areas improved as well: pgbench base smart | db_size | clients | tps | | tps | +---------+---------+-------+ +-------+ | 22 MB | 1 | 10598 | | 10796 | | 22 MB | 2 | 21257 | | 21336 | | 22 MB | 4 | 41386 | | 41622 | | 22 MB | 8 | 51253 | | 57932 | | 22 MB | 12 | 48570 | | 54000 | | 22 MB | 16 | 46748 | | 55982 | +19.75% | 22 MB | 24 | 44346 | | 55847 | +25.93% | 22 MB | 32 | 43460 | | 54614 | +25.66% | 7484 MB | 1 | 8951 | | 9193 | | 7484 MB | 2 | 19233 | | 19240 | | 7484 MB | 4 | 37239 | | 37302 | | 7484 MB | 8 | 46087 | | 50018 | | 7484 MB | 12 | 42054 | | 48763 | | 7484 MB | 16 | 40765 | | 51633 | +26.66% | 7484 MB | 24 | 37651 | | 52377 | +39.11% | 7484 MB | 32 | 37056 | | 51108 | +37.92% | 15 GB | 1 | 8845 | | 9104 | | 15 GB | 2 | 19094 | | 19162 | | 15 GB | 4 | 36979 | | 36983 | | 15 GB | 8 | 46087 | | 49977 | | 15 GB | 12 | 41901 | | 48591 | | 15 GB | 16 | 40147 | | 50651 | +26.16% | 15 GB | 24 | 37250 | | 52365 | +40.58% | 15 GB | 32 | 36470 | | 50015 | +37.14% Signed-off-by: Michael Wang <wangyun@linux.vnet.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/51D50057.9000809@linux.vnet.ibm.com [ Improved the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-04 04:55:51 +00:00
current->wakee_flip_decay_ts = jiffies;
}
if (current->last_wakee != p) {
current->last_wakee = p;
current->wakee_flips++;
}
}
static void task_waking_fair(struct task_struct *p)
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
{
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
u64 min_vruntime;
#ifndef CONFIG_64BIT
u64 min_vruntime_copy;
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
do {
min_vruntime_copy = cfs_rq->min_vruntime_copy;
smp_rmb();
min_vruntime = cfs_rq->min_vruntime;
} while (min_vruntime != min_vruntime_copy);
#else
min_vruntime = cfs_rq->min_vruntime;
#endif
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
se->vruntime -= min_vruntime;
sched: Implement smarter wake-affine logic The wake-affine scheduler feature is currently always trying to pull the wakee close to the waker. In theory this should be beneficial if the waker's CPU caches hot data for the wakee, and it's also beneficial in the extreme ping-pong high context switch rate case. Testing shows it can benefit hackbench up to 15%. However, the feature is somewhat blind, from which some workloads such as pgbench suffer. It's also time-consuming algorithmically. Testing shows it can damage pgbench up to 50% - far more than the benefit it brings in the best case. So wake-affine should be smarter and it should realize when to stop its thankless effort at trying to find a suitable CPU to wake on. This patch introduces 'wakee_flips', which will be increased each time the task flips (switches) its wakee target. So a high 'wakee_flips' value means the task has more than one wakee, and the bigger the number, the higher the wakeup frequency. Now when making the decision on whether to pull or not, pay attention to the wakee with a high 'wakee_flips', pulling such a task may benefit the wakee. Also imply that the waker will face cruel competition later, it could be very cruel or very fast depends on the story behind 'wakee_flips', waker therefore suffers. Furthermore, if waker also has a high 'wakee_flips', that implies that multiple tasks rely on it, then waker's higher latency will damage all of them, so pulling wakee seems to be a bad deal. Thus, when 'waker->wakee_flips / wakee->wakee_flips' becomes higher and higher, the cost of pulling seems to be worse and worse. The patch therefore helps the wake-affine feature to stop its pulling work when: wakee->wakee_flips > factor && waker->wakee_flips > (factor * wakee->wakee_flips) The 'factor' here is the number of CPUs in the current CPU's NUMA node, so a bigger node will lead to more pulling since the trial becomes more severe. After applying the patch, pgbench shows up to 40% improvements and no regressions. Tested with 12 cpu x86 server and tip 3.10.0-rc7. The percentages in the final column highlight the areas with the biggest wins, all other areas improved as well: pgbench base smart | db_size | clients | tps | | tps | +---------+---------+-------+ +-------+ | 22 MB | 1 | 10598 | | 10796 | | 22 MB | 2 | 21257 | | 21336 | | 22 MB | 4 | 41386 | | 41622 | | 22 MB | 8 | 51253 | | 57932 | | 22 MB | 12 | 48570 | | 54000 | | 22 MB | 16 | 46748 | | 55982 | +19.75% | 22 MB | 24 | 44346 | | 55847 | +25.93% | 22 MB | 32 | 43460 | | 54614 | +25.66% | 7484 MB | 1 | 8951 | | 9193 | | 7484 MB | 2 | 19233 | | 19240 | | 7484 MB | 4 | 37239 | | 37302 | | 7484 MB | 8 | 46087 | | 50018 | | 7484 MB | 12 | 42054 | | 48763 | | 7484 MB | 16 | 40765 | | 51633 | +26.66% | 7484 MB | 24 | 37651 | | 52377 | +39.11% | 7484 MB | 32 | 37056 | | 51108 | +37.92% | 15 GB | 1 | 8845 | | 9104 | | 15 GB | 2 | 19094 | | 19162 | | 15 GB | 4 | 36979 | | 36983 | | 15 GB | 8 | 46087 | | 49977 | | 15 GB | 12 | 41901 | | 48591 | | 15 GB | 16 | 40147 | | 50651 | +26.16% | 15 GB | 24 | 37250 | | 52365 | +40.58% | 15 GB | 32 | 36470 | | 50015 | +37.14% Signed-off-by: Michael Wang <wangyun@linux.vnet.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/51D50057.9000809@linux.vnet.ibm.com [ Improved the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-04 04:55:51 +00:00
record_wakee(p);
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
}
#ifdef CONFIG_FAIR_GROUP_SCHED
/*
* effective_load() calculates the load change as seen from the root_task_group
*
* Adding load to a group doesn't make a group heavier, but can cause movement
* of group shares between cpus. Assuming the shares were perfectly aligned one
* can calculate the shift in shares.
*
* Calculate the effective load difference if @wl is added (subtracted) to @tg
* on this @cpu and results in a total addition (subtraction) of @wg to the
* total group weight.
*
* Given a runqueue weight distribution (rw_i) we can compute a shares
* distribution (s_i) using:
*
* s_i = rw_i / \Sum rw_j (1)
*
* Suppose we have 4 CPUs and our @tg is a direct child of the root group and
* has 7 equal weight tasks, distributed as below (rw_i), with the resulting
* shares distribution (s_i):
*
* rw_i = { 2, 4, 1, 0 }
* s_i = { 2/7, 4/7, 1/7, 0 }
*
* As per wake_affine() we're interested in the load of two CPUs (the CPU the
* task used to run on and the CPU the waker is running on), we need to
* compute the effect of waking a task on either CPU and, in case of a sync
* wakeup, compute the effect of the current task going to sleep.
*
* So for a change of @wl to the local @cpu with an overall group weight change
* of @wl we can compute the new shares distribution (s'_i) using:
*
* s'_i = (rw_i + @wl) / (@wg + \Sum rw_j) (2)
*
* Suppose we're interested in CPUs 0 and 1, and want to compute the load
* differences in waking a task to CPU 0. The additional task changes the
* weight and shares distributions like:
*
* rw'_i = { 3, 4, 1, 0 }
* s'_i = { 3/8, 4/8, 1/8, 0 }
*
* We can then compute the difference in effective weight by using:
*
* dw_i = S * (s'_i - s_i) (3)
*
* Where 'S' is the group weight as seen by its parent.
*
* Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7)
* times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 -
* 4/7) times the weight of the group.
*/
static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
{
struct sched_entity *se = tg->se[cpu];
sched: Calculate effective load even if local weight is 0 Thomas Hellstrom bisected a regression where erratic 3D performance is experienced on virtual machines as measured by glxgears. It identified commit 58d081b5 ("sched/numa: Avoid overloading CPUs on a preferred NUMA node") as the problem which had modified the behaviour of effective_load. Effective load calculates the difference to the system-wide load if a scheduling entity was moved to another CPU. The task group is not heavier as a result of the move but overall system load can increase/decrease as a result of the change. Commit 58d081b5 ("sched/numa: Avoid overloading CPUs on a preferred NUMA node") changed effective_load to make it suitable for calculating if a particular NUMA node was compute overloaded. To reduce the cost of the function, it assumed that a current sched entity weight of 0 was uninteresting but that is not the case. wake_affine() uses a weight of 0 for sync wakeups on the grounds that it is assuming the waking task will sleep and not contribute to load in the near future. In this case, we still want to calculate the effective load of the sched entity hierarchy. As effective_load is no longer used by task_numa_compare since commit fb13c7ee (sched/numa: Use a system-wide search to find swap/migration candidates), this patch simply restores the historical behaviour. Reported-and-tested-by: Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by: Rik van Riel <riel@redhat.com> [ Wrote changelog] Signed-off-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20140106113912.GC6178@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-01-06 11:39:12 +00:00
if (!tg->parent) /* the trivial, non-cgroup case */
return wl;
for_each_sched_entity(se) {
long w, W;
tg = se->my_q->tg;
/*
* W = @wg + \Sum rw_j
*/
W = wg + calc_tg_weight(tg, se->my_q);
/*
* w = rw_i + @wl
*/
w = cfs_rq_load_avg(se->my_q) + wl;
/*
* wl = S * s'_i; see (2)
*/
if (W > 0 && w < W)
wl = (w * (long)tg->shares) / W;
else
wl = tg->shares;
/*
* Per the above, wl is the new se->load.weight value; since
* those are clipped to [MIN_SHARES, ...) do so now. See
* calc_cfs_shares().
*/
if (wl < MIN_SHARES)
wl = MIN_SHARES;
/*
* wl = dw_i = S * (s'_i - s_i); see (3)
*/
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
wl -= se->avg.load_avg;
/*
* Recursively apply this logic to all parent groups to compute
* the final effective load change on the root group. Since
* only the @tg group gets extra weight, all parent groups can
* only redistribute existing shares. @wl is the shift in shares
* resulting from this level per the above.
*/
wg = 0;
}
return wl;
}
#else
static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
{
return wl;
}
#endif
/*
* Detect M:N waker/wakee relationships via a switching-frequency heuristic.
* A waker of many should wake a different task than the one last awakened
* at a frequency roughly N times higher than one of its wakees. In order
* to determine whether we should let the load spread vs consolodating to
* shared cache, we look for a minimum 'flip' frequency of llc_size in one
* partner, and a factor of lls_size higher frequency in the other. With
* both conditions met, we can be relatively sure that the relationship is
* non-monogamous, with partner count exceeding socket size. Waker/wakee
* being client/server, worker/dispatcher, interrupt source or whatever is
* irrelevant, spread criteria is apparent partner count exceeds socket size.
*/
sched: Implement smarter wake-affine logic The wake-affine scheduler feature is currently always trying to pull the wakee close to the waker. In theory this should be beneficial if the waker's CPU caches hot data for the wakee, and it's also beneficial in the extreme ping-pong high context switch rate case. Testing shows it can benefit hackbench up to 15%. However, the feature is somewhat blind, from which some workloads such as pgbench suffer. It's also time-consuming algorithmically. Testing shows it can damage pgbench up to 50% - far more than the benefit it brings in the best case. So wake-affine should be smarter and it should realize when to stop its thankless effort at trying to find a suitable CPU to wake on. This patch introduces 'wakee_flips', which will be increased each time the task flips (switches) its wakee target. So a high 'wakee_flips' value means the task has more than one wakee, and the bigger the number, the higher the wakeup frequency. Now when making the decision on whether to pull or not, pay attention to the wakee with a high 'wakee_flips', pulling such a task may benefit the wakee. Also imply that the waker will face cruel competition later, it could be very cruel or very fast depends on the story behind 'wakee_flips', waker therefore suffers. Furthermore, if waker also has a high 'wakee_flips', that implies that multiple tasks rely on it, then waker's higher latency will damage all of them, so pulling wakee seems to be a bad deal. Thus, when 'waker->wakee_flips / wakee->wakee_flips' becomes higher and higher, the cost of pulling seems to be worse and worse. The patch therefore helps the wake-affine feature to stop its pulling work when: wakee->wakee_flips > factor && waker->wakee_flips > (factor * wakee->wakee_flips) The 'factor' here is the number of CPUs in the current CPU's NUMA node, so a bigger node will lead to more pulling since the trial becomes more severe. After applying the patch, pgbench shows up to 40% improvements and no regressions. Tested with 12 cpu x86 server and tip 3.10.0-rc7. The percentages in the final column highlight the areas with the biggest wins, all other areas improved as well: pgbench base smart | db_size | clients | tps | | tps | +---------+---------+-------+ +-------+ | 22 MB | 1 | 10598 | | 10796 | | 22 MB | 2 | 21257 | | 21336 | | 22 MB | 4 | 41386 | | 41622 | | 22 MB | 8 | 51253 | | 57932 | | 22 MB | 12 | 48570 | | 54000 | | 22 MB | 16 | 46748 | | 55982 | +19.75% | 22 MB | 24 | 44346 | | 55847 | +25.93% | 22 MB | 32 | 43460 | | 54614 | +25.66% | 7484 MB | 1 | 8951 | | 9193 | | 7484 MB | 2 | 19233 | | 19240 | | 7484 MB | 4 | 37239 | | 37302 | | 7484 MB | 8 | 46087 | | 50018 | | 7484 MB | 12 | 42054 | | 48763 | | 7484 MB | 16 | 40765 | | 51633 | +26.66% | 7484 MB | 24 | 37651 | | 52377 | +39.11% | 7484 MB | 32 | 37056 | | 51108 | +37.92% | 15 GB | 1 | 8845 | | 9104 | | 15 GB | 2 | 19094 | | 19162 | | 15 GB | 4 | 36979 | | 36983 | | 15 GB | 8 | 46087 | | 49977 | | 15 GB | 12 | 41901 | | 48591 | | 15 GB | 16 | 40147 | | 50651 | +26.16% | 15 GB | 24 | 37250 | | 52365 | +40.58% | 15 GB | 32 | 36470 | | 50015 | +37.14% Signed-off-by: Michael Wang <wangyun@linux.vnet.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/51D50057.9000809@linux.vnet.ibm.com [ Improved the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-04 04:55:51 +00:00
static int wake_wide(struct task_struct *p)
{
unsigned int master = current->wakee_flips;
unsigned int slave = p->wakee_flips;
int factor = this_cpu_read(sd_llc_size);
sched: Implement smarter wake-affine logic The wake-affine scheduler feature is currently always trying to pull the wakee close to the waker. In theory this should be beneficial if the waker's CPU caches hot data for the wakee, and it's also beneficial in the extreme ping-pong high context switch rate case. Testing shows it can benefit hackbench up to 15%. However, the feature is somewhat blind, from which some workloads such as pgbench suffer. It's also time-consuming algorithmically. Testing shows it can damage pgbench up to 50% - far more than the benefit it brings in the best case. So wake-affine should be smarter and it should realize when to stop its thankless effort at trying to find a suitable CPU to wake on. This patch introduces 'wakee_flips', which will be increased each time the task flips (switches) its wakee target. So a high 'wakee_flips' value means the task has more than one wakee, and the bigger the number, the higher the wakeup frequency. Now when making the decision on whether to pull or not, pay attention to the wakee with a high 'wakee_flips', pulling such a task may benefit the wakee. Also imply that the waker will face cruel competition later, it could be very cruel or very fast depends on the story behind 'wakee_flips', waker therefore suffers. Furthermore, if waker also has a high 'wakee_flips', that implies that multiple tasks rely on it, then waker's higher latency will damage all of them, so pulling wakee seems to be a bad deal. Thus, when 'waker->wakee_flips / wakee->wakee_flips' becomes higher and higher, the cost of pulling seems to be worse and worse. The patch therefore helps the wake-affine feature to stop its pulling work when: wakee->wakee_flips > factor && waker->wakee_flips > (factor * wakee->wakee_flips) The 'factor' here is the number of CPUs in the current CPU's NUMA node, so a bigger node will lead to more pulling since the trial becomes more severe. After applying the patch, pgbench shows up to 40% improvements and no regressions. Tested with 12 cpu x86 server and tip 3.10.0-rc7. The percentages in the final column highlight the areas with the biggest wins, all other areas improved as well: pgbench base smart | db_size | clients | tps | | tps | +---------+---------+-------+ +-------+ | 22 MB | 1 | 10598 | | 10796 | | 22 MB | 2 | 21257 | | 21336 | | 22 MB | 4 | 41386 | | 41622 | | 22 MB | 8 | 51253 | | 57932 | | 22 MB | 12 | 48570 | | 54000 | | 22 MB | 16 | 46748 | | 55982 | +19.75% | 22 MB | 24 | 44346 | | 55847 | +25.93% | 22 MB | 32 | 43460 | | 54614 | +25.66% | 7484 MB | 1 | 8951 | | 9193 | | 7484 MB | 2 | 19233 | | 19240 | | 7484 MB | 4 | 37239 | | 37302 | | 7484 MB | 8 | 46087 | | 50018 | | 7484 MB | 12 | 42054 | | 48763 | | 7484 MB | 16 | 40765 | | 51633 | +26.66% | 7484 MB | 24 | 37651 | | 52377 | +39.11% | 7484 MB | 32 | 37056 | | 51108 | +37.92% | 15 GB | 1 | 8845 | | 9104 | | 15 GB | 2 | 19094 | | 19162 | | 15 GB | 4 | 36979 | | 36983 | | 15 GB | 8 | 46087 | | 49977 | | 15 GB | 12 | 41901 | | 48591 | | 15 GB | 16 | 40147 | | 50651 | +26.16% | 15 GB | 24 | 37250 | | 52365 | +40.58% | 15 GB | 32 | 36470 | | 50015 | +37.14% Signed-off-by: Michael Wang <wangyun@linux.vnet.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/51D50057.9000809@linux.vnet.ibm.com [ Improved the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-04 04:55:51 +00:00
if (master < slave)
swap(master, slave);
if (slave < factor || master < slave * factor)
return 0;
return 1;
sched: Implement smarter wake-affine logic The wake-affine scheduler feature is currently always trying to pull the wakee close to the waker. In theory this should be beneficial if the waker's CPU caches hot data for the wakee, and it's also beneficial in the extreme ping-pong high context switch rate case. Testing shows it can benefit hackbench up to 15%. However, the feature is somewhat blind, from which some workloads such as pgbench suffer. It's also time-consuming algorithmically. Testing shows it can damage pgbench up to 50% - far more than the benefit it brings in the best case. So wake-affine should be smarter and it should realize when to stop its thankless effort at trying to find a suitable CPU to wake on. This patch introduces 'wakee_flips', which will be increased each time the task flips (switches) its wakee target. So a high 'wakee_flips' value means the task has more than one wakee, and the bigger the number, the higher the wakeup frequency. Now when making the decision on whether to pull or not, pay attention to the wakee with a high 'wakee_flips', pulling such a task may benefit the wakee. Also imply that the waker will face cruel competition later, it could be very cruel or very fast depends on the story behind 'wakee_flips', waker therefore suffers. Furthermore, if waker also has a high 'wakee_flips', that implies that multiple tasks rely on it, then waker's higher latency will damage all of them, so pulling wakee seems to be a bad deal. Thus, when 'waker->wakee_flips / wakee->wakee_flips' becomes higher and higher, the cost of pulling seems to be worse and worse. The patch therefore helps the wake-affine feature to stop its pulling work when: wakee->wakee_flips > factor && waker->wakee_flips > (factor * wakee->wakee_flips) The 'factor' here is the number of CPUs in the current CPU's NUMA node, so a bigger node will lead to more pulling since the trial becomes more severe. After applying the patch, pgbench shows up to 40% improvements and no regressions. Tested with 12 cpu x86 server and tip 3.10.0-rc7. The percentages in the final column highlight the areas with the biggest wins, all other areas improved as well: pgbench base smart | db_size | clients | tps | | tps | +---------+---------+-------+ +-------+ | 22 MB | 1 | 10598 | | 10796 | | 22 MB | 2 | 21257 | | 21336 | | 22 MB | 4 | 41386 | | 41622 | | 22 MB | 8 | 51253 | | 57932 | | 22 MB | 12 | 48570 | | 54000 | | 22 MB | 16 | 46748 | | 55982 | +19.75% | 22 MB | 24 | 44346 | | 55847 | +25.93% | 22 MB | 32 | 43460 | | 54614 | +25.66% | 7484 MB | 1 | 8951 | | 9193 | | 7484 MB | 2 | 19233 | | 19240 | | 7484 MB | 4 | 37239 | | 37302 | | 7484 MB | 8 | 46087 | | 50018 | | 7484 MB | 12 | 42054 | | 48763 | | 7484 MB | 16 | 40765 | | 51633 | +26.66% | 7484 MB | 24 | 37651 | | 52377 | +39.11% | 7484 MB | 32 | 37056 | | 51108 | +37.92% | 15 GB | 1 | 8845 | | 9104 | | 15 GB | 2 | 19094 | | 19162 | | 15 GB | 4 | 36979 | | 36983 | | 15 GB | 8 | 46087 | | 49977 | | 15 GB | 12 | 41901 | | 48591 | | 15 GB | 16 | 40147 | | 50651 | +26.16% | 15 GB | 24 | 37250 | | 52365 | +40.58% | 15 GB | 32 | 36470 | | 50015 | +37.14% Signed-off-by: Michael Wang <wangyun@linux.vnet.ibm.com> Cc: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/51D50057.9000809@linux.vnet.ibm.com [ Improved the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-04 04:55:51 +00:00
}
static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
{
s64 this_load, load;
s64 this_eff_load, prev_eff_load;
int idx, this_cpu, prev_cpu;
struct task_group *tg;
unsigned long weight;
int balanced;
idx = sd->wake_idx;
this_cpu = smp_processor_id();
prev_cpu = task_cpu(p);
load = source_load(prev_cpu, idx);
this_load = target_load(this_cpu, idx);
/*
* If sync wakeup then subtract the (maximum possible)
* effect of the currently running task from the load
* of the current CPU:
*/
if (sync) {
tg = task_group(current);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
weight = current->se.avg.load_avg;
this_load += effective_load(tg, this_cpu, -weight, -weight);
load += effective_load(tg, prev_cpu, 0, -weight);
}
tg = task_group(p);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
weight = p->se.avg.load_avg;
/*
* In low-load situations, where prev_cpu is idle and this_cpu is idle
* due to the sync cause above having dropped this_load to 0, we'll
* always have an imbalance, but there's really nothing you can do
* about that, so that's good too.
*
* Otherwise check if either cpus are near enough in load to allow this
* task to be woken on this_cpu.
*/
this_eff_load = 100;
this_eff_load *= capacity_of(prev_cpu);
prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
prev_eff_load *= capacity_of(this_cpu);
if (this_load > 0) {
this_eff_load *= this_load +
effective_load(tg, this_cpu, weight, weight);
prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight);
}
balanced = this_eff_load <= prev_eff_load;
schedstat_inc(p, se.statistics.nr_wakeups_affine_attempts);
sched: Remove a wake_affine() condition In wake_affine() I have tried to understand the meaning of the condition: (this_load <= load && this_load + target_load(prev_cpu, idx) <= tl_per_task) but I failed to find a use case that can take advantage of it and I haven't found clear description in the previous commit's log. Futhermore, the comment of the condition refers to the task_hot function that was used before being replaced by the current condition: /* * This domain has SD_WAKE_AFFINE and * p is cache cold in this domain, and * there is no bad imbalance. */ If we look more deeply the below condition: this_load + target_load(prev_cpu, idx) <= tl_per_task When sync is clear, we have: tl_per_task = runnable_load_avg / nr_running this_load = max(runnable_load_avg, cpuload[idx]) target_load = max(runnable_load_avg', cpuload'[idx]) It implies that runnable_load_avg == 0 and nr_running <= 1 in order to match the condition. This implies that runnable_load_avg == 0 too because of the condition: this_load <= load. but if this _load is null, 'balanced' is already set and the test is redundant. If sync is set, it's not as straight forward as above (especially if cgroup are involved) but the policy should be similar as we have removed a task that's going to sleep in order to get a more accurate load and this_load values. The current conclusion is that these additional condition don't give any benefit so we can remove them. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Morten.Rasmussen@arm.com Cc: efault@gmx.de Cc: nicolas.pitre@linaro.org Cc: daniel.lezcano@linaro.org Cc: dietmar.eggemann@arm.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1409051215-16788-3-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-26 11:06:45 +00:00
if (!balanced)
return 0;
sched: Remove a wake_affine() condition In wake_affine() I have tried to understand the meaning of the condition: (this_load <= load && this_load + target_load(prev_cpu, idx) <= tl_per_task) but I failed to find a use case that can take advantage of it and I haven't found clear description in the previous commit's log. Futhermore, the comment of the condition refers to the task_hot function that was used before being replaced by the current condition: /* * This domain has SD_WAKE_AFFINE and * p is cache cold in this domain, and * there is no bad imbalance. */ If we look more deeply the below condition: this_load + target_load(prev_cpu, idx) <= tl_per_task When sync is clear, we have: tl_per_task = runnable_load_avg / nr_running this_load = max(runnable_load_avg, cpuload[idx]) target_load = max(runnable_load_avg', cpuload'[idx]) It implies that runnable_load_avg == 0 and nr_running <= 1 in order to match the condition. This implies that runnable_load_avg == 0 too because of the condition: this_load <= load. but if this _load is null, 'balanced' is already set and the test is redundant. If sync is set, it's not as straight forward as above (especially if cgroup are involved) but the policy should be similar as we have removed a task that's going to sleep in order to get a more accurate load and this_load values. The current conclusion is that these additional condition don't give any benefit so we can remove them. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Morten.Rasmussen@arm.com Cc: efault@gmx.de Cc: nicolas.pitre@linaro.org Cc: daniel.lezcano@linaro.org Cc: dietmar.eggemann@arm.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1409051215-16788-3-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-26 11:06:45 +00:00
schedstat_inc(sd, ttwu_move_affine);
schedstat_inc(p, se.statistics.nr_wakeups_affine);
return 1;
}
/*
* find_idlest_group finds and returns the least busy CPU group within the
* domain.
*/
static struct sched_group *
find_idlest_group(struct sched_domain *sd, struct task_struct *p,
int this_cpu, int sd_flag)
{
struct sched_group *idlest = NULL, *group = sd->groups;
unsigned long min_load = ULONG_MAX, this_load = 0;
int load_idx = sd->forkexec_idx;
int imbalance = 100 + (sd->imbalance_pct-100)/2;
if (sd_flag & SD_BALANCE_WAKE)
load_idx = sd->wake_idx;
do {
unsigned long load, avg_load;
int local_group;
int i;
/* Skip over this group if it has no CPUs allowed */
if (!cpumask_intersects(sched_group_cpus(group),
tsk_cpus_allowed(p)))
continue;
local_group = cpumask_test_cpu(this_cpu,
sched_group_cpus(group));
/* Tally up the load of all CPUs in the group */
avg_load = 0;
for_each_cpu(i, sched_group_cpus(group)) {
/* Bias balancing toward cpus of our domain */
if (local_group)
load = source_load(i, load_idx);
else
load = target_load(i, load_idx);
avg_load += load;
}
/* Adjust by relative CPU capacity of the group */
sched: Final power vs. capacity cleanups It is better not to think about compute capacity as being equivalent to "CPU power". The upcoming "power aware" scheduler work may create confusion with the notion of energy consumption if "power" is used too liberally. This contains the architecture visible changes. Incidentally, only ARM takes advantage of the available pow^H^H^Hcapacity scaling hooks and therefore those changes outside kernel/sched/ are confined to one ARM specific file. The default arch_scale_smt_power() hook is not overridden by anyone. Replacements are as follows: arch_scale_freq_power --> arch_scale_freq_capacity arch_scale_smt_power --> arch_scale_smt_capacity SCHED_POWER_SCALE --> SCHED_CAPACITY_SCALE SCHED_POWER_SHIFT --> SCHED_CAPACITY_SHIFT The local usage of "power" in arch/arm/kernel/topology.c is also changed to "capacity" as appropriate. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Morten Rasmussen <morten.rasmussen@arm.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: linaro-kernel@lists.linaro.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com> Cc: Grant Likely <grant.likely@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Brown <broonie@linaro.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: devicetree@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/n/tip-48zba9qbznvglwelgq2cfygh@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-26 22:19:39 +00:00
avg_load = (avg_load * SCHED_CAPACITY_SCALE) / group->sgc->capacity;
if (local_group) {
this_load = avg_load;
} else if (avg_load < min_load) {
min_load = avg_load;
idlest = group;
}
} while (group = group->next, group != sd->groups);
if (!idlest || 100*this_load < imbalance*min_load)
return NULL;
return idlest;
}
/*
* find_idlest_cpu - find the idlest cpu among the cpus in group.
*/
static int
find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
{
unsigned long load, min_load = ULONG_MAX;
sched/fair: Leverage the idle state info when choosing the "idlest" cpu The code in find_idlest_cpu() looks for the CPU with the smallest load. However, if multiple CPUs are idle, the first idle CPU is selected irrespective of the depth of its idle state. Among the idle CPUs we should pick the one with with the shallowest idle state, or the latest to have gone idle if all idle CPUs are in the same state. The later applies even when cpuidle is configured out. This patch doesn't cover the following issues: - The idle exit latency of a CPU might be larger than the time needed to migrate the waking task to an already running CPU with sufficient capacity, and therefore performance would benefit from task packing in such case (in most cases task packing is about power saving). - Some idle states have a non negligible and non abortable entry latency which needs to run to completion before the exit latency can start. A concurrent patch series is making this info available to the cpuidle core. Once available, the entry latency with the idle timestamp could determine when the exit latency may be effective. Those issues will be handled in due course. In the mean time, what is implemented here should improve things already compared to the current state of affairs. Based on an initial patch from Daniel Lezcano. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: linux-pm@vger.kernel.org Cc: linaro-kernel@lists.linaro.org Link: http://lkml.kernel.org/n/tip-@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-09-04 15:32:10 +00:00
unsigned int min_exit_latency = UINT_MAX;
u64 latest_idle_timestamp = 0;
int least_loaded_cpu = this_cpu;
int shallowest_idle_cpu = -1;
int i;
/* Traverse only the allowed CPUs */
for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) {
sched/fair: Leverage the idle state info when choosing the "idlest" cpu The code in find_idlest_cpu() looks for the CPU with the smallest load. However, if multiple CPUs are idle, the first idle CPU is selected irrespective of the depth of its idle state. Among the idle CPUs we should pick the one with with the shallowest idle state, or the latest to have gone idle if all idle CPUs are in the same state. The later applies even when cpuidle is configured out. This patch doesn't cover the following issues: - The idle exit latency of a CPU might be larger than the time needed to migrate the waking task to an already running CPU with sufficient capacity, and therefore performance would benefit from task packing in such case (in most cases task packing is about power saving). - Some idle states have a non negligible and non abortable entry latency which needs to run to completion before the exit latency can start. A concurrent patch series is making this info available to the cpuidle core. Once available, the entry latency with the idle timestamp could determine when the exit latency may be effective. Those issues will be handled in due course. In the mean time, what is implemented here should improve things already compared to the current state of affairs. Based on an initial patch from Daniel Lezcano. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: linux-pm@vger.kernel.org Cc: linaro-kernel@lists.linaro.org Link: http://lkml.kernel.org/n/tip-@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-09-04 15:32:10 +00:00
if (idle_cpu(i)) {
struct rq *rq = cpu_rq(i);
struct cpuidle_state *idle = idle_get_state(rq);
if (idle && idle->exit_latency < min_exit_latency) {
/*
* We give priority to a CPU whose idle state
* has the smallest exit latency irrespective
* of any idle timestamp.
*/
min_exit_latency = idle->exit_latency;
latest_idle_timestamp = rq->idle_stamp;
shallowest_idle_cpu = i;
} else if ((!idle || idle->exit_latency == min_exit_latency) &&
rq->idle_stamp > latest_idle_timestamp) {
/*
* If equal or no active idle state, then
* the most recently idled CPU might have
* a warmer cache.
*/
latest_idle_timestamp = rq->idle_stamp;
shallowest_idle_cpu = i;
}
} else if (shallowest_idle_cpu == -1) {
sched/fair: Leverage the idle state info when choosing the "idlest" cpu The code in find_idlest_cpu() looks for the CPU with the smallest load. However, if multiple CPUs are idle, the first idle CPU is selected irrespective of the depth of its idle state. Among the idle CPUs we should pick the one with with the shallowest idle state, or the latest to have gone idle if all idle CPUs are in the same state. The later applies even when cpuidle is configured out. This patch doesn't cover the following issues: - The idle exit latency of a CPU might be larger than the time needed to migrate the waking task to an already running CPU with sufficient capacity, and therefore performance would benefit from task packing in such case (in most cases task packing is about power saving). - Some idle states have a non negligible and non abortable entry latency which needs to run to completion before the exit latency can start. A concurrent patch series is making this info available to the cpuidle core. Once available, the entry latency with the idle timestamp could determine when the exit latency may be effective. Those issues will be handled in due course. In the mean time, what is implemented here should improve things already compared to the current state of affairs. Based on an initial patch from Daniel Lezcano. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: linux-pm@vger.kernel.org Cc: linaro-kernel@lists.linaro.org Link: http://lkml.kernel.org/n/tip-@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-09-04 15:32:10 +00:00
load = weighted_cpuload(i);
if (load < min_load || (load == min_load && i == this_cpu)) {
min_load = load;
least_loaded_cpu = i;
}
}
}
sched/fair: Leverage the idle state info when choosing the "idlest" cpu The code in find_idlest_cpu() looks for the CPU with the smallest load. However, if multiple CPUs are idle, the first idle CPU is selected irrespective of the depth of its idle state. Among the idle CPUs we should pick the one with with the shallowest idle state, or the latest to have gone idle if all idle CPUs are in the same state. The later applies even when cpuidle is configured out. This patch doesn't cover the following issues: - The idle exit latency of a CPU might be larger than the time needed to migrate the waking task to an already running CPU with sufficient capacity, and therefore performance would benefit from task packing in such case (in most cases task packing is about power saving). - Some idle states have a non negligible and non abortable entry latency which needs to run to completion before the exit latency can start. A concurrent patch series is making this info available to the cpuidle core. Once available, the entry latency with the idle timestamp could determine when the exit latency may be effective. Those issues will be handled in due course. In the mean time, what is implemented here should improve things already compared to the current state of affairs. Based on an initial patch from Daniel Lezcano. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: linux-pm@vger.kernel.org Cc: linaro-kernel@lists.linaro.org Link: http://lkml.kernel.org/n/tip-@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-09-04 15:32:10 +00:00
return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
}
/*
* Try and locate an idle CPU in the sched_domain.
*/
sched: Fix select_idle_sibling() logic in select_task_rq_fair() Issues in the current select_idle_sibling() logic in select_task_rq_fair() in the context of a task wake-up: a) Once we select the idle sibling, we use that domain (spanning the cpu that the task is currently woken-up and the idle sibling that we found) in our wake_affine() decisions. This domain is completely different from the domain(we are supposed to use) that spans the cpu that the task currently woken-up and the cpu where the task previously ran. b) We do select_idle_sibling() check only for the cpu that the task is currently woken-up on. If select_task_rq_fair() selects the previously run cpu for waking the task, doing a select_idle_sibling() check for that cpu also helps and we don't do this currently. c) In the scenarios where the cpu that the task is woken-up is busy but with its HT siblings are idle, we are selecting the task be woken-up on the idle HT sibling instead of a core that it previously ran and currently completely idle. i.e., we are not taking decisions based on wake_affine() but directly selecting an idle sibling that can cause an imbalance at the SMT/MC level which will be later corrected by the periodic load balancer. Fix this by first going through the load imbalance calculations using wake_affine() and once we make a decision of woken-up cpu vs previously-ran cpu, then choose a possible idle sibling for waking up the task on. Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1270079265.7835.8.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-31 23:47:45 +00:00
static int select_idle_sibling(struct task_struct *p, int target)
{
sched: Fix select_idle_sibling() logic in select_task_rq_fair() Issues in the current select_idle_sibling() logic in select_task_rq_fair() in the context of a task wake-up: a) Once we select the idle sibling, we use that domain (spanning the cpu that the task is currently woken-up and the idle sibling that we found) in our wake_affine() decisions. This domain is completely different from the domain(we are supposed to use) that spans the cpu that the task currently woken-up and the cpu where the task previously ran. b) We do select_idle_sibling() check only for the cpu that the task is currently woken-up on. If select_task_rq_fair() selects the previously run cpu for waking the task, doing a select_idle_sibling() check for that cpu also helps and we don't do this currently. c) In the scenarios where the cpu that the task is woken-up is busy but with its HT siblings are idle, we are selecting the task be woken-up on the idle HT sibling instead of a core that it previously ran and currently completely idle. i.e., we are not taking decisions based on wake_affine() but directly selecting an idle sibling that can cause an imbalance at the SMT/MC level which will be later corrected by the periodic load balancer. Fix this by first going through the load imbalance calculations using wake_affine() and once we make a decision of woken-up cpu vs previously-ran cpu, then choose a possible idle sibling for waking up the task on. Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1270079265.7835.8.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-31 23:47:45 +00:00
struct sched_domain *sd;
struct sched_group *sg;
int i = task_cpu(p);
if (idle_cpu(target))
return target;
sched: Fix select_idle_sibling() logic in select_task_rq_fair() Issues in the current select_idle_sibling() logic in select_task_rq_fair() in the context of a task wake-up: a) Once we select the idle sibling, we use that domain (spanning the cpu that the task is currently woken-up and the idle sibling that we found) in our wake_affine() decisions. This domain is completely different from the domain(we are supposed to use) that spans the cpu that the task currently woken-up and the cpu where the task previously ran. b) We do select_idle_sibling() check only for the cpu that the task is currently woken-up on. If select_task_rq_fair() selects the previously run cpu for waking the task, doing a select_idle_sibling() check for that cpu also helps and we don't do this currently. c) In the scenarios where the cpu that the task is woken-up is busy but with its HT siblings are idle, we are selecting the task be woken-up on the idle HT sibling instead of a core that it previously ran and currently completely idle. i.e., we are not taking decisions based on wake_affine() but directly selecting an idle sibling that can cause an imbalance at the SMT/MC level which will be later corrected by the periodic load balancer. Fix this by first going through the load imbalance calculations using wake_affine() and once we make a decision of woken-up cpu vs previously-ran cpu, then choose a possible idle sibling for waking up the task on. Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1270079265.7835.8.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-31 23:47:45 +00:00
/*
* If the prevous cpu is cache affine and idle, don't be stupid.
sched: Fix select_idle_sibling() logic in select_task_rq_fair() Issues in the current select_idle_sibling() logic in select_task_rq_fair() in the context of a task wake-up: a) Once we select the idle sibling, we use that domain (spanning the cpu that the task is currently woken-up and the idle sibling that we found) in our wake_affine() decisions. This domain is completely different from the domain(we are supposed to use) that spans the cpu that the task currently woken-up and the cpu where the task previously ran. b) We do select_idle_sibling() check only for the cpu that the task is currently woken-up on. If select_task_rq_fair() selects the previously run cpu for waking the task, doing a select_idle_sibling() check for that cpu also helps and we don't do this currently. c) In the scenarios where the cpu that the task is woken-up is busy but with its HT siblings are idle, we are selecting the task be woken-up on the idle HT sibling instead of a core that it previously ran and currently completely idle. i.e., we are not taking decisions based on wake_affine() but directly selecting an idle sibling that can cause an imbalance at the SMT/MC level which will be later corrected by the periodic load balancer. Fix this by first going through the load imbalance calculations using wake_affine() and once we make a decision of woken-up cpu vs previously-ran cpu, then choose a possible idle sibling for waking up the task on. Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1270079265.7835.8.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-31 23:47:45 +00:00
*/
if (i != target && cpus_share_cache(i, target) && idle_cpu(i))
return i;
/*
* Otherwise, iterate the domains and find an elegible idle cpu.
*/
sd = rcu_dereference(per_cpu(sd_llc, target));
for_each_lower_domain(sd) {
sg = sd->groups;
do {
if (!cpumask_intersects(sched_group_cpus(sg),
tsk_cpus_allowed(p)))
goto next;
for_each_cpu(i, sched_group_cpus(sg)) {
if (i == target || !idle_cpu(i))
goto next;
}
target = cpumask_first_and(sched_group_cpus(sg),
tsk_cpus_allowed(p));
goto done;
next:
sg = sg->next;
} while (sg != sd->groups);
}
done:
return target;
}
sched: Calculate CPU's usage statistic and put it into struct sg_lb_stats::group_usage Monitor the usage level of each group of each sched_domain level. The usage is the portion of cpu_capacity_orig that is currently used on a CPU or group of CPUs. We use the utilization_load_avg to evaluate the usage level of each group. The utilization_load_avg only takes into account the running time of the CFS tasks on a CPU with a maximum value of SCHED_LOAD_SCALE when the CPU is fully utilized. Nevertheless, we must cap utilization_load_avg which can be temporally greater than SCHED_LOAD_SCALE after the migration of a task on this CPU and until the metrics are stabilized. The utilization_load_avg is in the range [0..SCHED_LOAD_SCALE] to reflect the running load on the CPU whereas the available capacity for the CFS task is in the range [0..cpu_capacity_orig]. In order to test if a CPU is fully utilized by CFS tasks, we have to scale the utilization in the cpu_capacity_orig range of the CPU to get the usage of the latter. The usage can then be compared with the available capacity (ie cpu_capacity) to deduct the usage level of a CPU. The frequency scaling invariance of the usage is not taken into account in this patch, it will be solved in another patch which will deal with frequency scaling invariance on the utilization_load_avg. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425455327-13508-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-03-04 07:48:47 +00:00
/*
* get_cpu_usage returns the amount of capacity of a CPU that is used by CFS
* tasks. The unit of the return value must be the one of capacity so we can
* compare the usage with the capacity of the CPU that is available for CFS
* task (ie cpu_capacity).
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
* cfs.avg.util_avg is the sum of running time of runnable tasks on a
sched: Calculate CPU's usage statistic and put it into struct sg_lb_stats::group_usage Monitor the usage level of each group of each sched_domain level. The usage is the portion of cpu_capacity_orig that is currently used on a CPU or group of CPUs. We use the utilization_load_avg to evaluate the usage level of each group. The utilization_load_avg only takes into account the running time of the CFS tasks on a CPU with a maximum value of SCHED_LOAD_SCALE when the CPU is fully utilized. Nevertheless, we must cap utilization_load_avg which can be temporally greater than SCHED_LOAD_SCALE after the migration of a task on this CPU and until the metrics are stabilized. The utilization_load_avg is in the range [0..SCHED_LOAD_SCALE] to reflect the running load on the CPU whereas the available capacity for the CFS task is in the range [0..cpu_capacity_orig]. In order to test if a CPU is fully utilized by CFS tasks, we have to scale the utilization in the cpu_capacity_orig range of the CPU to get the usage of the latter. The usage can then be compared with the available capacity (ie cpu_capacity) to deduct the usage level of a CPU. The frequency scaling invariance of the usage is not taken into account in this patch, it will be solved in another patch which will deal with frequency scaling invariance on the utilization_load_avg. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425455327-13508-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-03-04 07:48:47 +00:00
* CPU. It represents the amount of utilization of a CPU in the range
* [0..SCHED_LOAD_SCALE]. The usage of a CPU can't be higher than the full
* capacity of the CPU because it's about the running time on this CPU.
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
* Nevertheless, cfs.avg.util_avg can be higher than SCHED_LOAD_SCALE
* because of unfortunate rounding in util_avg or just
sched: Calculate CPU's usage statistic and put it into struct sg_lb_stats::group_usage Monitor the usage level of each group of each sched_domain level. The usage is the portion of cpu_capacity_orig that is currently used on a CPU or group of CPUs. We use the utilization_load_avg to evaluate the usage level of each group. The utilization_load_avg only takes into account the running time of the CFS tasks on a CPU with a maximum value of SCHED_LOAD_SCALE when the CPU is fully utilized. Nevertheless, we must cap utilization_load_avg which can be temporally greater than SCHED_LOAD_SCALE after the migration of a task on this CPU and until the metrics are stabilized. The utilization_load_avg is in the range [0..SCHED_LOAD_SCALE] to reflect the running load on the CPU whereas the available capacity for the CFS task is in the range [0..cpu_capacity_orig]. In order to test if a CPU is fully utilized by CFS tasks, we have to scale the utilization in the cpu_capacity_orig range of the CPU to get the usage of the latter. The usage can then be compared with the available capacity (ie cpu_capacity) to deduct the usage level of a CPU. The frequency scaling invariance of the usage is not taken into account in this patch, it will be solved in another patch which will deal with frequency scaling invariance on the utilization_load_avg. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425455327-13508-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-03-04 07:48:47 +00:00
* after migrating tasks until the average stabilizes with the new running
* time. So we need to check that the usage stays into the range
* [0..cpu_capacity_orig] and cap if necessary.
