leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

sched: fix nohz load balancer on cpu offline

Browse Source 
Christian Borntraeger reports:

> After a logical cpu offline, even on a complete idle system, there
> is one cpu with full ticks. It turns out that nohz.cpu_mask has the
> the offlined cpu still set.
>
> In select_nohz_load_balancer() we check if the system is completely
> idle to turn of load balancing. We compare cpu_online_map with
> nohz.cpu_mask.  Since cpu_online_map is updated on cpu unplug,
> but nohz.cpu_mask is not, the check fails and the scheduler believes
> that we need an "idle load balancer" even on a fully idle system.
> Since the ilb cpu does not deactivate the timer tick this breaks NOHZ.

Fix the select_nohz_load_balancer() to not set the nohz.cpu_mask
while a cpu is going offline.

Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Suresh Siddha
2009-02-04 11:59:44 -08:00
committed by Ingo Molnar
parent 35626129ab
commit 483b4ee60e
1 changed files with 11 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
kernel/sched.c
View File

@@ -3890,19 +3890,24 @@ int select_nohz_load_balancer(int stop_tick)
int cpu = smp_processor_id(); int cpu = smp_processor_id();
if (stop_tick) { if (stop_tick) {
cpumask_set_cpu(cpu, nohz.cpu_mask);
cpu_rq(cpu)->in_nohz_recently = 1; cpu_rq(cpu)->in_nohz_recently = 1;
/* if (!cpu_active(cpu)) {
* If we are going offline and still the leader, give up! if (atomic_read(&nohz.load_balancer) != cpu)
*/ return 0;
if (!cpu_active(cpu) &&
atomic_read(&nohz.load_balancer) == cpu) { /*
* If we are going offline and still the leader,
* give up!
*/
if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
BUG(); BUG();
return 0; return 0;
} }
cpumask_set_cpu(cpu, nohz.cpu_mask);
/* time for ilb owner also to sleep */ /* time for ilb owner also to sleep */
if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
if (atomic_read(&nohz.load_balancer) == cpu) if (atomic_read(&nohz.load_balancer) == cpu)