From 7386cdbf2f57ea8cff3c9fde93f206e58b9fe13f Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 10 Oct 2012 11:51:09 +0530 Subject: [PATCH 1/2] nohz: Fix idle ticks in cpu summary line of /proc/stat Git commit 09a1d34f8535ecf9 "nohz: Make idle/iowait counter update conditional" introduced a bug in regard to cpu hotplug. The effect is that the number of idle ticks in the cpu summary line in /proc/stat is still counting ticks for offline cpus. Reproduction is easy, just start a workload that keeps all cpus busy, switch off one or more cpus and then watch the idle field in top. On a dual-core with one cpu 100% busy and one offline cpu you will get something like this: %Cpu(s): 48.7 us, 1.3 sy, 0.0 ni, 50.0 id, 0.0 wa, 0.0 hi, 0.0 si, %0.0 st The problem is that an offline cpu still has ts->idle_active == 1. To fix this we should make sure that the cpu is online when calling get_cpu_idle_time_us and get_cpu_iowait_time_us. [Srivatsa: Rebased to current mainline] Reported-by: Martin Schwidefsky Signed-off-by: Michal Hocko Reviewed-by: Srivatsa S. Bhat Signed-off-by: Srivatsa S. Bhat Link: http://lkml.kernel.org/r/20121010061820.8999.57245.stgit@srivatsabhat.in.ibm.com Cc: deepthi@linux.vnet.ibm.com Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner --- fs/proc/stat.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 64c3b3172367..e296572c73ed 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -45,10 +45,13 @@ static cputime64_t get_iowait_time(int cpu) static u64 get_idle_time(int cpu) { - u64 idle, idle_time = get_cpu_idle_time_us(cpu, NULL); + u64 idle, idle_time = -1ULL; + + if (cpu_online(cpu)) + idle_time = get_cpu_idle_time_us(cpu, NULL); if (idle_time == -1ULL) - /* !NO_HZ so we can rely on cpustat.idle */ + /* !NO_HZ or cpu offline so we can rely on cpustat.idle */ idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; else idle = usecs_to_cputime64(idle_time); @@ -58,10 +61,13 @@ static u64 get_idle_time(int cpu) static u64 get_iowait_time(int cpu) { - u64 iowait, iowait_time = get_cpu_iowait_time_us(cpu, NULL); + u64 iowait, iowait_time = -1ULL; + + if (cpu_online(cpu)) + iowait_time = get_cpu_iowait_time_us(cpu, NULL); if (iowait_time == -1ULL) - /* !NO_HZ so we can rely on cpustat.iowait */ + /* !NO_HZ or cpu offline so we can rely on cpustat.iowait */ iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; else iowait = usecs_to_cputime64(iowait_time); From fd0587339d80dd2fea5ead7f734676c9c618eace Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 21 Oct 2012 12:05:51 +0200 Subject: [PATCH 2/2] Documentation: Reflect the new location of the NMI watchdog info Commit 9919cba7 ("watchdog: Update documentation") moved the NMI watchdog documentation from nmi_watchdog.txt to lockup-watchdogs.txt. Update the index file accordingly. Signed-off-by: Jean Delvare Cc: Fernando Luis Vazquez Cao Cc: Randy Dunlap Cc: Don Zickus Link: http://lkml.kernel.org/r/20121021120551.4656d99b@endymion.delvare Signed-off-by: Ingo Molnar --- Documentation/00-INDEX | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX index 49c051380daf..fec55dc5ed2f 100644 --- a/Documentation/00-INDEX +++ b/Documentation/00-INDEX @@ -210,6 +210,8 @@ local_ops.txt - semantics and behavior of local atomic operations. lockdep-design.txt - documentation on the runtime locking correctness validator. +lockup-watchdogs.txt + - info on soft and hard lockup detectors (aka nmi_watchdog). logo.gif - full colour GIF image of Linux logo (penguin - Tux). logo.txt @@ -240,8 +242,6 @@ netlabel/ - directory with information on the NetLabel subsystem. networking/ - directory with info on various aspects of networking with Linux. -nmi_watchdog.txt - - info on NMI watchdog for SMP systems. nommu-mmap.txt - documentation about no-mmu memory mapping support. numastat.txt