* Without capping the usage, a group could be seen as overloaded (CPU0 usage
* at 121% + CPU1 usage at 80%) whereas CPU1 has 20% of available capacity
*/
static int get_cpu_usage(int cpu)
{
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
unsigned long usage = cpu_rq(cpu)->cfs.avg.util_avg;
sched: Calculate CPU's usage statistic and put it into struct sg_lb_stats::group_usage Monitor the usage level of each group of each sched_domain level. The usage is the portion of cpu_capacity_orig that is currently used on a CPU or group of CPUs. We use the utilization_load_avg to evaluate the usage level of each group. The utilization_load_avg only takes into account the running time of the CFS tasks on a CPU with a maximum value of SCHED_LOAD_SCALE when the CPU is fully utilized. Nevertheless, we must cap utilization_load_avg which can be temporally greater than SCHED_LOAD_SCALE after the migration of a task on this CPU and until the metrics are stabilized. The utilization_load_avg is in the range [0..SCHED_LOAD_SCALE] to reflect the running load on the CPU whereas the available capacity for the CFS task is in the range [0..cpu_capacity_orig]. In order to test if a CPU is fully utilized by CFS tasks, we have to scale the utilization in the cpu_capacity_orig range of the CPU to get the usage of the latter. The usage can then be compared with the available capacity (ie cpu_capacity) to deduct the usage level of a CPU. The frequency scaling invariance of the usage is not taken into account in this patch, it will be solved in another patch which will deal with frequency scaling invariance on the utilization_load_avg. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425455327-13508-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-03-04 07:48:47 +00:00
unsigned long capacity = capacity_orig_of(cpu);
if (usage >= SCHED_LOAD_SCALE)
return capacity;
return (usage * capacity) >> SCHED_LOAD_SHIFT;
}
/*
* select_task_rq_fair: Select target runqueue for the waking task in domains
* that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
* SD_BALANCE_FORK, or SD_BALANCE_EXEC.
*
* Balances load by selecting the idlest cpu in the idlest group, or under
* certain conditions an idle sibling cpu if the domain has SD_WAKE_AFFINE set.
*
* Returns the target cpu number.
*
* preempt must be disabled.
*/
static int
select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
{
struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
int cpu = smp_processor_id();
int new_cpu = prev_cpu;
sched: Fix select_idle_sibling() logic in select_task_rq_fair() Issues in the current select_idle_sibling() logic in select_task_rq_fair() in the context of a task wake-up: a) Once we select the idle sibling, we use that domain (spanning the cpu that the task is currently woken-up and the idle sibling that we found) in our wake_affine() decisions. This domain is completely different from the domain(we are supposed to use) that spans the cpu that the task currently woken-up and the cpu where the task previously ran. b) We do select_idle_sibling() check only for the cpu that the task is currently woken-up on. If select_task_rq_fair() selects the previously run cpu for waking the task, doing a select_idle_sibling() check for that cpu also helps and we don't do this currently. c) In the scenarios where the cpu that the task is woken-up is busy but with its HT siblings are idle, we are selecting the task be woken-up on the idle HT sibling instead of a core that it previously ran and currently completely idle. i.e., we are not taking decisions based on wake_affine() but directly selecting an idle sibling that can cause an imbalance at the SMT/MC level which will be later corrected by the periodic load balancer. Fix this by first going through the load imbalance calculations using wake_affine() and once we make a decision of woken-up cpu vs previously-ran cpu, then choose a possible idle sibling for waking up the task on. Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1270079265.7835.8.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-31 23:47:45 +00:00
int want_affine = 0;
int sync = wake_flags & WF_SYNC;
if (sd_flag & SD_BALANCE_WAKE)
want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
sched: Dynamically allocate sched_domain/sched_group data-structures Instead of relying on static allocations for the sched_domain and sched_group trees, dynamically allocate and RCU free them. Allocating this dynamically also allows for some build_sched_groups() simplification since we can now (like with other simplifications) rely on the sched_domain tree instead of hard-coded knowledge. One tricky to note is that detach_destroy_domains() needs to hold rcu_read_lock() over the entire tear-down, per-cpu is not sufficient since that can lead to partial sched_group existance (could possibly be solved by doing the tear-down backwards but this is much more robust). A concequence of the above is that we can no longer print the sched_domain debug stuff from cpu_attach_domain() since that might now run with preemption disabled (due to classic RCU etc.) and sched_domain_debug() does some GFP_KERNEL allocations. Another thing to note is that we now fully rely on normal RCU and not RCU-sched, this is because with the new and exiting RCU flavours we grew over the years BH doesn't necessarily hold off RCU-sched grace periods (-rt is known to break this). This would in fact already cause us grief since we do sched_domain/sched_group iterations from softirq context. This patch is somewhat larger than I would like it to be, but I didn't find any means of shrinking/splitting this. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20110407122942.245307941@chello.nl Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-07 12:09:50 +00:00
rcu_read_lock();
for_each_domain(cpu, tmp) {
if (!(tmp->flags & SD_LOAD_BALANCE))
break;
/*
sched: Fix select_idle_sibling() logic in select_task_rq_fair() Issues in the current select_idle_sibling() logic in select_task_rq_fair() in the context of a task wake-up: a) Once we select the idle sibling, we use that domain (spanning the cpu that the task is currently woken-up and the idle sibling that we found) in our wake_affine() decisions. This domain is completely different from the domain(we are supposed to use) that spans the cpu that the task currently woken-up and the cpu where the task previously ran. b) We do select_idle_sibling() check only for the cpu that the task is currently woken-up on. If select_task_rq_fair() selects the previously run cpu for waking the task, doing a select_idle_sibling() check for that cpu also helps and we don't do this currently. c) In the scenarios where the cpu that the task is woken-up is busy but with its HT siblings are idle, we are selecting the task be woken-up on the idle HT sibling instead of a core that it previously ran and currently completely idle. i.e., we are not taking decisions based on wake_affine() but directly selecting an idle sibling that can cause an imbalance at the SMT/MC level which will be later corrected by the periodic load balancer. Fix this by first going through the load imbalance calculations using wake_affine() and once we make a decision of woken-up cpu vs previously-ran cpu, then choose a possible idle sibling for waking up the task on. Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1270079265.7835.8.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-31 23:47:45 +00:00
* If both cpu and prev_cpu are part of this domain,
* cpu is a valid SD_WAKE_AFFINE target.
*/
sched: Fix select_idle_sibling() logic in select_task_rq_fair() Issues in the current select_idle_sibling() logic in select_task_rq_fair() in the context of a task wake-up: a) Once we select the idle sibling, we use that domain (spanning the cpu that the task is currently woken-up and the idle sibling that we found) in our wake_affine() decisions. This domain is completely different from the domain(we are supposed to use) that spans the cpu that the task currently woken-up and the cpu where the task previously ran. b) We do select_idle_sibling() check only for the cpu that the task is currently woken-up on. If select_task_rq_fair() selects the previously run cpu for waking the task, doing a select_idle_sibling() check for that cpu also helps and we don't do this currently. c) In the scenarios where the cpu that the task is woken-up is busy but with its HT siblings are idle, we are selecting the task be woken-up on the idle HT sibling instead of a core that it previously ran and currently completely idle. i.e., we are not taking decisions based on wake_affine() but directly selecting an idle sibling that can cause an imbalance at the SMT/MC level which will be later corrected by the periodic load balancer. Fix this by first going through the load imbalance calculations using wake_affine() and once we make a decision of woken-up cpu vs previously-ran cpu, then choose a possible idle sibling for waking up the task on. Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1270079265.7835.8.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-31 23:47:45 +00:00
if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
affine_sd = tmp;
break;
}
if (tmp->flags & sd_flag)
sd = tmp;
else if (!want_affine)
break;
}
if (affine_sd) {
sd = NULL; /* Prefer wake_affine over balance flags */
if (cpu != prev_cpu && wake_affine(affine_sd, p, sync))
new_cpu = cpu;
}
if (!sd) {
if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
new_cpu = select_idle_sibling(p, new_cpu);
} else while (sd) {
struct sched_group *group;
int weight;
if (!(sd->flags & sd_flag)) {
sd = sd->child;
continue;
}
group = find_idlest_group(sd, p, cpu, sd_flag);
if (!group) {
sd = sd->child;
continue;
}
new_cpu = find_idlest_cpu(group, p, cpu);
if (new_cpu == -1 || new_cpu == cpu) {
/* Now try balancing at a lower domain level of cpu */
sd = sd->child;
continue;
}
/* Now try balancing at a lower domain level of new_cpu */
cpu = new_cpu;
weight = sd->span_weight;
sd = NULL;
for_each_domain(cpu, tmp) {
if (weight <= tmp->span_weight)
break;
if (tmp->flags & sd_flag)
sd = tmp;
}
/* while loop will break here if sd == NULL */
}
sched: Dynamically allocate sched_domain/sched_group data-structures Instead of relying on static allocations for the sched_domain and sched_group trees, dynamically allocate and RCU free them. Allocating this dynamically also allows for some build_sched_groups() simplification since we can now (like with other simplifications) rely on the sched_domain tree instead of hard-coded knowledge. One tricky to note is that detach_destroy_domains() needs to hold rcu_read_lock() over the entire tear-down, per-cpu is not sufficient since that can lead to partial sched_group existance (could possibly be solved by doing the tear-down backwards but this is much more robust). A concequence of the above is that we can no longer print the sched_domain debug stuff from cpu_attach_domain() since that might now run with preemption disabled (due to classic RCU etc.) and sched_domain_debug() does some GFP_KERNEL allocations. Another thing to note is that we now fully rely on normal RCU and not RCU-sched, this is because with the new and exiting RCU flavours we grew over the years BH doesn't necessarily hold off RCU-sched grace periods (-rt is known to break this). This would in fact already cause us grief since we do sched_domain/sched_group iterations from softirq context. This patch is somewhat larger than I would like it to be, but I didn't find any means of shrinking/splitting this. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20110407122942.245307941@chello.nl Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-07 12:09:50 +00:00
rcu_read_unlock();
return new_cpu;
}
/*
* Called immediately before a task is migrated to a new cpu; task_cpu(p) and
* cfs_rq_of(p) references at time of call are still valid and identify the
* previous cpu. However, the caller only guarantees p->pi_lock is held; no
* other assumptions, including the state of rq->lock, should be made.
*/
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
static void migrate_task_rq_fair(struct task_struct *p, int next_cpu)
{
/*
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
* We are supposed to update the task to "current" time, then its up to date
* and ready to go to new CPU/cfs_rq. But we have difficulty in getting
* what current time is, so simply throw away the out-of-date time. This
* will result in the wakee task is less decayed, but giving the wakee more
* load sounds not bad.
*/
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
remove_entity_load_avg(&p->se);
/* Tell new CPU we are migrated */
p->se.avg.last_update_time = 0;
/* We have migrated, no longer consider this task hot */
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
p->se.exec_start = 0;
}
static void task_dead_fair(struct task_struct *p)
{
remove_entity_load_avg(&p->se);
}
#endif /* CONFIG_SMP */
static unsigned long
wakeup_gran(struct sched_entity *curr, struct sched_entity *se)
{
unsigned long gran = sysctl_sched_wakeup_granularity;
/*
* Since its curr running now, convert the gran from real-time
* to virtual-time in his units.
*
* By using 'se' instead of 'curr' we penalize light tasks, so
* they get preempted easier. That is, if 'se' < 'curr' then
* the resulting gran will be larger, therefore penalizing the
* lighter, if otoh 'se' > 'curr' then the resulting gran will
* be smaller, again penalizing the lighter task.
*
* This is especially important for buddies when the leftmost
* task is higher priority than the buddy.
*/
return calc_delta_fair(gran, se);
}
/*
* Should 'se' preempt 'curr'.
*
* |s1
* |s2
* |s3
* g
* |<--->|c
*
* w(c, s1) = -1
* w(c, s2) = 0
* w(c, s3) = 1
*
*/
static int
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
{
s64 gran, vdiff = curr->vruntime - se->vruntime;
if (vdiff <= 0)
return -1;
gran = wakeup_gran(curr, se);
if (vdiff > gran)
return 1;
return 0;
}
static void set_last_buddy(struct sched_entity *se)
{
if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
return;
for_each_sched_entity(se)
cfs_rq_of(se)->last = se;
}
static void set_next_buddy(struct sched_entity *se)
{
if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
return;
for_each_sched_entity(se)
cfs_rq_of(se)->next = se;
}
static void set_skip_buddy(struct sched_entity *se)
{
for_each_sched_entity(se)
cfs_rq_of(se)->skip = se;
}
/*
* Preempt the current task with a newly woken task if needed:
*/
static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
{
struct task_struct *curr = rq->curr;
struct sched_entity *se = &curr->se, *pse = &p->se;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
sched: Strengthen buddies and mitigate buddy induced latencies This patch restores the effectiveness of LAST_BUDDY in preventing pgsql+oltp from collapsing due to wakeup preemption. It also switches LAST_BUDDY to exclusively do what it does best, namely mitigate the effects of aggressive wakeup preemption, which improves vmark throughput markedly, and restores mysql+oltp scalability. Since buddies are about scalability, enable them beginning at the point where we begin expanding sched_latency, namely sched_nr_latency. Previously, buddies were cleared aggressively, which seriously reduced their effectiveness. Not clearing aggressively however, produces a small drop in mysql+oltp throughput immediately after peak, indicating that LAST_BUDDY is actually doing some harm. This is right at the point where X on the desktop in competition with another load wants low latency service. Ergo, do not enable until we need to scale. To mitigate latency induced by buddies, or by a task just missing wakeup preemption, check latency at tick time. Last hunk prevents buddies from stymieing BALANCE_NEWIDLE via CACHE_HOT_BUDDY. Supporting performance tests: tip = v2.6.32-rc5-1497-ga525b32 tipx = NO_GENTLE_FAIR_SLEEPERS NEXT_BUDDY granularity knobs = 31 knobs + 31 buddies tip+x = NO_GENTLE_FAIR_SLEEPERS granularity knobs = 31 knobs (Three run averages except where noted.) vmark: ------ tip 108466 messages per second tip+ 125307 messages per second tip+x 125335 messages per second tipx 117781 messages per second 2.6.31.3 122729 messages per second mysql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 9949.89 18690.20 34801.24 34460.04 32682.88 30765.97 28305.27 25059.64 19548.08 tip+ 10013.90 18526.84 34900.38 34420.14 33069.83 32083.40 30578.30 28010.71 25605.47 tipx 9698.71 18002.70 34477.56 33420.01 32634.30 31657.27 29932.67 26827.52 21487.18 2.6.31.3 8243.11 18784.20 34404.83 33148.38 31900.32 31161.90 29663.81 25995.94 18058.86 pgsql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 13686.37 26609.25 51934.28 51347.81 49479.51 45312.65 36691.91 26851.57 24145.35 tip+ (1x) 13907.85 27135.87 52951.98 52514.04 51742.52 50705.43 49947.97 48374.19 46227.94 tip+x 13906.78 27065.81 52951.19 52542.59 52176.11 51815.94 50838.90 49439.46 46891.00 tipx 13742.46 26769.81 52351.99 51891.73 51320.79 50938.98 50248.65 48908.70 46553.84 2.6.31.3 13815.35 26906.46 52683.34 52061.31 51937.10 51376.80 50474.28 49394.47 47003.25 Signed-off-by: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-23 21:09:22 +00:00
int scale = cfs_rq->nr_running >= sched_nr_latency;
sched: Next buddy hint on sleep and preempt path When a task in a taskgroup sleeps, pick_next_task starts all the way back at the root and picks the task/taskgroup with the min vruntime across all runnable tasks. But when there are many frequently sleeping tasks across different taskgroups, it makes better sense to stay with same taskgroup for its slice period (or until all tasks in the taskgroup sleeps) instead of switching cross taskgroup on each sleep after a short runtime. This helps specifically where taskgroups corresponds to a process with multiple threads. The change reduces the number of CR3 switches in this case. Example: Two taskgroups with 2 threads each which are running for 2ms and sleeping for 1ms. Looking at sched:sched_switch shows: BEFORE: taskgroup_1 threads [5004, 5005], taskgroup_2 threads [5016, 5017] cpu-soaker-5004 [003] 3683.391089 cpu-soaker-5016 [003] 3683.393106 cpu-soaker-5005 [003] 3683.395119 cpu-soaker-5017 [003] 3683.397130 cpu-soaker-5004 [003] 3683.399143 cpu-soaker-5016 [003] 3683.401155 cpu-soaker-5005 [003] 3683.403168 cpu-soaker-5017 [003] 3683.405170 AFTER: taskgroup_1 threads [21890, 21891], taskgroup_2 threads [21934, 21935] cpu-soaker-21890 [003] 865.895494 cpu-soaker-21935 [003] 865.897506 cpu-soaker-21934 [003] 865.899520 cpu-soaker-21935 [003] 865.901532 cpu-soaker-21934 [003] 865.903543 cpu-soaker-21935 [003] 865.905546 cpu-soaker-21891 [003] 865.907548 cpu-soaker-21890 [003] 865.909560 cpu-soaker-21891 [003] 865.911571 cpu-soaker-21890 [003] 865.913582 cpu-soaker-21891 [003] 865.915594 cpu-soaker-21934 [003] 865.917606 Similar problem is there when there are multiple taskgroups and say a task A preempts currently running task B of taskgroup_1. On schedule, pick_next_task can pick an unrelated task on taskgroup_2. Here it would be better to give some preference to task B on pick_next_task. A simple (may be extreme case) benchmark I tried was tbench with 2 tbench client processes with 2 threads each running on a single CPU. Avg throughput across 5 50 sec runs was: BEFORE: 105.84 MB/sec AFTER: 112.42 MB/sec Signed-off-by: Venkatesh Pallipadi <venki@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1302802253-25760-1-git-send-email-venki@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-14 17:30:53 +00:00
int next_buddy_marked = 0;
if (unlikely(se == pse))
return;
/*
* This is possible from callers such as attach_tasks(), in which we
* unconditionally check_prempt_curr() after an enqueue (which may have
* lead to a throttle). This both saves work and prevents false
* next-buddy nomination below.
*/
if (unlikely(throttled_hierarchy(cfs_rq_of(pse))))
return;
sched: Next buddy hint on sleep and preempt path When a task in a taskgroup sleeps, pick_next_task starts all the way back at the root and picks the task/taskgroup with the min vruntime across all runnable tasks. But when there are many frequently sleeping tasks across different taskgroups, it makes better sense to stay with same taskgroup for its slice period (or until all tasks in the taskgroup sleeps) instead of switching cross taskgroup on each sleep after a short runtime. This helps specifically where taskgroups corresponds to a process with multiple threads. The change reduces the number of CR3 switches in this case. Example: Two taskgroups with 2 threads each which are running for 2ms and sleeping for 1ms. Looking at sched:sched_switch shows: BEFORE: taskgroup_1 threads [5004, 5005], taskgroup_2 threads [5016, 5017] cpu-soaker-5004 [003] 3683.391089 cpu-soaker-5016 [003] 3683.393106 cpu-soaker-5005 [003] 3683.395119 cpu-soaker-5017 [003] 3683.397130 cpu-soaker-5004 [003] 3683.399143 cpu-soaker-5016 [003] 3683.401155 cpu-soaker-5005 [003] 3683.403168 cpu-soaker-5017 [003] 3683.405170 AFTER: taskgroup_1 threads [21890, 21891], taskgroup_2 threads [21934, 21935] cpu-soaker-21890 [003] 865.895494 cpu-soaker-21935 [003] 865.897506 cpu-soaker-21934 [003] 865.899520 cpu-soaker-21935 [003] 865.901532 cpu-soaker-21934 [003] 865.903543 cpu-soaker-21935 [003] 865.905546 cpu-soaker-21891 [003] 865.907548 cpu-soaker-21890 [003] 865.909560 cpu-soaker-21891 [003] 865.911571 cpu-soaker-21890 [003] 865.913582 cpu-soaker-21891 [003] 865.915594 cpu-soaker-21934 [003] 865.917606 Similar problem is there when there are multiple taskgroups and say a task A preempts currently running task B of taskgroup_1. On schedule, pick_next_task can pick an unrelated task on taskgroup_2. Here it would be better to give some preference to task B on pick_next_task. A simple (may be extreme case) benchmark I tried was tbench with 2 tbench client processes with 2 threads each running on a single CPU. Avg throughput across 5 50 sec runs was: BEFORE: 105.84 MB/sec AFTER: 112.42 MB/sec Signed-off-by: Venkatesh Pallipadi <venki@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1302802253-25760-1-git-send-email-venki@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-14 17:30:53 +00:00
if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) {
set_next_buddy(pse);
sched: Next buddy hint on sleep and preempt path When a task in a taskgroup sleeps, pick_next_task starts all the way back at the root and picks the task/taskgroup with the min vruntime across all runnable tasks. But when there are many frequently sleeping tasks across different taskgroups, it makes better sense to stay with same taskgroup for its slice period (or until all tasks in the taskgroup sleeps) instead of switching cross taskgroup on each sleep after a short runtime. This helps specifically where taskgroups corresponds to a process with multiple threads. The change reduces the number of CR3 switches in this case. Example: Two taskgroups with 2 threads each which are running for 2ms and sleeping for 1ms. Looking at sched:sched_switch shows: BEFORE: taskgroup_1 threads [5004, 5005], taskgroup_2 threads [5016, 5017] cpu-soaker-5004 [003] 3683.391089 cpu-soaker-5016 [003] 3683.393106 cpu-soaker-5005 [003] 3683.395119 cpu-soaker-5017 [003] 3683.397130 cpu-soaker-5004 [003] 3683.399143 cpu-soaker-5016 [003] 3683.401155 cpu-soaker-5005 [003] 3683.403168 cpu-soaker-5017 [003] 3683.405170 AFTER: taskgroup_1 threads [21890, 21891], taskgroup_2 threads [21934, 21935] cpu-soaker-21890 [003] 865.895494 cpu-soaker-21935 [003] 865.897506 cpu-soaker-21934 [003] 865.899520 cpu-soaker-21935 [003] 865.901532 cpu-soaker-21934 [003] 865.903543 cpu-soaker-21935 [003] 865.905546 cpu-soaker-21891 [003] 865.907548 cpu-soaker-21890 [003] 865.909560 cpu-soaker-21891 [003] 865.911571 cpu-soaker-21890 [003] 865.913582 cpu-soaker-21891 [003] 865.915594 cpu-soaker-21934 [003] 865.917606 Similar problem is there when there are multiple taskgroups and say a task A preempts currently running task B of taskgroup_1. On schedule, pick_next_task can pick an unrelated task on taskgroup_2. Here it would be better to give some preference to task B on pick_next_task. A simple (may be extreme case) benchmark I tried was tbench with 2 tbench client processes with 2 threads each running on a single CPU. Avg throughput across 5 50 sec runs was: BEFORE: 105.84 MB/sec AFTER: 112.42 MB/sec Signed-off-by: Venkatesh Pallipadi <venki@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1302802253-25760-1-git-send-email-venki@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-14 17:30:53 +00:00
next_buddy_marked = 1;
}
/*
* We can come here with TIF_NEED_RESCHED already set from new task
* wake up path.
*
* Note: this also catches the edge-case of curr being in a throttled
* group (e.g. via set_curr_task), since update_curr() (in the
* enqueue of curr) will have resulted in resched being set. This
* prevents us from potentially nominating it as a false LAST_BUDDY
* below.
*/
if (test_tsk_need_resched(curr))
return;
/* Idle tasks are by definition preempted by non-idle tasks. */
if (unlikely(curr->policy == SCHED_IDLE) &&
likely(p->policy != SCHED_IDLE))
goto preempt;
/*
* Batch and idle tasks do not preempt non-idle tasks (their preemption
* is driven by the tick):
*/
if (unlikely(p->policy != SCHED_NORMAL) || !sched_feat(WAKEUP_PREEMPTION))
return;
find_matching_se(&se, &pse);
update_curr(cfs_rq_of(se));
BUG_ON(!pse);
sched: Next buddy hint on sleep and preempt path When a task in a taskgroup sleeps, pick_next_task starts all the way back at the root and picks the task/taskgroup with the min vruntime across all runnable tasks. But when there are many frequently sleeping tasks across different taskgroups, it makes better sense to stay with same taskgroup for its slice period (or until all tasks in the taskgroup sleeps) instead of switching cross taskgroup on each sleep after a short runtime. This helps specifically where taskgroups corresponds to a process with multiple threads. The change reduces the number of CR3 switches in this case. Example: Two taskgroups with 2 threads each which are running for 2ms and sleeping for 1ms. Looking at sched:sched_switch shows: BEFORE: taskgroup_1 threads [5004, 5005], taskgroup_2 threads [5016, 5017] cpu-soaker-5004 [003] 3683.391089 cpu-soaker-5016 [003] 3683.393106 cpu-soaker-5005 [003] 3683.395119 cpu-soaker-5017 [003] 3683.397130 cpu-soaker-5004 [003] 3683.399143 cpu-soaker-5016 [003] 3683.401155 cpu-soaker-5005 [003] 3683.403168 cpu-soaker-5017 [003] 3683.405170 AFTER: taskgroup_1 threads [21890, 21891], taskgroup_2 threads [21934, 21935] cpu-soaker-21890 [003] 865.895494 cpu-soaker-21935 [003] 865.897506 cpu-soaker-21934 [003] 865.899520 cpu-soaker-21935 [003] 865.901532 cpu-soaker-21934 [003] 865.903543 cpu-soaker-21935 [003] 865.905546 cpu-soaker-21891 [003] 865.907548 cpu-soaker-21890 [003] 865.909560 cpu-soaker-21891 [003] 865.911571 cpu-soaker-21890 [003] 865.913582 cpu-soaker-21891 [003] 865.915594 cpu-soaker-21934 [003] 865.917606 Similar problem is there when there are multiple taskgroups and say a task A preempts currently running task B of taskgroup_1. On schedule, pick_next_task can pick an unrelated task on taskgroup_2. Here it would be better to give some preference to task B on pick_next_task. A simple (may be extreme case) benchmark I tried was tbench with 2 tbench client processes with 2 threads each running on a single CPU. Avg throughput across 5 50 sec runs was: BEFORE: 105.84 MB/sec AFTER: 112.42 MB/sec Signed-off-by: Venkatesh Pallipadi <venki@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1302802253-25760-1-git-send-email-venki@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-14 17:30:53 +00:00
if (wakeup_preempt_entity(se, pse) == 1) {
/*
* Bias pick_next to pick the sched entity that is
* triggering this preemption.
*/
if (!next_buddy_marked)
set_next_buddy(pse);
goto preempt;
sched: Next buddy hint on sleep and preempt path When a task in a taskgroup sleeps, pick_next_task starts all the way back at the root and picks the task/taskgroup with the min vruntime across all runnable tasks. But when there are many frequently sleeping tasks across different taskgroups, it makes better sense to stay with same taskgroup for its slice period (or until all tasks in the taskgroup sleeps) instead of switching cross taskgroup on each sleep after a short runtime. This helps specifically where taskgroups corresponds to a process with multiple threads. The change reduces the number of CR3 switches in this case. Example: Two taskgroups with 2 threads each which are running for 2ms and sleeping for 1ms. Looking at sched:sched_switch shows: BEFORE: taskgroup_1 threads [5004, 5005], taskgroup_2 threads [5016, 5017] cpu-soaker-5004 [003] 3683.391089 cpu-soaker-5016 [003] 3683.393106 cpu-soaker-5005 [003] 3683.395119 cpu-soaker-5017 [003] 3683.397130 cpu-soaker-5004 [003] 3683.399143 cpu-soaker-5016 [003] 3683.401155 cpu-soaker-5005 [003] 3683.403168 cpu-soaker-5017 [003] 3683.405170 AFTER: taskgroup_1 threads [21890, 21891], taskgroup_2 threads [21934, 21935] cpu-soaker-21890 [003] 865.895494 cpu-soaker-21935 [003] 865.897506 cpu-soaker-21934 [003] 865.899520 cpu-soaker-21935 [003] 865.901532 cpu-soaker-21934 [003] 865.903543 cpu-soaker-21935 [003] 865.905546 cpu-soaker-21891 [003] 865.907548 cpu-soaker-21890 [003] 865.909560 cpu-soaker-21891 [003] 865.911571 cpu-soaker-21890 [003] 865.913582 cpu-soaker-21891 [003] 865.915594 cpu-soaker-21934 [003] 865.917606 Similar problem is there when there are multiple taskgroups and say a task A preempts currently running task B of taskgroup_1. On schedule, pick_next_task can pick an unrelated task on taskgroup_2. Here it would be better to give some preference to task B on pick_next_task. A simple (may be extreme case) benchmark I tried was tbench with 2 tbench client processes with 2 threads each running on a single CPU. Avg throughput across 5 50 sec runs was: BEFORE: 105.84 MB/sec AFTER: 112.42 MB/sec Signed-off-by: Venkatesh Pallipadi <venki@google.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1302802253-25760-1-git-send-email-venki@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-14 17:30:53 +00:00
}
return;
preempt:
resched_curr(rq);
/*
* Only set the backward buddy when the current task is still
* on the rq. This can happen when a wakeup gets interleaved
* with schedule on the ->pre_schedule() or idle_balance()
* point, either of which can * drop the rq lock.
*
* Also, during early boot the idle thread is in the fair class,
* for obvious reasons its a bad idea to schedule back to it.
*/
if (unlikely(!se->on_rq || curr == rq->idle))
return;
if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
set_last_buddy(se);
}
static struct task_struct *
pick_next_task_fair(struct rq *rq, struct task_struct *prev)
{
struct cfs_rq *cfs_rq = &rq->cfs;
struct sched_entity *se;
struct task_struct *p;
int new_tasks;
again:
#ifdef CONFIG_FAIR_GROUP_SCHED
if (!cfs_rq->nr_running)
goto idle;
sched: Fix hotplug task migration Dan Carpenter reported: > kernel/sched/rt.c:1347 pick_next_task_rt() warn: variable dereferenced before check 'prev' (see line 1338) > kernel/sched/deadline.c:1011 pick_next_task_dl() warn: variable dereferenced before check 'prev' (see line 1005) Kirill also spotted that migrate_tasks() will have an instant NULL deref because pick_next_task() will immediately deref prev. Instead of fixing all the corner cases because migrate_tasks() can pass in a NULL prev task in the unlikely case of hot-un-plug, provide a fake task such that we can remove all the NULL checks from the far more common paths. A further problem; not previously spotted; is that because we pushed pre_schedule() and idle_balance() into pick_next_task() we now need to avoid those getting called and pulling more tasks on our dying CPU. We avoid pull_{dl,rt}_task() by setting fake_task.prio to MAX_PRIO+1. We also note that since we call pick_next_task() exactly the amount of times we have runnable tasks present, we should never land in idle_balance(). Fixes: 38033c37faab ("sched: Push down pre_schedule() and idle_balance()") Cc: Juri Lelli <juri.lelli@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Steven Rostedt <rostedt@goodmis.org> Reported-by: Kirill Tkhai <tkhai@yandex.ru> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20140212094930.GB3545@laptop.programming.kicks-ass.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-02-12 09:49:30 +00:00
if (prev->sched_class != &fair_sched_class)
goto simple;
/*
* Because of the set_next_buddy() in dequeue_task_fair() it is rather
* likely that a next task is from the same cgroup as the current.
*
* Therefore attempt to avoid putting and setting the entire cgroup
* hierarchy, only change the part that actually changes.
*/
do {
struct sched_entity *curr = cfs_rq->curr;
/*
* Since we got here without doing put_prev_entity() we also
* have to consider cfs_rq->curr. If it is still a runnable
* entity, update_curr() will update its vruntime, otherwise
* forget we've ever seen it.
*/
sched/fair: Prevent throttling in early pick_next_task_fair() The optimized task selection logic optimistically selects a new task to run without first doing a full put_prev_task(). This is so that we can avoid a put/set on the common ancestors of the old and new task. Similarly, we should only call check_cfs_rq_runtime() to throttle eligible groups if they're part of the common ancestry, otherwise it is possible to end up with no eligible task in the simple task selection. Imagine: /root /prev /next /A /B If our optimistic selection ends up throttling /next, we goto simple and our put_prev_task() ends up throttling /prev, after which we're going to bug out in set_next_entity() because there aren't any tasks left. Avoid this scenario by only throttling common ancestors. Reported-by: Mohammed Naser <mnaser@vexxhost.com> Reported-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Signed-off-by: Ben Segall <bsegall@google.com> [ munged Changelog ] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: pjt@google.com Fixes: 678d5718d8d0 ("sched/fair: Optimize cgroup pick_next_task_fair()") Link: http://lkml.kernel.org/r/xm26wq1oswoq.fsf@sword-of-the-dawn.mtv.corp.google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-06 22:28:10 +00:00
if (curr) {
if (curr->on_rq)
update_curr(cfs_rq);
else
curr = NULL;
sched/fair: Prevent throttling in early pick_next_task_fair() The optimized task selection logic optimistically selects a new task to run without first doing a full put_prev_task(). This is so that we can avoid a put/set on the common ancestors of the old and new task. Similarly, we should only call check_cfs_rq_runtime() to throttle eligible groups if they're part of the common ancestry, otherwise it is possible to end up with no eligible task in the simple task selection. Imagine: /root /prev /next /A /B If our optimistic selection ends up throttling /next, we goto simple and our put_prev_task() ends up throttling /prev, after which we're going to bug out in set_next_entity() because there aren't any tasks left. Avoid this scenario by only throttling common ancestors. Reported-by: Mohammed Naser <mnaser@vexxhost.com> Reported-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Signed-off-by: Ben Segall <bsegall@google.com> [ munged Changelog ] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: pjt@google.com Fixes: 678d5718d8d0 ("sched/fair: Optimize cgroup pick_next_task_fair()") Link: http://lkml.kernel.org/r/xm26wq1oswoq.fsf@sword-of-the-dawn.mtv.corp.google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-06 22:28:10 +00:00
/*
* This call to check_cfs_rq_runtime() will do the
* throttle and dequeue its entity in the parent(s).
* Therefore the 'simple' nr_running test will indeed
* be correct.
*/
if (unlikely(check_cfs_rq_runtime(cfs_rq)))
goto simple;
}
se = pick_next_entity(cfs_rq, curr);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
p = task_of(se);
/*
* Since we haven't yet done put_prev_entity and if the selected task
* is a different task than we started out with, try and touch the
* least amount of cfs_rqs.
*/
if (prev != p) {
struct sched_entity *pse = &prev->se;
while (!(cfs_rq = is_same_group(se, pse))) {
int se_depth = se->depth;
int pse_depth = pse->depth;
if (se_depth <= pse_depth) {
put_prev_entity(cfs_rq_of(pse), pse);
pse = parent_entity(pse);
}
if (se_depth >= pse_depth) {
set_next_entity(cfs_rq_of(se), se);
se = parent_entity(se);
}
}
put_prev_entity(cfs_rq, pse);
set_next_entity(cfs_rq, se);
}
if (hrtick_enabled(rq))
hrtick_start_fair(rq, p);
return p;
simple:
cfs_rq = &rq->cfs;
#endif
if (!cfs_rq->nr_running)
goto idle;
sched: Fix hotplug task migration Dan Carpenter reported: > kernel/sched/rt.c:1347 pick_next_task_rt() warn: variable dereferenced before check 'prev' (see line 1338) > kernel/sched/deadline.c:1011 pick_next_task_dl() warn: variable dereferenced before check 'prev' (see line 1005) Kirill also spotted that migrate_tasks() will have an instant NULL deref because pick_next_task() will immediately deref prev. Instead of fixing all the corner cases because migrate_tasks() can pass in a NULL prev task in the unlikely case of hot-un-plug, provide a fake task such that we can remove all the NULL checks from the far more common paths. A further problem; not previously spotted; is that because we pushed pre_schedule() and idle_balance() into pick_next_task() we now need to avoid those getting called and pulling more tasks on our dying CPU. We avoid pull_{dl,rt}_task() by setting fake_task.prio to MAX_PRIO+1. We also note that since we call pick_next_task() exactly the amount of times we have runnable tasks present, we should never land in idle_balance(). Fixes: 38033c37faab ("sched: Push down pre_schedule() and idle_balance()") Cc: Juri Lelli <juri.lelli@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Steven Rostedt <rostedt@goodmis.org> Reported-by: Kirill Tkhai <tkhai@yandex.ru> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20140212094930.GB3545@laptop.programming.kicks-ass.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-02-12 09:49:30 +00:00
put_prev_task(rq, prev);
do {
se = pick_next_entity(cfs_rq, NULL);
set_next_entity(cfs_rq, se);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
p = task_of(se);
sched: Save some hrtick_start_fair cycles hrtick_start_fair() shows up in profiles even when disabled. v3.0.6 taskset -c 3 pipe-test PerfTop: 997 irqs/sec kernel:89.5% exact: 0.0% [1000Hz cycles], (all, CPU: 3) ------------------------------------------------------------------------------------------------ Virgin Patched samples pcnt function samples pcnt function _______ _____ ___________________________ _______ _____ ___________________________ 2880.00 10.2% __schedule 3136.00 11.3% __schedule 1634.00 5.8% pipe_read 1615.00 5.8% pipe_read 1458.00 5.2% system_call 1534.00 5.5% system_call 1382.00 4.9% _raw_spin_lock_irqsave 1412.00 5.1% _raw_spin_lock_irqsave 1202.00 4.3% pipe_write 1255.00 4.5% copy_user_generic_string 1164.00 4.1% copy_user_generic_string 1241.00 4.5% __switch_to 1097.00 3.9% __switch_to 929.00 3.3% mutex_lock 872.00 3.1% mutex_lock 846.00 3.0% mutex_unlock 687.00 2.4% mutex_unlock 804.00 2.9% pipe_write 682.00 2.4% native_sched_clock 713.00 2.6% native_sched_clock 643.00 2.3% system_call_after_swapgs 653.00 2.3% _raw_spin_unlock_irqrestore 617.00 2.2% sched_clock_local 633.00 2.3% fsnotify 612.00 2.2% fsnotify 605.00 2.2% sched_clock_local 596.00 2.1% _raw_spin_unlock_irqrestore 593.00 2.1% system_call_after_swapgs 542.00 1.9% sysret_check 559.00 2.0% sysret_check 467.00 1.7% fget_light 472.00 1.7% fget_light 462.00 1.6% finish_task_switch 461.00 1.7% finish_task_switch 437.00 1.5% vfs_write 442.00 1.6% vfs_write 431.00 1.5% do_sync_write 428.00 1.5% do_sync_write 413.00 1.5% select_task_rq_fair 404.00 1.5% _raw_spin_lock_irq 386.00 1.4% update_curr 402.00 1.4% update_curr 385.00 1.4% rw_verify_area 389.00 1.4% do_sync_read 377.00 1.3% _raw_spin_lock_irq 378.00 1.4% vfs_read 369.00 1.3% do_sync_read 340.00 1.2% pipe_iov_copy_from_user 360.00 1.3% vfs_read 316.00 1.1% __wake_up_sync_key * 342.00 1.2% hrtick_start_fair 313.00 1.1% __wake_up_common Signed-off-by: Mike Galbraith <efault@gmx.de> [ fixed !CONFIG_SCHED_HRTICK borkage ] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1321971607.6855.17.camel@marge.simson.net Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-11-22 14:20:07 +00:00
if (hrtick_enabled(rq))
hrtick_start_fair(rq, p);
return p;
idle:
/*
* This is OK, because current is on_cpu, which avoids it being picked
* for load-balance and preemption/IRQs are still disabled avoiding
* further scheduler activity on it and we're being very careful to
* re-start the picking loop.
*/
lockdep_unpin_lock(&rq->lock);
new_tasks = idle_balance(rq);
lockdep_pin_lock(&rq->lock);
/*
* Because idle_balance() releases (and re-acquires) rq->lock, it is
* possible for any higher priority task to appear. In that case we
* must re-start the pick_next_entity() loop.
*/
if (new_tasks < 0)
return RETRY_TASK;
if (new_tasks > 0)
goto again;
return NULL;
}
/*
* Account for a descheduled task:
*/
static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
{
struct sched_entity *se = &prev->se;
struct cfs_rq *cfs_rq;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
put_prev_entity(cfs_rq, se);
}
}
/*
* sched_yield() is very simple
*
* The magic of dealing with the ->skip buddy is in pick_next_entity.
*/
static void yield_task_fair(struct rq *rq)
{
struct task_struct *curr = rq->curr;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
struct sched_entity *se = &curr->se;
/*
* Are we the only task in the tree?
*/
if (unlikely(rq->nr_running == 1))
return;
clear_buddies(cfs_rq, se);
if (curr->policy != SCHED_BATCH) {
update_rq_clock(rq);
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
/*
* Tell update_rq_clock() that we've just updated,
* so we don't do microscopic update in schedule()
* and double the fastpath cost.
*/
rq_clock_skip_update(rq, true);
}
set_skip_buddy(se);
}
static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt)
{
struct sched_entity *se = &p->se;
/* throttled hierarchies are not runnable */
if (!se->on_rq || throttled_hierarchy(cfs_rq_of(se)))
return false;
/* Tell the scheduler that we'd really like pse to run next. */
set_next_buddy(se);
yield_task_fair(rq);
return true;
}
#ifdef CONFIG_SMP
/**************************************************
* Fair scheduling class load-balancing methods.
*
* BASICS
*
* The purpose of load-balancing is to achieve the same basic fairness the
* per-cpu scheduler provides, namely provide a proportional amount of compute
* time to each task. This is expressed in the following equation:
*
* W_i,n/P_i == W_j,n/P_j for all i,j (1)
*
* Where W_i,n is the n-th weight average for cpu i. The instantaneous weight
* W_i,0 is defined as:
*
* W_i,0 = \Sum_j w_i,j (2)
*
* Where w_i,j is the weight of the j-th runnable task on cpu i. This weight
* is derived from the nice value as per prio_to_weight[].
*
* The weight average is an exponential decay average of the instantaneous
* weight:
*
* W'_i,n = (2^n - 1) / 2^n * W_i,n + 1 / 2^n * W_i,0 (3)
*
* C_i is the compute capacity of cpu i, typically it is the
* fraction of 'recent' time available for SCHED_OTHER task execution. But it
* can also include other factors [XXX].
*
* To achieve this balance we define a measure of imbalance which follows
* directly from (1):
*
* imb_i,j = max{ avg(W/C), W_i/C_i } - min{ avg(W/C), W_j/C_j } (4)
*
* We them move tasks around to minimize the imbalance. In the continuous
* function space it is obvious this converges, in the discrete case we get
* a few fun cases generally called infeasible weight scenarios.
*
* [XXX expand on:
* - infeasible weights;
* - local vs global optima in the discrete case. ]
*
*
* SCHED DOMAINS
*
* In order to solve the imbalance equation (4), and avoid the obvious O(n^2)
* for all i,j solution, we create a tree of cpus that follows the hardware
* topology where each level pairs two lower groups (or better). This results
* in O(log n) layers. Furthermore we reduce the number of cpus going up the
* tree to only the first of the previous level and we decrease the frequency
* of load-balance at each level inv. proportional to the number of cpus in
* the groups.
*
* This yields:
*
* log_2 n 1 n
* \Sum { --- * --- * 2^i } = O(n) (5)
* i = 0 2^i 2^i
* `- size of each group
* | | `- number of cpus doing load-balance
* | `- freq
* `- sum over all levels
*
* Coupled with a limit on how many tasks we can migrate every balance pass,
* this makes (5) the runtime complexity of the balancer.
*
* An important property here is that each CPU is still (indirectly) connected
* to every other cpu in at most O(log n) steps:
*
* The adjacency matrix of the resulting graph is given by:
*
* log_2 n
* A_i,j = \Union (i % 2^k == 0) && i / 2^(k+1) == j / 2^(k+1) (6)
* k = 0
*
* And you'll find that:
*
* A^(log_2 n)_i,j != 0 for all i,j (7)
*
* Showing there's indeed a path between every cpu in at most O(log n) steps.
* The task movement gives a factor of O(m), giving a convergence complexity
* of:
*
* O(nm log n), n := nr_cpus, m := nr_tasks (8)
*
*
* WORK CONSERVING
*
* In order to avoid CPUs going idle while there's still work to do, new idle
* balancing is more aggressive and has the newly idle cpu iterate up the domain
* tree itself instead of relying on other CPUs to bring it work.
*
* This adds some complexity to both (5) and (8) but it reduces the total idle
* time.
*
* [XXX more?]
*
*
* CGROUPS
*
* Cgroups make a horror show out of (2), instead of a simple sum we get:
*
* s_k,i
* W_i,0 = \Sum_j \Prod_k w_k * ----- (9)
* S_k
*
* Where
*
* s_k,i = \Sum_j w_i,j,k and S_k = \Sum_i s_k,i (10)
*
* w_i,j,k is the weight of the j-th runnable task in the k-th cgroup on cpu i.
*
* The big problem is S_k, its a global sum needed to compute a local (W_i)
* property.
*
* [XXX write more on how we solve this.. _after_ merging pjt's patches that
* rewrite all of this once again.]
*/
static unsigned long __read_mostly max_load_balance_interval = HZ/10;
enum fbq_type { regular, remote, all };
#define LBF_ALL_PINNED 0x01
#define LBF_NEED_BREAK 0x02
#define LBF_DST_PINNED 0x04
#define LBF_SOME_PINNED 0x08
struct lb_env {
struct sched_domain *sd;
struct rq *src_rq;
int src_cpu;
int dst_cpu;
struct rq *dst_rq;
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
struct cpumask *dst_grpmask;
int new_dst_cpu;
enum cpu_idle_type idle;
long imbalance;
/* The set of CPUs under consideration for load-balancing */
struct cpumask *cpus;
unsigned int flags;
unsigned int loop;
unsigned int loop_break;
unsigned int loop_max;
enum fbq_type fbq_type;
struct list_head tasks;
};
/*
* Is this task likely cache-hot:
*/
static int task_hot(struct task_struct *p, struct lb_env *env)
{
s64 delta;
lockdep_assert_held(&env->src_rq->lock);
if (p->sched_class != &fair_sched_class)
return 0;
if (unlikely(p->policy == SCHED_IDLE))
return 0;
/*
* Buddy candidates are cache hot:
*/
if (sched_feat(CACHE_HOT_BUDDY) && env->dst_rq->nr_running &&
(&p->se == cfs_rq_of(&p->se)->next ||
&p->se == cfs_rq_of(&p->se)->last))
return 1;
if (sysctl_sched_migration_cost == -1)
return 1;
if (sysctl_sched_migration_cost == 0)
return 0;
delta = rq_clock_task(env->src_rq) - p->se.exec_start;
return delta < (s64)sysctl_sched_migration_cost;
}
#ifdef CONFIG_NUMA_BALANCING
/*
* Returns 1, if task migration degrades locality
* Returns 0, if task migration improves locality i.e migration preferred.
* Returns -1, if task migration is not affected by locality.
*/
static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
{
struct numa_group *numa_group = rcu_dereference(p->numa_group);
unsigned long src_faults, dst_faults;
int src_nid, dst_nid;
if (!static_branch_likely(&sched_numa_balancing))
return -1;
if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
return -1;
src_nid = cpu_to_node(env->src_cpu);
dst_nid = cpu_to_node(env->dst_cpu);
if (src_nid == dst_nid)
return -1;
/* Migrating away from the preferred node is always bad. */
if (src_nid == p->numa_preferred_nid) {
if (env->src_rq->nr_running > env->src_rq->nr_preferred_running)
return 1;
else
return -1;
}
/* Encourage migration to the preferred node. */
if (dst_nid == p->numa_preferred_nid)
return 0;
if (numa_group) {
src_faults = group_faults(p, src_nid);
dst_faults = group_faults(p, dst_nid);
} else {
src_faults = task_faults(p, src_nid);
dst_faults = task_faults(p, dst_nid);
}
return dst_faults < src_faults;
}
#else
static inline int migrate_degrades_locality(struct task_struct *p,
struct lb_env *env)
{
return -1;
}
#endif
/*
* can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
*/
static
int can_migrate_task(struct task_struct *p, struct lb_env *env)
{
int tsk_cache_hot;
lockdep_assert_held(&env->src_rq->lock);
/*
* We do not migrate tasks that are:
* 1) throttled_lb_pair, or
* 2) cannot be migrated to this CPU due to cpus_allowed, or
* 3) running (obviously), or
* 4) are cache-hot on their current CPU.
*/
if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
return 0;
if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) {
int cpu;
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
env->flags |= LBF_SOME_PINNED;
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
/*
* Remember if this task can be migrated to any other cpu in
* our sched_group. We may want to revisit it if we couldn't
* meet load balance goals by pulling other tasks on src_cpu.
*
* Also avoid computing new_dst_cpu if we have already computed
* one in current iteration.
*/
if (!env->dst_grpmask || (env->flags & LBF_DST_PINNED))
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
return 0;
/* Prevent to re-select dst_cpu via env's cpus */
for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) {
if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) {
env->flags |= LBF_DST_PINNED;
env->new_dst_cpu = cpu;
break;
}
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
}
return 0;
}
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
/* Record that we found atleast one task that could run on dst_cpu */
env->flags &= ~LBF_ALL_PINNED;
if (task_running(env->src_rq, p)) {
schedstat_inc(p, se.statistics.nr_failed_migrations_running);
return 0;
}
/*
* Aggressive migration if:
* 1) destination numa is preferred
* 2) task is cache cold, or
* 3) too many balance attempts have failed.
*/
tsk_cache_hot = migrate_degrades_locality(p, env);
if (tsk_cache_hot == -1)
tsk_cache_hot = task_hot(p, env);
if (tsk_cache_hot <= 0 ||
env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
if (tsk_cache_hot == 1) {
schedstat_inc(env->sd, lb_hot_gained[env->idle]);
schedstat_inc(p, se.statistics.nr_forced_migrations);
}
return 1;
}
schedstat_inc(p, se.statistics.nr_failed_migrations_hot);
return 0;
}
/*
* detach_task() -- detach the task for the migration specified in env
*/
static void detach_task(struct task_struct *p, struct lb_env *env)
{
lockdep_assert_held(&env->src_rq->lock);
deactivate_task(env->src_rq, p, 0);
p->on_rq = TASK_ON_RQ_MIGRATING;
set_task_cpu(p, env->dst_cpu);
}
/*
* detach_one_task() -- tries to dequeue exactly one task from env->src_rq, as
* part of active balancing operations within "domain".
*
* Returns a task if successful and NULL otherwise.
*/
static struct task_struct *detach_one_task(struct lb_env *env)
{
struct task_struct *p, *n;
lockdep_assert_held(&env->src_rq->lock);
list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) {
if (!can_migrate_task(p, env))
continue;
detach_task(p, env);
/*
* Right now, this is only the second place where
* lb_gained[env->idle] is updated (other is detach_tasks)
* so we can safely collect stats here rather than
* inside detach_tasks().
*/
schedstat_inc(env->sd, lb_gained[env->idle]);
return p;
}
return NULL;
}
static const unsigned int sched_nr_migrate_break = 32;
/*
* detach_tasks() -- tries to detach up to imbalance weighted load from
* busiest_rq, as part of a balancing operation within domain "sd".
*
* Returns number of detached tasks if successful and 0 otherwise.
*/
static int detach_tasks(struct lb_env *env)
{
struct list_head *tasks = &env->src_rq->cfs_tasks;
struct task_struct *p;
unsigned long load;
int detached = 0;
lockdep_assert_held(&env->src_rq->lock);
if (env->imbalance <= 0)
return 0;
while (!list_empty(tasks)) {
/*
* We don't want to steal all, otherwise we may be treated likewise,
* which could at worst lead to a livelock crash.
*/
if (env->idle != CPU_NOT_IDLE && env->src_rq->nr_running <= 1)
break;
p = list_first_entry(tasks, struct task_struct, se.group_node);
env->loop++;
/* We've more or less seen every task there is, call it quits */
if (env->loop > env->loop_max)
break;
/* take a breather every nr_migrate tasks */
if (env->loop > env->loop_break) {
env->loop_break += sched_nr_migrate_break;
env->flags |= LBF_NEED_BREAK;
break;
}
if (!can_migrate_task(p, env))
goto next;
load = task_h_load(p);
if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
goto next;
if ((load / 2) > env->imbalance)
goto next;
detach_task(p, env);
list_add(&p->se.group_node, &env->tasks);
detached++;
env->imbalance -= load;
#ifdef CONFIG_PREEMPT
/*
* NEWIDLE balancing is a source of latency, so preemptible
* kernels will stop after the first task is detached to minimize
* the critical section.
*/
if (env->idle == CPU_NEWLY_IDLE)
break;
#endif
/*
* We only want to steal up to the prescribed amount of
* weighted load.
*/
if (env->imbalance <= 0)
break;
continue;
next:
list_move_tail(&p->se.group_node, tasks);
}
/*
* Right now, this is one of only two places we collect this stat
* so we can safely collect detach_one_task() stats here rather
* than inside detach_one_task().
*/
schedstat_add(env->sd, lb_gained[env->idle], detached);
return detached;
}
/*
* attach_task() -- attach the task detached by detach_task() to its new rq.
*/
static void attach_task(struct rq *rq, struct task_struct *p)
{
lockdep_assert_held(&rq->lock);
BUG_ON(task_rq(p) != rq);
p->on_rq = TASK_ON_RQ_QUEUED;
activate_task(rq, p, 0);
check_preempt_curr(rq, p, 0);
}
/*
* attach_one_task() -- attaches the task returned from detach_one_task() to
* its new rq.
*/
static void attach_one_task(struct rq *rq, struct task_struct *p)
{
raw_spin_lock(&rq->lock);
attach_task(rq, p);
raw_spin_unlock(&rq->lock);
}
/*
* attach_tasks() -- attaches all tasks detached by detach_tasks() to their
* new rq.
*/
static void attach_tasks(struct lb_env *env)
{
struct list_head *tasks = &env->tasks;
struct task_struct *p;
raw_spin_lock(&env->dst_rq->lock);
while (!list_empty(tasks)) {
p = list_first_entry(tasks, struct task_struct, se.group_node);
list_del_init(&p->se.group_node);
attach_task(env->dst_rq, p);
}
raw_spin_unlock(&env->dst_rq->lock);
}
#ifdef CONFIG_FAIR_GROUP_SCHED
static void update_blocked_averages(int cpu)
{
struct rq *rq = cpu_rq(cpu);
struct cfs_rq *cfs_rq;
unsigned long flags;
raw_spin_lock_irqsave(&rq->lock, flags);
update_rq_clock(rq);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
/*
* Iterates the task_group tree in a bottom up fashion, see
* list_add_leaf_cfs_rq() for details.
*/
for_each_leaf_cfs_rq(rq, cfs_rq) {
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
/* throttled entities do not contribute to load */
if (throttled_hierarchy(cfs_rq))
continue;
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq))
update_tg_load_avg(cfs_rq, 0);
}
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
/*
sched: Move h_load calculation to task_h_load() The bad thing about update_h_load(), which computes hierarchical load factor for task groups, is that it is called for each task group in the system before every load balancer run, and since rebalance can be triggered very often, this function can eat really a lot of cpu time if there are many cpu cgroups in the system. Although the situation was improved significantly by commit a35b646 ('sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies'), the problem still can arise under some kinds of loads, e.g. when cpus are switching from idle to busy and back very frequently. For instance, when I start 1000 of processes that wake up every millisecond on my 8 cpus host, 'top' and 'perf top' show: Cpu(s): 17.8%us, 24.3%sy, 0.0%ni, 57.9%id, 0.0%wa, 0.0%hi, 0.0%si Events: 243K cycles 7.57% [kernel] [k] __schedule 7.08% [kernel] [k] timerqueue_add 6.13% libc-2.12.so [.] usleep Then if I create 10000 *idle* cpu cgroups (no processes in them), cpu usage increases significantly although the 'wakers' are still executing in the root cpu cgroup: Cpu(s): 19.1%us, 48.7%sy, 0.0%ni, 31.6%id, 0.0%wa, 0.0%hi, 0.7%si Events: 230K cycles 24.56% [kernel] [k] tg_load_down 5.76% [kernel] [k] __schedule This happens because this particular kind of load triggers 'new idle' rebalance very frequently, which requires calling update_h_load(), which, in turn, calls tg_load_down() for every *idle* cpu cgroup even though it is absolutely useless, because idle cpu cgroups have no tasks to pull. This patch tries to improve the situation by making h_load calculation proceed only when h_load is really necessary. To achieve this, it substitutes update_h_load() with update_cfs_rq_h_load(), which computes h_load only for a given cfs_rq and all its ascendants, and makes the load balancer call this function whenever it considers if a task should be pulled, i.e. it moves h_load calculations directly to task_h_load(). For h_load of the same cfs_rq not to be updated multiple times (in case several tasks in the same cgroup are considered during the same balance run), the patch keeps the time of the last h_load update for each cfs_rq and breaks calculation when it finds h_load to be uptodate. The benefit of it is that h_load is computed only for those cfs_rq's, which really need it, in particular all idle task groups are skipped. Although this, in fact, moves h_load calculation under rq lock, it should not affect latency much, because the amount of work done under rq lock while trying to pull tasks is limited by sched_nr_migrate. After the patch applied with the setup described above (1000 wakers in the root cgroup and 10000 idle cgroups), I get: Cpu(s): 16.9%us, 24.8%sy, 0.0%ni, 58.4%id, 0.0%wa, 0.0%hi, 0.0%si Events: 242K cycles 7.57% [kernel] [k] __schedule 6.70% [kernel] [k] timerqueue_add 5.93% libc-2.12.so [.] usleep Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1373896159-1278-1-git-send-email-vdavydov@parallels.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-15 13:49:19 +00:00
* Compute the hierarchical load factor for cfs_rq and all its ascendants.
* This needs to be done in a top-down fashion because the load of a child
* group is a fraction of its parents load.
*/
sched: Move h_load calculation to task_h_load() The bad thing about update_h_load(), which computes hierarchical load factor for task groups, is that it is called for each task group in the system before every load balancer run, and since rebalance can be triggered very often, this function can eat really a lot of cpu time if there are many cpu cgroups in the system. Although the situation was improved significantly by commit a35b646 ('sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies'), the problem still can arise under some kinds of loads, e.g. when cpus are switching from idle to busy and back very frequently. For instance, when I start 1000 of processes that wake up every millisecond on my 8 cpus host, 'top' and 'perf top' show: Cpu(s): 17.8%us, 24.3%sy, 0.0%ni, 57.9%id, 0.0%wa, 0.0%hi, 0.0%si Events: 243K cycles 7.57% [kernel] [k] __schedule 7.08% [kernel] [k] timerqueue_add 6.13% libc-2.12.so [.] usleep Then if I create 10000 *idle* cpu cgroups (no processes in them), cpu usage increases significantly although the 'wakers' are still executing in the root cpu cgroup: Cpu(s): 19.1%us, 48.7%sy, 0.0%ni, 31.6%id, 0.0%wa, 0.0%hi, 0.7%si Events: 230K cycles 24.56% [kernel] [k] tg_load_down 5.76% [kernel] [k] __schedule This happens because this particular kind of load triggers 'new idle' rebalance very frequently, which requires calling update_h_load(), which, in turn, calls tg_load_down() for every *idle* cpu cgroup even though it is absolutely useless, because idle cpu cgroups have no tasks to pull. This patch tries to improve the situation by making h_load calculation proceed only when h_load is really necessary. To achieve this, it substitutes update_h_load() with update_cfs_rq_h_load(), which computes h_load only for a given cfs_rq and all its ascendants, and makes the load balancer call this function whenever it considers if a task should be pulled, i.e. it moves h_load calculations directly to task_h_load(). For h_load of the same cfs_rq not to be updated multiple times (in case several tasks in the same cgroup are considered during the same balance run), the patch keeps the time of the last h_load update for each cfs_rq and breaks calculation when it finds h_load to be uptodate. The benefit of it is that h_load is computed only for those cfs_rq's, which really need it, in particular all idle task groups are skipped. Although this, in fact, moves h_load calculation under rq lock, it should not affect latency much, because the amount of work done under rq lock while trying to pull tasks is limited by sched_nr_migrate. After the patch applied with the setup described above (1000 wakers in the root cgroup and 10000 idle cgroups), I get: Cpu(s): 16.9%us, 24.8%sy, 0.0%ni, 58.4%id, 0.0%wa, 0.0%hi, 0.0%si Events: 242K cycles 7.57% [kernel] [k] __schedule 6.70% [kernel] [k] timerqueue_add 5.93% libc-2.12.so [.] usleep Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1373896159-1278-1-git-send-email-vdavydov@parallels.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-15 13:49:19 +00:00
static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
{
sched: Move h_load calculation to task_h_load() The bad thing about update_h_load(), which computes hierarchical load factor for task groups, is that it is called for each task group in the system before every load balancer run, and since rebalance can be triggered very often, this function can eat really a lot of cpu time if there are many cpu cgroups in the system. Although the situation was improved significantly by commit a35b646 ('sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies'), the problem still can arise under some kinds of loads, e.g. when cpus are switching from idle to busy and back very frequently. For instance, when I start 1000 of processes that wake up every millisecond on my 8 cpus host, 'top' and 'perf top' show: Cpu(s): 17.8%us, 24.3%sy, 0.0%ni, 57.9%id, 0.0%wa, 0.0%hi, 0.0%si Events: 243K cycles 7.57% [kernel] [k] __schedule 7.08% [kernel] [k] timerqueue_add 6.13% libc-2.12.so [.] usleep Then if I create 10000 *idle* cpu cgroups (no processes in them), cpu usage increases significantly although the 'wakers' are still executing in the root cpu cgroup: Cpu(s): 19.1%us, 48.7%sy, 0.0%ni, 31.6%id, 0.0%wa, 0.0%hi, 0.7%si Events: 230K cycles 24.56% [kernel] [k] tg_load_down 5.76% [kernel] [k] __schedule This happens because this particular kind of load triggers 'new idle' rebalance very frequently, which requires calling update_h_load(), which, in turn, calls tg_load_down() for every *idle* cpu cgroup even though it is absolutely useless, because idle cpu cgroups have no tasks to pull. This patch tries to improve the situation by making h_load calculation proceed only when h_load is really necessary. To achieve this, it substitutes update_h_load() with update_cfs_rq_h_load(), which computes h_load only for a given cfs_rq and all its ascendants, and makes the load balancer call this function whenever it considers if a task should be pulled, i.e. it moves h_load calculations directly to task_h_load(). For h_load of the same cfs_rq not to be updated multiple times (in case several tasks in the same cgroup are considered during the same balance run), the patch keeps the time of the last h_load update for each cfs_rq and breaks calculation when it finds h_load to be uptodate. The benefit of it is that h_load is computed only for those cfs_rq's, which really need it, in particular all idle task groups are skipped. Although this, in fact, moves h_load calculation under rq lock, it should not affect latency much, because the amount of work done under rq lock while trying to pull tasks is limited by sched_nr_migrate. After the patch applied with the setup described above (1000 wakers in the root cgroup and 10000 idle cgroups), I get: Cpu(s): 16.9%us, 24.8%sy, 0.0%ni, 58.4%id, 0.0%wa, 0.0%hi, 0.0%si Events: 242K cycles 7.57% [kernel] [k] __schedule 6.70% [kernel] [k] timerqueue_add 5.93% libc-2.12.so [.] usleep Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1373896159-1278-1-git-send-email-vdavydov@parallels.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-15 13:49:19 +00:00
struct rq *rq = rq_of(cfs_rq);
struct sched_entity *se = cfs_rq->tg->se[cpu_of(rq)];
sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies Peter Portante reported that for large cgroup hierarchies (and or on large CPU counts) we get immense lock contention on rq->lock and stuff stops working properly. His workload was a ton of processes, each in their own cgroup, everybody idling except for a sporadic wakeup once every so often. It was found that: schedule() idle_balance() load_balance() local_irq_save() double_rq_lock() update_h_load() walk_tg_tree(tg_load_down) tg_load_down() Results in an entire cgroup hierarchy walk under rq->lock for every new-idle balance and since new-idle balance isn't throttled this results in a lot of work while holding the rq->lock. This patch does two things, it removes the work from under rq->lock based on the good principle of race and pray which is widely employed in the load-balancer as a whole. And secondly it throttles the update_h_load() calculation to max once per jiffy. I considered excluding update_h_load() for new-idle balance all-together, but purely relying on regular balance passes to update this data might not work out under some rare circumstances where the new-idle busiest isn't the regular busiest for a while (unlikely, but a nightmare to debug if someone hits it and suffers). Cc: pjt@google.com Cc: Larry Woodman <lwoodman@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Reported-by: Peter Portante <pportant@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/n/tip-aaarrzfpnaam7pqrekofu8a6@git.kernel.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2012-08-08 19:46:40 +00:00
unsigned long now = jiffies;
sched: Move h_load calculation to task_h_load() The bad thing about update_h_load(), which computes hierarchical load factor for task groups, is that it is called for each task group in the system before every load balancer run, and since rebalance can be triggered very often, this function can eat really a lot of cpu time if there are many cpu cgroups in the system. Although the situation was improved significantly by commit a35b646 ('sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies'), the problem still can arise under some kinds of loads, e.g. when cpus are switching from idle to busy and back very frequently. For instance, when I start 1000 of processes that wake up every millisecond on my 8 cpus host, 'top' and 'perf top' show: Cpu(s): 17.8%us, 24.3%sy, 0.0%ni, 57.9%id, 0.0%wa, 0.0%hi, 0.0%si Events: 243K cycles 7.57% [kernel] [k] __schedule 7.08% [kernel] [k] timerqueue_add 6.13% libc-2.12.so [.] usleep Then if I create 10000 *idle* cpu cgroups (no processes in them), cpu usage increases significantly although the 'wakers' are still executing in the root cpu cgroup: Cpu(s): 19.1%us, 48.7%sy, 0.0%ni, 31.6%id, 0.0%wa, 0.0%hi, 0.7%si Events: 230K cycles 24.56% [kernel] [k] tg_load_down 5.76% [kernel] [k] __schedule This happens because this particular kind of load triggers 'new idle' rebalance very frequently, which requires calling update_h_load(), which, in turn, calls tg_load_down() for every *idle* cpu cgroup even though it is absolutely useless, because idle cpu cgroups have no tasks to pull. This patch tries to improve the situation by making h_load calculation proceed only when h_load is really necessary. To achieve this, it substitutes update_h_load() with update_cfs_rq_h_load(), which computes h_load only for a given cfs_rq and all its ascendants, and makes the load balancer call this function whenever it considers if a task should be pulled, i.e. it moves h_load calculations directly to task_h_load(). For h_load of the same cfs_rq not to be updated multiple times (in case several tasks in the same cgroup are considered during the same balance run), the patch keeps the time of the last h_load update for each cfs_rq and breaks calculation when it finds h_load to be uptodate. The benefit of it is that h_load is computed only for those cfs_rq's, which really need it, in particular all idle task groups are skipped. Although this, in fact, moves h_load calculation under rq lock, it should not affect latency much, because the amount of work done under rq lock while trying to pull tasks is limited by sched_nr_migrate. After the patch applied with the setup described above (1000 wakers in the root cgroup and 10000 idle cgroups), I get: Cpu(s): 16.9%us, 24.8%sy, 0.0%ni, 58.4%id, 0.0%wa, 0.0%hi, 0.0%si Events: 242K cycles 7.57% [kernel] [k] __schedule 6.70% [kernel] [k] timerqueue_add 5.93% libc-2.12.so [.] usleep Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1373896159-1278-1-git-send-email-vdavydov@parallels.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-15 13:49:19 +00:00
unsigned long load;
sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies Peter Portante reported that for large cgroup hierarchies (and or on large CPU counts) we get immense lock contention on rq->lock and stuff stops working properly. His workload was a ton of processes, each in their own cgroup, everybody idling except for a sporadic wakeup once every so often. It was found that: schedule() idle_balance() load_balance() local_irq_save() double_rq_lock() update_h_load() walk_tg_tree(tg_load_down) tg_load_down() Results in an entire cgroup hierarchy walk under rq->lock for every new-idle balance and since new-idle balance isn't throttled this results in a lot of work while holding the rq->lock. This patch does two things, it removes the work from under rq->lock based on the good principle of race and pray which is widely employed in the load-balancer as a whole. And secondly it throttles the update_h_load() calculation to max once per jiffy. I considered excluding update_h_load() for new-idle balance all-together, but purely relying on regular balance passes to update this data might not work out under some rare circumstances where the new-idle busiest isn't the regular busiest for a while (unlikely, but a nightmare to debug if someone hits it and suffers). Cc: pjt@google.com Cc: Larry Woodman <lwoodman@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Reported-by: Peter Portante <pportant@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/n/tip-aaarrzfpnaam7pqrekofu8a6@git.kernel.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2012-08-08 19:46:40 +00:00
sched: Move h_load calculation to task_h_load() The bad thing about update_h_load(), which computes hierarchical load factor for task groups, is that it is called for each task group in the system before every load balancer run, and since rebalance can be triggered very often, this function can eat really a lot of cpu time if there are many cpu cgroups in the system. Although the situation was improved significantly by commit a35b646 ('sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies'), the problem still can arise under some kinds of loads, e.g. when cpus are switching from idle to busy and back very frequently. For instance, when I start 1000 of processes that wake up every millisecond on my 8 cpus host, 'top' and 'perf top' show: Cpu(s): 17.8%us, 24.3%sy, 0.0%ni, 57.9%id, 0.0%wa, 0.0%hi, 0.0%si Events: 243K cycles 7.57% [kernel] [k] __schedule 7.08% [kernel] [k] timerqueue_add 6.13% libc-2.12.so [.] usleep Then if I create 10000 *idle* cpu cgroups (no processes in them), cpu usage increases significantly although the 'wakers' are still executing in the root cpu cgroup: Cpu(s): 19.1%us, 48.7%sy, 0.0%ni, 31.6%id, 0.0%wa, 0.0%hi, 0.7%si Events: 230K cycles 24.56% [kernel] [k] tg_load_down 5.76% [kernel] [k] __schedule This happens because this particular kind of load triggers 'new idle' rebalance very frequently, which requires calling update_h_load(), which, in turn, calls tg_load_down() for every *idle* cpu cgroup even though it is absolutely useless, because idle cpu cgroups have no tasks to pull. This patch tries to improve the situation by making h_load calculation proceed only when h_load is really necessary. To achieve this, it substitutes update_h_load() with update_cfs_rq_h_load(), which computes h_load only for a given cfs_rq and all its ascendants, and makes the load balancer call this function whenever it considers if a task should be pulled, i.e. it moves h_load calculations directly to task_h_load(). For h_load of the same cfs_rq not to be updated multiple times (in case several tasks in the same cgroup are considered during the same balance run), the patch keeps the time of the last h_load update for each cfs_rq and breaks calculation when it finds h_load to be uptodate. The benefit of it is that h_load is computed only for those cfs_rq's, which really need it, in particular all idle task groups are skipped. Although this, in fact, moves h_load calculation under rq lock, it should not affect latency much, because the amount of work done under rq lock while trying to pull tasks is limited by sched_nr_migrate. After the patch applied with the setup described above (1000 wakers in the root cgroup and 10000 idle cgroups), I get: Cpu(s): 16.9%us, 24.8%sy, 0.0%ni, 58.4%id, 0.0%wa, 0.0%hi, 0.0%si Events: 242K cycles 7.57% [kernel] [k] __schedule 6.70% [kernel] [k] timerqueue_add 5.93% libc-2.12.so [.] usleep Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1373896159-1278-1-git-send-email-vdavydov@parallels.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-15 13:49:19 +00:00
if (cfs_rq->last_h_load_update == now)
sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies Peter Portante reported that for large cgroup hierarchies (and or on large CPU counts) we get immense lock contention on rq->lock and stuff stops working properly. His workload was a ton of processes, each in their own cgroup, everybody idling except for a sporadic wakeup once every so often. It was found that: schedule() idle_balance() load_balance() local_irq_save() double_rq_lock() update_h_load() walk_tg_tree(tg_load_down) tg_load_down() Results in an entire cgroup hierarchy walk under rq->lock for every new-idle balance and since new-idle balance isn't throttled this results in a lot of work while holding the rq->lock. This patch does two things, it removes the work from under rq->lock based on the good principle of race and pray which is widely employed in the load-balancer as a whole. And secondly it throttles the update_h_load() calculation to max once per jiffy. I considered excluding update_h_load() for new-idle balance all-together, but purely relying on regular balance passes to update this data might not work out under some rare circumstances where the new-idle busiest isn't the regular busiest for a while (unlikely, but a nightmare to debug if someone hits it and suffers). Cc: pjt@google.com Cc: Larry Woodman <lwoodman@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Reported-by: Peter Portante <pportant@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/n/tip-aaarrzfpnaam7pqrekofu8a6@git.kernel.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2012-08-08 19:46:40 +00:00
return;
sched: Move h_load calculation to task_h_load() The bad thing about update_h_load(), which computes hierarchical load factor for task groups, is that it is called for each task group in the system before every load balancer run, and since rebalance can be triggered very often, this function can eat really a lot of cpu time if there are many cpu cgroups in the system. Although the situation was improved significantly by commit a35b646 ('sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies'), the problem still can arise under some kinds of loads, e.g. when cpus are switching from idle to busy and back very frequently. For instance, when I start 1000 of processes that wake up every millisecond on my 8 cpus host, 'top' and 'perf top' show: Cpu(s): 17.8%us, 24.3%sy, 0.0%ni, 57.9%id, 0.0%wa, 0.0%hi, 0.0%si Events: 243K cycles 7.57% [kernel] [k] __schedule 7.08% [kernel] [k] timerqueue_add 6.13% libc-2.12.so [.] usleep Then if I create 10000 *idle* cpu cgroups (no processes in them), cpu usage increases significantly although the 'wakers' are still executing in the root cpu cgroup: Cpu(s): 19.1%us, 48.7%sy, 0.0%ni, 31.6%id, 0.0%wa, 0.0%hi, 0.7%si Events: 230K cycles 24.56% [kernel] [k] tg_load_down 5.76% [kernel] [k] __schedule This happens because this particular kind of load triggers 'new idle' rebalance very frequently, which requires calling update_h_load(), which, in turn, calls tg_load_down() for every *idle* cpu cgroup even though it is absolutely useless, because idle cpu cgroups have no tasks to pull. This patch tries to improve the situation by making h_load calculation proceed only when h_load is really necessary. To achieve this, it substitutes update_h_load() with update_cfs_rq_h_load(), which computes h_load only for a given cfs_rq and all its ascendants, and makes the load balancer call this function whenever it considers if a task should be pulled, i.e. it moves h_load calculations directly to task_h_load(). For h_load of the same cfs_rq not to be updated multiple times (in case several tasks in the same cgroup are considered during the same balance run), the patch keeps the time of the last h_load update for each cfs_rq and breaks calculation when it finds h_load to be uptodate. The benefit of it is that h_load is computed only for those cfs_rq's, which really need it, in particular all idle task groups are skipped. Although this, in fact, moves h_load calculation under rq lock, it should not affect latency much, because the amount of work done under rq lock while trying to pull tasks is limited by sched_nr_migrate. After the patch applied with the setup described above (1000 wakers in the root cgroup and 10000 idle cgroups), I get: Cpu(s): 16.9%us, 24.8%sy, 0.0%ni, 58.4%id, 0.0%wa, 0.0%hi, 0.0%si Events: 242K cycles 7.57% [kernel] [k] __schedule 6.70% [kernel] [k] timerqueue_add 5.93% libc-2.12.so [.] usleep Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1373896159-1278-1-git-send-email-vdavydov@parallels.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-15 13:49:19 +00:00
cfs_rq->h_load_next = NULL;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
cfs_rq->h_load_next = se;
if (cfs_rq->last_h_load_update == now)
break;
}
sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies Peter Portante reported that for large cgroup hierarchies (and or on large CPU counts) we get immense lock contention on rq->lock and stuff stops working properly. His workload was a ton of processes, each in their own cgroup, everybody idling except for a sporadic wakeup once every so often. It was found that: schedule() idle_balance() load_balance() local_irq_save() double_rq_lock() update_h_load() walk_tg_tree(tg_load_down) tg_load_down() Results in an entire cgroup hierarchy walk under rq->lock for every new-idle balance and since new-idle balance isn't throttled this results in a lot of work while holding the rq->lock. This patch does two things, it removes the work from under rq->lock based on the good principle of race and pray which is widely employed in the load-balancer as a whole. And secondly it throttles the update_h_load() calculation to max once per jiffy. I considered excluding update_h_load() for new-idle balance all-together, but purely relying on regular balance passes to update this data might not work out under some rare circumstances where the new-idle busiest isn't the regular busiest for a while (unlikely, but a nightmare to debug if someone hits it and suffers). Cc: pjt@google.com Cc: Larry Woodman <lwoodman@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Reported-by: Peter Portante <pportant@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/n/tip-aaarrzfpnaam7pqrekofu8a6@git.kernel.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2012-08-08 19:46:40 +00:00
sched: Move h_load calculation to task_h_load() The bad thing about update_h_load(), which computes hierarchical load factor for task groups, is that it is called for each task group in the system before every load balancer run, and since rebalance can be triggered very often, this function can eat really a lot of cpu time if there are many cpu cgroups in the system. Although the situation was improved significantly by commit a35b646 ('sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies'), the problem still can arise under some kinds of loads, e.g. when cpus are switching from idle to busy and back very frequently. For instance, when I start 1000 of processes that wake up every millisecond on my 8 cpus host, 'top' and 'perf top' show: Cpu(s): 17.8%us, 24.3%sy, 0.0%ni, 57.9%id, 0.0%wa, 0.0%hi, 0.0%si Events: 243K cycles 7.57% [kernel] [k] __schedule 7.08% [kernel] [k] timerqueue_add 6.13% libc-2.12.so [.] usleep Then if I create 10000 *idle* cpu cgroups (no processes in them), cpu usage increases significantly although the 'wakers' are still executing in the root cpu cgroup: Cpu(s): 19.1%us, 48.7%sy, 0.0%ni, 31.6%id, 0.0%wa, 0.0%hi, 0.7%si Events: 230K cycles 24.56% [kernel] [k] tg_load_down 5.76% [kernel] [k] __schedule This happens because this particular kind of load triggers 'new idle' rebalance very frequently, which requires calling update_h_load(), which, in turn, calls tg_load_down() for every *idle* cpu cgroup even though it is absolutely useless, because idle cpu cgroups have no tasks to pull. This patch tries to improve the situation by making h_load calculation proceed only when h_load is really necessary. To achieve this, it substitutes update_h_load() with update_cfs_rq_h_load(), which computes h_load only for a given cfs_rq and all its ascendants, and makes the load balancer call this function whenever it considers if a task should be pulled, i.e. it moves h_load calculations directly to task_h_load(). For h_load of the same cfs_rq not to be updated multiple times (in case several tasks in the same cgroup are considered during the same balance run), the patch keeps the time of the last h_load update for each cfs_rq and breaks calculation when it finds h_load to be uptodate. The benefit of it is that h_load is computed only for those cfs_rq's, which really need it, in particular all idle task groups are skipped. Although this, in fact, moves h_load calculation under rq lock, it should not affect latency much, because the amount of work done under rq lock while trying to pull tasks is limited by sched_nr_migrate. After the patch applied with the setup described above (1000 wakers in the root cgroup and 10000 idle cgroups), I get: Cpu(s): 16.9%us, 24.8%sy, 0.0%ni, 58.4%id, 0.0%wa, 0.0%hi, 0.0%si Events: 242K cycles 7.57% [kernel] [k] __schedule 6.70% [kernel] [k] timerqueue_add 5.93% libc-2.12.so [.] usleep Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1373896159-1278-1-git-send-email-vdavydov@parallels.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-15 13:49:19 +00:00
if (!se) {
cfs_rq->h_load = cfs_rq_load_avg(cfs_rq);
sched: Move h_load calculation to task_h_load() The bad thing about update_h_load(), which computes hierarchical load factor for task groups, is that it is called for each task group in the system before every load balancer run, and since rebalance can be triggered very often, this function can eat really a lot of cpu time if there are many cpu cgroups in the system. Although the situation was improved significantly by commit a35b646 ('sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies'), the problem still can arise under some kinds of loads, e.g. when cpus are switching from idle to busy and back very frequently. For instance, when I start 1000 of processes that wake up every millisecond on my 8 cpus host, 'top' and 'perf top' show: Cpu(s): 17.8%us, 24.3%sy, 0.0%ni, 57.9%id, 0.0%wa, 0.0%hi, 0.0%si Events: 243K cycles 7.57% [kernel] [k] __schedule 7.08% [kernel] [k] timerqueue_add 6.13% libc-2.12.so [.] usleep Then if I create 10000 *idle* cpu cgroups (no processes in them), cpu usage increases significantly although the 'wakers' are still executing in the root cpu cgroup: Cpu(s): 19.1%us, 48.7%sy, 0.0%ni, 31.6%id, 0.0%wa, 0.0%hi, 0.7%si Events: 230K cycles 24.56% [kernel] [k] tg_load_down 5.76% [kernel] [k] __schedule This happens because this particular kind of load triggers 'new idle' rebalance very frequently, which requires calling update_h_load(), which, in turn, calls tg_load_down() for every *idle* cpu cgroup even though it is absolutely useless, because idle cpu cgroups have no tasks to pull. This patch tries to improve the situation by making h_load calculation proceed only when h_load is really necessary. To achieve this, it substitutes update_h_load() with update_cfs_rq_h_load(), which computes h_load only for a given cfs_rq and all its ascendants, and makes the load balancer call this function whenever it considers if a task should be pulled, i.e. it moves h_load calculations directly to task_h_load(). For h_load of the same cfs_rq not to be updated multiple times (in case several tasks in the same cgroup are considered during the same balance run), the patch keeps the time of the last h_load update for each cfs_rq and breaks calculation when it finds h_load to be uptodate. The benefit of it is that h_load is computed only for those cfs_rq's, which really need it, in particular all idle task groups are skipped. Although this, in fact, moves h_load calculation under rq lock, it should not affect latency much, because the amount of work done under rq lock while trying to pull tasks is limited by sched_nr_migrate. After the patch applied with the setup described above (1000 wakers in the root cgroup and 10000 idle cgroups), I get: Cpu(s): 16.9%us, 24.8%sy, 0.0%ni, 58.4%id, 0.0%wa, 0.0%hi, 0.0%si Events: 242K cycles 7.57% [kernel] [k] __schedule 6.70% [kernel] [k] timerqueue_add 5.93% libc-2.12.so [.] usleep Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1373896159-1278-1-git-send-email-vdavydov@parallels.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-15 13:49:19 +00:00
cfs_rq->last_h_load_update = now;
}
while ((se = cfs_rq->h_load_next) != NULL) {
load = cfs_rq->h_load;
load = div64_ul(load * se->avg.load_avg,
cfs_rq_load_avg(cfs_rq) + 1);
sched: Move h_load calculation to task_h_load() The bad thing about update_h_load(), which computes hierarchical load factor for task groups, is that it is called for each task group in the system before every load balancer run, and since rebalance can be triggered very often, this function can eat really a lot of cpu time if there are many cpu cgroups in the system. Although the situation was improved significantly by commit a35b646 ('sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies'), the problem still can arise under some kinds of loads, e.g. when cpus are switching from idle to busy and back very frequently. For instance, when I start 1000 of processes that wake up every millisecond on my 8 cpus host, 'top' and 'perf top' show: Cpu(s): 17.8%us, 24.3%sy, 0.0%ni, 57.9%id, 0.0%wa, 0.0%hi, 0.0%si Events: 243K cycles 7.57% [kernel] [k] __schedule 7.08% [kernel] [k] timerqueue_add 6.13% libc-2.12.so [.] usleep Then if I create 10000 *idle* cpu cgroups (no processes in them), cpu usage increases significantly although the 'wakers' are still executing in the root cpu cgroup: Cpu(s): 19.1%us, 48.7%sy, 0.0%ni, 31.6%id, 0.0%wa, 0.0%hi, 0.7%si Events: 230K cycles 24.56% [kernel] [k] tg_load_down 5.76% [kernel] [k] __schedule This happens because this particular kind of load triggers 'new idle' rebalance very frequently, which requires calling update_h_load(), which, in turn, calls tg_load_down() for every *idle* cpu cgroup even though it is absolutely useless, because idle cpu cgroups have no tasks to pull. This patch tries to improve the situation by making h_load calculation proceed only when h_load is really necessary. To achieve this, it substitutes update_h_load() with update_cfs_rq_h_load(), which computes h_load only for a given cfs_rq and all its ascendants, and makes the load balancer call this function whenever it considers if a task should be pulled, i.e. it moves h_load calculations directly to task_h_load(). For h_load of the same cfs_rq not to be updated multiple times (in case several tasks in the same cgroup are considered during the same balance run), the patch keeps the time of the last h_load update for each cfs_rq and breaks calculation when it finds h_load to be uptodate. The benefit of it is that h_load is computed only for those cfs_rq's, which really need it, in particular all idle task groups are skipped. Although this, in fact, moves h_load calculation under rq lock, it should not affect latency much, because the amount of work done under rq lock while trying to pull tasks is limited by sched_nr_migrate. After the patch applied with the setup described above (1000 wakers in the root cgroup and 10000 idle cgroups), I get: Cpu(s): 16.9%us, 24.8%sy, 0.0%ni, 58.4%id, 0.0%wa, 0.0%hi, 0.0%si Events: 242K cycles 7.57% [kernel] [k] __schedule 6.70% [kernel] [k] timerqueue_add 5.93% libc-2.12.so [.] usleep Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1373896159-1278-1-git-send-email-vdavydov@parallels.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-15 13:49:19 +00:00
cfs_rq = group_cfs_rq(se);
cfs_rq->h_load = load;
cfs_rq->last_h_load_update = now;
}
}
static unsigned long task_h_load(struct task_struct *p)
{
struct cfs_rq *cfs_rq = task_cfs_rq(p);
sched: Move h_load calculation to task_h_load() The bad thing about update_h_load(), which computes hierarchical load factor for task groups, is that it is called for each task group in the system before every load balancer run, and since rebalance can be triggered very often, this function can eat really a lot of cpu time if there are many cpu cgroups in the system. Although the situation was improved significantly by commit a35b646 ('sched, cgroup: Reduce rq->lock hold times for large cgroup hierarchies'), the problem still can arise under some kinds of loads, e.g. when cpus are switching from idle to busy and back very frequently. For instance, when I start 1000 of processes that wake up every millisecond on my 8 cpus host, 'top' and 'perf top' show: Cpu(s): 17.8%us, 24.3%sy, 0.0%ni, 57.9%id, 0.0%wa, 0.0%hi, 0.0%si Events: 243K cycles 7.57% [kernel] [k] __schedule 7.08% [kernel] [k] timerqueue_add 6.13% libc-2.12.so [.] usleep Then if I create 10000 *idle* cpu cgroups (no processes in them), cpu usage increases significantly although the 'wakers' are still executing in the root cpu cgroup: Cpu(s): 19.1%us, 48.7%sy, 0.0%ni, 31.6%id, 0.0%wa, 0.0%hi, 0.7%si Events: 230K cycles 24.56% [kernel] [k] tg_load_down 5.76% [kernel] [k] __schedule This happens because this particular kind of load triggers 'new idle' rebalance very frequently, which requires calling update_h_load(), which, in turn, calls tg_load_down() for every *idle* cpu cgroup even though it is absolutely useless, because idle cpu cgroups have no tasks to pull. This patch tries to improve the situation by making h_load calculation proceed only when h_load is really necessary. To achieve this, it substitutes update_h_load() with update_cfs_rq_h_load(), which computes h_load only for a given cfs_rq and all its ascendants, and makes the load balancer call this function whenever it considers if a task should be pulled, i.e. it moves h_load calculations directly to task_h_load(). For h_load of the same cfs_rq not to be updated multiple times (in case several tasks in the same cgroup are considered during the same balance run), the patch keeps the time of the last h_load update for each cfs_rq and breaks calculation when it finds h_load to be uptodate. The benefit of it is that h_load is computed only for those cfs_rq's, which really need it, in particular all idle task groups are skipped. Although this, in fact, moves h_load calculation under rq lock, it should not affect latency much, because the amount of work done under rq lock while trying to pull tasks is limited by sched_nr_migrate. After the patch applied with the setup described above (1000 wakers in the root cgroup and 10000 idle cgroups), I get: Cpu(s): 16.9%us, 24.8%sy, 0.0%ni, 58.4%id, 0.0%wa, 0.0%hi, 0.0%si Events: 242K cycles 7.57% [kernel] [k] __schedule 6.70% [kernel] [k] timerqueue_add 5.93% libc-2.12.so [.] usleep Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1373896159-1278-1-git-send-email-vdavydov@parallels.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-15 13:49:19 +00:00
update_cfs_rq_h_load(cfs_rq);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
return div64_ul(p->se.avg.load_avg * cfs_rq->h_load,
cfs_rq_load_avg(cfs_rq) + 1);
}
#else
static inline void update_blocked_averages(int cpu)
{
struct rq *rq = cpu_rq(cpu);
struct cfs_rq *cfs_rq = &rq->cfs;
unsigned long flags;
raw_spin_lock_irqsave(&rq->lock, flags);
update_rq_clock(rq);
update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
static unsigned long task_h_load(struct task_struct *p)
{
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
return p->se.avg.load_avg;
}
#endif
/********** Helpers for find_busiest_group ************************/
sched/fair: Make update_sd_pick_busiest() return 'true' on a busier sd Currently update_sd_pick_busiest only identifies the busiest sd that is either overloaded, or has a group imbalance. When no sd is imbalanced or overloaded, the load balancer fails to find the busiest domain. This breaks load balancing between domains that are not overloaded, in the !SD_ASYM_PACKING case. This patch makes update_sd_pick_busiest return true when the busiest sd yet is encountered. Groups are ranked in the order overloaded > imbalanced > other, with higher ranked groups getting priority even when their load is lower. This is necessary due to the possibility of unequal capacities and cpumasks between domains within a sched group. Behaviour for SD_ASYM_PACKING does not seem to match the comment, but I have no hardware to test that so I have left the behaviour of that code unchanged. Enum for group classification suggested by Peter Zijlstra. Signed-off-by: Rik van Riel <riel@redhat.com> [peterz: replaced sg_lb_stats::group_imb with the new enum group_type in an attempt to avoid endless recalculation] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Michael Neuling <mikey@neuling.org> Cc: ktkhai@parallels.com Cc: tim.c.chen@linux.intel.com Cc: nicolas.pitre@linaro.org Cc: jhladky@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140729152743.GI3935@laptop Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-28 18:16:28 +00:00
enum group_type {
group_other = 0,
group_imbalanced,
group_overloaded,
};
/*
* sg_lb_stats - stats of a sched_group required for load_balancing
*/
struct sg_lb_stats {
unsigned long avg_load; /*Avg load across the CPUs of the group */
unsigned long group_load; /* Total load over the CPUs of the group */
unsigned long sum_weighted_load; /* Weighted load of group's tasks */
unsigned long load_per_task;
unsigned long group_capacity;
sched: Calculate CPU's usage statistic and put it into struct sg_lb_stats::group_usage Monitor the usage level of each group of each sched_domain level. The usage is the portion of cpu_capacity_orig that is currently used on a CPU or group of CPUs. We use the utilization_load_avg to evaluate the usage level of each group. The utilization_load_avg only takes into account the running time of the CFS tasks on a CPU with a maximum value of SCHED_LOAD_SCALE when the CPU is fully utilized. Nevertheless, we must cap utilization_load_avg which can be temporally greater than SCHED_LOAD_SCALE after the migration of a task on this CPU and until the metrics are stabilized. The utilization_load_avg is in the range [0..SCHED_LOAD_SCALE] to reflect the running load on the CPU whereas the available capacity for the CFS task is in the range [0..cpu_capacity_orig]. In order to test if a CPU is fully utilized by CFS tasks, we have to scale the utilization in the cpu_capacity_orig range of the CPU to get the usage of the latter. The usage can then be compared with the available capacity (ie cpu_capacity) to deduct the usage level of a CPU. The frequency scaling invariance of the usage is not taken into account in this patch, it will be solved in another patch which will deal with frequency scaling invariance on the utilization_load_avg. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425455327-13508-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-03-04 07:48:47 +00:00
unsigned long group_usage; /* Total usage of the group */
unsigned int sum_nr_running; /* Nr tasks running in the group */
unsigned int idle_cpus;
unsigned int group_weight;
sched/fair: Make update_sd_pick_busiest() return 'true' on a busier sd Currently update_sd_pick_busiest only identifies the busiest sd that is either overloaded, or has a group imbalance. When no sd is imbalanced or overloaded, the load balancer fails to find the busiest domain. This breaks load balancing between domains that are not overloaded, in the !SD_ASYM_PACKING case. This patch makes update_sd_pick_busiest return true when the busiest sd yet is encountered. Groups are ranked in the order overloaded > imbalanced > other, with higher ranked groups getting priority even when their load is lower. This is necessary due to the possibility of unequal capacities and cpumasks between domains within a sched group. Behaviour for SD_ASYM_PACKING does not seem to match the comment, but I have no hardware to test that so I have left the behaviour of that code unchanged. Enum for group classification suggested by Peter Zijlstra. Signed-off-by: Rik van Riel <riel@redhat.com> [peterz: replaced sg_lb_stats::group_imb with the new enum group_type in an attempt to avoid endless recalculation] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Michael Neuling <mikey@neuling.org> Cc: ktkhai@parallels.com Cc: tim.c.chen@linux.intel.com Cc: nicolas.pitre@linaro.org Cc: jhladky@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140729152743.GI3935@laptop Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-28 18:16:28 +00:00
enum group_type group_type;
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
int group_no_capacity;
#ifdef CONFIG_NUMA_BALANCING
unsigned int nr_numa_running;
unsigned int nr_preferred_running;
#endif
};
/*
* sd_lb_stats - Structure to store the statistics of a sched_domain
* during load balancing.
*/
struct sd_lb_stats {
struct sched_group *busiest; /* Busiest group in this sd */
struct sched_group *local; /* Local group in this sd */
unsigned long total_load; /* Total load of all groups in sd */
unsigned long total_capacity; /* Total capacity of all groups in sd */
unsigned long avg_load; /* Average load across all groups in sd */
struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */
struct sg_lb_stats local_stat; /* Statistics of the local group */
};
static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
{
/*
* Skimp on the clearing to avoid duplicate work. We can avoid clearing
* local_stat because update_sg_lb_stats() does a full clear/assignment.
* We must however clear busiest_stat::avg_load because
* update_sd_pick_busiest() reads this before assignment.
*/
*sds = (struct sd_lb_stats){
.busiest = NULL,
.local = NULL,
.total_load = 0UL,
.total_capacity = 0UL,
.busiest_stat = {
.avg_load = 0UL,
sched/fair: Make update_sd_pick_busiest() return 'true' on a busier sd Currently update_sd_pick_busiest only identifies the busiest sd that is either overloaded, or has a group imbalance. When no sd is imbalanced or overloaded, the load balancer fails to find the busiest domain. This breaks load balancing between domains that are not overloaded, in the !SD_ASYM_PACKING case. This patch makes update_sd_pick_busiest return true when the busiest sd yet is encountered. Groups are ranked in the order overloaded > imbalanced > other, with higher ranked groups getting priority even when their load is lower. This is necessary due to the possibility of unequal capacities and cpumasks between domains within a sched group. Behaviour for SD_ASYM_PACKING does not seem to match the comment, but I have no hardware to test that so I have left the behaviour of that code unchanged. Enum for group classification suggested by Peter Zijlstra. Signed-off-by: Rik van Riel <riel@redhat.com> [peterz: replaced sg_lb_stats::group_imb with the new enum group_type in an attempt to avoid endless recalculation] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Michael Neuling <mikey@neuling.org> Cc: ktkhai@parallels.com Cc: tim.c.chen@linux.intel.com Cc: nicolas.pitre@linaro.org Cc: jhladky@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140729152743.GI3935@laptop Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-28 18:16:28 +00:00
.sum_nr_running = 0,
.group_type = group_other,
},
};
}
/**
* get_sd_load_idx - Obtain the load index for a given sched domain.
* @sd: The sched_domain whose load_idx is to be obtained.
* @idle: The idle status of the CPU for whose sd load_idx is obtained.
*
* Return: The load index.
*/
static inline int get_sd_load_idx(struct sched_domain *sd,
enum cpu_idle_type idle)
{
int load_idx;
switch (idle) {
case CPU_NOT_IDLE:
load_idx = sd->busy_idx;
break;
case CPU_NEWLY_IDLE:
load_idx = sd->newidle_idx;
break;
default:
load_idx = sd->idle_idx;
break;
}
return load_idx;
}
static unsigned long default_scale_cpu_capacity(struct sched_domain *sd, int cpu)
{
if ((sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
return sd->smt_gain / sd->span_weight;
return SCHED_CAPACITY_SCALE;
}
unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
{
return default_scale_cpu_capacity(sd, cpu);
}
static unsigned long scale_rt_capacity(int cpu)
{
struct rq *rq = cpu_rq(cpu);
sched: Make scale_rt invariant with frequency The average running time of RT tasks is used to estimate the remaining compute capacity for CFS tasks. This remaining capacity is the original capacity scaled down by a factor (aka scale_rt_capacity). This estimation of available capacity must also be invariant with frequency scaling. A frequency scaling factor is applied on the running time of the RT tasks for computing scale_rt_capacity. In sched_rt_avg_update(), we now scale the RT execution time like below: rq->rt_avg += rt_delta * arch_scale_freq_capacity() >> SCHED_CAPACITY_SHIFT Then, scale_rt_capacity can be summarized by: scale_rt_capacity = SCHED_CAPACITY_SCALE * available / total with available = total - rq->rt_avg This has been been optimized in current code by: scale_rt_capacity = available / (total >> SCHED_CAPACITY_SHIFT) But we can also developed the equation like below: scale_rt_capacity = SCHED_CAPACITY_SCALE - ((rq->rt_avg << SCHED_CAPACITY_SHIFT) / total) and we can optimize the equation by removing SCHED_CAPACITY_SHIFT shift in the computation of rq->rt_avg and scale_rt_capacity(). so rq->rt_avg += rt_delta * arch_scale_freq_capacity() and scale_rt_capacity = SCHED_CAPACITY_SCALE - (rq->rt_avg / total) arch_scale_frequency_capacity() will be called in the hot path of the scheduler which implies to have a short and efficient function. As an example, arch_scale_frequency_capacity() should return a cached value that is updated periodically outside of the hot path. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-6-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:08 +00:00
u64 total, used, age_stamp, avg;
s64 delta;
/*
* Since we're reading these variables without serialization make sure
* we read them once before doing sanity checks on them.
*/
age_stamp = READ_ONCE(rq->age_stamp);
avg = READ_ONCE(rq->rt_avg);
delta = __rq_clock_broken(rq) - age_stamp;
if (unlikely(delta < 0))
delta = 0;
total = sched_avg_period() + delta;
sched: Make scale_rt invariant with frequency The average running time of RT tasks is used to estimate the remaining compute capacity for CFS tasks. This remaining capacity is the original capacity scaled down by a factor (aka scale_rt_capacity). This estimation of available capacity must also be invariant with frequency scaling. A frequency scaling factor is applied on the running time of the RT tasks for computing scale_rt_capacity. In sched_rt_avg_update(), we now scale the RT execution time like below: rq->rt_avg += rt_delta * arch_scale_freq_capacity() >> SCHED_CAPACITY_SHIFT Then, scale_rt_capacity can be summarized by: scale_rt_capacity = SCHED_CAPACITY_SCALE * available / total with available = total - rq->rt_avg This has been been optimized in current code by: scale_rt_capacity = available / (total >> SCHED_CAPACITY_SHIFT) But we can also developed the equation like below: scale_rt_capacity = SCHED_CAPACITY_SCALE - ((rq->rt_avg << SCHED_CAPACITY_SHIFT) / total) and we can optimize the equation by removing SCHED_CAPACITY_SHIFT shift in the computation of rq->rt_avg and scale_rt_capacity(). so rq->rt_avg += rt_delta * arch_scale_freq_capacity() and scale_rt_capacity = SCHED_CAPACITY_SCALE - (rq->rt_avg / total) arch_scale_frequency_capacity() will be called in the hot path of the scheduler which implies to have a short and efficient function. As an example, arch_scale_frequency_capacity() should return a cached value that is updated periodically outside of the hot path. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-6-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:08 +00:00
used = div_u64(avg, total);
sched: Make scale_rt invariant with frequency The average running time of RT tasks is used to estimate the remaining compute capacity for CFS tasks. This remaining capacity is the original capacity scaled down by a factor (aka scale_rt_capacity). This estimation of available capacity must also be invariant with frequency scaling. A frequency scaling factor is applied on the running time of the RT tasks for computing scale_rt_capacity. In sched_rt_avg_update(), we now scale the RT execution time like below: rq->rt_avg += rt_delta * arch_scale_freq_capacity() >> SCHED_CAPACITY_SHIFT Then, scale_rt_capacity can be summarized by: scale_rt_capacity = SCHED_CAPACITY_SCALE * available / total with available = total - rq->rt_avg This has been been optimized in current code by: scale_rt_capacity = available / (total >> SCHED_CAPACITY_SHIFT) But we can also developed the equation like below: scale_rt_capacity = SCHED_CAPACITY_SCALE - ((rq->rt_avg << SCHED_CAPACITY_SHIFT) / total) and we can optimize the equation by removing SCHED_CAPACITY_SHIFT shift in the computation of rq->rt_avg and scale_rt_capacity(). so rq->rt_avg += rt_delta * arch_scale_freq_capacity() and scale_rt_capacity = SCHED_CAPACITY_SCALE - (rq->rt_avg / total) arch_scale_frequency_capacity() will be called in the hot path of the scheduler which implies to have a short and efficient function. As an example, arch_scale_frequency_capacity() should return a cached value that is updated periodically outside of the hot path. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-6-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:08 +00:00
if (likely(used < SCHED_CAPACITY_SCALE))
return SCHED_CAPACITY_SCALE - used;
sched: Make scale_rt invariant with frequency The average running time of RT tasks is used to estimate the remaining compute capacity for CFS tasks. This remaining capacity is the original capacity scaled down by a factor (aka scale_rt_capacity). This estimation of available capacity must also be invariant with frequency scaling. A frequency scaling factor is applied on the running time of the RT tasks for computing scale_rt_capacity. In sched_rt_avg_update(), we now scale the RT execution time like below: rq->rt_avg += rt_delta * arch_scale_freq_capacity() >> SCHED_CAPACITY_SHIFT Then, scale_rt_capacity can be summarized by: scale_rt_capacity = SCHED_CAPACITY_SCALE * available / total with available = total - rq->rt_avg This has been been optimized in current code by: scale_rt_capacity = available / (total >> SCHED_CAPACITY_SHIFT) But we can also developed the equation like below: scale_rt_capacity = SCHED_CAPACITY_SCALE - ((rq->rt_avg << SCHED_CAPACITY_SHIFT) / total) and we can optimize the equation by removing SCHED_CAPACITY_SHIFT shift in the computation of rq->rt_avg and scale_rt_capacity(). so rq->rt_avg += rt_delta * arch_scale_freq_capacity() and scale_rt_capacity = SCHED_CAPACITY_SCALE - (rq->rt_avg / total) arch_scale_frequency_capacity() will be called in the hot path of the scheduler which implies to have a short and efficient function. As an example, arch_scale_frequency_capacity() should return a cached value that is updated periodically outside of the hot path. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-6-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:08 +00:00
return 1;
}
static void update_cpu_capacity(struct sched_domain *sd, int cpu)
{
sched: Final power vs. capacity cleanups It is better not to think about compute capacity as being equivalent to "CPU power". The upcoming "power aware" scheduler work may create confusion with the notion of energy consumption if "power" is used too liberally. This contains the architecture visible changes. Incidentally, only ARM takes advantage of the available pow^H^H^Hcapacity scaling hooks and therefore those changes outside kernel/sched/ are confined to one ARM specific file. The default arch_scale_smt_power() hook is not overridden by anyone. Replacements are as follows: arch_scale_freq_power --> arch_scale_freq_capacity arch_scale_smt_power --> arch_scale_smt_capacity SCHED_POWER_SCALE --> SCHED_CAPACITY_SCALE SCHED_POWER_SHIFT --> SCHED_CAPACITY_SHIFT The local usage of "power" in arch/arm/kernel/topology.c is also changed to "capacity" as appropriate. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Morten Rasmussen <morten.rasmussen@arm.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: linaro-kernel@lists.linaro.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com> Cc: Grant Likely <grant.likely@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Brown <broonie@linaro.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: devicetree@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/n/tip-48zba9qbznvglwelgq2cfygh@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-26 22:19:39 +00:00
unsigned long capacity = SCHED_CAPACITY_SCALE;
struct sched_group *sdg = sd->groups;
if (sched_feat(ARCH_CAPACITY))
capacity *= arch_scale_cpu_capacity(sd, cpu);
else
capacity *= default_scale_cpu_capacity(sd, cpu);
capacity >>= SCHED_CAPACITY_SHIFT;
cpu_rq(cpu)->cpu_capacity_orig = capacity;
capacity *= scale_rt_capacity(cpu);
sched: Final power vs. capacity cleanups It is better not to think about compute capacity as being equivalent to "CPU power". The upcoming "power aware" scheduler work may create confusion with the notion of energy consumption if "power" is used too liberally. This contains the architecture visible changes. Incidentally, only ARM takes advantage of the available pow^H^H^Hcapacity scaling hooks and therefore those changes outside kernel/sched/ are confined to one ARM specific file. The default arch_scale_smt_power() hook is not overridden by anyone. Replacements are as follows: arch_scale_freq_power --> arch_scale_freq_capacity arch_scale_smt_power --> arch_scale_smt_capacity SCHED_POWER_SCALE --> SCHED_CAPACITY_SCALE SCHED_POWER_SHIFT --> SCHED_CAPACITY_SHIFT The local usage of "power" in arch/arm/kernel/topology.c is also changed to "capacity" as appropriate. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Morten Rasmussen <morten.rasmussen@arm.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: linaro-kernel@lists.linaro.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com> Cc: Grant Likely <grant.likely@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Brown <broonie@linaro.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: devicetree@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/n/tip-48zba9qbznvglwelgq2cfygh@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-26 22:19:39 +00:00
capacity >>= SCHED_CAPACITY_SHIFT;
if (!capacity)
capacity = 1;
cpu_rq(cpu)->cpu_capacity = capacity;
sdg->sgc->capacity = capacity;
}
void update_group_capacity(struct sched_domain *sd, int cpu)
{
struct sched_domain *child = sd->child;
struct sched_group *group, *sdg = sd->groups;
unsigned long capacity;
unsigned long interval;
interval = msecs_to_jiffies(sd->balance_interval);
interval = clamp(interval, 1UL, max_load_balance_interval);
sdg->sgc->next_update = jiffies + interval;
if (!child) {
update_cpu_capacity(sd, cpu);
return;
}
capacity = 0;
if (child->flags & SD_OVERLAP) {
/*
* SD_OVERLAP domains cannot assume that child groups
* span the current group.
*/
for_each_cpu(cpu, sched_group_cpus(sdg)) {
struct sched_group_capacity *sgc;
struct rq *rq = cpu_rq(cpu);
/*
* build_sched_domains() -> init_sched_groups_capacity()
* gets here before we've attached the domains to the
* runqueues.
*
* Use capacity_of(), which is set irrespective of domains
* in update_cpu_capacity().
*
* This avoids capacity from being 0 and
* causing divide-by-zero issues on boot.
*/
if (unlikely(!rq->sd)) {
capacity += capacity_of(cpu);
continue;
}
sgc = rq->sd->groups->sgc;
capacity += sgc->capacity;
}
} else {
/*
* !SD_OVERLAP domains can assume that child groups
* span the current group.
*/
group = child->groups;
do {
capacity += group->sgc->capacity;
group = group->next;
} while (group != child->groups);
}
sdg->sgc->capacity = capacity;
}
/*
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
* Check whether the capacity of the rq has been noticeably reduced by side
* activity. The imbalance_pct is used for the threshold.
* Return true is the capacity is reduced
*/
static inline int
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
{
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
return ((rq->cpu_capacity * sd->imbalance_pct) <
(rq->cpu_capacity_orig * 100));
}
/*
* Group imbalance indicates (and tries to solve) the problem where balancing
* groups is inadequate due to tsk_cpus_allowed() constraints.
*
* Imagine a situation of two groups of 4 cpus each and 4 tasks each with a
* cpumask covering 1 cpu of the first group and 3 cpus of the second group.
* Something like:
*
* { 0 1 2 3 } { 4 5 6 7 }
* * * * *
*
* If we were to balance group-wise we'd place two tasks in the first group and
* two tasks in the second group. Clearly this is undesired as it will overload
* cpu 3 and leave one of the cpus in the second group unused.
*
* The current solution to this issue is detecting the skew in the first group
* by noticing the lower domain failed to reach balance and had difficulty
* moving tasks due to affinity constraints.
*
* When this is so detected; this group becomes a candidate for busiest; see
* update_sd_pick_busiest(). And calculate_imbalance() and
* find_busiest_group() avoid some of the usual balance conditions to allow it
* to create an effective group imbalance.
*
* This is a somewhat tricky proposition since the next run might not find the
* group imbalance and decide the groups need to be balanced again. A most
* subtle and fragile situation.
*/
static inline int sg_imbalanced(struct sched_group *group)
{
return group->sgc->imbalance;
}
/*
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
* group_has_capacity returns true if the group has spare capacity that could
* be used by some tasks.
* We consider that a group has spare capacity if the * number of task is
* smaller than the number of CPUs or if the usage is lower than the available
* capacity for CFS tasks.
* For the latter, we use a threshold to stabilize the state, to take into
* account the variance of the tasks' load and to return true if the available
* capacity in meaningful for the load balancer.
* As an example, an available capacity of 1% can appear but it doesn't make
* any benefit for the load balance.
*/
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
static inline bool
group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs)
{
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
if (sgs->sum_nr_running < sgs->group_weight)
return true;
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
if ((sgs->group_capacity * 100) >
(sgs->group_usage * env->sd->imbalance_pct))
return true;
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
return false;
}
/*
* group_is_overloaded returns true if the group has more tasks than it can
* handle.
* group_is_overloaded is not equals to !group_has_capacity because a group
* with the exact right number of tasks, has no more spare capacity but is not
* overloaded so both group_has_capacity and group_is_overloaded return
* false.
*/
static inline bool
group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
{
if (sgs->sum_nr_running <= sgs->group_weight)
return false;
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
if ((sgs->group_capacity * 100) <
(sgs->group_usage * env->sd->imbalance_pct))
return true;
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
return false;
}
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
static enum group_type group_classify(struct lb_env *env,
struct sched_group *group,
struct sg_lb_stats *sgs)
sched/fair: Make update_sd_pick_busiest() return 'true' on a busier sd Currently update_sd_pick_busiest only identifies the busiest sd that is either overloaded, or has a group imbalance. When no sd is imbalanced or overloaded, the load balancer fails to find the busiest domain. This breaks load balancing between domains that are not overloaded, in the !SD_ASYM_PACKING case. This patch makes update_sd_pick_busiest return true when the busiest sd yet is encountered. Groups are ranked in the order overloaded > imbalanced > other, with higher ranked groups getting priority even when their load is lower. This is necessary due to the possibility of unequal capacities and cpumasks between domains within a sched group. Behaviour for SD_ASYM_PACKING does not seem to match the comment, but I have no hardware to test that so I have left the behaviour of that code unchanged. Enum for group classification suggested by Peter Zijlstra. Signed-off-by: Rik van Riel <riel@redhat.com> [peterz: replaced sg_lb_stats::group_imb with the new enum group_type in an attempt to avoid endless recalculation] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Michael Neuling <mikey@neuling.org> Cc: ktkhai@parallels.com Cc: tim.c.chen@linux.intel.com Cc: nicolas.pitre@linaro.org Cc: jhladky@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140729152743.GI3935@laptop Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-28 18:16:28 +00:00
{
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
if (sgs->group_no_capacity)
sched/fair: Make update_sd_pick_busiest() return 'true' on a busier sd Currently update_sd_pick_busiest only identifies the busiest sd that is either overloaded, or has a group imbalance. When no sd is imbalanced or overloaded, the load balancer fails to find the busiest domain. This breaks load balancing between domains that are not overloaded, in the !SD_ASYM_PACKING case. This patch makes update_sd_pick_busiest return true when the busiest sd yet is encountered. Groups are ranked in the order overloaded > imbalanced > other, with higher ranked groups getting priority even when their load is lower. This is necessary due to the possibility of unequal capacities and cpumasks between domains within a sched group. Behaviour for SD_ASYM_PACKING does not seem to match the comment, but I have no hardware to test that so I have left the behaviour of that code unchanged. Enum for group classification suggested by Peter Zijlstra. Signed-off-by: Rik van Riel <riel@redhat.com> [peterz: replaced sg_lb_stats::group_imb with the new enum group_type in an attempt to avoid endless recalculation] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Michael Neuling <mikey@neuling.org> Cc: ktkhai@parallels.com Cc: tim.c.chen@linux.intel.com Cc: nicolas.pitre@linaro.org Cc: jhladky@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140729152743.GI3935@laptop Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-28 18:16:28 +00:00
return group_overloaded;
if (sg_imbalanced(group))
return group_imbalanced;
return group_other;
}
/**
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
* @env: The load balancing environment.
* @group: sched_group whose statistics are to be updated.
* @load_idx: Load index of sched_domain of this_cpu for load calc.
* @local_group: Does group contain this_cpu.
* @sgs: variable to hold the statistics for this group.
* @overload: Indicate more than one runnable task for any CPU.
*/
static inline void update_sg_lb_stats(struct lb_env *env,
struct sched_group *group, int load_idx,
sched/fair: Implement fast idling of CPUs when the system is partially loaded When a system is lightly loaded (i.e. no more than 1 job per cpu), attempt to pull job to a cpu before putting it to idle is unnecessary and can be skipped. This patch adds an indicator so the scheduler can know when there's no more than 1 active job is on any CPU in the system to skip needless job pulls. On a 4 socket machine with a request/response kind of workload from clients, we saw about 0.13 msec delay when we go through a full load balance to try pull job from all the other cpus. While 0.1 msec was spent on processing the request and generating a response, the 0.13 msec load balance overhead was actually more than the actual work being done. This overhead can be skipped much of the time for lightly loaded systems. With this patch, we tested with a netperf request/response workload that has the server busy with half the cpus in a 4 socket system. We found the patch eliminated 75% of the load balance attempts before idling a cpu. The overhead of setting/clearing the indicator is low as we already gather the necessary info while we call add_nr_running() and update_sd_lb_stats.() We switch to full load balance load immediately if any cpu got more than one job on its run queue in add_nr_running. We'll clear the indicator to avoid load balance when we detect no cpu's have more than one job when we scan the work queues in update_sg_lb_stats(). We are aggressive in turning on the load balance and opportunistic in skipping the load balance. Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Jason Low <jason.low2@hp.com> Cc: "Paul E.McKenney" <paulmck@linux.vnet.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Alex Shi <alex.shi@linaro.org> Cc: Michel Lespinasse <walken@google.com> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1403551009.2970.613.camel@schen9-DESK Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-23 19:16:49 +00:00
int local_group, struct sg_lb_stats *sgs,
bool *overload)
{
unsigned long load;
int i;
memset(sgs, 0, sizeof(*sgs));
for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
struct rq *rq = cpu_rq(i);
/* Bias balancing toward cpus of our domain */
if (local_group)
load = target_load(i, load_idx);
else
load = source_load(i, load_idx);
sgs->group_load += load;
sched: Calculate CPU's usage statistic and put it into struct sg_lb_stats::group_usage Monitor the usage level of each group of each sched_domain level. The usage is the portion of cpu_capacity_orig that is currently used on a CPU or group of CPUs. We use the utilization_load_avg to evaluate the usage level of each group. The utilization_load_avg only takes into account the running time of the CFS tasks on a CPU with a maximum value of SCHED_LOAD_SCALE when the CPU is fully utilized. Nevertheless, we must cap utilization_load_avg which can be temporally greater than SCHED_LOAD_SCALE after the migration of a task on this CPU and until the metrics are stabilized. The utilization_load_avg is in the range [0..SCHED_LOAD_SCALE] to reflect the running load on the CPU whereas the available capacity for the CFS task is in the range [0..cpu_capacity_orig]. In order to test if a CPU is fully utilized by CFS tasks, we have to scale the utilization in the cpu_capacity_orig range of the CPU to get the usage of the latter. The usage can then be compared with the available capacity (ie cpu_capacity) to deduct the usage level of a CPU. The frequency scaling invariance of the usage is not taken into account in this patch, it will be solved in another patch which will deal with frequency scaling invariance on the utilization_load_avg. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Morten Rasmussen <morten.rasmussen@arm.com> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425455327-13508-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-03-04 07:48:47 +00:00
sgs->group_usage += get_cpu_usage(i);
sgs->sum_nr_running += rq->cfs.h_nr_running;
sched/fair: Implement fast idling of CPUs when the system is partially loaded When a system is lightly loaded (i.e. no more than 1 job per cpu), attempt to pull job to a cpu before putting it to idle is unnecessary and can be skipped. This patch adds an indicator so the scheduler can know when there's no more than 1 active job is on any CPU in the system to skip needless job pulls. On a 4 socket machine with a request/response kind of workload from clients, we saw about 0.13 msec delay when we go through a full load balance to try pull job from all the other cpus. While 0.1 msec was spent on processing the request and generating a response, the 0.13 msec load balance overhead was actually more than the actual work being done. This overhead can be skipped much of the time for lightly loaded systems. With this patch, we tested with a netperf request/response workload that has the server busy with half the cpus in a 4 socket system. We found the patch eliminated 75% of the load balance attempts before idling a cpu. The overhead of setting/clearing the indicator is low as we already gather the necessary info while we call add_nr_running() and update_sd_lb_stats.() We switch to full load balance load immediately if any cpu got more than one job on its run queue in add_nr_running. We'll clear the indicator to avoid load balance when we detect no cpu's have more than one job when we scan the work queues in update_sg_lb_stats(). We are aggressive in turning on the load balance and opportunistic in skipping the load balance. Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Jason Low <jason.low2@hp.com> Cc: "Paul E.McKenney" <paulmck@linux.vnet.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Alex Shi <alex.shi@linaro.org> Cc: Michel Lespinasse <walken@google.com> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1403551009.2970.613.camel@schen9-DESK Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-23 19:16:49 +00:00
if (rq->nr_running > 1)
*overload = true;
#ifdef CONFIG_NUMA_BALANCING
sgs->nr_numa_running += rq->nr_numa_running;
sgs->nr_preferred_running += rq->nr_preferred_running;
#endif
sgs->sum_weighted_load += weighted_cpuload(i);
sched: Use group weight, idle cpu metrics to fix imbalances during idle Currently we consider a sched domain to be well balanced when the imbalance is less than the domain's imablance_pct. As the number of cores and threads are increasing, current values of imbalance_pct (for example 25% for a NUMA domain) are not enough to detect imbalances like: a) On a WSM-EP system (two sockets, each having 6 cores and 12 logical threads), 24 cpu-hogging tasks get scheduled as 13 on one socket and 11 on another socket. Leading to an idle HT cpu. b) On a hypothetial 2 socket NHM-EX system (each socket having 8 cores and 16 logical threads), 16 cpu-hogging tasks can get scheduled as 9 on one socket and 7 on another socket. Leaving one core in a socket idle whereas in another socket we have a core having both its HT siblings busy. While this issue can be fixed by decreasing the domain's imbalance_pct (by making it a function of number of logical cpus in the domain), it can potentially cause more task migrations across sched groups in an overloaded case. Fix this by using imbalance_pct only during newly_idle and busy load balancing. And during idle load balancing, check if there is an imbalance in number of idle cpu's across the busiest and this sched_group or if the busiest group has more tasks than its weight that the idle cpu in this_group can pull. Reported-by: Nikhil Rao <ncrao@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1284760952.2676.11.camel@sbsiddha-MOBL3.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-09-17 22:02:32 +00:00
if (idle_cpu(i))
sgs->idle_cpus++;
}
/* Adjust by relative CPU capacity of the group */
sgs->group_capacity = group->sgc->capacity;
sched: Final power vs. capacity cleanups It is better not to think about compute capacity as being equivalent to "CPU power". The upcoming "power aware" scheduler work may create confusion with the notion of energy consumption if "power" is used too liberally. This contains the architecture visible changes. Incidentally, only ARM takes advantage of the available pow^H^H^Hcapacity scaling hooks and therefore those changes outside kernel/sched/ are confined to one ARM specific file. The default arch_scale_smt_power() hook is not overridden by anyone. Replacements are as follows: arch_scale_freq_power --> arch_scale_freq_capacity arch_scale_smt_power --> arch_scale_smt_capacity SCHED_POWER_SCALE --> SCHED_CAPACITY_SCALE SCHED_POWER_SHIFT --> SCHED_CAPACITY_SHIFT The local usage of "power" in arch/arm/kernel/topology.c is also changed to "capacity" as appropriate. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Morten Rasmussen <morten.rasmussen@arm.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: linaro-kernel@lists.linaro.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com> Cc: Grant Likely <grant.likely@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Brown <broonie@linaro.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: devicetree@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/n/tip-48zba9qbznvglwelgq2cfygh@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-26 22:19:39 +00:00
sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity;
sched: Fix SCHED_MC regression caused by change in sched cpu_power On platforms like dual socket quad-core platform, the scheduler load balancer is not detecting the load imbalances in certain scenarios. This is leading to scenarios like where one socket is completely busy (with all the 4 cores running with 4 tasks) and leaving another socket completely idle. This causes performance issues as those 4 tasks share the memory controller, last-level cache bandwidth etc. Also we won't be taking advantage of turbo-mode as much as we would like, etc. Some of the comparisons in the scheduler load balancing code are comparing the "weighted cpu load that is scaled wrt sched_group's cpu_power" with the "weighted average load per task that is not scaled wrt sched_group's cpu_power". While this has probably been broken for a longer time (for multi socket numa nodes etc), the problem got aggrevated via this recent change: | | commit f93e65c186ab3c05ce2068733ca10e34fd00125e | Author: Peter Zijlstra <a.p.zijlstra@chello.nl> | Date: Tue Sep 1 10:34:32 2009 +0200 | | sched: Restore __cpu_power to a straight sum of power | Also with this change, the sched group cpu power alone no longer reflects the group capacity that is needed to implement MC, MT performance (default) and power-savings (user-selectable) policies. We need to use the computed group capacity (sgs.group_capacity, that is computed using the SD_PREFER_SIBLING logic in update_sd_lb_stats()) to find out if the group with the max load is above its capacity and how much load to move etc. Reported-by: Ma Ling <ling.ma@intel.com> Initial-Analysis-by: Zhang, Yanmin <yanmin_zhang@linux.intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> [ -v2: build fix ] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: <stable@kernel.org> # [2.6.32.x, 2.6.33.x] LKML-Reference: <1266970432.11588.22.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-24 00:13:52 +00:00
if (sgs->sum_nr_running)
sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
sched: Use group weight, idle cpu metrics to fix imbalances during idle Currently we consider a sched domain to be well balanced when the imbalance is less than the domain's imablance_pct. As the number of cores and threads are increasing, current values of imbalance_pct (for example 25% for a NUMA domain) are not enough to detect imbalances like: a) On a WSM-EP system (two sockets, each having 6 cores and 12 logical threads), 24 cpu-hogging tasks get scheduled as 13 on one socket and 11 on another socket. Leading to an idle HT cpu. b) On a hypothetial 2 socket NHM-EX system (each socket having 8 cores and 16 logical threads), 16 cpu-hogging tasks can get scheduled as 9 on one socket and 7 on another socket. Leaving one core in a socket idle whereas in another socket we have a core having both its HT siblings busy. While this issue can be fixed by decreasing the domain's imbalance_pct (by making it a function of number of logical cpus in the domain), it can potentially cause more task migrations across sched groups in an overloaded case. Fix this by using imbalance_pct only during newly_idle and busy load balancing. And during idle load balancing, check if there is an imbalance in number of idle cpu's across the busiest and this sched_group or if the busiest group has more tasks than its weight that the idle cpu in this_group can pull. Reported-by: Nikhil Rao <ncrao@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1284760952.2676.11.camel@sbsiddha-MOBL3.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-09-17 22:02:32 +00:00
sgs->group_weight = group->group_weight;
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
sgs->group_no_capacity = group_is_overloaded(env, sgs);
sgs->group_type = group_classify(env, group, sgs);
}
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
/**
* update_sd_pick_busiest - return 1 on busiest group
* @env: The load balancing environment.
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
* @sds: sched_domain statistics
* @sg: sched_group candidate to be checked for being the busiest
* @sgs: sched_group statistics
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
*
* Determine if @sg is a busier group than the previously selected
* busiest group.
*
* Return: %true if @sg is a busier group than the previously selected
* busiest group. %false otherwise.
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
*/
static bool update_sd_pick_busiest(struct lb_env *env,
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
struct sd_lb_stats *sds,
struct sched_group *sg,
struct sg_lb_stats *sgs)
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
{
sched/fair: Make update_sd_pick_busiest() return 'true' on a busier sd Currently update_sd_pick_busiest only identifies the busiest sd that is either overloaded, or has a group imbalance. When no sd is imbalanced or overloaded, the load balancer fails to find the busiest domain. This breaks load balancing between domains that are not overloaded, in the !SD_ASYM_PACKING case. This patch makes update_sd_pick_busiest return true when the busiest sd yet is encountered. Groups are ranked in the order overloaded > imbalanced > other, with higher ranked groups getting priority even when their load is lower. This is necessary due to the possibility of unequal capacities and cpumasks between domains within a sched group. Behaviour for SD_ASYM_PACKING does not seem to match the comment, but I have no hardware to test that so I have left the behaviour of that code unchanged. Enum for group classification suggested by Peter Zijlstra. Signed-off-by: Rik van Riel <riel@redhat.com> [peterz: replaced sg_lb_stats::group_imb with the new enum group_type in an attempt to avoid endless recalculation] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Michael Neuling <mikey@neuling.org> Cc: ktkhai@parallels.com Cc: tim.c.chen@linux.intel.com Cc: nicolas.pitre@linaro.org Cc: jhladky@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140729152743.GI3935@laptop Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-28 18:16:28 +00:00
struct sg_lb_stats *busiest = &sds->busiest_stat;
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
sched/fair: Make update_sd_pick_busiest() return 'true' on a busier sd Currently update_sd_pick_busiest only identifies the busiest sd that is either overloaded, or has a group imbalance. When no sd is imbalanced or overloaded, the load balancer fails to find the busiest domain. This breaks load balancing between domains that are not overloaded, in the !SD_ASYM_PACKING case. This patch makes update_sd_pick_busiest return true when the busiest sd yet is encountered. Groups are ranked in the order overloaded > imbalanced > other, with higher ranked groups getting priority even when their load is lower. This is necessary due to the possibility of unequal capacities and cpumasks between domains within a sched group. Behaviour for SD_ASYM_PACKING does not seem to match the comment, but I have no hardware to test that so I have left the behaviour of that code unchanged. Enum for group classification suggested by Peter Zijlstra. Signed-off-by: Rik van Riel <riel@redhat.com> [peterz: replaced sg_lb_stats::group_imb with the new enum group_type in an attempt to avoid endless recalculation] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Michael Neuling <mikey@neuling.org> Cc: ktkhai@parallels.com Cc: tim.c.chen@linux.intel.com Cc: nicolas.pitre@linaro.org Cc: jhladky@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140729152743.GI3935@laptop Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-28 18:16:28 +00:00
if (sgs->group_type > busiest->group_type)
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
return true;
sched/fair: Make update_sd_pick_busiest() return 'true' on a busier sd Currently update_sd_pick_busiest only identifies the busiest sd that is either overloaded, or has a group imbalance. When no sd is imbalanced or overloaded, the load balancer fails to find the busiest domain. This breaks load balancing between domains that are not overloaded, in the !SD_ASYM_PACKING case. This patch makes update_sd_pick_busiest return true when the busiest sd yet is encountered. Groups are ranked in the order overloaded > imbalanced > other, with higher ranked groups getting priority even when their load is lower. This is necessary due to the possibility of unequal capacities and cpumasks between domains within a sched group. Behaviour for SD_ASYM_PACKING does not seem to match the comment, but I have no hardware to test that so I have left the behaviour of that code unchanged. Enum for group classification suggested by Peter Zijlstra. Signed-off-by: Rik van Riel <riel@redhat.com> [peterz: replaced sg_lb_stats::group_imb with the new enum group_type in an attempt to avoid endless recalculation] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Michael Neuling <mikey@neuling.org> Cc: ktkhai@parallels.com Cc: tim.c.chen@linux.intel.com Cc: nicolas.pitre@linaro.org Cc: jhladky@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140729152743.GI3935@laptop Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-28 18:16:28 +00:00
if (sgs->group_type < busiest->group_type)
return false;
if (sgs->avg_load <= busiest->avg_load)
return false;
/* This is the busiest node in its class. */
if (!(env->sd->flags & SD_ASYM_PACKING))
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
return true;
/*
* ASYM_PACKING needs to move all the work to the lowest
* numbered CPUs in the group, therefore mark all groups
* higher than ourself as busy.
*/
sched/fair: Make update_sd_pick_busiest() return 'true' on a busier sd Currently update_sd_pick_busiest only identifies the busiest sd that is either overloaded, or has a group imbalance. When no sd is imbalanced or overloaded, the load balancer fails to find the busiest domain. This breaks load balancing between domains that are not overloaded, in the !SD_ASYM_PACKING case. This patch makes update_sd_pick_busiest return true when the busiest sd yet is encountered. Groups are ranked in the order overloaded > imbalanced > other, with higher ranked groups getting priority even when their load is lower. This is necessary due to the possibility of unequal capacities and cpumasks between domains within a sched group. Behaviour for SD_ASYM_PACKING does not seem to match the comment, but I have no hardware to test that so I have left the behaviour of that code unchanged. Enum for group classification suggested by Peter Zijlstra. Signed-off-by: Rik van Riel <riel@redhat.com> [peterz: replaced sg_lb_stats::group_imb with the new enum group_type in an attempt to avoid endless recalculation] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Michael Neuling <mikey@neuling.org> Cc: ktkhai@parallels.com Cc: tim.c.chen@linux.intel.com Cc: nicolas.pitre@linaro.org Cc: jhladky@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140729152743.GI3935@laptop Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-28 18:16:28 +00:00
if (sgs->sum_nr_running && env->dst_cpu < group_first_cpu(sg)) {
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
if (!sds->busiest)
return true;
if (group_first_cpu(sds->busiest) > group_first_cpu(sg))
return true;
}
return false;
}
#ifdef CONFIG_NUMA_BALANCING
static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs)
{
if (sgs->sum_nr_running > sgs->nr_numa_running)
return regular;
if (sgs->sum_nr_running > sgs->nr_preferred_running)
return remote;
return all;
}
static inline enum fbq_type fbq_classify_rq(struct rq *rq)
{
if (rq->nr_running > rq->nr_numa_running)
return regular;
if (rq->nr_running > rq->nr_preferred_running)
return remote;
return all;
}
#else
static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs)
{
return all;
}
static inline enum fbq_type fbq_classify_rq(struct rq *rq)
{
return regular;
}
#endif /* CONFIG_NUMA_BALANCING */
/**
* update_sd_lb_stats - Update sched_domain's statistics for load balancing.
* @env: The load balancing environment.
* @sds: variable to hold the statistics for this sched_domain.
*/
static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds)
{
struct sched_domain *child = env->sd->child;
struct sched_group *sg = env->sd->groups;
struct sg_lb_stats tmp_sgs;
int load_idx, prefer_sibling = 0;
sched/fair: Implement fast idling of CPUs when the system is partially loaded When a system is lightly loaded (i.e. no more than 1 job per cpu), attempt to pull job to a cpu before putting it to idle is unnecessary and can be skipped. This patch adds an indicator so the scheduler can know when there's no more than 1 active job is on any CPU in the system to skip needless job pulls. On a 4 socket machine with a request/response kind of workload from clients, we saw about 0.13 msec delay when we go through a full load balance to try pull job from all the other cpus. While 0.1 msec was spent on processing the request and generating a response, the 0.13 msec load balance overhead was actually more than the actual work being done. This overhead can be skipped much of the time for lightly loaded systems. With this patch, we tested with a netperf request/response workload that has the server busy with half the cpus in a 4 socket system. We found the patch eliminated 75% of the load balance attempts before idling a cpu. The overhead of setting/clearing the indicator is low as we already gather the necessary info while we call add_nr_running() and update_sd_lb_stats.() We switch to full load balance load immediately if any cpu got more than one job on its run queue in add_nr_running. We'll clear the indicator to avoid load balance when we detect no cpu's have more than one job when we scan the work queues in update_sg_lb_stats(). We are aggressive in turning on the load balance and opportunistic in skipping the load balance. Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Jason Low <jason.low2@hp.com> Cc: "Paul E.McKenney" <paulmck@linux.vnet.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Alex Shi <alex.shi@linaro.org> Cc: Michel Lespinasse <walken@google.com> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1403551009.2970.613.camel@schen9-DESK Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-23 19:16:49 +00:00
bool overload = false;
if (child && child->flags & SD_PREFER_SIBLING)
prefer_sibling = 1;
load_idx = get_sd_load_idx(env->sd, env->idle);
do {
struct sg_lb_stats *sgs = &tmp_sgs;
int local_group;
local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
if (local_group) {
sds->local = sg;
sgs = &sds->local_stat;
if (env->idle != CPU_NEWLY_IDLE ||
time_after_eq(jiffies, sg->sgc->next_update))
update_group_capacity(env->sd, env->dst_cpu);
}
sched/fair: Implement fast idling of CPUs when the system is partially loaded When a system is lightly loaded (i.e. no more than 1 job per cpu), attempt to pull job to a cpu before putting it to idle is unnecessary and can be skipped. This patch adds an indicator so the scheduler can know when there's no more than 1 active job is on any CPU in the system to skip needless job pulls. On a 4 socket machine with a request/response kind of workload from clients, we saw about 0.13 msec delay when we go through a full load balance to try pull job from all the other cpus. While 0.1 msec was spent on processing the request and generating a response, the 0.13 msec load balance overhead was actually more than the actual work being done. This overhead can be skipped much of the time for lightly loaded systems. With this patch, we tested with a netperf request/response workload that has the server busy with half the cpus in a 4 socket system. We found the patch eliminated 75% of the load balance attempts before idling a cpu. The overhead of setting/clearing the indicator is low as we already gather the necessary info while we call add_nr_running() and update_sd_lb_stats.() We switch to full load balance load immediately if any cpu got more than one job on its run queue in add_nr_running. We'll clear the indicator to avoid load balance when we detect no cpu's have more than one job when we scan the work queues in update_sg_lb_stats(). We are aggressive in turning on the load balance and opportunistic in skipping the load balance. Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Jason Low <jason.low2@hp.com> Cc: "Paul E.McKenney" <paulmck@linux.vnet.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Alex Shi <alex.shi@linaro.org> Cc: Michel Lespinasse <walken@google.com> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1403551009.2970.613.camel@schen9-DESK Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-23 19:16:49 +00:00
update_sg_lb_stats(env, sg, load_idx, local_group, sgs,
&overload);
if (local_group)
goto next_group;
/*
* In case the child domain prefers tasks go to siblings
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
* first, lower the sg capacity so that we'll try
sched: Drop group_capacity to 1 only if local group has extra capacity When SD_PREFER_SIBLING is set on a sched domain, drop group_capacity to 1 only if the local group has extra capacity. The extra check prevents the case where you always pull from the heaviest group when it is already under-utilized (possible with a large weight task outweighs the tasks on the system). For example, consider a 16-cpu quad-core quad-socket machine with MC and NUMA scheduling domains. Let's say we spawn 15 nice0 tasks and one nice-15 task, and each task is running on one core. In this case, we observe the following events when balancing at the NUMA domain: - find_busiest_group() will always pick the sched group containing the niced task to be the busiest group. - find_busiest_queue() will then always pick one of the cpus running the nice0 task (never picks the cpu with the nice -15 task since weighted_cpuload > imbalance). - The load balancer fails to migrate the task since it is the running task and increments sd->nr_balance_failed. - It repeats the above steps a few more times until sd->nr_balance_failed > 5, at which point it kicks off the active load balancer, wakes up the migration thread and kicks the nice 0 task off the cpu. The load balancer doesn't stop until we kick out all nice 0 tasks from the sched group, leaving you with 3 idle cpus and one cpu running the nice -15 task. When balancing at the NUMA domain, we drop sgs.group_capacity to 1 if the child domain (in this case MC) has SD_PREFER_SIBLING set. Subsequent load checks are not relevant because the niced task has a very large weight. In this patch, we add an extra condition to the "if(prefer_sibling)" check in update_sd_lb_stats(). We drop the capacity of a group only if the local group has extra capacity, ie. nr_running < group_capacity. This patch preserves the original intent of the prefer_siblings check (to spread tasks across the system in low utilization scenarios) and fixes the case above. It helps in the following ways: - In low utilization cases (where nr_tasks << nr_cpus), we still drop group_capacity down to 1 if we prefer siblings. - On very busy systems (where nr_tasks >> nr_cpus), sgs.nr_running will most likely be > sgs.group_capacity. - When balancing large weight tasks, if the local group does not have extra capacity, we do not pick the group with the niced task as the busiest group. This prevents failed balances, active migration and the under-utilization described above. Signed-off-by: Nikhil Rao <ncrao@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1287173550-30365-5-git-send-email-ncrao@google.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-10-15 20:12:30 +00:00
* and move all the excess tasks away. We lower the capacity
* of a group only if the local group has the capacity to fit
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
* these excess tasks. The extra check prevents the case where
* you always pull from the heaviest group when it is already
* under-utilized (possible with a large weight task outweighs
* the tasks on the system).
*/
if (prefer_sibling && sds->local &&
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
group_has_capacity(env, &sds->local_stat) &&
(sgs->sum_nr_running > 1)) {
sgs->group_no_capacity = 1;
sgs->group_type = group_overloaded;
}
if (update_sd_pick_busiest(env, sds, sg, sgs)) {
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
sds->busiest = sg;
sds->busiest_stat = *sgs;
}
next_group:
/* Now, start updating sd_lb_stats */
sds->total_load += sgs->group_load;
sds->total_capacity += sgs->group_capacity;
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
sg = sg->next;
} while (sg != env->sd->groups);
if (env->sd->flags & SD_NUMA)
env->fbq_type = fbq_classify_group(&sds->busiest_stat);
sched/fair: Implement fast idling of CPUs when the system is partially loaded When a system is lightly loaded (i.e. no more than 1 job per cpu), attempt to pull job to a cpu before putting it to idle is unnecessary and can be skipped. This patch adds an indicator so the scheduler can know when there's no more than 1 active job is on any CPU in the system to skip needless job pulls. On a 4 socket machine with a request/response kind of workload from clients, we saw about 0.13 msec delay when we go through a full load balance to try pull job from all the other cpus. While 0.1 msec was spent on processing the request and generating a response, the 0.13 msec load balance overhead was actually more than the actual work being done. This overhead can be skipped much of the time for lightly loaded systems. With this patch, we tested with a netperf request/response workload that has the server busy with half the cpus in a 4 socket system. We found the patch eliminated 75% of the load balance attempts before idling a cpu. The overhead of setting/clearing the indicator is low as we already gather the necessary info while we call add_nr_running() and update_sd_lb_stats.() We switch to full load balance load immediately if any cpu got more than one job on its run queue in add_nr_running. We'll clear the indicator to avoid load balance when we detect no cpu's have more than one job when we scan the work queues in update_sg_lb_stats(). We are aggressive in turning on the load balance and opportunistic in skipping the load balance. Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Jason Low <jason.low2@hp.com> Cc: "Paul E.McKenney" <paulmck@linux.vnet.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Alex Shi <alex.shi@linaro.org> Cc: Michel Lespinasse <walken@google.com> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1403551009.2970.613.camel@schen9-DESK Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-23 19:16:49 +00:00
if (!env->sd->parent) {
/* update overload indicator if we are at root domain */
if (env->dst_rq->rd->overload != overload)
env->dst_rq->rd->overload = overload;
}
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
}
/**
* check_asym_packing - Check to see if the group is packed into the
* sched doman.
*
* This is primarily intended to used at the sibling level. Some
* cores like POWER7 prefer to use lower numbered SMT threads. In the
* case of POWER7, it can move to lower SMT modes only when higher
* threads are idle. When in lower SMT modes, the threads will
* perform better since they share less core resources. Hence when we
* have idle threads, we want them to be the higher ones.
*
* This packing function is run on idle threads. It checks to see if
* the busiest CPU in this domain (core in the P7 case) has a higher
* CPU number than the packing function is being run on. Here we are
* assuming lower CPU number will be equivalent to lower a SMT thread
* number.
*
* Return: 1 when packing is required and a task should be moved to
* this CPU. The amount of the imbalance is returned in *imbalance.
*
* @env: The load balancing environment.
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
* @sds: Statistics of the sched_domain which is to be packed
*/
static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
{
int busiest_cpu;
if (!(env->sd->flags & SD_ASYM_PACKING))
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
return 0;
if (!sds->busiest)
return 0;
busiest_cpu = group_first_cpu(sds->busiest);
if (env->dst_cpu > busiest_cpu)
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
return 0;
env->imbalance = DIV_ROUND_CLOSEST(
sds->busiest_stat.avg_load * sds->busiest_stat.group_capacity,
sched: Final power vs. capacity cleanups It is better not to think about compute capacity as being equivalent to "CPU power". The upcoming "power aware" scheduler work may create confusion with the notion of energy consumption if "power" is used too liberally. This contains the architecture visible changes. Incidentally, only ARM takes advantage of the available pow^H^H^Hcapacity scaling hooks and therefore those changes outside kernel/sched/ are confined to one ARM specific file. The default arch_scale_smt_power() hook is not overridden by anyone. Replacements are as follows: arch_scale_freq_power --> arch_scale_freq_capacity arch_scale_smt_power --> arch_scale_smt_capacity SCHED_POWER_SCALE --> SCHED_CAPACITY_SCALE SCHED_POWER_SHIFT --> SCHED_CAPACITY_SHIFT The local usage of "power" in arch/arm/kernel/topology.c is also changed to "capacity" as appropriate. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Morten Rasmussen <morten.rasmussen@arm.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: linaro-kernel@lists.linaro.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com> Cc: Grant Likely <grant.likely@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Brown <broonie@linaro.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: devicetree@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/n/tip-48zba9qbznvglwelgq2cfygh@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-26 22:19:39 +00:00
SCHED_CAPACITY_SCALE);
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
return 1;
}
/**
* fix_small_imbalance - Calculate the minor imbalance that exists
* amongst the groups of a sched_domain, during
* load balancing.
* @env: The load balancing environment.
* @sds: Statistics of the sched_domain whose imbalance is to be calculated.
*/
static inline
void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
{
unsigned long tmp, capa_now = 0, capa_move = 0;
unsigned int imbn = 2;
sched: Fix SCHED_MC regression caused by change in sched cpu_power On platforms like dual socket quad-core platform, the scheduler load balancer is not detecting the load imbalances in certain scenarios. This is leading to scenarios like where one socket is completely busy (with all the 4 cores running with 4 tasks) and leaving another socket completely idle. This causes performance issues as those 4 tasks share the memory controller, last-level cache bandwidth etc. Also we won't be taking advantage of turbo-mode as much as we would like, etc. Some of the comparisons in the scheduler load balancing code are comparing the "weighted cpu load that is scaled wrt sched_group's cpu_power" with the "weighted average load per task that is not scaled wrt sched_group's cpu_power". While this has probably been broken for a longer time (for multi socket numa nodes etc), the problem got aggrevated via this recent change: | | commit f93e65c186ab3c05ce2068733ca10e34fd00125e | Author: Peter Zijlstra <a.p.zijlstra@chello.nl> | Date: Tue Sep 1 10:34:32 2009 +0200 | | sched: Restore __cpu_power to a straight sum of power | Also with this change, the sched group cpu power alone no longer reflects the group capacity that is needed to implement MC, MT performance (default) and power-savings (user-selectable) policies. We need to use the computed group capacity (sgs.group_capacity, that is computed using the SD_PREFER_SIBLING logic in update_sd_lb_stats()) to find out if the group with the max load is above its capacity and how much load to move etc. Reported-by: Ma Ling <ling.ma@intel.com> Initial-Analysis-by: Zhang, Yanmin <yanmin_zhang@linux.intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> [ -v2: build fix ] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: <stable@kernel.org> # [2.6.32.x, 2.6.33.x] LKML-Reference: <1266970432.11588.22.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-24 00:13:52 +00:00
unsigned long scaled_busy_load_per_task;
struct sg_lb_stats *local, *busiest;
local = &sds->local_stat;
busiest = &sds->busiest_stat;
if (!local->sum_nr_running)
local->load_per_task = cpu_avg_load_per_task(env->dst_cpu);
else if (busiest->load_per_task > local->load_per_task)
imbn = 1;
sched: Fix SCHED_MC regression caused by change in sched cpu_power On platforms like dual socket quad-core platform, the scheduler load balancer is not detecting the load imbalances in certain scenarios. This is leading to scenarios like where one socket is completely busy (with all the 4 cores running with 4 tasks) and leaving another socket completely idle. This causes performance issues as those 4 tasks share the memory controller, last-level cache bandwidth etc. Also we won't be taking advantage of turbo-mode as much as we would like, etc. Some of the comparisons in the scheduler load balancing code are comparing the "weighted cpu load that is scaled wrt sched_group's cpu_power" with the "weighted average load per task that is not scaled wrt sched_group's cpu_power". While this has probably been broken for a longer time (for multi socket numa nodes etc), the problem got aggrevated via this recent change: | | commit f93e65c186ab3c05ce2068733ca10e34fd00125e | Author: Peter Zijlstra <a.p.zijlstra@chello.nl> | Date: Tue Sep 1 10:34:32 2009 +0200 | | sched: Restore __cpu_power to a straight sum of power | Also with this change, the sched group cpu power alone no longer reflects the group capacity that is needed to implement MC, MT performance (default) and power-savings (user-selectable) policies. We need to use the computed group capacity (sgs.group_capacity, that is computed using the SD_PREFER_SIBLING logic in update_sd_lb_stats()) to find out if the group with the max load is above its capacity and how much load to move etc. Reported-by: Ma Ling <ling.ma@intel.com> Initial-Analysis-by: Zhang, Yanmin <yanmin_zhang@linux.intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> [ -v2: build fix ] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: <stable@kernel.org> # [2.6.32.x, 2.6.33.x] LKML-Reference: <1266970432.11588.22.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-24 00:13:52 +00:00
scaled_busy_load_per_task =
sched: Final power vs. capacity cleanups It is better not to think about compute capacity as being equivalent to "CPU power". The upcoming "power aware" scheduler work may create confusion with the notion of energy consumption if "power" is used too liberally. This contains the architecture visible changes. Incidentally, only ARM takes advantage of the available pow^H^H^Hcapacity scaling hooks and therefore those changes outside kernel/sched/ are confined to one ARM specific file. The default arch_scale_smt_power() hook is not overridden by anyone. Replacements are as follows: arch_scale_freq_power --> arch_scale_freq_capacity arch_scale_smt_power --> arch_scale_smt_capacity SCHED_POWER_SCALE --> SCHED_CAPACITY_SCALE SCHED_POWER_SHIFT --> SCHED_CAPACITY_SHIFT The local usage of "power" in arch/arm/kernel/topology.c is also changed to "capacity" as appropriate. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Morten Rasmussen <morten.rasmussen@arm.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: linaro-kernel@lists.linaro.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com> Cc: Grant Likely <grant.likely@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Brown <broonie@linaro.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: devicetree@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/n/tip-48zba9qbznvglwelgq2cfygh@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-26 22:19:39 +00:00
(busiest->load_per_task * SCHED_CAPACITY_SCALE) /
busiest->group_capacity;
if (busiest->avg_load + scaled_busy_load_per_task >=
local->avg_load + (scaled_busy_load_per_task * imbn)) {
env->imbalance = busiest->load_per_task;
return;
}
/*
* OK, we don't have enough imbalance to justify moving tasks,
* however we may be able to increase total CPU capacity used by
* moving them.
*/
capa_now += busiest->group_capacity *
min(busiest->load_per_task, busiest->avg_load);
capa_now += local->group_capacity *
min(local->load_per_task, local->avg_load);
sched: Final power vs. capacity cleanups It is better not to think about compute capacity as being equivalent to "CPU power". The upcoming "power aware" scheduler work may create confusion with the notion of energy consumption if "power" is used too liberally. This contains the architecture visible changes. Incidentally, only ARM takes advantage of the available pow^H^H^Hcapacity scaling hooks and therefore those changes outside kernel/sched/ are confined to one ARM specific file. The default arch_scale_smt_power() hook is not overridden by anyone. Replacements are as follows: arch_scale_freq_power --> arch_scale_freq_capacity arch_scale_smt_power --> arch_scale_smt_capacity SCHED_POWER_SCALE --> SCHED_CAPACITY_SCALE SCHED_POWER_SHIFT --> SCHED_CAPACITY_SHIFT The local usage of "power" in arch/arm/kernel/topology.c is also changed to "capacity" as appropriate. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Morten Rasmussen <morten.rasmussen@arm.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: linaro-kernel@lists.linaro.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com> Cc: Grant Likely <grant.likely@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Brown <broonie@linaro.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: devicetree@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/n/tip-48zba9qbznvglwelgq2cfygh@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-26 22:19:39 +00:00
capa_now /= SCHED_CAPACITY_SCALE;
/* Amount of load we'd subtract */
if (busiest->avg_load > scaled_busy_load_per_task) {
capa_move += busiest->group_capacity *
min(busiest->load_per_task,
busiest->avg_load - scaled_busy_load_per_task);
}
/* Amount of load we'd add */
if (busiest->avg_load * busiest->group_capacity <
sched: Final power vs. capacity cleanups It is better not to think about compute capacity as being equivalent to "CPU power". The upcoming "power aware" scheduler work may create confusion with the notion of energy consumption if "power" is used too liberally. This contains the architecture visible changes. Incidentally, only ARM takes advantage of the available pow^H^H^Hcapacity scaling hooks and therefore those changes outside kernel/sched/ are confined to one ARM specific file. The default arch_scale_smt_power() hook is not overridden by anyone. Replacements are as follows: arch_scale_freq_power --> arch_scale_freq_capacity arch_scale_smt_power --> arch_scale_smt_capacity SCHED_POWER_SCALE --> SCHED_CAPACITY_SCALE SCHED_POWER_SHIFT --> SCHED_CAPACITY_SHIFT The local usage of "power" in arch/arm/kernel/topology.c is also changed to "capacity" as appropriate. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Morten Rasmussen <morten.rasmussen@arm.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: linaro-kernel@lists.linaro.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com> Cc: Grant Likely <grant.likely@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Brown <broonie@linaro.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: devicetree@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/n/tip-48zba9qbznvglwelgq2cfygh@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-26 22:19:39 +00:00
busiest->load_per_task * SCHED_CAPACITY_SCALE) {
tmp = (busiest->avg_load * busiest->group_capacity) /
local->group_capacity;
} else {
sched: Final power vs. capacity cleanups It is better not to think about compute capacity as being equivalent to "CPU power". The upcoming "power aware" scheduler work may create confusion with the notion of energy consumption if "power" is used too liberally. This contains the architecture visible changes. Incidentally, only ARM takes advantage of the available pow^H^H^Hcapacity scaling hooks and therefore those changes outside kernel/sched/ are confined to one ARM specific file. The default arch_scale_smt_power() hook is not overridden by anyone. Replacements are as follows: arch_scale_freq_power --> arch_scale_freq_capacity arch_scale_smt_power --> arch_scale_smt_capacity SCHED_POWER_SCALE --> SCHED_CAPACITY_SCALE SCHED_POWER_SHIFT --> SCHED_CAPACITY_SHIFT The local usage of "power" in arch/arm/kernel/topology.c is also changed to "capacity" as appropriate. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Morten Rasmussen <morten.rasmussen@arm.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: linaro-kernel@lists.linaro.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com> Cc: Grant Likely <grant.likely@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Brown <broonie@linaro.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: devicetree@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/n/tip-48zba9qbznvglwelgq2cfygh@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-26 22:19:39 +00:00
tmp = (busiest->load_per_task * SCHED_CAPACITY_SCALE) /
local->group_capacity;
}
capa_move += local->group_capacity *
min(local->load_per_task, local->avg_load + tmp);
sched: Final power vs. capacity cleanups It is better not to think about compute capacity as being equivalent to "CPU power". The upcoming "power aware" scheduler work may create confusion with the notion of energy consumption if "power" is used too liberally. This contains the architecture visible changes. Incidentally, only ARM takes advantage of the available pow^H^H^Hcapacity scaling hooks and therefore those changes outside kernel/sched/ are confined to one ARM specific file. The default arch_scale_smt_power() hook is not overridden by anyone. Replacements are as follows: arch_scale_freq_power --> arch_scale_freq_capacity arch_scale_smt_power --> arch_scale_smt_capacity SCHED_POWER_SCALE --> SCHED_CAPACITY_SCALE SCHED_POWER_SHIFT --> SCHED_CAPACITY_SHIFT The local usage of "power" in arch/arm/kernel/topology.c is also changed to "capacity" as appropriate. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Morten Rasmussen <morten.rasmussen@arm.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: linaro-kernel@lists.linaro.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com> Cc: Grant Likely <grant.likely@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Brown <broonie@linaro.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: devicetree@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/n/tip-48zba9qbznvglwelgq2cfygh@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-26 22:19:39 +00:00
capa_move /= SCHED_CAPACITY_SCALE;
/* Move if we gain throughput */
if (capa_move > capa_now)
env->imbalance = busiest->load_per_task;
}
/**
* calculate_imbalance - Calculate the amount of imbalance present within the
* groups of a given sched_domain during load balance.
* @env: load balance environment
* @sds: statistics of the sched_domain whose imbalance is to be calculated.
*/
static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
{
sched: Fix SCHED_MC regression caused by change in sched cpu_power On platforms like dual socket quad-core platform, the scheduler load balancer is not detecting the load imbalances in certain scenarios. This is leading to scenarios like where one socket is completely busy (with all the 4 cores running with 4 tasks) and leaving another socket completely idle. This causes performance issues as those 4 tasks share the memory controller, last-level cache bandwidth etc. Also we won't be taking advantage of turbo-mode as much as we would like, etc. Some of the comparisons in the scheduler load balancing code are comparing the "weighted cpu load that is scaled wrt sched_group's cpu_power" with the "weighted average load per task that is not scaled wrt sched_group's cpu_power". While this has probably been broken for a longer time (for multi socket numa nodes etc), the problem got aggrevated via this recent change: | | commit f93e65c186ab3c05ce2068733ca10e34fd00125e | Author: Peter Zijlstra <a.p.zijlstra@chello.nl> | Date: Tue Sep 1 10:34:32 2009 +0200 | | sched: Restore __cpu_power to a straight sum of power | Also with this change, the sched group cpu power alone no longer reflects the group capacity that is needed to implement MC, MT performance (default) and power-savings (user-selectable) policies. We need to use the computed group capacity (sgs.group_capacity, that is computed using the SD_PREFER_SIBLING logic in update_sd_lb_stats()) to find out if the group with the max load is above its capacity and how much load to move etc. Reported-by: Ma Ling <ling.ma@intel.com> Initial-Analysis-by: Zhang, Yanmin <yanmin_zhang@linux.intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> [ -v2: build fix ] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: <stable@kernel.org> # [2.6.32.x, 2.6.33.x] LKML-Reference: <1266970432.11588.22.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-24 00:13:52 +00:00
unsigned long max_pull, load_above_capacity = ~0UL;
struct sg_lb_stats *local, *busiest;
local = &sds->local_stat;
busiest = &sds->busiest_stat;
sched: Fix SCHED_MC regression caused by change in sched cpu_power On platforms like dual socket quad-core platform, the scheduler load balancer is not detecting the load imbalances in certain scenarios. This is leading to scenarios like where one socket is completely busy (with all the 4 cores running with 4 tasks) and leaving another socket completely idle. This causes performance issues as those 4 tasks share the memory controller, last-level cache bandwidth etc. Also we won't be taking advantage of turbo-mode as much as we would like, etc. Some of the comparisons in the scheduler load balancing code are comparing the "weighted cpu load that is scaled wrt sched_group's cpu_power" with the "weighted average load per task that is not scaled wrt sched_group's cpu_power". While this has probably been broken for a longer time (for multi socket numa nodes etc), the problem got aggrevated via this recent change: | | commit f93e65c186ab3c05ce2068733ca10e34fd00125e | Author: Peter Zijlstra <a.p.zijlstra@chello.nl> | Date: Tue Sep 1 10:34:32 2009 +0200 | | sched: Restore __cpu_power to a straight sum of power | Also with this change, the sched group cpu power alone no longer reflects the group capacity that is needed to implement MC, MT performance (default) and power-savings (user-selectable) policies. We need to use the computed group capacity (sgs.group_capacity, that is computed using the SD_PREFER_SIBLING logic in update_sd_lb_stats()) to find out if the group with the max load is above its capacity and how much load to move etc. Reported-by: Ma Ling <ling.ma@intel.com> Initial-Analysis-by: Zhang, Yanmin <yanmin_zhang@linux.intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> [ -v2: build fix ] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: <stable@kernel.org> # [2.6.32.x, 2.6.33.x] LKML-Reference: <1266970432.11588.22.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-24 00:13:52 +00:00
sched/fair: Make update_sd_pick_busiest() return 'true' on a busier sd Currently update_sd_pick_busiest only identifies the busiest sd that is either overloaded, or has a group imbalance. When no sd is imbalanced or overloaded, the load balancer fails to find the busiest domain. This breaks load balancing between domains that are not overloaded, in the !SD_ASYM_PACKING case. This patch makes update_sd_pick_busiest return true when the busiest sd yet is encountered. Groups are ranked in the order overloaded > imbalanced > other, with higher ranked groups getting priority even when their load is lower. This is necessary due to the possibility of unequal capacities and cpumasks between domains within a sched group. Behaviour for SD_ASYM_PACKING does not seem to match the comment, but I have no hardware to test that so I have left the behaviour of that code unchanged. Enum for group classification suggested by Peter Zijlstra. Signed-off-by: Rik van Riel <riel@redhat.com> [peterz: replaced sg_lb_stats::group_imb with the new enum group_type in an attempt to avoid endless recalculation] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Michael Neuling <mikey@neuling.org> Cc: ktkhai@parallels.com Cc: tim.c.chen@linux.intel.com Cc: nicolas.pitre@linaro.org Cc: jhladky@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140729152743.GI3935@laptop Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-28 18:16:28 +00:00
if (busiest->group_type == group_imbalanced) {
/*
* In the group_imb case we cannot rely on group-wide averages
* to ensure cpu-load equilibrium, look at wider averages. XXX
*/
busiest->load_per_task =
min(busiest->load_per_task, sds->avg_load);
sched: Fix SCHED_MC regression caused by change in sched cpu_power On platforms like dual socket quad-core platform, the scheduler load balancer is not detecting the load imbalances in certain scenarios. This is leading to scenarios like where one socket is completely busy (with all the 4 cores running with 4 tasks) and leaving another socket completely idle. This causes performance issues as those 4 tasks share the memory controller, last-level cache bandwidth etc. Also we won't be taking advantage of turbo-mode as much as we would like, etc. Some of the comparisons in the scheduler load balancing code are comparing the "weighted cpu load that is scaled wrt sched_group's cpu_power" with the "weighted average load per task that is not scaled wrt sched_group's cpu_power". While this has probably been broken for a longer time (for multi socket numa nodes etc), the problem got aggrevated via this recent change: | | commit f93e65c186ab3c05ce2068733ca10e34fd00125e | Author: Peter Zijlstra <a.p.zijlstra@chello.nl> | Date: Tue Sep 1 10:34:32 2009 +0200 | | sched: Restore __cpu_power to a straight sum of power | Also with this change, the sched group cpu power alone no longer reflects the group capacity that is needed to implement MC, MT performance (default) and power-savings (user-selectable) policies. We need to use the computed group capacity (sgs.group_capacity, that is computed using the SD_PREFER_SIBLING logic in update_sd_lb_stats()) to find out if the group with the max load is above its capacity and how much load to move etc. Reported-by: Ma Ling <ling.ma@intel.com> Initial-Analysis-by: Zhang, Yanmin <yanmin_zhang@linux.intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> [ -v2: build fix ] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: <stable@kernel.org> # [2.6.32.x, 2.6.33.x] LKML-Reference: <1266970432.11588.22.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-24 00:13:52 +00:00
}
/*
* In the presence of smp nice balancing, certain scenarios can have
* max load less than avg load(as we skip the groups at or below
* its cpu_capacity, while calculating max_load..)
*/
if (busiest->avg_load <= sds->avg_load ||
local->avg_load >= sds->avg_load) {
env->imbalance = 0;
return fix_small_imbalance(env, sds);
}
/*
* If there aren't any idle cpus, avoid creating some.
*/
if (busiest->group_type == group_overloaded &&
local->group_type == group_overloaded) {
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
load_above_capacity = busiest->sum_nr_running *
SCHED_LOAD_SCALE;
if (load_above_capacity > busiest->group_capacity)
load_above_capacity -= busiest->group_capacity;
else
load_above_capacity = ~0UL;
sched: Fix SCHED_MC regression caused by change in sched cpu_power On platforms like dual socket quad-core platform, the scheduler load balancer is not detecting the load imbalances in certain scenarios. This is leading to scenarios like where one socket is completely busy (with all the 4 cores running with 4 tasks) and leaving another socket completely idle. This causes performance issues as those 4 tasks share the memory controller, last-level cache bandwidth etc. Also we won't be taking advantage of turbo-mode as much as we would like, etc. Some of the comparisons in the scheduler load balancing code are comparing the "weighted cpu load that is scaled wrt sched_group's cpu_power" with the "weighted average load per task that is not scaled wrt sched_group's cpu_power". While this has probably been broken for a longer time (for multi socket numa nodes etc), the problem got aggrevated via this recent change: | | commit f93e65c186ab3c05ce2068733ca10e34fd00125e | Author: Peter Zijlstra <a.p.zijlstra@chello.nl> | Date: Tue Sep 1 10:34:32 2009 +0200 | | sched: Restore __cpu_power to a straight sum of power | Also with this change, the sched group cpu power alone no longer reflects the group capacity that is needed to implement MC, MT performance (default) and power-savings (user-selectable) policies. We need to use the computed group capacity (sgs.group_capacity, that is computed using the SD_PREFER_SIBLING logic in update_sd_lb_stats()) to find out if the group with the max load is above its capacity and how much load to move etc. Reported-by: Ma Ling <ling.ma@intel.com> Initial-Analysis-by: Zhang, Yanmin <yanmin_zhang@linux.intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> [ -v2: build fix ] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: <stable@kernel.org> # [2.6.32.x, 2.6.33.x] LKML-Reference: <1266970432.11588.22.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-24 00:13:52 +00:00
}
/*
* We're trying to get all the cpus to the average_load, so we don't
* want to push ourselves above the average load, nor do we wish to
* reduce the max loaded cpu below the average load. At the same time,
* we also don't want to reduce the group load below the group capacity
* (so that we can implement power-savings policies etc). Thus we look
* for the minimum possible imbalance.
*/
max_pull = min(busiest->avg_load - sds->avg_load, load_above_capacity);
/* How much load to actually move to equalise the imbalance */
env->imbalance = min(
max_pull * busiest->group_capacity,
(sds->avg_load - local->avg_load) * local->group_capacity
sched: Final power vs. capacity cleanups It is better not to think about compute capacity as being equivalent to "CPU power". The upcoming "power aware" scheduler work may create confusion with the notion of energy consumption if "power" is used too liberally. This contains the architecture visible changes. Incidentally, only ARM takes advantage of the available pow^H^H^Hcapacity scaling hooks and therefore those changes outside kernel/sched/ are confined to one ARM specific file. The default arch_scale_smt_power() hook is not overridden by anyone. Replacements are as follows: arch_scale_freq_power --> arch_scale_freq_capacity arch_scale_smt_power --> arch_scale_smt_capacity SCHED_POWER_SCALE --> SCHED_CAPACITY_SCALE SCHED_POWER_SHIFT --> SCHED_CAPACITY_SHIFT The local usage of "power" in arch/arm/kernel/topology.c is also changed to "capacity" as appropriate. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Morten Rasmussen <morten.rasmussen@arm.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: linaro-kernel@lists.linaro.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com> Cc: Grant Likely <grant.likely@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Brown <broonie@linaro.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: devicetree@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/n/tip-48zba9qbznvglwelgq2cfygh@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-26 22:19:39 +00:00
) / SCHED_CAPACITY_SCALE;
/*
* if *imbalance is less than the average load per runnable task
* there is no guarantee that any tasks will be moved so we'll have
* a think about bumping its value to force at least one task to be
* moved
*/
if (env->imbalance < busiest->load_per_task)
return fix_small_imbalance(env, sds);
}
/******* find_busiest_group() helpers end here *********************/
/**
* find_busiest_group - Returns the busiest group within the sched_domain
* if there is an imbalance. If there isn't an imbalance, and
* the user has opted for power-savings, it returns a group whose
* CPUs can be put to idle by rebalancing those tasks elsewhere, if
* such a group exists.
*
* Also calculates the amount of weighted load which should be moved
* to restore balance.
*
* @env: The load balancing environment.
*
* Return: - The busiest group if imbalance exists.
* - If no imbalance and user has opted for power-savings balance,
* return the least loaded group whose CPUs can be
* put to idle by rebalancing its tasks onto our group.
*/
static struct sched_group *find_busiest_group(struct lb_env *env)
{
struct sg_lb_stats *local, *busiest;
struct sd_lb_stats sds;
init_sd_lb_stats(&sds);
/*
* Compute the various statistics relavent for load balancing at
* this level.
*/
update_sd_lb_stats(env, &sds);
local = &sds.local_stat;
busiest = &sds.busiest_stat;
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
/* ASYM feature bypasses nice load balance check */
if ((env->idle == CPU_IDLE || env->idle == CPU_NEWLY_IDLE) &&
check_asym_packing(env, &sds))
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
return sds.busiest;
/* There is no busy sibling group to pull tasks from */
if (!sds.busiest || busiest->sum_nr_running == 0)
goto out_balanced;
sched: Final power vs. capacity cleanups It is better not to think about compute capacity as being equivalent to "CPU power". The upcoming "power aware" scheduler work may create confusion with the notion of energy consumption if "power" is used too liberally. This contains the architecture visible changes. Incidentally, only ARM takes advantage of the available pow^H^H^Hcapacity scaling hooks and therefore those changes outside kernel/sched/ are confined to one ARM specific file. The default arch_scale_smt_power() hook is not overridden by anyone. Replacements are as follows: arch_scale_freq_power --> arch_scale_freq_capacity arch_scale_smt_power --> arch_scale_smt_capacity SCHED_POWER_SCALE --> SCHED_CAPACITY_SCALE SCHED_POWER_SHIFT --> SCHED_CAPACITY_SHIFT The local usage of "power" in arch/arm/kernel/topology.c is also changed to "capacity" as appropriate. Signed-off-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Morten Rasmussen <morten.rasmussen@arm.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: linaro-kernel@lists.linaro.org Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com> Cc: Grant Likely <grant.likely@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Brown <broonie@linaro.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: devicetree@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/n/tip-48zba9qbznvglwelgq2cfygh@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-26 22:19:39 +00:00
sds.avg_load = (SCHED_CAPACITY_SCALE * sds.total_load)
/ sds.total_capacity;
/*
* If the busiest group is imbalanced the below checks don't
* work because they assume all things are equal, which typically
* isn't true due to cpus_allowed constraints and the like.
*/
sched/fair: Make update_sd_pick_busiest() return 'true' on a busier sd Currently update_sd_pick_busiest only identifies the busiest sd that is either overloaded, or has a group imbalance. When no sd is imbalanced or overloaded, the load balancer fails to find the busiest domain. This breaks load balancing between domains that are not overloaded, in the !SD_ASYM_PACKING case. This patch makes update_sd_pick_busiest return true when the busiest sd yet is encountered. Groups are ranked in the order overloaded > imbalanced > other, with higher ranked groups getting priority even when their load is lower. This is necessary due to the possibility of unequal capacities and cpumasks between domains within a sched group. Behaviour for SD_ASYM_PACKING does not seem to match the comment, but I have no hardware to test that so I have left the behaviour of that code unchanged. Enum for group classification suggested by Peter Zijlstra. Signed-off-by: Rik van Riel <riel@redhat.com> [peterz: replaced sg_lb_stats::group_imb with the new enum group_type in an attempt to avoid endless recalculation] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Michael Neuling <mikey@neuling.org> Cc: ktkhai@parallels.com Cc: tim.c.chen@linux.intel.com Cc: nicolas.pitre@linaro.org Cc: jhladky@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140729152743.GI3935@laptop Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-28 18:16:28 +00:00
if (busiest->group_type == group_imbalanced)
goto force_balance;
/* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
if (env->idle == CPU_NEWLY_IDLE && group_has_capacity(env, local) &&
busiest->group_no_capacity)
goto force_balance;
/*
* If the local group is busier than the selected busiest group
* don't try and pull any tasks.
*/
if (local->avg_load >= busiest->avg_load)
goto out_balanced;
/*
* Don't pull any tasks if this group is already above the domain
* average load.
*/
if (local->avg_load >= sds.avg_load)
goto out_balanced;
if (env->idle == CPU_IDLE) {
sched: Use group weight, idle cpu metrics to fix imbalances during idle Currently we consider a sched domain to be well balanced when the imbalance is less than the domain's imablance_pct. As the number of cores and threads are increasing, current values of imbalance_pct (for example 25% for a NUMA domain) are not enough to detect imbalances like: a) On a WSM-EP system (two sockets, each having 6 cores and 12 logical threads), 24 cpu-hogging tasks get scheduled as 13 on one socket and 11 on another socket. Leading to an idle HT cpu. b) On a hypothetial 2 socket NHM-EX system (each socket having 8 cores and 16 logical threads), 16 cpu-hogging tasks can get scheduled as 9 on one socket and 7 on another socket. Leaving one core in a socket idle whereas in another socket we have a core having both its HT siblings busy. While this issue can be fixed by decreasing the domain's imbalance_pct (by making it a function of number of logical cpus in the domain), it can potentially cause more task migrations across sched groups in an overloaded case. Fix this by using imbalance_pct only during newly_idle and busy load balancing. And during idle load balancing, check if there is an imbalance in number of idle cpu's across the busiest and this sched_group or if the busiest group has more tasks than its weight that the idle cpu in this_group can pull. Reported-by: Nikhil Rao <ncrao@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1284760952.2676.11.camel@sbsiddha-MOBL3.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-09-17 22:02:32 +00:00
/*
sched: Improve sysbench performance by fixing spurious active migration Since commit caeb178c60f4 ("sched/fair: Make update_sd_pick_busiest() ...") sd_pick_busiest returns a group that can be neither imbalanced nor overloaded but is only more loaded than others. This change has been introduced to ensure a better load balance in system that are not overloaded but as a side effect, it can also generate useless active migration between groups. Let take the example of 3 tasks on a quad cores system. We will always have an idle core so the load balance will find a busiest group (core) whenever an ILB is triggered and it will force an active migration (once above nr_balance_failed threshold) so the idle core becomes busy but another core will become idle. With the next ILB, the freshly idle core will try to pull the task of a busy CPU. The number of spurious active migration is not so huge in quad core system because the ILB is not triggered so much. But it becomes significant as soon as you have more than one sched_domain level like on a dual cluster of quad cores where the ILB is triggered every tick when you have more than 1 busy_cpu We need to ensure that the migration generate a real improveùent and will not only move the avg_load imbalance on another CPU. Before caeb178c60f4f93f1b45c0bc056b5cf6d217b67f, the filtering of such use case was ensured by the following test in f_b_g: if ((local->idle_cpus < busiest->idle_cpus) && busiest->sum_nr_running <= busiest->group_weight) This patch modified the condition to take into account situation where busiest group is not overloaded: If the diff between the number of idle cpus in 2 groups is less than or equal to 1 and the busiest group is not overloaded, moving a task will not improve the load balance but just move it. A test with sysbench on a dual clusters of quad cores gives the following results: command: sysbench --test=cpu --num-threads=5 --max-time=5 run The HZ is 200 which means that 1000 ticks has fired during the test. With Mainline, perf gives the following figures: Samples: 727 of event 'sched:sched_migrate_task' Event count (approx.): 727 Overhead Command Shared Object Symbol ........ ............... ............. .............. 12.52% migration/1 [unknown] [.] 00000000 12.52% migration/5 [unknown] [.] 00000000 12.52% migration/7 [unknown] [.] 00000000 12.10% migration/6 [unknown] [.] 00000000 11.83% migration/0 [unknown] [.] 00000000 11.83% migration/3 [unknown] [.] 00000000 11.14% migration/4 [unknown] [.] 00000000 10.87% migration/2 [unknown] [.] 00000000 2.75% sysbench [unknown] [.] 00000000 0.83% swapper [unknown] [.] 00000000 0.55% ktps65090charge [unknown] [.] 00000000 0.41% mmcqd/1 [unknown] [.] 00000000 0.14% perf [unknown] [.] 00000000 With this patch, perf gives the following figures Samples: 20 of event 'sched:sched_migrate_task' Event count (approx.): 20 Overhead Command Shared Object Symbol ........ ............... ............. .............. 80.00% sysbench [unknown] [.] 00000000 10.00% swapper [unknown] [.] 00000000 5.00% ktps65090charge [unknown] [.] 00000000 5.00% migration/1 [unknown] [.] 00000000 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Reviewed-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1412170735-5356-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-10-01 13:38:55 +00:00
* This cpu is idle. If the busiest group is not overloaded
* and there is no imbalance between this and busiest group
* wrt idle cpus, it is balanced. The imbalance becomes
* significant if the diff is greater than 1 otherwise we
* might end up to just move the imbalance on another group
sched: Use group weight, idle cpu metrics to fix imbalances during idle Currently we consider a sched domain to be well balanced when the imbalance is less than the domain's imablance_pct. As the number of cores and threads are increasing, current values of imbalance_pct (for example 25% for a NUMA domain) are not enough to detect imbalances like: a) On a WSM-EP system (two sockets, each having 6 cores and 12 logical threads), 24 cpu-hogging tasks get scheduled as 13 on one socket and 11 on another socket. Leading to an idle HT cpu. b) On a hypothetial 2 socket NHM-EX system (each socket having 8 cores and 16 logical threads), 16 cpu-hogging tasks can get scheduled as 9 on one socket and 7 on another socket. Leaving one core in a socket idle whereas in another socket we have a core having both its HT siblings busy. While this issue can be fixed by decreasing the domain's imbalance_pct (by making it a function of number of logical cpus in the domain), it can potentially cause more task migrations across sched groups in an overloaded case. Fix this by using imbalance_pct only during newly_idle and busy load balancing. And during idle load balancing, check if there is an imbalance in number of idle cpu's across the busiest and this sched_group or if the busiest group has more tasks than its weight that the idle cpu in this_group can pull. Reported-by: Nikhil Rao <ncrao@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1284760952.2676.11.camel@sbsiddha-MOBL3.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-09-17 22:02:32 +00:00
*/
sched: Improve sysbench performance by fixing spurious active migration Since commit caeb178c60f4 ("sched/fair: Make update_sd_pick_busiest() ...") sd_pick_busiest returns a group that can be neither imbalanced nor overloaded but is only more loaded than others. This change has been introduced to ensure a better load balance in system that are not overloaded but as a side effect, it can also generate useless active migration between groups. Let take the example of 3 tasks on a quad cores system. We will always have an idle core so the load balance will find a busiest group (core) whenever an ILB is triggered and it will force an active migration (once above nr_balance_failed threshold) so the idle core becomes busy but another core will become idle. With the next ILB, the freshly idle core will try to pull the task of a busy CPU. The number of spurious active migration is not so huge in quad core system because the ILB is not triggered so much. But it becomes significant as soon as you have more than one sched_domain level like on a dual cluster of quad cores where the ILB is triggered every tick when you have more than 1 busy_cpu We need to ensure that the migration generate a real improveùent and will not only move the avg_load imbalance on another CPU. Before caeb178c60f4f93f1b45c0bc056b5cf6d217b67f, the filtering of such use case was ensured by the following test in f_b_g: if ((local->idle_cpus < busiest->idle_cpus) && busiest->sum_nr_running <= busiest->group_weight) This patch modified the condition to take into account situation where busiest group is not overloaded: If the diff between the number of idle cpus in 2 groups is less than or equal to 1 and the busiest group is not overloaded, moving a task will not improve the load balance but just move it. A test with sysbench on a dual clusters of quad cores gives the following results: command: sysbench --test=cpu --num-threads=5 --max-time=5 run The HZ is 200 which means that 1000 ticks has fired during the test. With Mainline, perf gives the following figures: Samples: 727 of event 'sched:sched_migrate_task' Event count (approx.): 727 Overhead Command Shared Object Symbol ........ ............... ............. .............. 12.52% migration/1 [unknown] [.] 00000000 12.52% migration/5 [unknown] [.] 00000000 12.52% migration/7 [unknown] [.] 00000000 12.10% migration/6 [unknown] [.] 00000000 11.83% migration/0 [unknown] [.] 00000000 11.83% migration/3 [unknown] [.] 00000000 11.14% migration/4 [unknown] [.] 00000000 10.87% migration/2 [unknown] [.] 00000000 2.75% sysbench [unknown] [.] 00000000 0.83% swapper [unknown] [.] 00000000 0.55% ktps65090charge [unknown] [.] 00000000 0.41% mmcqd/1 [unknown] [.] 00000000 0.14% perf [unknown] [.] 00000000 With this patch, perf gives the following figures Samples: 20 of event 'sched:sched_migrate_task' Event count (approx.): 20 Overhead Command Shared Object Symbol ........ ............... ............. .............. 80.00% sysbench [unknown] [.] 00000000 10.00% swapper [unknown] [.] 00000000 5.00% ktps65090charge [unknown] [.] 00000000 5.00% migration/1 [unknown] [.] 00000000 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Reviewed-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1412170735-5356-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-10-01 13:38:55 +00:00
if ((busiest->group_type != group_overloaded) &&
(local->idle_cpus <= (busiest->idle_cpus + 1)))
sched: Use group weight, idle cpu metrics to fix imbalances during idle Currently we consider a sched domain to be well balanced when the imbalance is less than the domain's imablance_pct. As the number of cores and threads are increasing, current values of imbalance_pct (for example 25% for a NUMA domain) are not enough to detect imbalances like: a) On a WSM-EP system (two sockets, each having 6 cores and 12 logical threads), 24 cpu-hogging tasks get scheduled as 13 on one socket and 11 on another socket. Leading to an idle HT cpu. b) On a hypothetial 2 socket NHM-EX system (each socket having 8 cores and 16 logical threads), 16 cpu-hogging tasks can get scheduled as 9 on one socket and 7 on another socket. Leaving one core in a socket idle whereas in another socket we have a core having both its HT siblings busy. While this issue can be fixed by decreasing the domain's imbalance_pct (by making it a function of number of logical cpus in the domain), it can potentially cause more task migrations across sched groups in an overloaded case. Fix this by using imbalance_pct only during newly_idle and busy load balancing. And during idle load balancing, check if there is an imbalance in number of idle cpu's across the busiest and this sched_group or if the busiest group has more tasks than its weight that the idle cpu in this_group can pull. Reported-by: Nikhil Rao <ncrao@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1284760952.2676.11.camel@sbsiddha-MOBL3.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-09-17 22:02:32 +00:00
goto out_balanced;
} else {
/*
* In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
* imbalance_pct to be conservative.
*/
if (100 * busiest->avg_load <=
env->sd->imbalance_pct * local->avg_load)
goto out_balanced;
sched: Use group weight, idle cpu metrics to fix imbalances during idle Currently we consider a sched domain to be well balanced when the imbalance is less than the domain's imablance_pct. As the number of cores and threads are increasing, current values of imbalance_pct (for example 25% for a NUMA domain) are not enough to detect imbalances like: a) On a WSM-EP system (two sockets, each having 6 cores and 12 logical threads), 24 cpu-hogging tasks get scheduled as 13 on one socket and 11 on another socket. Leading to an idle HT cpu. b) On a hypothetial 2 socket NHM-EX system (each socket having 8 cores and 16 logical threads), 16 cpu-hogging tasks can get scheduled as 9 on one socket and 7 on another socket. Leaving one core in a socket idle whereas in another socket we have a core having both its HT siblings busy. While this issue can be fixed by decreasing the domain's imbalance_pct (by making it a function of number of logical cpus in the domain), it can potentially cause more task migrations across sched groups in an overloaded case. Fix this by using imbalance_pct only during newly_idle and busy load balancing. And during idle load balancing, check if there is an imbalance in number of idle cpu's across the busiest and this sched_group or if the busiest group has more tasks than its weight that the idle cpu in this_group can pull. Reported-by: Nikhil Rao <ncrao@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1284760952.2676.11.camel@sbsiddha-MOBL3.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-09-17 22:02:32 +00:00
}
force_balance:
/* Looks like there is an imbalance. Compute it */
calculate_imbalance(env, &sds);
return sds.busiest;
out_balanced:
env->imbalance = 0;
return NULL;
}
/*
* find_busiest_queue - find the busiest runqueue among the cpus in group.
*/
static struct rq *find_busiest_queue(struct lb_env *env,
struct sched_group *group)
{
struct rq *busiest = NULL, *rq;
unsigned long busiest_load = 0, busiest_capacity = 1;
int i;
for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
unsigned long capacity, wl;
enum fbq_type rt;
rq = cpu_rq(i);
rt = fbq_classify_rq(rq);
/*
* We classify groups/runqueues into three groups:
* - regular: there are !numa tasks
* - remote: there are numa tasks that run on the 'wrong' node
* - all: there is no distinction
*
* In order to avoid migrating ideally placed numa tasks,
* ignore those when there's better options.
*
* If we ignore the actual busiest queue to migrate another
* task, the next balance pass can still reduce the busiest
* queue by moving tasks around inside the node.
*
* If we cannot move enough load due to this classification
* the next pass will adjust the group classification and
* allow migration of more tasks.
*
* Both cases only affect the total convergence complexity.
*/
if (rt > env->fbq_type)
continue;
capacity = capacity_of(i);
wl = weighted_cpuload(i);
/*
* When comparing with imbalance, use weighted_cpuload()
* which is not scaled with the cpu capacity.
*/
sched: Replace capacity_factor by usage The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is SCHED_CAPACITY_SCALE. 'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it compares this value with the sum of nr_running to decide if the group is overloaded or not. But the 'group_capacity_factor' concept is hardly working for SMT systems, it sometimes works for big cores but fails to do the right thing for little cores. Below are two examples to illustrate the problem that this patch solves: 1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 (div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded even if we have only one task per CPU. 2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix [0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]). So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics: - The available CPU's capacity for CFS tasks which is already used by load_balance(). - The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib has been re-introduced to compute the usage of a CPU by CFS tasks. 'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced by 'group_no_capacity'. We compare the number of task with the number of CPUs and we evaluate the level of utilization of the CPUs to define if a group is overloaded or if a group has capacity to handle more tasks. For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task so it will be selected in priority (among the overloaded groups). Since [1], SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity' because local is not overloaded. [1] 9a5d9ba6a363 ("sched/fair: Allow calculate_imbalance() to move idle cpus") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org [ Tidied up the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:11 +00:00
if (rq->nr_running == 1 && wl > env->imbalance &&
!check_cpu_capacity(rq, env->sd))
continue;
/*
* For the load comparisons with the other cpu's, consider
* the weighted_cpuload() scaled with the cpu capacity, so
* that the load can be moved away from the cpu that is
* potentially running at a lower capacity.
*
* Thus we're looking for max(wl_i / capacity_i), crosswise
* multiplication to rid ourselves of the division works out
* to: wl_i * capacity_j > wl_j * capacity_i; where j is
* our previous maximum.
*/
if (wl * busiest_capacity > busiest_load * capacity) {
busiest_load = wl;
busiest_capacity = capacity;
busiest = rq;
}
}
return busiest;
}
/*
* Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
* so long as it is large enough.
*/
#define MAX_PINNED_INTERVAL 512
/* Working cpumask for load_balance and load_balance_newidle. */
DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
static int need_active_balance(struct lb_env *env)
{
struct sched_domain *sd = env->sd;
if (env->idle == CPU_NEWLY_IDLE) {
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
/*
* ASYM_PACKING needs to force migrate tasks from busy but
* higher numbered CPUs in order to pack all tasks in the
* lowest numbered CPUs.
*/
if ((sd->flags & SD_ASYM_PACKING) && env->src_cpu > env->dst_cpu)
sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-08 04:57:02 +00:00
return 1;
}
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
/*
* The dst_cpu is idle and the src_cpu CPU has only 1 CFS task.
* It's worth migrating the task if the src_cpu's capacity is reduced
* because of other sched_class or IRQs if more capacity stays
* available on dst_cpu.
*/
if ((env->idle != CPU_NOT_IDLE) &&
(env->src_rq->cfs.h_nr_running == 1)) {
if ((check_cpu_capacity(env->src_rq, sd)) &&
(capacity_of(env->src_cpu)*sd->imbalance_pct < capacity_of(env->dst_cpu)*100))
return 1;
}
return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
}
sched: replace migration_thread with cpu_stop Currently migration_thread is serving three purposes - migration pusher, context to execute active_load_balance() and forced context switcher for expedited RCU synchronize_sched. All three roles are hardcoded into migration_thread() and determining which job is scheduled is slightly messy. This patch kills migration_thread and replaces all three uses with cpu_stop. The three different roles of migration_thread() are splitted into three separate cpu_stop callbacks - migration_cpu_stop(), active_load_balance_cpu_stop() and synchronize_sched_expedited_cpu_stop() - and each use case now simply asks cpu_stop to execute the callback as necessary. synchronize_sched_expedited() was implemented with private preallocated resources and custom multi-cpu queueing and waiting logic, both of which are provided by cpu_stop. synchronize_sched_expedited_count is made atomic and all other shared resources along with the mutex are dropped. synchronize_sched_expedited() also implemented a check to detect cases where not all the callback got executed on their assigned cpus and fall back to synchronize_sched(). If called with cpu hotplug blocked, cpu_stop already guarantees that and the condition cannot happen; otherwise, stop_machine() would break. However, this patch preserves the paranoid check using a cpumask to record on which cpus the stopper ran so that it can serve as a bisection point if something actually goes wrong theree. Because the internal execution state is no longer visible, rcu_expedited_torture_stats() is removed. This patch also renames cpu_stop threads to from "stopper/%d" to "migration/%d". The names of these threads ultimately don't matter and there's no reason to make unnecessary userland visible changes. With this patch applied, stop_machine() and sched now share the same resources. stop_machine() is faster without wasting any resources and sched migration users are much cleaner. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Josh Triplett <josh@freedesktop.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Dimitri Sivanich <sivanich@sgi.com>
2010-05-06 16:49:21 +00:00
static int active_load_balance_cpu_stop(void *data);
static int should_we_balance(struct lb_env *env)
{
struct sched_group *sg = env->sd->groups;
struct cpumask *sg_cpus, *sg_mask;
int cpu, balance_cpu = -1;
/*
* In the newly idle case, we will allow all the cpu's
* to do the newly idle load balance.
*/
if (env->idle == CPU_NEWLY_IDLE)
return 1;
sg_cpus = sched_group_cpus(sg);
sg_mask = sched_group_mask(sg);
/* Try to find first idle cpu */
for_each_cpu_and(cpu, sg_cpus, env->cpus) {
if (!cpumask_test_cpu(cpu, sg_mask) || !idle_cpu(cpu))
continue;
balance_cpu = cpu;
break;
}
if (balance_cpu == -1)
balance_cpu = group_balance_cpu(sg);
/*
* First idle cpu or the first cpu(busiest) in this sched group
* is eligible for doing load balancing at this and above domains.
*/
return balance_cpu == env->dst_cpu;
}
/*
* Check this_cpu to ensure it is balanced within domain. Attempt to move
* tasks if there is an imbalance.
*/
static int load_balance(int this_cpu, struct rq *this_rq,
struct sched_domain *sd, enum cpu_idle_type idle,
int *continue_balancing)
{
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
int ld_moved, cur_ld_moved, active_balance = 0;
struct sched_domain *sd_parent = sd->parent;
struct sched_group *group;
struct rq *busiest;
unsigned long flags;
struct cpumask *cpus = this_cpu_cpumask_var_ptr(load_balance_mask);
struct lb_env env = {
.sd = sd,
.dst_cpu = this_cpu,
.dst_rq = this_rq,
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
.dst_grpmask = sched_group_cpus(sd->groups),
.idle = idle,
.loop_break = sched_nr_migrate_break,
.cpus = cpus,
.fbq_type = all,
.tasks = LIST_HEAD_INIT(env.tasks),
};
/*
* For NEWLY_IDLE load_balancing, we don't need to consider
* other cpus in our group
*/
if (idle == CPU_NEWLY_IDLE)
env.dst_grpmask = NULL;
cpumask_copy(cpus, cpu_active_mask);
schedstat_inc(sd, lb_count[idle]);
redo:
if (!should_we_balance(&env)) {
*continue_balancing = 0;
goto out_balanced;
}
group = find_busiest_group(&env);
if (!group) {
schedstat_inc(sd, lb_nobusyg[idle]);
goto out_balanced;
}
busiest = find_busiest_queue(&env, group);
if (!busiest) {
schedstat_inc(sd, lb_nobusyq[idle]);
goto out_balanced;
}
BUG_ON(busiest == env.dst_rq);
schedstat_add(sd, lb_imbalance[idle], env.imbalance);
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
env.src_cpu = busiest->cpu;
env.src_rq = busiest;
ld_moved = 0;
if (busiest->nr_running > 1) {
/*
* Attempt to move tasks. If find_busiest_group has found
* an imbalance but busiest->nr_running <= 1, the group is
* still unbalanced. ld_moved simply stays zero, so it is
* correctly treated as an imbalance.
*/
env.flags |= LBF_ALL_PINNED;
env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running);
more_balance:
raw_spin_lock_irqsave(&busiest->lock, flags);
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
/*
* cur_ld_moved - load moved in current iteration
* ld_moved - cumulative load moved across iterations
*/
cur_ld_moved = detach_tasks(&env);
/*
* We've detached some tasks from busiest_rq. Every
* task is masked "TASK_ON_RQ_MIGRATING", so we can safely
* unlock busiest->lock, and we are able to be sure
* that nobody can manipulate the tasks in parallel.
* See task_rq_lock() family for the details.
*/
raw_spin_unlock(&busiest->lock);
if (cur_ld_moved) {
attach_tasks(&env);
ld_moved += cur_ld_moved;
}
local_irq_restore(flags);
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
if (env.flags & LBF_NEED_BREAK) {
env.flags &= ~LBF_NEED_BREAK;
goto more_balance;
}
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
/*
* Revisit (affine) tasks on src_cpu that couldn't be moved to
* us and move them to an alternate dst_cpu in our sched_group
* where they can run. The upper limit on how many times we
* iterate on same src_cpu is dependent on number of cpus in our
* sched_group.
*
* This changes load balance semantics a bit on who can move
* load to a given_cpu. In addition to the given_cpu itself
* (or a ilb_cpu acting on its behalf where given_cpu is
* nohz-idle), we now have balance_cpu in a position to move
* load to given_cpu. In rare situations, this may cause
* conflicts (balance_cpu and given_cpu/ilb_cpu deciding
* _independently_ and at _same_ time to move some load to
* given_cpu) causing exceess load to be moved to given_cpu.
* This however should not happen so much in practice and
* moreover subsequent load balance cycles should correct the
* excess load moved.
*/
if ((env.flags & LBF_DST_PINNED) && env.imbalance > 0) {
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
/* Prevent to re-select dst_cpu via env's cpus */
cpumask_clear_cpu(env.dst_cpu, env.cpus);
env.dst_rq = cpu_rq(env.new_dst_cpu);
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
env.dst_cpu = env.new_dst_cpu;
env.flags &= ~LBF_DST_PINNED;
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
env.loop = 0;
env.loop_break = sched_nr_migrate_break;
sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task Current load balance scheme requires only one cpu in a sched_group (balance_cpu) to look at other peer sched_groups for imbalance and pull tasks towards itself from a busy cpu. Tasks thus pulled by balance_cpu could later get picked up by cpus that are in the same sched_group as that of balance_cpu. This scheme however fails to pull tasks that are not allowed to run on balance_cpu (but are allowed to run on other cpus in its sched_group). That can affect fairness and in some worst case scenarios cause starvation. Consider a two core (2 threads/core) system running tasks as below: Core0 Core1 / \ / \ C0 C1 C2 C3 | | | | v v v v F0 T1 F1 [idle] T2 F0 = SCHED_FIFO task (pinned to C0) F1 = SCHED_FIFO task (pinned to C2) T1 = SCHED_OTHER task (pinned to C1) T2 = SCHED_OTHER task (pinned to C1 and C2) F1 could become a cpu hog, which will starve T2 unless C1 pulls it. Between C0 and C1 however, C0 is required to look for imbalance between cores, which will fail to pull T2 towards Core0. T2 will starve eternally in this case. The same scenario can arise in presence of non-rt tasks as well (say we replace F1 with high irq load). We tackle this problem by having balance_cpu move pinned tasks to one of its sibling cpus (where they can run). We first check if load balance goal can be met by ignoring pinned tasks, failing which we retry move_tasks() with a new env->dst_cpu. This patch modifies load balance semantics on who can move load towards a given cpu in a given sched_domain. Before this patch, a given_cpu or a ilb_cpu acting on behalf of an idle given_cpu is responsible for moving load to given_cpu. With this patch applied, balance_cpu can in addition decide on moving some load to a given_cpu. There is a remote possibility that excess load could get moved as a result of this (balance_cpu and given_cpu/ilb_cpu deciding *independently* and at *same* time to move some load to a given_cpu). However we should see less of such conflicting decisions in practice and moreover subsequent load balance cycles should correct the excess load moved to given_cpu. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4FE06CDB.2060605@linux.vnet.ibm.com [ minor edits ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-19 12:13:15 +00:00
/*
* Go back to "more_balance" rather than "redo" since we
* need to continue with same src_cpu.
*/
goto more_balance;
}
/*
* We failed to reach balance because of affinity.
*/
if (sd_parent) {
int *group_imbalance = &sd_parent->groups->sgc->imbalance;
sched: Fix imbalance flag reset The imbalance flag can stay set whereas there is no imbalance. Let assume that we have 3 tasks that run on a dual cores /dual cluster system. We will have some idle load balance which are triggered during tick. Unfortunately, the tick is also used to queue background work so we can reach the situation where short work has been queued on a CPU which already runs a task. The load balance will detect this imbalance (2 tasks on 1 CPU and an idle CPU) and will try to pull the waiting task on the idle CPU. The waiting task is a worker thread that is pinned on a CPU so an imbalance due to pinned task is detected and the imbalance flag is set. Then, we will not be able to clear the flag because we have at most 1 task on each CPU but the imbalance flag will trig to useless active load balance between the idle CPU and the busy CPU. We need to reset of the imbalance flag as soon as we have reached a balanced state. If all tasks are pinned, we don't consider that as a balanced state and let the imbalance flag set. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: riel@redhat.com Cc: Morten.Rasmussen@arm.com Cc: efault@gmx.de Cc: nicolas.pitre@linaro.org Cc: daniel.lezcano@linaro.org Cc: dietmar.eggemann@arm.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1409051215-16788-2-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-26 11:06:44 +00:00
if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0)
*group_imbalance = 1;
}
/* All tasks on this runqueue were pinned by CPU affinity */
if (unlikely(env.flags & LBF_ALL_PINNED)) {
cpumask_clear_cpu(cpu_of(busiest), cpus);
if (!cpumask_empty(cpus)) {
env.loop = 0;
env.loop_break = sched_nr_migrate_break;
goto redo;
}
sched: Fix imbalance flag reset The imbalance flag can stay set whereas there is no imbalance. Let assume that we have 3 tasks that run on a dual cores /dual cluster system. We will have some idle load balance which are triggered during tick. Unfortunately, the tick is also used to queue background work so we can reach the situation where short work has been queued on a CPU which already runs a task. The load balance will detect this imbalance (2 tasks on 1 CPU and an idle CPU) and will try to pull the waiting task on the idle CPU. The waiting task is a worker thread that is pinned on a CPU so an imbalance due to pinned task is detected and the imbalance flag is set. Then, we will not be able to clear the flag because we have at most 1 task on each CPU but the imbalance flag will trig to useless active load balance between the idle CPU and the busy CPU. We need to reset of the imbalance flag as soon as we have reached a balanced state. If all tasks are pinned, we don't consider that as a balanced state and let the imbalance flag set. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: riel@redhat.com Cc: Morten.Rasmussen@arm.com Cc: efault@gmx.de Cc: nicolas.pitre@linaro.org Cc: daniel.lezcano@linaro.org Cc: dietmar.eggemann@arm.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1409051215-16788-2-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-26 11:06:44 +00:00
goto out_all_pinned;
}
}
if (!ld_moved) {
schedstat_inc(sd, lb_failed[idle]);
sched: Increment cache_nice_tries only on periodic lb scheduler uses cache_nice_tries as an indicator to do cache_hot and active load balance, when normal load balance fails. Currently, this value is changed on any failed load balance attempt. That ends up being not so nice to workloads that enter/exit idle often, as they do more frequent new_idle balance and that pretty soon results in cache hot tasks being pulled in. Making the cache_nice_tries ignore failed new_idle balance seems to make better sense. With that only the failed load balance in periodic load balance gets accounted and the rate of accumulation of cache_nice_tries will not depend on idle entry/exit (short running sleep-wakeup kind of tasks). This reduces movement of cache_hot tasks. schedstat diff (after-before) excerpt from a workload that has frequent and short wakeup-idle pattern (:2 in cpu col below refers to NEWIDLE idx) This snapshot was across ~400 seconds. Without this change: domainstats: domain0 cpu cnt bln fld imb gain hgain nobusyq nobusyg 0:2 306487 219575 73167 110069413 44583 19070 1172 218403 1:2 292139 194853 81421 120893383 50745 21902 1259 193594 2:2 283166 174607 91359 129699642 54931 23688 1287 173320 3:2 273998 161788 93991 132757146 57122 24351 1366 160422 4:2 289851 215692 62190 83398383 36377 13680 851 214841 5:2 316312 222146 77605 117582154 49948 20281 988 221158 6:2 297172 195596 83623 122133390 52801 21301 929 194667 7:2 283391 178078 86378 126622761 55122 22239 928 177150 8:2 297655 210359 72995 110246694 45798 19777 1125 209234 9:2 297357 202011 79363 119753474 50953 22088 1089 200922 10:2 278797 178703 83180 122514385 52969 22726 1128 177575 11:2 272661 167669 86978 127342327 55857 24342 1195 166474 12:2 293039 204031 73211 110282059 47285 19651 948 203083 13:2 289502 196762 76803 114712942 49339 20547 1016 195746 14:2 264446 169609 78292 115715605 50459 21017 982 168627 15:2 260968 163660 80142 116811793 51483 21281 1064 162596 With this change: domainstats: domain0 cpu cnt bln fld imb gain hgain nobusyq nobusyg 0:2 272347 187380 77455 105420270 24975 1 953 186427 1:2 267276 172360 86234 116242264 28087 6 1028 171332 2:2 259769 156777 93281 123243134 30555 1 1043 155734 3:2 250870 143129 97627 127370868 32026 6 1188 141941 4:2 248422 177116 64096 78261112 22202 2 757 176359 5:2 275595 180683 84950 116075022 29400 6 778 179905 6:2 262418 162609 88944 119256898 31056 4 817 161792 7:2 252204 147946 92646 122388300 32879 4 824 147122 8:2 262335 172239 81631 110477214 26599 4 864 171375 9:2 261563 164775 88016 117203621 28331 3 849 163926 10:2 243389 140949 93379 121353071 29585 2 909 140040 11:2 242795 134651 98310 124768957 30895 2 1016 133635 12:2 255234 166622 79843 104696912 26483 4 746 165876 13:2 244944 151595 83855 109808099 27787 3 801 150794 14:2 241301 140982 89935 116954383 30403 6 845 140137 15:2 232271 128564 92821 119185207 31207 4 1416 127148 Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1284167957-3675-1-git-send-email-venki@google.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-09-11 01:19:17 +00:00
/*
* Increment the failure counter only on periodic balance.
* We do not want newidle balance, which can be very
* frequent, pollute the failure counter causing
* excessive cache_hot migrations and active balances.
*/
if (idle != CPU_NEWLY_IDLE)
sd->nr_balance_failed++;
if (need_active_balance(&env)) {
raw_spin_lock_irqsave(&busiest->lock, flags);
sched: replace migration_thread with cpu_stop Currently migration_thread is serving three purposes - migration pusher, context to execute active_load_balance() and forced context switcher for expedited RCU synchronize_sched. All three roles are hardcoded into migration_thread() and determining which job is scheduled is slightly messy. This patch kills migration_thread and replaces all three uses with cpu_stop. The three different roles of migration_thread() are splitted into three separate cpu_stop callbacks - migration_cpu_stop(), active_load_balance_cpu_stop() and synchronize_sched_expedited_cpu_stop() - and each use case now simply asks cpu_stop to execute the callback as necessary. synchronize_sched_expedited() was implemented with private preallocated resources and custom multi-cpu queueing and waiting logic, both of which are provided by cpu_stop. synchronize_sched_expedited_count is made atomic and all other shared resources along with the mutex are dropped. synchronize_sched_expedited() also implemented a check to detect cases where not all the callback got executed on their assigned cpus and fall back to synchronize_sched(). If called with cpu hotplug blocked, cpu_stop already guarantees that and the condition cannot happen; otherwise, stop_machine() would break. However, this patch preserves the paranoid check using a cpumask to record on which cpus the stopper ran so that it can serve as a bisection point if something actually goes wrong theree. Because the internal execution state is no longer visible, rcu_expedited_torture_stats() is removed. This patch also renames cpu_stop threads to from "stopper/%d" to "migration/%d". The names of these threads ultimately don't matter and there's no reason to make unnecessary userland visible changes. With this patch applied, stop_machine() and sched now share the same resources. stop_machine() is faster without wasting any resources and sched migration users are much cleaner. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Josh Triplett <josh@freedesktop.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Dimitri Sivanich <sivanich@sgi.com>
2010-05-06 16:49:21 +00:00
/* don't kick the active_load_balance_cpu_stop,
* if the curr task on busiest cpu can't be
* moved to this_cpu
*/
if (!cpumask_test_cpu(this_cpu,
tsk_cpus_allowed(busiest->curr))) {
raw_spin_unlock_irqrestore(&busiest->lock,
flags);
env.flags |= LBF_ALL_PINNED;
goto out_one_pinned;
}
sched: replace migration_thread with cpu_stop Currently migration_thread is serving three purposes - migration pusher, context to execute active_load_balance() and forced context switcher for expedited RCU synchronize_sched. All three roles are hardcoded into migration_thread() and determining which job is scheduled is slightly messy. This patch kills migration_thread and replaces all three uses with cpu_stop. The three different roles of migration_thread() are splitted into three separate cpu_stop callbacks - migration_cpu_stop(), active_load_balance_cpu_stop() and synchronize_sched_expedited_cpu_stop() - and each use case now simply asks cpu_stop to execute the callback as necessary. synchronize_sched_expedited() was implemented with private preallocated resources and custom multi-cpu queueing and waiting logic, both of which are provided by cpu_stop. synchronize_sched_expedited_count is made atomic and all other shared resources along with the mutex are dropped. synchronize_sched_expedited() also implemented a check to detect cases where not all the callback got executed on their assigned cpus and fall back to synchronize_sched(). If called with cpu hotplug blocked, cpu_stop already guarantees that and the condition cannot happen; otherwise, stop_machine() would break. However, this patch preserves the paranoid check using a cpumask to record on which cpus the stopper ran so that it can serve as a bisection point if something actually goes wrong theree. Because the internal execution state is no longer visible, rcu_expedited_torture_stats() is removed. This patch also renames cpu_stop threads to from "stopper/%d" to "migration/%d". The names of these threads ultimately don't matter and there's no reason to make unnecessary userland visible changes. With this patch applied, stop_machine() and sched now share the same resources. stop_machine() is faster without wasting any resources and sched migration users are much cleaner. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Josh Triplett <josh@freedesktop.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Dimitri Sivanich <sivanich@sgi.com>
2010-05-06 16:49:21 +00:00
/*
* ->active_balance synchronizes accesses to
* ->active_balance_work. Once set, it's cleared
* only after active load balance is finished.
*/
if (!busiest->active_balance) {
busiest->active_balance = 1;
busiest->push_cpu = this_cpu;
active_balance = 1;
}
raw_spin_unlock_irqrestore(&busiest->lock, flags);
sched: replace migration_thread with cpu_stop Currently migration_thread is serving three purposes - migration pusher, context to execute active_load_balance() and forced context switcher for expedited RCU synchronize_sched. All three roles are hardcoded into migration_thread() and determining which job is scheduled is slightly messy. This patch kills migration_thread and replaces all three uses with cpu_stop. The three different roles of migration_thread() are splitted into three separate cpu_stop callbacks - migration_cpu_stop(), active_load_balance_cpu_stop() and synchronize_sched_expedited_cpu_stop() - and each use case now simply asks cpu_stop to execute the callback as necessary. synchronize_sched_expedited() was implemented with private preallocated resources and custom multi-cpu queueing and waiting logic, both of which are provided by cpu_stop. synchronize_sched_expedited_count is made atomic and all other shared resources along with the mutex are dropped. synchronize_sched_expedited() also implemented a check to detect cases where not all the callback got executed on their assigned cpus and fall back to synchronize_sched(). If called with cpu hotplug blocked, cpu_stop already guarantees that and the condition cannot happen; otherwise, stop_machine() would break. However, this patch preserves the paranoid check using a cpumask to record on which cpus the stopper ran so that it can serve as a bisection point if something actually goes wrong theree. Because the internal execution state is no longer visible, rcu_expedited_torture_stats() is removed. This patch also renames cpu_stop threads to from "stopper/%d" to "migration/%d". The names of these threads ultimately don't matter and there's no reason to make unnecessary userland visible changes. With this patch applied, stop_machine() and sched now share the same resources. stop_machine() is faster without wasting any resources and sched migration users are much cleaner. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Josh Triplett <josh@freedesktop.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Dimitri Sivanich <sivanich@sgi.com>
2010-05-06 16:49:21 +00:00
if (active_balance) {
sched: replace migration_thread with cpu_stop Currently migration_thread is serving three purposes - migration pusher, context to execute active_load_balance() and forced context switcher for expedited RCU synchronize_sched. All three roles are hardcoded into migration_thread() and determining which job is scheduled is slightly messy. This patch kills migration_thread and replaces all three uses with cpu_stop. The three different roles of migration_thread() are splitted into three separate cpu_stop callbacks - migration_cpu_stop(), active_load_balance_cpu_stop() and synchronize_sched_expedited_cpu_stop() - and each use case now simply asks cpu_stop to execute the callback as necessary. synchronize_sched_expedited() was implemented with private preallocated resources and custom multi-cpu queueing and waiting logic, both of which are provided by cpu_stop. synchronize_sched_expedited_count is made atomic and all other shared resources along with the mutex are dropped. synchronize_sched_expedited() also implemented a check to detect cases where not all the callback got executed on their assigned cpus and fall back to synchronize_sched(). If called with cpu hotplug blocked, cpu_stop already guarantees that and the condition cannot happen; otherwise, stop_machine() would break. However, this patch preserves the paranoid check using a cpumask to record on which cpus the stopper ran so that it can serve as a bisection point if something actually goes wrong theree. Because the internal execution state is no longer visible, rcu_expedited_torture_stats() is removed. This patch also renames cpu_stop threads to from "stopper/%d" to "migration/%d". The names of these threads ultimately don't matter and there's no reason to make unnecessary userland visible changes. With this patch applied, stop_machine() and sched now share the same resources. stop_machine() is faster without wasting any resources and sched migration users are much cleaner. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Josh Triplett <josh@freedesktop.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Dimitri Sivanich <sivanich@sgi.com>
2010-05-06 16:49:21 +00:00
stop_one_cpu_nowait(cpu_of(busiest),
active_load_balance_cpu_stop, busiest,
&busiest->active_balance_work);
}
/*
* We've kicked active balancing, reset the failure
* counter.
*/
sd->nr_balance_failed = sd->cache_nice_tries+1;
}
} else
sd->nr_balance_failed = 0;
if (likely(!active_balance)) {
/* We were unbalanced, so reset the balancing interval */
sd->balance_interval = sd->min_interval;
} else {
/*
* If we've begun active balancing, start to back off. This
* case may not be covered by the all_pinned logic if there
* is only 1 task on the busy runqueue (because we don't call
* detach_tasks).
*/
if (sd->balance_interval < sd->max_interval)
sd->balance_interval *= 2;
}
goto out;
out_balanced:
sched: Fix imbalance flag reset The imbalance flag can stay set whereas there is no imbalance. Let assume that we have 3 tasks that run on a dual cores /dual cluster system. We will have some idle load balance which are triggered during tick. Unfortunately, the tick is also used to queue background work so we can reach the situation where short work has been queued on a CPU which already runs a task. The load balance will detect this imbalance (2 tasks on 1 CPU and an idle CPU) and will try to pull the waiting task on the idle CPU. The waiting task is a worker thread that is pinned on a CPU so an imbalance due to pinned task is detected and the imbalance flag is set. Then, we will not be able to clear the flag because we have at most 1 task on each CPU but the imbalance flag will trig to useless active load balance between the idle CPU and the busy CPU. We need to reset of the imbalance flag as soon as we have reached a balanced state. If all tasks are pinned, we don't consider that as a balanced state and let the imbalance flag set. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: riel@redhat.com Cc: Morten.Rasmussen@arm.com Cc: efault@gmx.de Cc: nicolas.pitre@linaro.org Cc: daniel.lezcano@linaro.org Cc: dietmar.eggemann@arm.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1409051215-16788-2-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-26 11:06:44 +00:00
/*
* We reach balance although we may have faced some affinity
* constraints. Clear the imbalance flag if it was set.
*/
if (sd_parent) {
int *group_imbalance = &sd_parent->groups->sgc->imbalance;
if (*group_imbalance)
*group_imbalance = 0;
}
out_all_pinned:
/*
* We reach balance because all tasks are pinned at this level so
* we can't migrate them. Let the imbalance flag set so parent level
* can try to migrate them.
*/
schedstat_inc(sd, lb_balanced[idle]);
sd->nr_balance_failed = 0;
out_one_pinned:
/* tune up the balancing interval */
if (((env.flags & LBF_ALL_PINNED) &&
sd->balance_interval < MAX_PINNED_INTERVAL) ||
(sd->balance_interval < sd->max_interval))
sd->balance_interval *= 2;
ld_moved = 0;
out:
return ld_moved;
}
sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance() Currently, in idle_balance(), we update rq->next_balance when we pull_tasks. However, it is also important to update this in the !pulled_tasks case too. When the CPU is "busy" (the CPU isn't idle), rq->next_balance gets computed using sd->busy_factor (so we increase the balance interval when the CPU is busy). However, when the CPU goes idle, rq->next_balance could still be set to a large value that was computed with the sd->busy_factor. Thus, we need to also update rq->next_balance in idle_balance() in the cases where !pulled_tasks too, so that rq->next_balance gets updated without taking the busy_factor into account when the CPU is about to go idle. This patch makes rq->next_balance get updated independently of whether or not we pulled_task. Also, we add logic to ensure that we always traverse at least 1 of the sched domains to get a proper next_balance value for updating rq->next_balance. Additionally, since load_balance() modifies the sd->balance_interval, we need to re-obtain the sched domain's interval after the call to load_balance() in rebalance_domains() before we update rq->next_balance. This patch adds and uses 2 new helper functions, update_next_balance() and get_sd_balance_interval() to update next_balance and obtain the sched domain's balance_interval. Signed-off-by: Jason Low <jason.low2@hp.com> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: daniel.lezcano@linaro.org Cc: alex.shi@linaro.org Cc: efault@gmx.de Cc: vincent.guittot@linaro.org Cc: morten.rasmussen@arm.com Cc: aswin@hp.com Link: http://lkml.kernel.org/r/1399596562.2200.7.camel@j-VirtualBox Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-09 00:49:22 +00:00
static inline unsigned long
get_sd_balance_interval(struct sched_domain *sd, int cpu_busy)
{
unsigned long interval = sd->balance_interval;
if (cpu_busy)
interval *= sd->busy_factor;
/* scale ms to jiffies */
interval = msecs_to_jiffies(interval);
interval = clamp(interval, 1UL, max_load_balance_interval);
return interval;
}
static inline void
update_next_balance(struct sched_domain *sd, int cpu_busy, unsigned long *next_balance)
{
unsigned long interval, next;
interval = get_sd_balance_interval(sd, cpu_busy);
next = sd->last_balance + interval;
if (time_after(*next_balance, next))
*next_balance = next;
}
/*
* idle_balance is called by schedule() if this_cpu is about to become
* idle. Attempts to pull tasks from other CPUs.
*/
static int idle_balance(struct rq *this_rq)
{
sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance() Currently, in idle_balance(), we update rq->next_balance when we pull_tasks. However, it is also important to update this in the !pulled_tasks case too. When the CPU is "busy" (the CPU isn't idle), rq->next_balance gets computed using sd->busy_factor (so we increase the balance interval when the CPU is busy). However, when the CPU goes idle, rq->next_balance could still be set to a large value that was computed with the sd->busy_factor. Thus, we need to also update rq->next_balance in idle_balance() in the cases where !pulled_tasks too, so that rq->next_balance gets updated without taking the busy_factor into account when the CPU is about to go idle. This patch makes rq->next_balance get updated independently of whether or not we pulled_task. Also, we add logic to ensure that we always traverse at least 1 of the sched domains to get a proper next_balance value for updating rq->next_balance. Additionally, since load_balance() modifies the sd->balance_interval, we need to re-obtain the sched domain's interval after the call to load_balance() in rebalance_domains() before we update rq->next_balance. This patch adds and uses 2 new helper functions, update_next_balance() and get_sd_balance_interval() to update next_balance and obtain the sched domain's balance_interval. Signed-off-by: Jason Low <jason.low2@hp.com> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: daniel.lezcano@linaro.org Cc: alex.shi@linaro.org Cc: efault@gmx.de Cc: vincent.guittot@linaro.org Cc: morten.rasmussen@arm.com Cc: aswin@hp.com Link: http://lkml.kernel.org/r/1399596562.2200.7.camel@j-VirtualBox Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-09 00:49:22 +00:00
unsigned long next_balance = jiffies + HZ;
int this_cpu = this_rq->cpu;
struct sched_domain *sd;
int pulled_task = 0;
u64 curr_cost = 0;
idle_enter_fair(this_rq);
/*
* We must set idle_stamp _before_ calling idle_balance(), such that we
* measure the duration of idle_balance() as idle time.
*/
this_rq->idle_stamp = rq_clock(this_rq);
sched/fair: Implement fast idling of CPUs when the system is partially loaded When a system is lightly loaded (i.e. no more than 1 job per cpu), attempt to pull job to a cpu before putting it to idle is unnecessary and can be skipped. This patch adds an indicator so the scheduler can know when there's no more than 1 active job is on any CPU in the system to skip needless job pulls. On a 4 socket machine with a request/response kind of workload from clients, we saw about 0.13 msec delay when we go through a full load balance to try pull job from all the other cpus. While 0.1 msec was spent on processing the request and generating a response, the 0.13 msec load balance overhead was actually more than the actual work being done. This overhead can be skipped much of the time for lightly loaded systems. With this patch, we tested with a netperf request/response workload that has the server busy with half the cpus in a 4 socket system. We found the patch eliminated 75% of the load balance attempts before idling a cpu. The overhead of setting/clearing the indicator is low as we already gather the necessary info while we call add_nr_running() and update_sd_lb_stats.() We switch to full load balance load immediately if any cpu got more than one job on its run queue in add_nr_running. We'll clear the indicator to avoid load balance when we detect no cpu's have more than one job when we scan the work queues in update_sg_lb_stats(). We are aggressive in turning on the load balance and opportunistic in skipping the load balance. Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Jason Low <jason.low2@hp.com> Cc: "Paul E.McKenney" <paulmck@linux.vnet.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Alex Shi <alex.shi@linaro.org> Cc: Michel Lespinasse <walken@google.com> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1403551009.2970.613.camel@schen9-DESK Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-23 19:16:49 +00:00
if (this_rq->avg_idle < sysctl_sched_migration_cost ||
!this_rq->rd->overload) {
sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance() Currently, in idle_balance(), we update rq->next_balance when we pull_tasks. However, it is also important to update this in the !pulled_tasks case too. When the CPU is "busy" (the CPU isn't idle), rq->next_balance gets computed using sd->busy_factor (so we increase the balance interval when the CPU is busy). However, when the CPU goes idle, rq->next_balance could still be set to a large value that was computed with the sd->busy_factor. Thus, we need to also update rq->next_balance in idle_balance() in the cases where !pulled_tasks too, so that rq->next_balance gets updated without taking the busy_factor into account when the CPU is about to go idle. This patch makes rq->next_balance get updated independently of whether or not we pulled_task. Also, we add logic to ensure that we always traverse at least 1 of the sched domains to get a proper next_balance value for updating rq->next_balance. Additionally, since load_balance() modifies the sd->balance_interval, we need to re-obtain the sched domain's interval after the call to load_balance() in rebalance_domains() before we update rq->next_balance. This patch adds and uses 2 new helper functions, update_next_balance() and get_sd_balance_interval() to update next_balance and obtain the sched domain's balance_interval. Signed-off-by: Jason Low <jason.low2@hp.com> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: daniel.lezcano@linaro.org Cc: alex.shi@linaro.org Cc: efault@gmx.de Cc: vincent.guittot@linaro.org Cc: morten.rasmussen@arm.com Cc: aswin@hp.com Link: http://lkml.kernel.org/r/1399596562.2200.7.camel@j-VirtualBox Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-09 00:49:22 +00:00
rcu_read_lock();
sd = rcu_dereference_check_sched_domain(this_rq->sd);
if (sd)
update_next_balance(sd, 0, &next_balance);
rcu_read_unlock();
goto out;
sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance() Currently, in idle_balance(), we update rq->next_balance when we pull_tasks. However, it is also important to update this in the !pulled_tasks case too. When the CPU is "busy" (the CPU isn't idle), rq->next_balance gets computed using sd->busy_factor (so we increase the balance interval when the CPU is busy). However, when the CPU goes idle, rq->next_balance could still be set to a large value that was computed with the sd->busy_factor. Thus, we need to also update rq->next_balance in idle_balance() in the cases where !pulled_tasks too, so that rq->next_balance gets updated without taking the busy_factor into account when the CPU is about to go idle. This patch makes rq->next_balance get updated independently of whether or not we pulled_task. Also, we add logic to ensure that we always traverse at least 1 of the sched domains to get a proper next_balance value for updating rq->next_balance. Additionally, since load_balance() modifies the sd->balance_interval, we need to re-obtain the sched domain's interval after the call to load_balance() in rebalance_domains() before we update rq->next_balance. This patch adds and uses 2 new helper functions, update_next_balance() and get_sd_balance_interval() to update next_balance and obtain the sched domain's balance_interval. Signed-off-by: Jason Low <jason.low2@hp.com> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: daniel.lezcano@linaro.org Cc: alex.shi@linaro.org Cc: efault@gmx.de Cc: vincent.guittot@linaro.org Cc: morten.rasmussen@arm.com Cc: aswin@hp.com Link: http://lkml.kernel.org/r/1399596562.2200.7.camel@j-VirtualBox Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-09 00:49:22 +00:00
}
raw_spin_unlock(&this_rq->lock);
update_blocked_averages(this_cpu);
sched: Dynamically allocate sched_domain/sched_group data-structures Instead of relying on static allocations for the sched_domain and sched_group trees, dynamically allocate and RCU free them. Allocating this dynamically also allows for some build_sched_groups() simplification since we can now (like with other simplifications) rely on the sched_domain tree instead of hard-coded knowledge. One tricky to note is that detach_destroy_domains() needs to hold rcu_read_lock() over the entire tear-down, per-cpu is not sufficient since that can lead to partial sched_group existance (could possibly be solved by doing the tear-down backwards but this is much more robust). A concequence of the above is that we can no longer print the sched_domain debug stuff from cpu_attach_domain() since that might now run with preemption disabled (due to classic RCU etc.) and sched_domain_debug() does some GFP_KERNEL allocations. Another thing to note is that we now fully rely on normal RCU and not RCU-sched, this is because with the new and exiting RCU flavours we grew over the years BH doesn't necessarily hold off RCU-sched grace periods (-rt is known to break this). This would in fact already cause us grief since we do sched_domain/sched_group iterations from softirq context. This patch is somewhat larger than I would like it to be, but I didn't find any means of shrinking/splitting this. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20110407122942.245307941@chello.nl Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-07 12:09:50 +00:00
rcu_read_lock();
for_each_domain(this_cpu, sd) {
int continue_balancing = 1;
u64 t0, domain_cost;
if (!(sd->flags & SD_LOAD_BALANCE))
continue;
sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance() Currently, in idle_balance(), we update rq->next_balance when we pull_tasks. However, it is also important to update this in the !pulled_tasks case too. When the CPU is "busy" (the CPU isn't idle), rq->next_balance gets computed using sd->busy_factor (so we increase the balance interval when the CPU is busy). However, when the CPU goes idle, rq->next_balance could still be set to a large value that was computed with the sd->busy_factor. Thus, we need to also update rq->next_balance in idle_balance() in the cases where !pulled_tasks too, so that rq->next_balance gets updated without taking the busy_factor into account when the CPU is about to go idle. This patch makes rq->next_balance get updated independently of whether or not we pulled_task. Also, we add logic to ensure that we always traverse at least 1 of the sched domains to get a proper next_balance value for updating rq->next_balance. Additionally, since load_balance() modifies the sd->balance_interval, we need to re-obtain the sched domain's interval after the call to load_balance() in rebalance_domains() before we update rq->next_balance. This patch adds and uses 2 new helper functions, update_next_balance() and get_sd_balance_interval() to update next_balance and obtain the sched domain's balance_interval. Signed-off-by: Jason Low <jason.low2@hp.com> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: daniel.lezcano@linaro.org Cc: alex.shi@linaro.org Cc: efault@gmx.de Cc: vincent.guittot@linaro.org Cc: morten.rasmussen@arm.com Cc: aswin@hp.com Link: http://lkml.kernel.org/r/1399596562.2200.7.camel@j-VirtualBox Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-09 00:49:22 +00:00
if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) {
update_next_balance(sd, 0, &next_balance);
break;
sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance() Currently, in idle_balance(), we update rq->next_balance when we pull_tasks. However, it is also important to update this in the !pulled_tasks case too. When the CPU is "busy" (the CPU isn't idle), rq->next_balance gets computed using sd->busy_factor (so we increase the balance interval when the CPU is busy). However, when the CPU goes idle, rq->next_balance could still be set to a large value that was computed with the sd->busy_factor. Thus, we need to also update rq->next_balance in idle_balance() in the cases where !pulled_tasks too, so that rq->next_balance gets updated without taking the busy_factor into account when the CPU is about to go idle. This patch makes rq->next_balance get updated independently of whether or not we pulled_task. Also, we add logic to ensure that we always traverse at least 1 of the sched domains to get a proper next_balance value for updating rq->next_balance. Additionally, since load_balance() modifies the sd->balance_interval, we need to re-obtain the sched domain's interval after the call to load_balance() in rebalance_domains() before we update rq->next_balance. This patch adds and uses 2 new helper functions, update_next_balance() and get_sd_balance_interval() to update next_balance and obtain the sched domain's balance_interval. Signed-off-by: Jason Low <jason.low2@hp.com> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: daniel.lezcano@linaro.org Cc: alex.shi@linaro.org Cc: efault@gmx.de Cc: vincent.guittot@linaro.org Cc: morten.rasmussen@arm.com Cc: aswin@hp.com Link: http://lkml.kernel.org/r/1399596562.2200.7.camel@j-VirtualBox Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-09 00:49:22 +00:00
}
if (sd->flags & SD_BALANCE_NEWIDLE) {
t0 = sched_clock_cpu(this_cpu);
pulled_task = load_balance(this_cpu, this_rq,
sd, CPU_NEWLY_IDLE,
&continue_balancing);
domain_cost = sched_clock_cpu(this_cpu) - t0;
if (domain_cost > sd->max_newidle_lb_cost)
sd->max_newidle_lb_cost = domain_cost;
curr_cost += domain_cost;
}
sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance() Currently, in idle_balance(), we update rq->next_balance when we pull_tasks. However, it is also important to update this in the !pulled_tasks case too. When the CPU is "busy" (the CPU isn't idle), rq->next_balance gets computed using sd->busy_factor (so we increase the balance interval when the CPU is busy). However, when the CPU goes idle, rq->next_balance could still be set to a large value that was computed with the sd->busy_factor. Thus, we need to also update rq->next_balance in idle_balance() in the cases where !pulled_tasks too, so that rq->next_balance gets updated without taking the busy_factor into account when the CPU is about to go idle. This patch makes rq->next_balance get updated independently of whether or not we pulled_task. Also, we add logic to ensure that we always traverse at least 1 of the sched domains to get a proper next_balance value for updating rq->next_balance. Additionally, since load_balance() modifies the sd->balance_interval, we need to re-obtain the sched domain's interval after the call to load_balance() in rebalance_domains() before we update rq->next_balance. This patch adds and uses 2 new helper functions, update_next_balance() and get_sd_balance_interval() to update next_balance and obtain the sched domain's balance_interval. Signed-off-by: Jason Low <jason.low2@hp.com> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: daniel.lezcano@linaro.org Cc: alex.shi@linaro.org Cc: efault@gmx.de Cc: vincent.guittot@linaro.org Cc: morten.rasmussen@arm.com Cc: aswin@hp.com Link: http://lkml.kernel.org/r/1399596562.2200.7.camel@j-VirtualBox Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-09 00:49:22 +00:00
update_next_balance(sd, 0, &next_balance);
/*
* Stop searching for tasks to pull if there are
* now runnable tasks on this rq.
*/
if (pulled_task || this_rq->nr_running > 0)
break;
}
sched: Dynamically allocate sched_domain/sched_group data-structures Instead of relying on static allocations for the sched_domain and sched_group trees, dynamically allocate and RCU free them. Allocating this dynamically also allows for some build_sched_groups() simplification since we can now (like with other simplifications) rely on the sched_domain tree instead of hard-coded knowledge. One tricky to note is that detach_destroy_domains() needs to hold rcu_read_lock() over the entire tear-down, per-cpu is not sufficient since that can lead to partial sched_group existance (could possibly be solved by doing the tear-down backwards but this is much more robust). A concequence of the above is that we can no longer print the sched_domain debug stuff from cpu_attach_domain() since that might now run with preemption disabled (due to classic RCU etc.) and sched_domain_debug() does some GFP_KERNEL allocations. Another thing to note is that we now fully rely on normal RCU and not RCU-sched, this is because with the new and exiting RCU flavours we grew over the years BH doesn't necessarily hold off RCU-sched grace periods (-rt is known to break this). This would in fact already cause us grief since we do sched_domain/sched_group iterations from softirq context. This patch is somewhat larger than I would like it to be, but I didn't find any means of shrinking/splitting this. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20110407122942.245307941@chello.nl Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-07 12:09:50 +00:00
rcu_read_unlock();
raw_spin_lock(&this_rq->lock);
if (curr_cost > this_rq->max_idle_balance_cost)
this_rq->max_idle_balance_cost = curr_cost;
/*
* While browsing the domains, we released the rq lock, a task could
* have been enqueued in the meantime. Since we're not going idle,
* pretend we pulled a task.
*/
if (this_rq->cfs.h_nr_running && !pulled_task)
pulled_task = 1;
sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance() Currently, in idle_balance(), we update rq->next_balance when we pull_tasks. However, it is also important to update this in the !pulled_tasks case too. When the CPU is "busy" (the CPU isn't idle), rq->next_balance gets computed using sd->busy_factor (so we increase the balance interval when the CPU is busy). However, when the CPU goes idle, rq->next_balance could still be set to a large value that was computed with the sd->busy_factor. Thus, we need to also update rq->next_balance in idle_balance() in the cases where !pulled_tasks too, so that rq->next_balance gets updated without taking the busy_factor into account when the CPU is about to go idle. This patch makes rq->next_balance get updated independently of whether or not we pulled_task. Also, we add logic to ensure that we always traverse at least 1 of the sched domains to get a proper next_balance value for updating rq->next_balance. Additionally, since load_balance() modifies the sd->balance_interval, we need to re-obtain the sched domain's interval after the call to load_balance() in rebalance_domains() before we update rq->next_balance. This patch adds and uses 2 new helper functions, update_next_balance() and get_sd_balance_interval() to update next_balance and obtain the sched domain's balance_interval. Signed-off-by: Jason Low <jason.low2@hp.com> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: daniel.lezcano@linaro.org Cc: alex.shi@linaro.org Cc: efault@gmx.de Cc: vincent.guittot@linaro.org Cc: morten.rasmussen@arm.com Cc: aswin@hp.com Link: http://lkml.kernel.org/r/1399596562.2200.7.camel@j-VirtualBox Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-09 00:49:22 +00:00
out:
/* Move the next balance forward */
if (time_after(this_rq->next_balance, next_balance))
this_rq->next_balance = next_balance;
/* Is there a task of a high priority class? */
if (this_rq->nr_running != this_rq->cfs.h_nr_running)
pulled_task = -1;
if (pulled_task) {
idle_exit_fair(this_rq);
this_rq->idle_stamp = 0;
}
return pulled_task;
}
/*
sched: replace migration_thread with cpu_stop Currently migration_thread is serving three purposes - migration pusher, context to execute active_load_balance() and forced context switcher for expedited RCU synchronize_sched. All three roles are hardcoded into migration_thread() and determining which job is scheduled is slightly messy. This patch kills migration_thread and replaces all three uses with cpu_stop. The three different roles of migration_thread() are splitted into three separate cpu_stop callbacks - migration_cpu_stop(), active_load_balance_cpu_stop() and synchronize_sched_expedited_cpu_stop() - and each use case now simply asks cpu_stop to execute the callback as necessary. synchronize_sched_expedited() was implemented with private preallocated resources and custom multi-cpu queueing and waiting logic, both of which are provided by cpu_stop. synchronize_sched_expedited_count is made atomic and all other shared resources along with the mutex are dropped. synchronize_sched_expedited() also implemented a check to detect cases where not all the callback got executed on their assigned cpus and fall back to synchronize_sched(). If called with cpu hotplug blocked, cpu_stop already guarantees that and the condition cannot happen; otherwise, stop_machine() would break. However, this patch preserves the paranoid check using a cpumask to record on which cpus the stopper ran so that it can serve as a bisection point if something actually goes wrong theree. Because the internal execution state is no longer visible, rcu_expedited_torture_stats() is removed. This patch also renames cpu_stop threads to from "stopper/%d" to "migration/%d". The names of these threads ultimately don't matter and there's no reason to make unnecessary userland visible changes. With this patch applied, stop_machine() and sched now share the same resources. stop_machine() is faster without wasting any resources and sched migration users are much cleaner. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Josh Triplett <josh@freedesktop.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Dimitri Sivanich <sivanich@sgi.com>
2010-05-06 16:49:21 +00:00
* active_load_balance_cpu_stop is run by cpu stopper. It pushes
* running tasks off the busiest CPU onto idle CPUs. It requires at
* least 1 task to be running on each physical CPU where possible, and
* avoids physical / logical imbalances.
*/
sched: replace migration_thread with cpu_stop Currently migration_thread is serving three purposes - migration pusher, context to execute active_load_balance() and forced context switcher for expedited RCU synchronize_sched. All three roles are hardcoded into migration_thread() and determining which job is scheduled is slightly messy. This patch kills migration_thread and replaces all three uses with cpu_stop. The three different roles of migration_thread() are splitted into three separate cpu_stop callbacks - migration_cpu_stop(), active_load_balance_cpu_stop() and synchronize_sched_expedited_cpu_stop() - and each use case now simply asks cpu_stop to execute the callback as necessary. synchronize_sched_expedited() was implemented with private preallocated resources and custom multi-cpu queueing and waiting logic, both of which are provided by cpu_stop. synchronize_sched_expedited_count is made atomic and all other shared resources along with the mutex are dropped. synchronize_sched_expedited() also implemented a check to detect cases where not all the callback got executed on their assigned cpus and fall back to synchronize_sched(). If called with cpu hotplug blocked, cpu_stop already guarantees that and the condition cannot happen; otherwise, stop_machine() would break. However, this patch preserves the paranoid check using a cpumask to record on which cpus the stopper ran so that it can serve as a bisection point if something actually goes wrong theree. Because the internal execution state is no longer visible, rcu_expedited_torture_stats() is removed. This patch also renames cpu_stop threads to from "stopper/%d" to "migration/%d". The names of these threads ultimately don't matter and there's no reason to make unnecessary userland visible changes. With this patch applied, stop_machine() and sched now share the same resources. stop_machine() is faster without wasting any resources and sched migration users are much cleaner. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Josh Triplett <josh@freedesktop.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Dimitri Sivanich <sivanich@sgi.com>
2010-05-06 16:49:21 +00:00
static int active_load_balance_cpu_stop(void *data)
{
sched: replace migration_thread with cpu_stop Currently migration_thread is serving three purposes - migration pusher, context to execute active_load_balance() and forced context switcher for expedited RCU synchronize_sched. All three roles are hardcoded into migration_thread() and determining which job is scheduled is slightly messy. This patch kills migration_thread and replaces all three uses with cpu_stop. The three different roles of migration_thread() are splitted into three separate cpu_stop callbacks - migration_cpu_stop(), active_load_balance_cpu_stop() and synchronize_sched_expedited_cpu_stop() - and each use case now simply asks cpu_stop to execute the callback as necessary. synchronize_sched_expedited() was implemented with private preallocated resources and custom multi-cpu queueing and waiting logic, both of which are provided by cpu_stop. synchronize_sched_expedited_count is made atomic and all other shared resources along with the mutex are dropped. synchronize_sched_expedited() also implemented a check to detect cases where not all the callback got executed on their assigned cpus and fall back to synchronize_sched(). If called with cpu hotplug blocked, cpu_stop already guarantees that and the condition cannot happen; otherwise, stop_machine() would break. However, this patch preserves the paranoid check using a cpumask to record on which cpus the stopper ran so that it can serve as a bisection point if something actually goes wrong theree. Because the internal execution state is no longer visible, rcu_expedited_torture_stats() is removed. This patch also renames cpu_stop threads to from "stopper/%d" to "migration/%d". The names of these threads ultimately don't matter and there's no reason to make unnecessary userland visible changes. With this patch applied, stop_machine() and sched now share the same resources. stop_machine() is faster without wasting any resources and sched migration users are much cleaner. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Josh Triplett <josh@freedesktop.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Dimitri Sivanich <sivanich@sgi.com>
2010-05-06 16:49:21 +00:00
struct rq *busiest_rq = data;
int busiest_cpu = cpu_of(busiest_rq);
int target_cpu = busiest_rq->push_cpu;
sched: replace migration_thread with cpu_stop Currently migration_thread is serving three purposes - migration pusher, context to execute active_load_balance() and forced context switcher for expedited RCU synchronize_sched. All three roles are hardcoded into migration_thread() and determining which job is scheduled is slightly messy. This patch kills migration_thread and replaces all three uses with cpu_stop. The three different roles of migration_thread() are splitted into three separate cpu_stop callbacks - migration_cpu_stop(), active_load_balance_cpu_stop() and synchronize_sched_expedited_cpu_stop() - and each use case now simply asks cpu_stop to execute the callback as necessary. synchronize_sched_expedited() was implemented with private preallocated resources and custom multi-cpu queueing and waiting logic, both of which are provided by cpu_stop. synchronize_sched_expedited_count is made atomic and all other shared resources along with the mutex are dropped. synchronize_sched_expedited() also implemented a check to detect cases where not all the callback got executed on their assigned cpus and fall back to synchronize_sched(). If called with cpu hotplug blocked, cpu_stop already guarantees that and the condition cannot happen; otherwise, stop_machine() would break. However, this patch preserves the paranoid check using a cpumask to record on which cpus the stopper ran so that it can serve as a bisection point if something actually goes wrong theree. Because the internal execution state is no longer visible, rcu_expedited_torture_stats() is removed. This patch also renames cpu_stop threads to from "stopper/%d" to "migration/%d". The names of these threads ultimately don't matter and there's no reason to make unnecessary userland visible changes. With this patch applied, stop_machine() and sched now share the same resources. stop_machine() is faster without wasting any resources and sched migration users are much cleaner. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Josh Triplett <josh@freedesktop.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Dimitri Sivanich <sivanich@sgi.com>
2010-05-06 16:49:21 +00:00
struct rq *target_rq = cpu_rq(target_cpu);
struct sched_domain *sd;
struct task_struct *p = NULL;
sched: replace migration_thread with cpu_stop Currently migration_thread is serving three purposes - migration pusher, context to execute active_load_balance() and forced context switcher for expedited RCU synchronize_sched. All three roles are hardcoded into migration_thread() and determining which job is scheduled is slightly messy. This patch kills migration_thread and replaces all three uses with cpu_stop. The three different roles of migration_thread() are splitted into three separate cpu_stop callbacks - migration_cpu_stop(), active_load_balance_cpu_stop() and synchronize_sched_expedited_cpu_stop() - and each use case now simply asks cpu_stop to execute the callback as necessary. synchronize_sched_expedited() was implemented with private preallocated resources and custom multi-cpu queueing and waiting logic, both of which are provided by cpu_stop. synchronize_sched_expedited_count is made atomic and all other shared resources along with the mutex are dropped. synchronize_sched_expedited() also implemented a check to detect cases where not all the callback got executed on their assigned cpus and fall back to synchronize_sched(). If called with cpu hotplug blocked, cpu_stop already guarantees that and the condition cannot happen; otherwise, stop_machine() would break. However, this patch preserves the paranoid check using a cpumask to record on which cpus the stopper ran so that it can serve as a bisection point if something actually goes wrong theree. Because the internal execution state is no longer visible, rcu_expedited_torture_stats() is removed. This patch also renames cpu_stop threads to from "stopper/%d" to "migration/%d". The names of these threads ultimately don't matter and there's no reason to make unnecessary userland visible changes. With this patch applied, stop_machine() and sched now share the same resources. stop_machine() is faster without wasting any resources and sched migration users are much cleaner. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Josh Triplett <josh@freedesktop.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Dimitri Sivanich <sivanich@sgi.com>
2010-05-06 16:49:21 +00:00
raw_spin_lock_irq(&busiest_rq->lock);
/* make sure the requested cpu hasn't gone down in the meantime */
if (unlikely(busiest_cpu != smp_processor_id() ||
!busiest_rq->active_balance))
goto out_unlock;
/* Is there any task to move? */
if (busiest_rq->nr_running <= 1)
sched: replace migration_thread with cpu_stop Currently migration_thread is serving three purposes - migration pusher, context to execute active_load_balance() and forced context switcher for expedited RCU synchronize_sched. All three roles are hardcoded into migration_thread() and determining which job is scheduled is slightly messy. This patch kills migration_thread and replaces all three uses with cpu_stop. The three different roles of migration_thread() are splitted into three separate cpu_stop callbacks - migration_cpu_stop(), active_load_balance_cpu_stop() and synchronize_sched_expedited_cpu_stop() - and each use case now simply asks cpu_stop to execute the callback as necessary. synchronize_sched_expedited() was implemented with private preallocated resources and custom multi-cpu queueing and waiting logic, both of which are provided by cpu_stop. synchronize_sched_expedited_count is made atomic and all other shared resources along with the mutex are dropped. synchronize_sched_expedited() also implemented a check to detect cases where not all the callback got executed on their assigned cpus and fall back to synchronize_sched(). If called with cpu hotplug blocked, cpu_stop already guarantees that and the condition cannot happen; otherwise, stop_machine() would break. However, this patch preserves the paranoid check using a cpumask to record on which cpus the stopper ran so that it can serve as a bisection point if something actually goes wrong theree. Because the internal execution state is no longer visible, rcu_expedited_torture_stats() is removed. This patch also renames cpu_stop threads to from "stopper/%d" to "migration/%d". The names of these threads ultimately don't matter and there's no reason to make unnecessary userland visible changes. With this patch applied, stop_machine() and sched now share the same resources. stop_machine() is faster without wasting any resources and sched migration users are much cleaner. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Josh Triplett <josh@freedesktop.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Dimitri Sivanich <sivanich@sgi.com>
2010-05-06 16:49:21 +00:00
goto out_unlock;
/*
* This condition is "impossible", if it occurs
* we need to fix it. Originally reported by
* Bjorn Helgaas on a 128-cpu setup.
*/
BUG_ON(busiest_rq == target_rq);
/* Search for an sd spanning us and the target CPU. */
sched: Dynamically allocate sched_domain/sched_group data-structures Instead of relying on static allocations for the sched_domain and sched_group trees, dynamically allocate and RCU free them. Allocating this dynamically also allows for some build_sched_groups() simplification since we can now (like with other simplifications) rely on the sched_domain tree instead of hard-coded knowledge. One tricky to note is that detach_destroy_domains() needs to hold rcu_read_lock() over the entire tear-down, per-cpu is not sufficient since that can lead to partial sched_group existance (could possibly be solved by doing the tear-down backwards but this is much more robust). A concequence of the above is that we can no longer print the sched_domain debug stuff from cpu_attach_domain() since that might now run with preemption disabled (due to classic RCU etc.) and sched_domain_debug() does some GFP_KERNEL allocations. Another thing to note is that we now fully rely on normal RCU and not RCU-sched, this is because with the new and exiting RCU flavours we grew over the years BH doesn't necessarily hold off RCU-sched grace periods (-rt is known to break this). This would in fact already cause us grief since we do sched_domain/sched_group iterations from softirq context. This patch is somewhat larger than I would like it to be, but I didn't find any means of shrinking/splitting this. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20110407122942.245307941@chello.nl Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-07 12:09:50 +00:00
rcu_read_lock();
for_each_domain(target_cpu, sd) {
if ((sd->flags & SD_LOAD_BALANCE) &&
cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
break;
}
if (likely(sd)) {
struct lb_env env = {
.sd = sd,
.dst_cpu = target_cpu,
.dst_rq = target_rq,
.src_cpu = busiest_rq->cpu,
.src_rq = busiest_rq,
.idle = CPU_IDLE,
};
schedstat_inc(sd, alb_count);
p = detach_one_task(&env);
if (p)
schedstat_inc(sd, alb_pushed);
else
schedstat_inc(sd, alb_failed);
}
sched: Dynamically allocate sched_domain/sched_group data-structures Instead of relying on static allocations for the sched_domain and sched_group trees, dynamically allocate and RCU free them. Allocating this dynamically also allows for some build_sched_groups() simplification since we can now (like with other simplifications) rely on the sched_domain tree instead of hard-coded knowledge. One tricky to note is that detach_destroy_domains() needs to hold rcu_read_lock() over the entire tear-down, per-cpu is not sufficient since that can lead to partial sched_group existance (could possibly be solved by doing the tear-down backwards but this is much more robust). A concequence of the above is that we can no longer print the sched_domain debug stuff from cpu_attach_domain() since that might now run with preemption disabled (due to classic RCU etc.) and sched_domain_debug() does some GFP_KERNEL allocations. Another thing to note is that we now fully rely on normal RCU and not RCU-sched, this is because with the new and exiting RCU flavours we grew over the years BH doesn't necessarily hold off RCU-sched grace periods (-rt is known to break this). This would in fact already cause us grief since we do sched_domain/sched_group iterations from softirq context. This patch is somewhat larger than I would like it to be, but I didn't find any means of shrinking/splitting this. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20110407122942.245307941@chello.nl Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-07 12:09:50 +00:00
rcu_read_unlock();
sched: replace migration_thread with cpu_stop Currently migration_thread is serving three purposes - migration pusher, context to execute active_load_balance() and forced context switcher for expedited RCU synchronize_sched. All three roles are hardcoded into migration_thread() and determining which job is scheduled is slightly messy. This patch kills migration_thread and replaces all three uses with cpu_stop. The three different roles of migration_thread() are splitted into three separate cpu_stop callbacks - migration_cpu_stop(), active_load_balance_cpu_stop() and synchronize_sched_expedited_cpu_stop() - and each use case now simply asks cpu_stop to execute the callback as necessary. synchronize_sched_expedited() was implemented with private preallocated resources and custom multi-cpu queueing and waiting logic, both of which are provided by cpu_stop. synchronize_sched_expedited_count is made atomic and all other shared resources along with the mutex are dropped. synchronize_sched_expedited() also implemented a check to detect cases where not all the callback got executed on their assigned cpus and fall back to synchronize_sched(). If called with cpu hotplug blocked, cpu_stop already guarantees that and the condition cannot happen; otherwise, stop_machine() would break. However, this patch preserves the paranoid check using a cpumask to record on which cpus the stopper ran so that it can serve as a bisection point if something actually goes wrong theree. Because the internal execution state is no longer visible, rcu_expedited_torture_stats() is removed. This patch also renames cpu_stop threads to from "stopper/%d" to "migration/%d". The names of these threads ultimately don't matter and there's no reason to make unnecessary userland visible changes. With this patch applied, stop_machine() and sched now share the same resources. stop_machine() is faster without wasting any resources and sched migration users are much cleaner. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Josh Triplett <josh@freedesktop.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Dimitri Sivanich <sivanich@sgi.com>
2010-05-06 16:49:21 +00:00
out_unlock:
busiest_rq->active_balance = 0;
raw_spin_unlock(&busiest_rq->lock);
if (p)
attach_one_task(target_rq, p);
local_irq_enable();
sched: replace migration_thread with cpu_stop Currently migration_thread is serving three purposes - migration pusher, context to execute active_load_balance() and forced context switcher for expedited RCU synchronize_sched. All three roles are hardcoded into migration_thread() and determining which job is scheduled is slightly messy. This patch kills migration_thread and replaces all three uses with cpu_stop. The three different roles of migration_thread() are splitted into three separate cpu_stop callbacks - migration_cpu_stop(), active_load_balance_cpu_stop() and synchronize_sched_expedited_cpu_stop() - and each use case now simply asks cpu_stop to execute the callback as necessary. synchronize_sched_expedited() was implemented with private preallocated resources and custom multi-cpu queueing and waiting logic, both of which are provided by cpu_stop. synchronize_sched_expedited_count is made atomic and all other shared resources along with the mutex are dropped. synchronize_sched_expedited() also implemented a check to detect cases where not all the callback got executed on their assigned cpus and fall back to synchronize_sched(). If called with cpu hotplug blocked, cpu_stop already guarantees that and the condition cannot happen; otherwise, stop_machine() would break. However, this patch preserves the paranoid check using a cpumask to record on which cpus the stopper ran so that it can serve as a bisection point if something actually goes wrong theree. Because the internal execution state is no longer visible, rcu_expedited_torture_stats() is removed. This patch also renames cpu_stop threads to from "stopper/%d" to "migration/%d". The names of these threads ultimately don't matter and there's no reason to make unnecessary userland visible changes. With this patch applied, stop_machine() and sched now share the same resources. stop_machine() is faster without wasting any resources and sched migration users are much cleaner. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Josh Triplett <josh@freedesktop.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Dimitri Sivanich <sivanich@sgi.com>
2010-05-06 16:49:21 +00:00
return 0;
}
static inline int on_null_domain(struct rq *rq)
{
return unlikely(!rcu_dereference_sched(rq->sd));
}
nohz: Rename CONFIG_NO_HZ to CONFIG_NO_HZ_COMMON We are planning to convert the dynticks Kconfig options layout into a choice menu. The user must be able to easily pick any of the following implementations: constant periodic tick, idle dynticks, full dynticks. As this implies a mutual exclusion, the two dynticks implementions need to converge on the selection of a common Kconfig option in order to ease the sharing of a common infrastructure. It would thus seem pretty natural to reuse CONFIG_NO_HZ to that end. It already implements all the idle dynticks code and the full dynticks depends on all that code for now. So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ. On the other hand we want to stay backward compatible: if CONFIG_NO_HZ is set in an older config file, we want to enable CONFIG_NO_HZ_IDLE by default. But we can't afford both at the same time or we run into a circular dependency: 1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select CONFIG_NO_HZ 2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE We might be able to support that from Kconfig/Kbuild but it may not be wise to introduce such a confusing behaviour. So to solve this, create a new CONFIG_NO_HZ_COMMON option which gathers the common code between idle and full dynticks (that common code for now is simply the idle dynticks code) and select it from their referring Kconfig. Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ to it for backward compatibility. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2011-08-10 21:21:01 +00:00
#ifdef CONFIG_NO_HZ_COMMON
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
/*
* idle load balancing details
* - When one of the busy CPUs notice that there may be an idle rebalancing
* needed, they will kick the idle load balancer, which then does idle
* load balancing for all the idle CPUs.
*/
static struct {
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
cpumask_var_t idle_cpus_mask;
atomic_t nr_cpus;
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
unsigned long next_balance; /* in jiffy units */
} nohz ____cacheline_aligned;
static inline int find_new_ilb(void)
{
int ilb = cpumask_first(nohz.idle_cpus_mask);
if (ilb < nr_cpu_ids && idle_cpu(ilb))
return ilb;
return nr_cpu_ids;
}
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
/*
* Kick a CPU to do the nohz balancing, if it is time for it. We pick the
* nohz_load_balancer CPU (if there is one) otherwise fallback to any idle
* CPU (if there is one).
*/
static void nohz_balancer_kick(void)
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
{
int ilb_cpu;
nohz.next_balance++;
ilb_cpu = find_new_ilb();
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
if (ilb_cpu >= nr_cpu_ids)
return;
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
if (test_and_set_bit(NOHZ_BALANCE_KICK, nohz_flags(ilb_cpu)))
return;
/*
* Use smp_send_reschedule() instead of resched_cpu().
* This way we generate a sched IPI on the target cpu which
* is idle. And the softirq performing nohz idle load balance
* will be run before returning from the IPI.
*/
smp_send_reschedule(ilb_cpu);
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
return;
}
static inline void nohz_balance_exit_idle(int cpu)
{
if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) {
/*
* Completely isolated CPUs don't ever set, so we must test.
*/
if (likely(cpumask_test_cpu(cpu, nohz.idle_cpus_mask))) {
cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
atomic_dec(&nohz.nr_cpus);
}
clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
}
}
static inline void set_cpu_sd_state_busy(void)
{
struct sched_domain *sd;
sched: Remove unnecessary iteration over sched domains to update nr_busy_cpus nr_busy_cpus parameter is used by nohz_kick_needed() to find out the number of busy cpus in a sched domain which has SD_SHARE_PKG_RESOURCES flag set. Therefore instead of updating nr_busy_cpus at every level of sched domain, since it is irrelevant, we can update this parameter only at the parent domain of the sd which has this flag set. Introduce a per-cpu parameter sd_busy which represents this parent domain. In nohz_kick_needed() we directly query the nr_busy_cpus parameter associated with the groups of sd_busy. By associating sd_busy with the highest domain which has SD_SHARE_PKG_RESOURCES flag set, we cover all lower level domains which could have this flag set and trigger nohz_idle_balancing if any of the levels have more than one busy cpu. sd_busy is irrelevant for asymmetric load balancing. However sd_asym has been introduced to represent the highest sched domain which has SD_ASYM_PACKING flag set so that it can be queried directly when required. While we are at it, we might as well change the nohz_idle parameter to be updated at the sd_busy domain level alone and not the base domain level of a CPU. This will unify the concept of busy cpus at just one level of sched domain where it is currently used. Signed-off-by: Preeti U Murthy<preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: svaidy@linux.vnet.ibm.com Cc: vincent.guittot@linaro.org Cc: bitbucket@online.de Cc: benh@kernel.crashing.org Cc: anton@samba.org Cc: Morten.Rasmussen@arm.com Cc: pjt@google.com Cc: peterz@infradead.org Cc: mikey@neuling.org Link: http://lkml.kernel.org/r/20131030031252.23426.4417.stgit@preeti.in.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-30 03:12:52 +00:00
int cpu = smp_processor_id();
rcu_read_lock();
sched: Remove unnecessary iteration over sched domains to update nr_busy_cpus nr_busy_cpus parameter is used by nohz_kick_needed() to find out the number of busy cpus in a sched domain which has SD_SHARE_PKG_RESOURCES flag set. Therefore instead of updating nr_busy_cpus at every level of sched domain, since it is irrelevant, we can update this parameter only at the parent domain of the sd which has this flag set. Introduce a per-cpu parameter sd_busy which represents this parent domain. In nohz_kick_needed() we directly query the nr_busy_cpus parameter associated with the groups of sd_busy. By associating sd_busy with the highest domain which has SD_SHARE_PKG_RESOURCES flag set, we cover all lower level domains which could have this flag set and trigger nohz_idle_balancing if any of the levels have more than one busy cpu. sd_busy is irrelevant for asymmetric load balancing. However sd_asym has been introduced to represent the highest sched domain which has SD_ASYM_PACKING flag set so that it can be queried directly when required. While we are at it, we might as well change the nohz_idle parameter to be updated at the sd_busy domain level alone and not the base domain level of a CPU. This will unify the concept of busy cpus at just one level of sched domain where it is currently used. Signed-off-by: Preeti U Murthy<preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: svaidy@linux.vnet.ibm.com Cc: vincent.guittot@linaro.org Cc: bitbucket@online.de Cc: benh@kernel.crashing.org Cc: anton@samba.org Cc: Morten.Rasmussen@arm.com Cc: pjt@google.com Cc: peterz@infradead.org Cc: mikey@neuling.org Link: http://lkml.kernel.org/r/20131030031252.23426.4417.stgit@preeti.in.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-30 03:12:52 +00:00
sd = rcu_dereference(per_cpu(sd_busy, cpu));
sched: Fix init NOHZ_IDLE flag On my SMP platform which is made of 5 cores in 2 clusters, I have the nr_busy_cpu field of sched_group_power struct that is not null when the platform is fully idle - which makes the scheduler unhappy. The root cause is: During the boot sequence, some CPUs reach the idle loop and set their NOHZ_IDLE flag while waiting for others CPUs to boot. But the nr_busy_cpus field is initialized later with the assumption that all CPUs are in the busy state whereas some CPUs have already set their NOHZ_IDLE flag. More generally, the NOHZ_IDLE flag must be initialized when new sched_domains are created in order to ensure that NOHZ_IDLE and nr_busy_cpus are aligned. This condition can be ensured by adding a synchronize_rcu() between the destruction of old sched_domains and the creation of new ones so the NOHZ_IDLE flag will not be updated with old sched_domain once it has been initialized. But this solution introduces a additionnal latency in the rebuild sequence that is called during cpu hotplug. As suggested by Frederic Weisbecker, another solution is to have the same rcu lifecycle for both NOHZ_IDLE and sched_domain struct. A new nohz_idle field is added to sched_domain so both status and sched_domain will share the same RCU lifecycle and will be always synchronized. In addition, there is no more need to protect nohz_idle against concurrent access as it is only modified by 2 exclusive functions called by local cpu. This solution has been prefered to the creation of a new struct with an extra pointer indirection for sched_domain. The synchronization is done at the cost of : - An additional indirection and a rcu_dereference for accessing nohz_idle. - We use only the nohz_idle field of the top sched_domain. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linaro-kernel@lists.linaro.org Cc: peterz@infradead.org Cc: fweisbec@gmail.com Cc: pjt@google.com Cc: rostedt@goodmis.org Cc: efault@gmx.de Link: http://lkml.kernel.org/r/1366729142-14662-1-git-send-email-vincent.guittot@linaro.org [ Fixed !NO_HZ build bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-04-23 14:59:02 +00:00
if (!sd || !sd->nohz_idle)
goto unlock;
sd->nohz_idle = 0;
atomic_inc(&sd->groups->sgc->nr_busy_cpus);
sched: Fix init NOHZ_IDLE flag On my SMP platform which is made of 5 cores in 2 clusters, I have the nr_busy_cpu field of sched_group_power struct that is not null when the platform is fully idle - which makes the scheduler unhappy. The root cause is: During the boot sequence, some CPUs reach the idle loop and set their NOHZ_IDLE flag while waiting for others CPUs to boot. But the nr_busy_cpus field is initialized later with the assumption that all CPUs are in the busy state whereas some CPUs have already set their NOHZ_IDLE flag. More generally, the NOHZ_IDLE flag must be initialized when new sched_domains are created in order to ensure that NOHZ_IDLE and nr_busy_cpus are aligned. This condition can be ensured by adding a synchronize_rcu() between the destruction of old sched_domains and the creation of new ones so the NOHZ_IDLE flag will not be updated with old sched_domain once it has been initialized. But this solution introduces a additionnal latency in the rebuild sequence that is called during cpu hotplug. As suggested by Frederic Weisbecker, another solution is to have the same rcu lifecycle for both NOHZ_IDLE and sched_domain struct. A new nohz_idle field is added to sched_domain so both status and sched_domain will share the same RCU lifecycle and will be always synchronized. In addition, there is no more need to protect nohz_idle against concurrent access as it is only modified by 2 exclusive functions called by local cpu. This solution has been prefered to the creation of a new struct with an extra pointer indirection for sched_domain. The synchronization is done at the cost of : - An additional indirection and a rcu_dereference for accessing nohz_idle. - We use only the nohz_idle field of the top sched_domain. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linaro-kernel@lists.linaro.org Cc: peterz@infradead.org Cc: fweisbec@gmail.com Cc: pjt@google.com Cc: rostedt@goodmis.org Cc: efault@gmx.de Link: http://lkml.kernel.org/r/1366729142-14662-1-git-send-email-vincent.guittot@linaro.org [ Fixed !NO_HZ build bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-04-23 14:59:02 +00:00
unlock:
rcu_read_unlock();
}
void set_cpu_sd_state_idle(void)
{
struct sched_domain *sd;
sched: Remove unnecessary iteration over sched domains to update nr_busy_cpus nr_busy_cpus parameter is used by nohz_kick_needed() to find out the number of busy cpus in a sched domain which has SD_SHARE_PKG_RESOURCES flag set. Therefore instead of updating nr_busy_cpus at every level of sched domain, since it is irrelevant, we can update this parameter only at the parent domain of the sd which has this flag set. Introduce a per-cpu parameter sd_busy which represents this parent domain. In nohz_kick_needed() we directly query the nr_busy_cpus parameter associated with the groups of sd_busy. By associating sd_busy with the highest domain which has SD_SHARE_PKG_RESOURCES flag set, we cover all lower level domains which could have this flag set and trigger nohz_idle_balancing if any of the levels have more than one busy cpu. sd_busy is irrelevant for asymmetric load balancing. However sd_asym has been introduced to represent the highest sched domain which has SD_ASYM_PACKING flag set so that it can be queried directly when required. While we are at it, we might as well change the nohz_idle parameter to be updated at the sd_busy domain level alone and not the base domain level of a CPU. This will unify the concept of busy cpus at just one level of sched domain where it is currently used. Signed-off-by: Preeti U Murthy<preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: svaidy@linux.vnet.ibm.com Cc: vincent.guittot@linaro.org Cc: bitbucket@online.de Cc: benh@kernel.crashing.org Cc: anton@samba.org Cc: Morten.Rasmussen@arm.com Cc: pjt@google.com Cc: peterz@infradead.org Cc: mikey@neuling.org Link: http://lkml.kernel.org/r/20131030031252.23426.4417.stgit@preeti.in.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-30 03:12:52 +00:00
int cpu = smp_processor_id();
rcu_read_lock();
sched: Remove unnecessary iteration over sched domains to update nr_busy_cpus nr_busy_cpus parameter is used by nohz_kick_needed() to find out the number of busy cpus in a sched domain which has SD_SHARE_PKG_RESOURCES flag set. Therefore instead of updating nr_busy_cpus at every level of sched domain, since it is irrelevant, we can update this parameter only at the parent domain of the sd which has this flag set. Introduce a per-cpu parameter sd_busy which represents this parent domain. In nohz_kick_needed() we directly query the nr_busy_cpus parameter associated with the groups of sd_busy. By associating sd_busy with the highest domain which has SD_SHARE_PKG_RESOURCES flag set, we cover all lower level domains which could have this flag set and trigger nohz_idle_balancing if any of the levels have more than one busy cpu. sd_busy is irrelevant for asymmetric load balancing. However sd_asym has been introduced to represent the highest sched domain which has SD_ASYM_PACKING flag set so that it can be queried directly when required. While we are at it, we might as well change the nohz_idle parameter to be updated at the sd_busy domain level alone and not the base domain level of a CPU. This will unify the concept of busy cpus at just one level of sched domain where it is currently used. Signed-off-by: Preeti U Murthy<preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: svaidy@linux.vnet.ibm.com Cc: vincent.guittot@linaro.org Cc: bitbucket@online.de Cc: benh@kernel.crashing.org Cc: anton@samba.org Cc: Morten.Rasmussen@arm.com Cc: pjt@google.com Cc: peterz@infradead.org Cc: mikey@neuling.org Link: http://lkml.kernel.org/r/20131030031252.23426.4417.stgit@preeti.in.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-30 03:12:52 +00:00
sd = rcu_dereference(per_cpu(sd_busy, cpu));
sched: Fix init NOHZ_IDLE flag On my SMP platform which is made of 5 cores in 2 clusters, I have the nr_busy_cpu field of sched_group_power struct that is not null when the platform is fully idle - which makes the scheduler unhappy. The root cause is: During the boot sequence, some CPUs reach the idle loop and set their NOHZ_IDLE flag while waiting for others CPUs to boot. But the nr_busy_cpus field is initialized later with the assumption that all CPUs are in the busy state whereas some CPUs have already set their NOHZ_IDLE flag. More generally, the NOHZ_IDLE flag must be initialized when new sched_domains are created in order to ensure that NOHZ_IDLE and nr_busy_cpus are aligned. This condition can be ensured by adding a synchronize_rcu() between the destruction of old sched_domains and the creation of new ones so the NOHZ_IDLE flag will not be updated with old sched_domain once it has been initialized. But this solution introduces a additionnal latency in the rebuild sequence that is called during cpu hotplug. As suggested by Frederic Weisbecker, another solution is to have the same rcu lifecycle for both NOHZ_IDLE and sched_domain struct. A new nohz_idle field is added to sched_domain so both status and sched_domain will share the same RCU lifecycle and will be always synchronized. In addition, there is no more need to protect nohz_idle against concurrent access as it is only modified by 2 exclusive functions called by local cpu. This solution has been prefered to the creation of a new struct with an extra pointer indirection for sched_domain. The synchronization is done at the cost of : - An additional indirection and a rcu_dereference for accessing nohz_idle. - We use only the nohz_idle field of the top sched_domain. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linaro-kernel@lists.linaro.org Cc: peterz@infradead.org Cc: fweisbec@gmail.com Cc: pjt@google.com Cc: rostedt@goodmis.org Cc: efault@gmx.de Link: http://lkml.kernel.org/r/1366729142-14662-1-git-send-email-vincent.guittot@linaro.org [ Fixed !NO_HZ build bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-04-23 14:59:02 +00:00
if (!sd || sd->nohz_idle)
goto unlock;
sd->nohz_idle = 1;
atomic_dec(&sd->groups->sgc->nr_busy_cpus);
sched: Fix init NOHZ_IDLE flag On my SMP platform which is made of 5 cores in 2 clusters, I have the nr_busy_cpu field of sched_group_power struct that is not null when the platform is fully idle - which makes the scheduler unhappy. The root cause is: During the boot sequence, some CPUs reach the idle loop and set their NOHZ_IDLE flag while waiting for others CPUs to boot. But the nr_busy_cpus field is initialized later with the assumption that all CPUs are in the busy state whereas some CPUs have already set their NOHZ_IDLE flag. More generally, the NOHZ_IDLE flag must be initialized when new sched_domains are created in order to ensure that NOHZ_IDLE and nr_busy_cpus are aligned. This condition can be ensured by adding a synchronize_rcu() between the destruction of old sched_domains and the creation of new ones so the NOHZ_IDLE flag will not be updated with old sched_domain once it has been initialized. But this solution introduces a additionnal latency in the rebuild sequence that is called during cpu hotplug. As suggested by Frederic Weisbecker, another solution is to have the same rcu lifecycle for both NOHZ_IDLE and sched_domain struct. A new nohz_idle field is added to sched_domain so both status and sched_domain will share the same RCU lifecycle and will be always synchronized. In addition, there is no more need to protect nohz_idle against concurrent access as it is only modified by 2 exclusive functions called by local cpu. This solution has been prefered to the creation of a new struct with an extra pointer indirection for sched_domain. The synchronization is done at the cost of : - An additional indirection and a rcu_dereference for accessing nohz_idle. - We use only the nohz_idle field of the top sched_domain. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linaro-kernel@lists.linaro.org Cc: peterz@infradead.org Cc: fweisbec@gmail.com Cc: pjt@google.com Cc: rostedt@goodmis.org Cc: efault@gmx.de Link: http://lkml.kernel.org/r/1366729142-14662-1-git-send-email-vincent.guittot@linaro.org [ Fixed !NO_HZ build bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-04-23 14:59:02 +00:00
unlock:
rcu_read_unlock();
}
/*
* This routine will record that the cpu is going idle with tick stopped.
* This info will be used in performing idle load balancing in the future.
*/
void nohz_balance_enter_idle(int cpu)
{
/*
* If this cpu is going down, then nothing needs to be done.
*/
if (!cpu_active(cpu))
return;
if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
return;
/*
* If we're a completely isolated CPU, we don't play.
*/
if (on_null_domain(cpu_rq(cpu)))
return;
cpumask_set_cpu(cpu, nohz.idle_cpus_mask);
atomic_inc(&nohz.nr_cpus);
set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
}
static int sched_ilb_notifier(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DYING:
nohz_balance_exit_idle(smp_processor_id());
return NOTIFY_OK;
default:
return NOTIFY_DONE;
}
}
#endif
static DEFINE_SPINLOCK(balancing);
/*
* Scale the max load_balance interval with the number of CPUs in the system.
* This trades load-balance latency on larger machines for less cross talk.
*/
void update_max_interval(void)
{
max_load_balance_interval = HZ*num_online_cpus()/10;
}
/*
* It checks each scheduling domain to see if it is due to be balanced,
* and initiates a balancing operation if so.
*
* Balancing parameters are set up in init_sched_domains.
*/
static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
{
int continue_balancing = 1;
int cpu = rq->cpu;
unsigned long interval;
struct sched_domain *sd;
/* Earliest time when we have to do rebalance again */
unsigned long next_balance = jiffies + 60*HZ;
int update_next_balance = 0;
int need_serialize, need_decay = 0;
u64 max_cost = 0;
update_blocked_averages(cpu);
sched: Dynamically allocate sched_domain/sched_group data-structures Instead of relying on static allocations for the sched_domain and sched_group trees, dynamically allocate and RCU free them. Allocating this dynamically also allows for some build_sched_groups() simplification since we can now (like with other simplifications) rely on the sched_domain tree instead of hard-coded knowledge. One tricky to note is that detach_destroy_domains() needs to hold rcu_read_lock() over the entire tear-down, per-cpu is not sufficient since that can lead to partial sched_group existance (could possibly be solved by doing the tear-down backwards but this is much more robust). A concequence of the above is that we can no longer print the sched_domain debug stuff from cpu_attach_domain() since that might now run with preemption disabled (due to classic RCU etc.) and sched_domain_debug() does some GFP_KERNEL allocations. Another thing to note is that we now fully rely on normal RCU and not RCU-sched, this is because with the new and exiting RCU flavours we grew over the years BH doesn't necessarily hold off RCU-sched grace periods (-rt is known to break this). This would in fact already cause us grief since we do sched_domain/sched_group iterations from softirq context. This patch is somewhat larger than I would like it to be, but I didn't find any means of shrinking/splitting this. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20110407122942.245307941@chello.nl Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-07 12:09:50 +00:00
rcu_read_lock();
for_each_domain(cpu, sd) {
/*
* Decay the newidle max times here because this is a regular
* visit to all the domains. Decay ~1% per second.
*/
if (time_after(jiffies, sd->next_decay_max_lb_cost)) {
sd->max_newidle_lb_cost =
(sd->max_newidle_lb_cost * 253) / 256;
sd->next_decay_max_lb_cost = jiffies + HZ;
need_decay = 1;
}
max_cost += sd->max_newidle_lb_cost;
if (!(sd->flags & SD_LOAD_BALANCE))
continue;
/*
* Stop the load balance at this level. There is another
* CPU in our sched group which is doing load balancing more
* actively.
*/
if (!continue_balancing) {
if (need_decay)
continue;
break;
}
sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance() Currently, in idle_balance(), we update rq->next_balance when we pull_tasks. However, it is also important to update this in the !pulled_tasks case too. When the CPU is "busy" (the CPU isn't idle), rq->next_balance gets computed using sd->busy_factor (so we increase the balance interval when the CPU is busy). However, when the CPU goes idle, rq->next_balance could still be set to a large value that was computed with the sd->busy_factor. Thus, we need to also update rq->next_balance in idle_balance() in the cases where !pulled_tasks too, so that rq->next_balance gets updated without taking the busy_factor into account when the CPU is about to go idle. This patch makes rq->next_balance get updated independently of whether or not we pulled_task. Also, we add logic to ensure that we always traverse at least 1 of the sched domains to get a proper next_balance value for updating rq->next_balance. Additionally, since load_balance() modifies the sd->balance_interval, we need to re-obtain the sched domain's interval after the call to load_balance() in rebalance_domains() before we update rq->next_balance. This patch adds and uses 2 new helper functions, update_next_balance() and get_sd_balance_interval() to update next_balance and obtain the sched domain's balance_interval. Signed-off-by: Jason Low <jason.low2@hp.com> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: daniel.lezcano@linaro.org Cc: alex.shi@linaro.org Cc: efault@gmx.de Cc: vincent.guittot@linaro.org Cc: morten.rasmussen@arm.com Cc: aswin@hp.com Link: http://lkml.kernel.org/r/1399596562.2200.7.camel@j-VirtualBox Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-09 00:49:22 +00:00
interval = get_sd_balance_interval(sd, idle != CPU_IDLE);
need_serialize = sd->flags & SD_SERIALIZE;
if (need_serialize) {
if (!spin_trylock(&balancing))
goto out;
}
if (time_after_eq(jiffies, sd->last_balance + interval)) {
if (load_balance(cpu, rq, sd, idle, &continue_balancing)) {
/*
* The LBF_DST_PINNED logic could have changed
* env->dst_cpu, so we can't know our idle
* state even if we migrated tasks. Update it.
*/
idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE;
}
sd->last_balance = jiffies;
sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance() Currently, in idle_balance(), we update rq->next_balance when we pull_tasks. However, it is also important to update this in the !pulled_tasks case too. When the CPU is "busy" (the CPU isn't idle), rq->next_balance gets computed using sd->busy_factor (so we increase the balance interval when the CPU is busy). However, when the CPU goes idle, rq->next_balance could still be set to a large value that was computed with the sd->busy_factor. Thus, we need to also update rq->next_balance in idle_balance() in the cases where !pulled_tasks too, so that rq->next_balance gets updated without taking the busy_factor into account when the CPU is about to go idle. This patch makes rq->next_balance get updated independently of whether or not we pulled_task. Also, we add logic to ensure that we always traverse at least 1 of the sched domains to get a proper next_balance value for updating rq->next_balance. Additionally, since load_balance() modifies the sd->balance_interval, we need to re-obtain the sched domain's interval after the call to load_balance() in rebalance_domains() before we update rq->next_balance. This patch adds and uses 2 new helper functions, update_next_balance() and get_sd_balance_interval() to update next_balance and obtain the sched domain's balance_interval. Signed-off-by: Jason Low <jason.low2@hp.com> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: daniel.lezcano@linaro.org Cc: alex.shi@linaro.org Cc: efault@gmx.de Cc: vincent.guittot@linaro.org Cc: morten.rasmussen@arm.com Cc: aswin@hp.com Link: http://lkml.kernel.org/r/1399596562.2200.7.camel@j-VirtualBox Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-05-09 00:49:22 +00:00
interval = get_sd_balance_interval(sd, idle != CPU_IDLE);
}
if (need_serialize)
spin_unlock(&balancing);
out:
if (time_after(next_balance, sd->last_balance + interval)) {
next_balance = sd->last_balance + interval;
update_next_balance = 1;
}
}
if (need_decay) {
/*
* Ensure the rq-wide value also decays but keep it at a
* reasonable floor to avoid funnies with rq->avg_idle.
*/
rq->max_idle_balance_cost =
max((u64)sysctl_sched_migration_cost, max_cost);
}
sched: Dynamically allocate sched_domain/sched_group data-structures Instead of relying on static allocations for the sched_domain and sched_group trees, dynamically allocate and RCU free them. Allocating this dynamically also allows for some build_sched_groups() simplification since we can now (like with other simplifications) rely on the sched_domain tree instead of hard-coded knowledge. One tricky to note is that detach_destroy_domains() needs to hold rcu_read_lock() over the entire tear-down, per-cpu is not sufficient since that can lead to partial sched_group existance (could possibly be solved by doing the tear-down backwards but this is much more robust). A concequence of the above is that we can no longer print the sched_domain debug stuff from cpu_attach_domain() since that might now run with preemption disabled (due to classic RCU etc.) and sched_domain_debug() does some GFP_KERNEL allocations. Another thing to note is that we now fully rely on normal RCU and not RCU-sched, this is because with the new and exiting RCU flavours we grew over the years BH doesn't necessarily hold off RCU-sched grace periods (-rt is known to break this). This would in fact already cause us grief since we do sched_domain/sched_group iterations from softirq context. This patch is somewhat larger than I would like it to be, but I didn't find any means of shrinking/splitting this. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/20110407122942.245307941@chello.nl Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-07 12:09:50 +00:00
rcu_read_unlock();
/*
* next_balance will be updated only when there is a need.
* When the cpu is attached to null domain for ex, it will not be
* updated.
*/
if (likely(update_next_balance)) {
rq->next_balance = next_balance;
#ifdef CONFIG_NO_HZ_COMMON
/*
* If this CPU has been elected to perform the nohz idle
* balance. Other idle CPUs have already rebalanced with
* nohz_idle_balance() and nohz.next_balance has been
* updated accordingly. This CPU is now running the idle load
* balance for itself and we need to update the
* nohz.next_balance accordingly.
*/
if ((idle == CPU_IDLE) && time_after(nohz.next_balance, rq->next_balance))
nohz.next_balance = rq->next_balance;
#endif
}
}
nohz: Rename CONFIG_NO_HZ to CONFIG_NO_HZ_COMMON We are planning to convert the dynticks Kconfig options layout into a choice menu. The user must be able to easily pick any of the following implementations: constant periodic tick, idle dynticks, full dynticks. As this implies a mutual exclusion, the two dynticks implementions need to converge on the selection of a common Kconfig option in order to ease the sharing of a common infrastructure. It would thus seem pretty natural to reuse CONFIG_NO_HZ to that end. It already implements all the idle dynticks code and the full dynticks depends on all that code for now. So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ. On the other hand we want to stay backward compatible: if CONFIG_NO_HZ is set in an older config file, we want to enable CONFIG_NO_HZ_IDLE by default. But we can't afford both at the same time or we run into a circular dependency: 1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select CONFIG_NO_HZ 2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE We might be able to support that from Kconfig/Kbuild but it may not be wise to introduce such a confusing behaviour. So to solve this, create a new CONFIG_NO_HZ_COMMON option which gathers the common code between idle and full dynticks (that common code for now is simply the idle dynticks code) and select it from their referring Kconfig. Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ to it for backward compatibility. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2011-08-10 21:21:01 +00:00
#ifdef CONFIG_NO_HZ_COMMON
/*
nohz: Rename CONFIG_NO_HZ to CONFIG_NO_HZ_COMMON We are planning to convert the dynticks Kconfig options layout into a choice menu. The user must be able to easily pick any of the following implementations: constant periodic tick, idle dynticks, full dynticks. As this implies a mutual exclusion, the two dynticks implementions need to converge on the selection of a common Kconfig option in order to ease the sharing of a common infrastructure. It would thus seem pretty natural to reuse CONFIG_NO_HZ to that end. It already implements all the idle dynticks code and the full dynticks depends on all that code for now. So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ. On the other hand we want to stay backward compatible: if CONFIG_NO_HZ is set in an older config file, we want to enable CONFIG_NO_HZ_IDLE by default. But we can't afford both at the same time or we run into a circular dependency: 1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select CONFIG_NO_HZ 2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE We might be able to support that from Kconfig/Kbuild but it may not be wise to introduce such a confusing behaviour. So to solve this, create a new CONFIG_NO_HZ_COMMON option which gathers the common code between idle and full dynticks (that common code for now is simply the idle dynticks code) and select it from their referring Kconfig. Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ to it for backward compatibility. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2011-08-10 21:21:01 +00:00
* In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the
* rebalancing for all the cpus for whom scheduler ticks are stopped.
*/
static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
{
int this_cpu = this_rq->cpu;
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
struct rq *rq;
int balance_cpu;
/* Earliest time when we have to do rebalance again */
unsigned long next_balance = jiffies + 60*HZ;
int update_next_balance = 0;
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
if (idle != CPU_IDLE ||
!test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu)))
goto end;
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
for_each_cpu(balance_cpu, nohz.idle_cpus_mask) {
if (balance_cpu == this_cpu || !idle_cpu(balance_cpu))
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
continue;
/*
* If this cpu gets work to do, stop the load balancing
* work being done for other cpus. Next load
* balancing owner will pick it up.
*/
if (need_resched())
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
break;
rq = cpu_rq(balance_cpu);
/*
* If time for next balance is due,
* do the balance.
*/
if (time_after_eq(jiffies, rq->next_balance)) {
raw_spin_lock_irq(&rq->lock);
update_rq_clock(rq);
update_idle_cpu_load(rq);
raw_spin_unlock_irq(&rq->lock);
rebalance_domains(rq, CPU_IDLE);
}
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
if (time_after(next_balance, rq->next_balance)) {
next_balance = rq->next_balance;
update_next_balance = 1;
}
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
}
/*
* next_balance will be updated only when there is a need.
* When the CPU is attached to null domain for ex, it will not be
* updated.
*/
if (likely(update_next_balance))
nohz.next_balance = next_balance;
end:
clear_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu));
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
}
/*
* Current heuristic for kicking the idle load balancer in the presence
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
* of an idle cpu in the system.
* - This rq has more than one task.
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
* - This rq has at least one CFS task and the capacity of the CPU is
* significantly reduced because of RT tasks or IRQs.
* - At parent of LLC scheduler domain level, this cpu's scheduler group has
* multiple busy cpu.
* - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler
* domain span are idle.
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
*/
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
static inline bool nohz_kick_needed(struct rq *rq)
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
{
unsigned long now = jiffies;
struct sched_domain *sd;
struct sched_group_capacity *sgc;
int nr_busy, cpu = rq->cpu;
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
bool kick = false;
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
if (unlikely(rq->idle_balance))
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
return false;
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
/*
* We may be recently in ticked or tickless idle mode. At the first
* busy tick after returning from idle, we will update the busy stats.
*/
set_cpu_sd_state_busy();
nohz_balance_exit_idle(cpu);
/*
* None are in tickless mode and hence no need for NOHZ idle load
* balancing.
*/
if (likely(!atomic_read(&nohz.nr_cpus)))
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
return false;
if (time_before(now, nohz.next_balance))
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
return false;
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
if (rq->nr_running >= 2)
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
return true;
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
rcu_read_lock();
sched: Remove unnecessary iteration over sched domains to update nr_busy_cpus nr_busy_cpus parameter is used by nohz_kick_needed() to find out the number of busy cpus in a sched domain which has SD_SHARE_PKG_RESOURCES flag set. Therefore instead of updating nr_busy_cpus at every level of sched domain, since it is irrelevant, we can update this parameter only at the parent domain of the sd which has this flag set. Introduce a per-cpu parameter sd_busy which represents this parent domain. In nohz_kick_needed() we directly query the nr_busy_cpus parameter associated with the groups of sd_busy. By associating sd_busy with the highest domain which has SD_SHARE_PKG_RESOURCES flag set, we cover all lower level domains which could have this flag set and trigger nohz_idle_balancing if any of the levels have more than one busy cpu. sd_busy is irrelevant for asymmetric load balancing. However sd_asym has been introduced to represent the highest sched domain which has SD_ASYM_PACKING flag set so that it can be queried directly when required. While we are at it, we might as well change the nohz_idle parameter to be updated at the sd_busy domain level alone and not the base domain level of a CPU. This will unify the concept of busy cpus at just one level of sched domain where it is currently used. Signed-off-by: Preeti U Murthy<preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: svaidy@linux.vnet.ibm.com Cc: vincent.guittot@linaro.org Cc: bitbucket@online.de Cc: benh@kernel.crashing.org Cc: anton@samba.org Cc: Morten.Rasmussen@arm.com Cc: pjt@google.com Cc: peterz@infradead.org Cc: mikey@neuling.org Link: http://lkml.kernel.org/r/20131030031252.23426.4417.stgit@preeti.in.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-30 03:12:52 +00:00
sd = rcu_dereference(per_cpu(sd_busy, cpu));
if (sd) {
sgc = sd->groups->sgc;
nr_busy = atomic_read(&sgc->nr_busy_cpus);
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
if (nr_busy > 1) {
kick = true;
goto unlock;
}
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
}
sched: Remove unnecessary iteration over sched domains to update nr_busy_cpus nr_busy_cpus parameter is used by nohz_kick_needed() to find out the number of busy cpus in a sched domain which has SD_SHARE_PKG_RESOURCES flag set. Therefore instead of updating nr_busy_cpus at every level of sched domain, since it is irrelevant, we can update this parameter only at the parent domain of the sd which has this flag set. Introduce a per-cpu parameter sd_busy which represents this parent domain. In nohz_kick_needed() we directly query the nr_busy_cpus parameter associated with the groups of sd_busy. By associating sd_busy with the highest domain which has SD_SHARE_PKG_RESOURCES flag set, we cover all lower level domains which could have this flag set and trigger nohz_idle_balancing if any of the levels have more than one busy cpu. sd_busy is irrelevant for asymmetric load balancing. However sd_asym has been introduced to represent the highest sched domain which has SD_ASYM_PACKING flag set so that it can be queried directly when required. While we are at it, we might as well change the nohz_idle parameter to be updated at the sd_busy domain level alone and not the base domain level of a CPU. This will unify the concept of busy cpus at just one level of sched domain where it is currently used. Signed-off-by: Preeti U Murthy<preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: svaidy@linux.vnet.ibm.com Cc: vincent.guittot@linaro.org Cc: bitbucket@online.de Cc: benh@kernel.crashing.org Cc: anton@samba.org Cc: Morten.Rasmussen@arm.com Cc: pjt@google.com Cc: peterz@infradead.org Cc: mikey@neuling.org Link: http://lkml.kernel.org/r/20131030031252.23426.4417.stgit@preeti.in.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-30 03:12:52 +00:00
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
sd = rcu_dereference(rq->sd);
if (sd) {
if ((rq->cfs.h_nr_running >= 1) &&
check_cpu_capacity(rq, sd)) {
kick = true;
goto unlock;
}
}
sched: Remove unnecessary iteration over sched domains to update nr_busy_cpus nr_busy_cpus parameter is used by nohz_kick_needed() to find out the number of busy cpus in a sched domain which has SD_SHARE_PKG_RESOURCES flag set. Therefore instead of updating nr_busy_cpus at every level of sched domain, since it is irrelevant, we can update this parameter only at the parent domain of the sd which has this flag set. Introduce a per-cpu parameter sd_busy which represents this parent domain. In nohz_kick_needed() we directly query the nr_busy_cpus parameter associated with the groups of sd_busy. By associating sd_busy with the highest domain which has SD_SHARE_PKG_RESOURCES flag set, we cover all lower level domains which could have this flag set and trigger nohz_idle_balancing if any of the levels have more than one busy cpu. sd_busy is irrelevant for asymmetric load balancing. However sd_asym has been introduced to represent the highest sched domain which has SD_ASYM_PACKING flag set so that it can be queried directly when required. While we are at it, we might as well change the nohz_idle parameter to be updated at the sd_busy domain level alone and not the base domain level of a CPU. This will unify the concept of busy cpus at just one level of sched domain where it is currently used. Signed-off-by: Preeti U Murthy<preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: svaidy@linux.vnet.ibm.com Cc: vincent.guittot@linaro.org Cc: bitbucket@online.de Cc: benh@kernel.crashing.org Cc: anton@samba.org Cc: Morten.Rasmussen@arm.com Cc: pjt@google.com Cc: peterz@infradead.org Cc: mikey@neuling.org Link: http://lkml.kernel.org/r/20131030031252.23426.4417.stgit@preeti.in.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-30 03:12:52 +00:00
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
sd = rcu_dereference(per_cpu(sd_asym, cpu));
sched: Remove unnecessary iteration over sched domains to update nr_busy_cpus nr_busy_cpus parameter is used by nohz_kick_needed() to find out the number of busy cpus in a sched domain which has SD_SHARE_PKG_RESOURCES flag set. Therefore instead of updating nr_busy_cpus at every level of sched domain, since it is irrelevant, we can update this parameter only at the parent domain of the sd which has this flag set. Introduce a per-cpu parameter sd_busy which represents this parent domain. In nohz_kick_needed() we directly query the nr_busy_cpus parameter associated with the groups of sd_busy. By associating sd_busy with the highest domain which has SD_SHARE_PKG_RESOURCES flag set, we cover all lower level domains which could have this flag set and trigger nohz_idle_balancing if any of the levels have more than one busy cpu. sd_busy is irrelevant for asymmetric load balancing. However sd_asym has been introduced to represent the highest sched domain which has SD_ASYM_PACKING flag set so that it can be queried directly when required. While we are at it, we might as well change the nohz_idle parameter to be updated at the sd_busy domain level alone and not the base domain level of a CPU. This will unify the concept of busy cpus at just one level of sched domain where it is currently used. Signed-off-by: Preeti U Murthy<preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: svaidy@linux.vnet.ibm.com Cc: vincent.guittot@linaro.org Cc: bitbucket@online.de Cc: benh@kernel.crashing.org Cc: anton@samba.org Cc: Morten.Rasmussen@arm.com Cc: pjt@google.com Cc: peterz@infradead.org Cc: mikey@neuling.org Link: http://lkml.kernel.org/r/20131030031252.23426.4417.stgit@preeti.in.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-30 03:12:52 +00:00
if (sd && (cpumask_first_and(nohz.idle_cpus_mask,
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
sched_domain_span(sd)) < cpu)) {
kick = true;
goto unlock;
}
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
unlock:
rcu_read_unlock();
sched: Move CFS tasks to CPUs with higher capacity When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining capacity for CFS tasks can be significantly reduced. Once we detect such situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle load balance to check if it's worth moving its tasks on an idle CPU. It's worth trying to move the task before the CPU is fully utilized to minimize the preemption by irq or RT tasks. Once the idle load_balance has selected the busiest CPU, it will look for an active load balance for only two cases: - There is only 1 task on the busiest CPU. - We haven't been able to move a task of the busiest rq. A CPU with a reduced capacity is included in the 1st case, and it's worth to actively migrate its task if the idle CPU has got more available capacity for CFS tasks. This test has been added in need_active_balance. As a sidenote, this will not generate more spurious ilb because we already trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that has a task, we will trig the ilb once for migrating the task. The nohz_kick_needed function has been cleaned up a bit while adding the new test env.src_cpu and env.src_rq must be set unconditionnally because they are used in need_active_balance which is called even if busiest->nr_running equals 1 Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Morten.Rasmussen@arm.com Cc: dietmar.eggemann@arm.com Cc: efault@gmx.de Cc: kamalesh@linux.vnet.ibm.com Cc: linaro-kernel@lists.linaro.org Cc: nicolas.pitre@linaro.org Cc: preeti@linux.vnet.ibm.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-27 15:54:14 +00:00
return kick;
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
}
#else
static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
#endif
/*
* run_rebalance_domains is triggered when needed from the scheduler tick.
* Also triggered for nohz idle balancing (with nohz_balancing_kick set).
*/
static void run_rebalance_domains(struct softirq_action *h)
{
struct rq *this_rq = this_rq();
enum cpu_idle_type idle = this_rq->idle_balance ?
CPU_IDLE : CPU_NOT_IDLE;
/*
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
* If this cpu has a pending nohz_balance_kick, then do the
* balancing on behalf of the other idle cpus whose ticks are
sched: Improve load balancing in the presence of idle CPUs When a CPU is kicked to do nohz idle balancing, it wakes up to do load balancing on itself, followed by load balancing on behalf of idle CPUs. But it may end up with load after the load balancing attempt on itself. This aborts nohz idle balancing. As a result several idle CPUs are left without tasks till such a time that an ILB CPU finds it unfavorable to pull tasks upon itself. This delays spreading of load across idle CPUs and worse, clutters only a few CPUs with tasks. The effect of the above problem was observed on an SMT8 POWER server with 2 levels of numa domains. Busy loops equal to number of cores were spawned. Since load balancing on fork/exec is discouraged across numa domains, all busy loops would start on one of the numa domains. However it was expected that eventually one busy loop would run per core across all domains due to nohz idle load balancing. But it was observed that it took as long as 10 seconds to spread the load across numa domains. Further investigation showed that this was a consequence of the following: 1. An ILB CPU was chosen from the first numa domain to trigger nohz idle load balancing [Given the experiment, upto 6 CPUs per core could be potentially idle in this domain.] 2. However the ILB CPU would call load_balance() on itself before initiating nohz idle load balancing. 3. Given cores are SMT8, the ILB CPU had enough opportunities to pull tasks from its sibling cores to even out load. 4. Now that the ILB CPU was no longer idle, it would abort nohz idle load balancing As a result the opportunities to spread load across numa domains were lost until such a time that the cores within the first numa domain had equal number of tasks among themselves. This is a pretty bad scenario, since the cores within the first numa domain would have as many as 4 tasks each, while cores in the neighbouring numa domains would all remain idle. Fix this, by checking if a CPU was woken up to do nohz idle load balancing, before it does load balancing upon itself. This way we allow idle CPUs across the system to do load balancing which results in quicker spread of load, instead of performing load balancing within the local sched domain hierarchy of the ILB CPU alone under circumstances such as above. Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Jason Low <jason.low2@hp.com> Cc: benh@kernel.crashing.org Cc: daniel.lezcano@linaro.org Cc: efault@gmx.de Cc: iamjoonsoo.kim@lge.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: riel@redhat.com Cc: srikar@linux.vnet.ibm.com Cc: svaidy@linux.vnet.ibm.com Cc: tim.c.chen@linux.intel.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/20150326130014.21532.17158.stgit@preeti.in.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-03-26 13:02:44 +00:00
* stopped. Do nohz_idle_balance *before* rebalance_domains to
* give the idle cpus a chance to load balance. Else we may
* load balance only within the local sched_domain hierarchy
* and abort nohz_idle_balance altogether if we pull some load.
*/
nohz_idle_balance(this_rq, idle);
sched: Improve load balancing in the presence of idle CPUs When a CPU is kicked to do nohz idle balancing, it wakes up to do load balancing on itself, followed by load balancing on behalf of idle CPUs. But it may end up with load after the load balancing attempt on itself. This aborts nohz idle balancing. As a result several idle CPUs are left without tasks till such a time that an ILB CPU finds it unfavorable to pull tasks upon itself. This delays spreading of load across idle CPUs and worse, clutters only a few CPUs with tasks. The effect of the above problem was observed on an SMT8 POWER server with 2 levels of numa domains. Busy loops equal to number of cores were spawned. Since load balancing on fork/exec is discouraged across numa domains, all busy loops would start on one of the numa domains. However it was expected that eventually one busy loop would run per core across all domains due to nohz idle load balancing. But it was observed that it took as long as 10 seconds to spread the load across numa domains. Further investigation showed that this was a consequence of the following: 1. An ILB CPU was chosen from the first numa domain to trigger nohz idle load balancing [Given the experiment, upto 6 CPUs per core could be potentially idle in this domain.] 2. However the ILB CPU would call load_balance() on itself before initiating nohz idle load balancing. 3. Given cores are SMT8, the ILB CPU had enough opportunities to pull tasks from its sibling cores to even out load. 4. Now that the ILB CPU was no longer idle, it would abort nohz idle load balancing As a result the opportunities to spread load across numa domains were lost until such a time that the cores within the first numa domain had equal number of tasks among themselves. This is a pretty bad scenario, since the cores within the first numa domain would have as many as 4 tasks each, while cores in the neighbouring numa domains would all remain idle. Fix this, by checking if a CPU was woken up to do nohz idle load balancing, before it does load balancing upon itself. This way we allow idle CPUs across the system to do load balancing which results in quicker spread of load, instead of performing load balancing within the local sched domain hierarchy of the ILB CPU alone under circumstances such as above. Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Jason Low <jason.low2@hp.com> Cc: benh@kernel.crashing.org Cc: daniel.lezcano@linaro.org Cc: efault@gmx.de Cc: iamjoonsoo.kim@lge.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: riel@redhat.com Cc: srikar@linux.vnet.ibm.com Cc: svaidy@linux.vnet.ibm.com Cc: tim.c.chen@linux.intel.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/20150326130014.21532.17158.stgit@preeti.in.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-03-26 13:02:44 +00:00
rebalance_domains(this_rq, idle);
}
/*
* Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
*/
void trigger_load_balance(struct rq *rq)
{
/* Don't need to rebalance while attached to NULL domain */
if (unlikely(on_null_domain(rq)))
return;
if (time_after_eq(jiffies, rq->next_balance))
raise_softirq(SCHED_SOFTIRQ);
nohz: Rename CONFIG_NO_HZ to CONFIG_NO_HZ_COMMON We are planning to convert the dynticks Kconfig options layout into a choice menu. The user must be able to easily pick any of the following implementations: constant periodic tick, idle dynticks, full dynticks. As this implies a mutual exclusion, the two dynticks implementions need to converge on the selection of a common Kconfig option in order to ease the sharing of a common infrastructure. It would thus seem pretty natural to reuse CONFIG_NO_HZ to that end. It already implements all the idle dynticks code and the full dynticks depends on all that code for now. So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ. On the other hand we want to stay backward compatible: if CONFIG_NO_HZ is set in an older config file, we want to enable CONFIG_NO_HZ_IDLE by default. But we can't afford both at the same time or we run into a circular dependency: 1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select CONFIG_NO_HZ 2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE We might be able to support that from Kconfig/Kbuild but it may not be wise to introduce such a confusing behaviour. So to solve this, create a new CONFIG_NO_HZ_COMMON option which gathers the common code between idle and full dynticks (that common code for now is simply the idle dynticks code) and select it from their referring Kconfig. Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ to it for backward compatibility. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2011-08-10 21:21:01 +00:00
#ifdef CONFIG_NO_HZ_COMMON
if (nohz_kick_needed(rq))
nohz_balancer_kick();
sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi <venki@google.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-22 00:09:41 +00:00
#endif
}
static void rq_online_fair(struct rq *rq)
{
update_sysctl();
sched/fair: Disable runtime_enabled on dying rq We kill rq->rd on the CPU_DOWN_PREPARE stage: cpuset_cpu_inactive -> cpuset_update_active_cpus -> partition_sched_domains -> -> cpu_attach_domain -> rq_attach_root -> set_rq_offline This unthrottles all throttled cfs_rqs. But the cpu is still able to call schedule() till take_cpu_down->__cpu_disable() is called from stop_machine. This case the tasks from just unthrottled cfs_rqs are pickable in a standard scheduler way, and they are picked by dying cpu. The cfs_rqs becomes throttled again, and migrate_tasks() in migration_call skips their tasks (one more unthrottle in migrate_tasks()->CPU_DYING does not happen, because rq->rd is already NULL). Patch sets runtime_enabled to zero. This guarantees, the runtime is not accounted, and the cfs_rqs won't exceed given cfs_rq->runtime_remaining = 1, and tasks will be pickable in migrate_tasks(). runtime_enabled is recalculated again when rq becomes online again. Ben Segall also noticed, we always enable runtime in tg_set_cfs_bandwidth(). Actually, we should do that for online cpus only. To prevent races with unthrottle_offline_cfs_rqs() we take get_online_cpus() lock. Reviewed-by: Ben Segall <bsegall@google.com> Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Kirill Tkhai <ktkhai@parallels.com> CC: Konstantin Khorenko <khorenko@parallels.com> CC: Paul Turner <pjt@google.com> CC: Mike Galbraith <umgwanakikbuti@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1403684382.3462.42.camel@tkhai Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-25 08:19:42 +00:00
update_runtime_enabled(rq);
}
static void rq_offline_fair(struct rq *rq)
{
update_sysctl();
/* Ensure any throttled groups are reachable by pick_next_task */
unthrottle_offline_cfs_rqs(rq);
}
#endif /* CONFIG_SMP */
/*
* scheduler tick hitting a task of our scheduling class:
*/
static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &curr->se;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
entity_tick(cfs_rq, se, queued);
}
if (!static_branch_unlikely(&sched_numa_balancing))
task_tick_numa(rq, curr);
}
/*
* called on fork with the child task as argument from the parent's context
* - child not yet on the tasklist
* - preemption disabled
*/
static void task_fork_fair(struct task_struct *p)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se, *curr;
int this_cpu = smp_processor_id();
struct rq *rq = this_rq();
unsigned long flags;
raw_spin_lock_irqsave(&rq->lock, flags);
update_rq_clock(rq);
cfs_rq = task_cfs_rq(current);
curr = cfs_rq->curr;
sched/fair: Fix small race where child->se.parent,cfs_rq might point to invalid ones There is a small race between copy_process() and cgroup_attach_task() where child->se.parent,cfs_rq points to invalid (old) ones. parent doing fork() | someone moving the parent to another cgroup -------------------------------+--------------------------------------------- copy_process() + dup_task_struct() -> parent->se is copied to child->se. se.parent,cfs_rq of them point to old ones. cgroup_attach_task() + cgroup_task_migrate() -> parent->cgroup is updated. + cpu_cgroup_attach() + sched_move_task() + task_move_group_fair() +- set_task_rq() -> se.parent,cfs_rq of parent are updated. + cgroup_fork() -> parent->cgroup is copied to child->cgroup. (*1) + sched_fork() + task_fork_fair() -> se.parent,cfs_rq of child are accessed while they point to old ones. (*2) In the worst case, this bug can lead to "use-after-free" and cause a panic, because it's new cgroup's refcount that is incremented at (*1), so the old cgroup(and related data) can be freed before (*2). In fact, a panic caused by this bug was originally caught in RHEL6.4. BUG: unable to handle kernel NULL pointer dereference at (null) IP: [<ffffffff81051e3e>] sched_slice+0x6e/0xa0 [...] Call Trace: [<ffffffff81051f25>] place_entity+0x75/0xa0 [<ffffffff81056a3a>] task_fork_fair+0xaa/0x160 [<ffffffff81063c0b>] sched_fork+0x6b/0x140 [<ffffffff8106c3c2>] copy_process+0x5b2/0x1450 [<ffffffff81063b49>] ? wake_up_new_task+0xd9/0x130 [<ffffffff8106d2f4>] do_fork+0x94/0x460 [<ffffffff81072a9e>] ? sys_wait4+0xae/0x100 [<ffffffff81009598>] sys_clone+0x28/0x30 [<ffffffff8100b393>] stub_clone+0x13/0x20 [<ffffffff8100b072>] ? system_call_fastpath+0x16/0x1b Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: <stable@vger.kernel.org> Link: http://lkml.kernel.org/r/039601ceae06$733d3130$59b79390$@mxp.nes.nec.co.jp Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-09-10 09:16:36 +00:00
/*
* Not only the cpu but also the task_group of the parent might have
* been changed after parent->se.parent,cfs_rq were copied to
* child->se.parent,cfs_rq. So call __set_task_cpu() to make those
* of child point to valid ones.
*/
rcu_read_lock();
__set_task_cpu(p, this_cpu);
rcu_read_unlock();
update_curr(cfs_rq);
if (curr)
se->vruntime = curr->vruntime;
place_entity(cfs_rq, se, 1);
if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {
/*
* Upon rescheduling, sched_class::put_prev_task() will place
* 'current' within the tree based on its new key value.
*/
swap(curr->vruntime, se->vruntime);
resched_curr(rq);
}
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
se->vruntime -= cfs_rq->min_vruntime;
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
/*
* Priority of the task has changed. Check to see if we preempt
* the current task.
*/
static void
prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
{
if (!task_on_rq_queued(p))
return;
/*
* Reschedule if we are currently running on this runqueue and
* our priority decreased, or if we are not currently running on
* this runqueue and our priority is higher than the current's
*/
if (rq->curr == p) {
if (p->prio > oldprio)
resched_curr(rq);
} else
check_preempt_curr(rq, p, 0);
}
static inline bool vruntime_normalized(struct task_struct *p)
{
struct sched_entity *se = &p->se;
/*
* In both the TASK_ON_RQ_QUEUED and TASK_ON_RQ_MIGRATING cases,
* the dequeue_entity(.flags=0) will already have normalized the
* vruntime.
*/
if (p->on_rq)
return true;
/*
* When !on_rq, vruntime of the task has usually NOT been normalized.
* But there are some cases where it has already been normalized:
*
* - A forked child which is waiting for being woken up by
* wake_up_new_task().
* - A task which has been woken up by try_to_wake_up() and
* waiting for actually being woken up by sched_ttwu_pending().
*/
if (!se->sum_exec_runtime || p->state == TASK_WAKING)
return true;
return false;
}
static void detach_task_cfs_rq(struct task_struct *p)
{
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
if (!vruntime_normalized(p)) {
/*
* Fix up our vruntime so that the current sleep doesn't
* cause 'unlimited' sleep bonus.
*/
place_entity(cfs_rq, se, 0);
se->vruntime -= cfs_rq->min_vruntime;
}
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
/* Catch up with the cfs_rq and remove our load when we leave */
detach_entity_load_avg(cfs_rq, se);
}
static void attach_task_cfs_rq(struct task_struct *p)
{
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
#ifdef CONFIG_FAIR_GROUP_SCHED
/*
* Since the real-depth could have been changed (only FAIR
* class maintain depth value), reset depth properly.
*/
se->depth = se->parent ? se->parent->depth + 1 : 0;
#endif
sched/fair: Fix switched_to_fair()'s per entity load tracking Where switched_from_fair() will remove the entity's load from the runqueue, switched_to_fair() does not currently add it back. This means that when a task leaves the fair class for a short duration; say because of PI; we loose its load contribution. This can ripple forward and disturb the load tracking because other operations (enqueue, dequeue) assume its factored in. Only once the runqueue empties will the load tracking recover. When we add it back in, age the per entity average to match up with the runqueue age. This has the obvious problem that if the task leaves the fair class for a significant time, the load will age to 0. Employ the normal migration rule for inter-runqueue moves in task_move_group_fair(). Again, there is the obvious problem of the task migrating while not in the fair class. The alternative solution would be to to omit the chunk in attach_entity_load_avg(), which would effectively reset the timestamp and use whatever avg there was. Signed-off-by: Byungchul Park <byungchul.park@lge.com> [ Rewrote the changelog and comments. ] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: yuyang.du@intel.com Link: http://lkml.kernel.org/r/1440069720-27038-5-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-08-20 11:21:59 +00:00
/* Synchronize task with its cfs_rq */
attach_entity_load_avg(cfs_rq, se);
if (!vruntime_normalized(p))
se->vruntime += cfs_rq->min_vruntime;
}
sched/fair: Fix switched_to_fair()'s per entity load tracking Where switched_from_fair() will remove the entity's load from the runqueue, switched_to_fair() does not currently add it back. This means that when a task leaves the fair class for a short duration; say because of PI; we loose its load contribution. This can ripple forward and disturb the load tracking because other operations (enqueue, dequeue) assume its factored in. Only once the runqueue empties will the load tracking recover. When we add it back in, age the per entity average to match up with the runqueue age. This has the obvious problem that if the task leaves the fair class for a significant time, the load will age to 0. Employ the normal migration rule for inter-runqueue moves in task_move_group_fair(). Again, there is the obvious problem of the task migrating while not in the fair class. The alternative solution would be to to omit the chunk in attach_entity_load_avg(), which would effectively reset the timestamp and use whatever avg there was. Signed-off-by: Byungchul Park <byungchul.park@lge.com> [ Rewrote the changelog and comments. ] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: yuyang.du@intel.com Link: http://lkml.kernel.org/r/1440069720-27038-5-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-08-20 11:21:59 +00:00
static void switched_from_fair(struct rq *rq, struct task_struct *p)
{
detach_task_cfs_rq(p);
}
static void switched_to_fair(struct rq *rq, struct task_struct *p)
{
attach_task_cfs_rq(p);
if (task_on_rq_queued(p)) {
/*
* We were most likely switched from sched_rt, so
* kick off the schedule if running, otherwise just see
* if we can still preempt the current task.
*/
if (rq->curr == p)
resched_curr(rq);
else
check_preempt_curr(rq, p, 0);
}
}
/* Account for a task changing its policy or group.
*
* This routine is mostly called to set cfs_rq->curr field when a task
* migrates between groups/classes.
*/
static void set_curr_task_fair(struct rq *rq)
{
struct sched_entity *se = &rq->curr->se;
for_each_sched_entity(se) {
struct cfs_rq *cfs_rq = cfs_rq_of(se);
set_next_entity(cfs_rq, se);
/* ensure bandwidth has been allocated on our new cfs_rq */
account_cfs_rq_runtime(cfs_rq, 0);
}
}
void init_cfs_rq(struct cfs_rq *cfs_rq)
{
cfs_rq->tasks_timeline = RB_ROOT;
cfs_rq->min_vruntime = (u64)(-(1LL << 20));
#ifndef CONFIG_64BIT
cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
#endif
#ifdef CONFIG_SMP
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 00:04:37 +00:00
atomic_long_set(&cfs_rq->removed_load_avg, 0);
atomic_long_set(&cfs_rq->removed_util_avg, 0);
#endif
}
#ifdef CONFIG_FAIR_GROUP_SCHED
static void task_move_group_fair(struct task_struct *p)
{
detach_task_cfs_rq(p);
set_task_rq(p, task_cpu(p));
sched/fair: Fix switched_to_fair()'s per entity load tracking Where switched_from_fair() will remove the entity's load from the runqueue, switched_to_fair() does not currently add it back. This means that when a task leaves the fair class for a short duration; say because of PI; we loose its load contribution. This can ripple forward and disturb the load tracking because other operations (enqueue, dequeue) assume its factored in. Only once the runqueue empties will the load tracking recover. When we add it back in, age the per entity average to match up with the runqueue age. This has the obvious problem that if the task leaves the fair class for a significant time, the load will age to 0. Employ the normal migration rule for inter-runqueue moves in task_move_group_fair(). Again, there is the obvious problem of the task migrating while not in the fair class. The alternative solution would be to to omit the chunk in attach_entity_load_avg(), which would effectively reset the timestamp and use whatever avg there was. Signed-off-by: Byungchul Park <byungchul.park@lge.com> [ Rewrote the changelog and comments. ] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: yuyang.du@intel.com Link: http://lkml.kernel.org/r/1440069720-27038-5-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-08-20 11:21:59 +00:00
#ifdef CONFIG_SMP
/* Tell se's cfs_rq has been changed -- migrated */
p->se.avg.last_update_time = 0;
#endif
attach_task_cfs_rq(p);
}
void free_fair_sched_group(struct task_group *tg)
{
int i;
destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));
for_each_possible_cpu(i) {
if (tg->cfs_rq)
kfree(tg->cfs_rq[i]);
if (tg->se) {
if (tg->se[i])
remove_entity_load_avg(tg->se[i]);
kfree(tg->se[i]);
}
}
kfree(tg->cfs_rq);
kfree(tg->se);
}
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se;
int i;
tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
if (!tg->cfs_rq)
goto err;
tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL);
if (!tg->se)
goto err;
tg->shares = NICE_0_LOAD;
init_cfs_bandwidth(tg_cfs_bandwidth(tg));
for_each_possible_cpu(i) {
cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
GFP_KERNEL, cpu_to_node(i));
if (!cfs_rq)
goto err;
se = kzalloc_node(sizeof(struct sched_entity),
GFP_KERNEL, cpu_to_node(i));
if (!se)
goto err_free_rq;
init_cfs_rq(cfs_rq);
init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
init_entity_runnable_average(se);
}
return 1;
err_free_rq:
kfree(cfs_rq);
err:
return 0;
}
void unregister_fair_sched_group(struct task_group *tg, int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
/*
* Only empty task groups can be destroyed; so we can speculatively
* check on_list without danger of it being re-added.
*/
if (!tg->cfs_rq[cpu]->on_list)
return;
raw_spin_lock_irqsave(&rq->lock, flags);
list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
struct sched_entity *se, int cpu,
struct sched_entity *parent)
{
struct rq *rq = cpu_rq(cpu);
cfs_rq->tg = tg;
cfs_rq->rq = rq;
init_cfs_rq_runtime(cfs_rq);
tg->cfs_rq[cpu] = cfs_rq;
tg->se[cpu] = se;
/* se could be NULL for root_task_group */
if (!se)
return;
if (!parent) {
se->cfs_rq = &rq->cfs;
se->depth = 0;
} else {
se->cfs_rq = parent->my_q;
se->depth = parent->depth + 1;
}
se->my_q = cfs_rq;
/* guarantee group entities always have weight */
update_load_set(&se->load, NICE_0_LOAD);
se->parent = parent;
}
static DEFINE_MUTEX(shares_mutex);
int sched_group_set_shares(struct task_group *tg, unsigned long shares)
{
int i;
unsigned long flags;
/*
* We can't change the weight of the root cgroup.
*/
if (!tg->se[0])
return -EINVAL;
shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES));
mutex_lock(&shares_mutex);
if (tg->shares == shares)
goto done;
tg->shares = shares;
for_each_possible_cpu(i) {
struct rq *rq = cpu_rq(i);
struct sched_entity *se;
se = tg->se[i];
/* Propagate contribution to hierarchy */
raw_spin_lock_irqsave(&rq->lock, flags);
/* Possible calls to update_curr() need rq clock */
update_rq_clock(rq);
for_each_sched_entity(se)
update_cfs_shares(group_cfs_rq(se));
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
done:
mutex_unlock(&shares_mutex);
return 0;
}
#else /* CONFIG_FAIR_GROUP_SCHED */
void free_fair_sched_group(struct task_group *tg) { }
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
return 1;
}
void unregister_fair_sched_group(struct task_group *tg, int cpu) { }
#endif /* CONFIG_FAIR_GROUP_SCHED */
static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task)
{
struct sched_entity *se = &task->se;
unsigned int rr_interval = 0;
/*
* Time slice is 0 for SCHED_OTHER tasks that are on an otherwise
* idle runqueue:
*/
if (rq->cfs.load.weight)
rr_interval = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se));
return rr_interval;
}
/*
* All the scheduling class methods:
*/
const struct sched_class fair_sched_class = {
.next = &idle_sched_class,
.enqueue_task = enqueue_task_fair,
.dequeue_task = dequeue_task_fair,
.yield_task = yield_task_fair,
.yield_to_task = yield_to_task_fair,
.check_preempt_curr = check_preempt_wakeup,
.pick_next_task = pick_next_task_fair,
.put_prev_task = put_prev_task_fair,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_fair,
.migrate_task_rq = migrate_task_rq_fair,
.rq_online = rq_online_fair,
.rq_offline = rq_offline_fair,
sched: Remove the cfs_rq dependency from set_task_cpu() In order to remove the cfs_rq dependency from set_task_cpu() we need to ensure the task is cfs_rq invariant for all callsites. The simple approach is to substract cfs_rq->min_vruntime from se->vruntime on dequeue, and add cfs_rq->min_vruntime on enqueue. However, this has the downside of breaking FAIR_SLEEPERS since we loose the old vruntime as we only maintain the relative position. To solve this, we observe that we only migrate runnable tasks, we do this using deactivate_task(.sleep=0) and activate_task(.wakeup=0), therefore we can restrain the min_vruntime invariance to that state. The only other case is wakeup balancing, since we want to maintain the old vruntime we cannot make it relative on dequeue, but since we don't migrate inactive tasks, we can do so right before we activate it again. This is where we need the new pre-wakeup hook, we need to call this while still holding the old rq->lock. We could fold it into ->select_task_rq(), but since that has multiple callsites and would obfuscate the locking requirements, that seems like a fudge. This leaves the fork() case, simply make sure that ->task_fork() leaves the ->vruntime in a relative state. This covers all cases where set_task_cpu() gets called, and ensures it sees a relative vruntime. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091216170518.191697025@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 17:04:41 +00:00
.task_waking = task_waking_fair,
.task_dead = task_dead_fair,
.set_cpus_allowed = set_cpus_allowed_common,
#endif
.set_curr_task = set_curr_task_fair,
.task_tick = task_tick_fair,
.task_fork = task_fork_fair,
.prio_changed = prio_changed_fair,
.switched_from = switched_from_fair,
.switched_to = switched_to_fair,
.get_rr_interval = get_rr_interval_fair,
sched/cputime: Fix clock_nanosleep()/clock_gettime() inconsistency Commit d670ec13178d0 "posix-cpu-timers: Cure SMP wobbles" fixes one glibc test case in cost of breaking another one. After that commit, calling clock_nanosleep(TIMER_ABSTIME, X) and then clock_gettime(&Y) can result of Y time being smaller than X time. Reproducer/tester can be found further below, it can be compiled and ran by: gcc -o tst-cpuclock2 tst-cpuclock2.c -pthread while ./tst-cpuclock2 ; do : ; done This reproducer, when running on a buggy kernel, will complain about "clock_gettime difference too small". Issue happens because on start in thread_group_cputimer() we initialize sum_exec_runtime of cputimer with threads runtime not yet accounted and then add the threads runtime to running cputimer again on scheduler tick, making it's sum_exec_runtime bigger than actual threads runtime. KOSAKI Motohiro posted a fix for this problem, but that patch was never applied: https://lkml.org/lkml/2013/5/26/191 . This patch takes different approach to cure the problem. It calls update_curr() when cputimer starts, that assure we will have updated stats of running threads and on the next schedule tick we will account only the runtime that elapsed from cputimer start. That also assure we have consistent state between cpu times of individual threads and cpu time of the process consisted by those threads. Full reproducer (tst-cpuclock2.c): #define _GNU_SOURCE #include <unistd.h> #include <sys/syscall.h> #include <stdio.h> #include <time.h> #include <pthread.h> #include <stdint.h> #include <inttypes.h> /* Parameters for the Linux kernel ABI for CPU clocks. */ #define CPUCLOCK_SCHED 2 #define MAKE_PROCESS_CPUCLOCK(pid, clock) \ ((~(clockid_t) (pid) << 3) | (clockid_t) (clock)) static pthread_barrier_t barrier; /* Help advance the clock. */ static void *chew_cpu(void *arg) { pthread_barrier_wait(&barrier); while (1) ; return NULL; } /* Don't use the glibc wrapper. */ static int do_nanosleep(int flags, const struct timespec *req) { clockid_t clock_id = MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED); return syscall(SYS_clock_nanosleep, clock_id, flags, req, NULL); } static int64_t tsdiff(const struct timespec *before, const struct timespec *after) { int64_t before_i = before->tv_sec * 1000000000ULL + before->tv_nsec; int64_t after_i = after->tv_sec * 1000000000ULL + after->tv_nsec; return after_i - before_i; } int main(void) { int result = 0; pthread_t th; pthread_barrier_init(&barrier, NULL, 2); if (pthread_create(&th, NULL, chew_cpu, NULL) != 0) { perror("pthread_create"); return 1; } pthread_barrier_wait(&barrier); /* The test. */ struct timespec before, after, sleeptimeabs; int64_t sleepdiff, diffabs; const struct timespec sleeptime = {.tv_sec = 0,.tv_nsec = 100000000 }; /* The relative nanosleep. Not sure why this is needed, but its presence seems to make it easier to reproduce the problem. */ if (do_nanosleep(0, &sleeptime) != 0) { perror("clock_nanosleep"); return 1; } /* Get the current time. */ if (clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &before) < 0) { perror("clock_gettime[2]"); return 1; } /* Compute the absolute sleep time based on the current time. */ uint64_t nsec = before.tv_nsec + sleeptime.tv_nsec; sleeptimeabs.tv_sec = before.tv_sec + nsec / 1000000000; sleeptimeabs.tv_nsec = nsec % 1000000000; /* Sleep for the computed time. */ if (do_nanosleep(TIMER_ABSTIME, &sleeptimeabs) != 0) { perror("absolute clock_nanosleep"); return 1; } /* Get the time after the sleep. */ if (clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &after) < 0) { perror("clock_gettime[3]"); return 1; } /* The time after sleep should always be equal to or after the absolute sleep time passed to clock_nanosleep. */ sleepdiff = tsdiff(&sleeptimeabs, &after); if (sleepdiff < 0) { printf("absolute clock_nanosleep woke too early: %" PRId64 "\n", sleepdiff); result = 1; printf("Before %llu.%09llu\n", before.tv_sec, before.tv_nsec); printf("After %llu.%09llu\n", after.tv_sec, after.tv_nsec); printf("Sleep %llu.%09llu\n", sleeptimeabs.tv_sec, sleeptimeabs.tv_nsec); } /* The difference between the timestamps taken before and after the clock_nanosleep call should be equal to or more than the duration of the sleep. */ diffabs = tsdiff(&before, &after); if (diffabs < sleeptime.tv_nsec) { printf("clock_gettime difference too small: %" PRId64 "\n", diffabs); result = 1; } pthread_cancel(th); return result; } Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20141112155843.GA24803@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-11-12 15:58:44 +00:00
.update_curr = update_curr_fair,
#ifdef CONFIG_FAIR_GROUP_SCHED
.task_move_group = task_move_group_fair,
#endif
};
#ifdef CONFIG_SCHED_DEBUG
void print_cfs_stats(struct seq_file *m, int cpu)
{
struct cfs_rq *cfs_rq;
rcu_read_lock();
for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
print_cfs_rq(m, cpu, cfs_rq);
rcu_read_unlock();
}
sched/numa: Fix numa balancing stats in /proc/pid/sched Commit 44dba3d5d6a1 ("sched: Refactor task_struct to use numa_faults instead of numa_* pointers") modified the way tsk->numa_faults stats are accounted. However that commit never touched show_numa_stats() that is displayed in /proc/pid/sched and thus the numbers displayed in /proc/pid/sched don't match the actual numbers. Fix it by making sure that /proc/pid/sched reflects the task fault numbers. Also add group fault stats too. Also couple of more modifications are added here: 1. Format changes: - Previously we would list two entries per node, one for private and one for shared. Also the home node info was listed in each entry. - Now preferred node, total_faults and current node are displayed separately. - Now there is one entry per node, that lists private,shared task and group faults. 2. Unit changes: - p->numa_pages_migrated was getting reset after every read of /proc/pid/sched. It's more useful to have absolute numbers since differential migrations between two accesses can be more easily calculated. Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Iulia Manda <iulia.manda21@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1435252903-1081-4-git-send-email-srikar@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-06-25 17:21:43 +00:00
#ifdef CONFIG_NUMA_BALANCING
void show_numa_stats(struct task_struct *p, struct seq_file *m)
{
int node;
unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0;
for_each_online_node(node) {
if (p->numa_faults) {
tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)];
tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)];
}
if (p->numa_group) {
gsf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 0)],
gpf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 1)];
}
print_numa_stats(m, node, tsf, tpf, gsf, gpf);
}
}
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_SCHED_DEBUG */
__init void init_sched_fair_class(void)
{
#ifdef CONFIG_SMP
open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);
nohz: Rename CONFIG_NO_HZ to CONFIG_NO_HZ_COMMON We are planning to convert the dynticks Kconfig options layout into a choice menu. The user must be able to easily pick any of the following implementations: constant periodic tick, idle dynticks, full dynticks. As this implies a mutual exclusion, the two dynticks implementions need to converge on the selection of a common Kconfig option in order to ease the sharing of a common infrastructure. It would thus seem pretty natural to reuse CONFIG_NO_HZ to that end. It already implements all the idle dynticks code and the full dynticks depends on all that code for now. So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ. On the other hand we want to stay backward compatible: if CONFIG_NO_HZ is set in an older config file, we want to enable CONFIG_NO_HZ_IDLE by default. But we can't afford both at the same time or we run into a circular dependency: 1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select CONFIG_NO_HZ 2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE We might be able to support that from Kconfig/Kbuild but it may not be wise to introduce such a confusing behaviour. So to solve this, create a new CONFIG_NO_HZ_COMMON option which gathers the common code between idle and full dynticks (that common code for now is simply the idle dynticks code) and select it from their referring Kconfig. Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ to it for backward compatibility. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2011-08-10 21:21:01 +00:00
#ifdef CONFIG_NO_HZ_COMMON
nohz.next_balance = jiffies;
zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
cpu_notifier(sched_ilb_notifier, 0);
#endif
#endif /* SMP */
}