The patch titled proc: consider NO_HZ when printing idle and iowait times has been added to the -mm tree. Its filename is proc-consider-no_hz-when-printing-idle-and-iowait-times.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find out what to do about this The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ Subject: proc: consider NO_HZ when printing idle and iowait times From: Michal Hocko <mhocko@xxxxxxx> show_stat handler of the /proc/stat file relies on kstat_cpu(cpu) statistics when priting information about idle and iowait times. This is OK if we are not using tickless kernel (CONFIG_NO_HZ) because counters are updated periodically. With NO_HZ things got more tricky because we are not doing idle/iowait accounting while we are tickless so the value might get outdated. Users of /proc/stat will notice that by unchanged idle/iowait values which is then interpreted as 0% idle/iowait time. From the user space POV this is an unexpected behavior and a change of the interface. Let's fix this by using get_cpu_{idle,iowait}_time_us which accounts the total idle/iowait time since boot and it doesn't rely on sampling or any other periodic activity. Fall back to the previous behavior if NO_HZ is disabled or not configured. Signed-off-by: Michal Hocko <mhocko@xxxxxxx> Cc: Dave Jones <davej@xxxxxxxxxx> Cc: Arnd Bergmann <arnd@xxxxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: Alexey Dobriyan <adobriyan@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- fs/proc/stat.c | 41 ++++++++++++++++++++++++++++++++++------- 1 file changed, 34 insertions(+), 7 deletions(-) diff -puN fs/proc/stat.c~proc-consider-no_hz-when-printing-idle-and-iowait-times fs/proc/stat.c --- a/fs/proc/stat.c~proc-consider-no_hz-when-printing-idle-and-iowait-times +++ a/fs/proc/stat.c @@ -10,6 +10,7 @@ #include <linux/time.h> #include <linux/irqnr.h> #include <asm/cputime.h> +#include <linux/tick.h> #ifndef arch_irq_stat_cpu #define arch_irq_stat_cpu(cpu) 0 @@ -21,6 +22,35 @@ #define arch_idle_time(cpu) 0 #endif +static cputime64_t get_idle_time(int cpu) +{ + u64 idle_time = get_cpu_idle_time_us(cpu, NULL); + cputime64_t idle; + + if (idle_time == -1ULL) { + /* !NO_HZ so we can rely on cpustat.idle */ + idle = kstat_cpu(cpu).cpustat.idle; + idle = cputime64_add(idle, arch_idle_time(cpu)); + } else + idle = usecs_to_cputime(idle_time); + + return idle; +} + +static cputime64_t get_iowait_time(int cpu) +{ + u64 iowait_time = get_cpu_iowait_time_us(cpu, NULL); + cputime64_t iowait; + + if (iowait_time == -1ULL) + /* !NO_HZ so we can rely on cpustat.iowait */ + iowait = kstat_cpu(cpu).cpustat.iowait; + else + iowait = usecs_to_cputime(iowait_time); + + return iowait; +} + static int show_stat(struct seq_file *p, void *v) { int i, j; @@ -42,9 +72,8 @@ static int show_stat(struct seq_file *p, user = cputime64_add(user, kstat_cpu(i).cpustat.user); nice = cputime64_add(nice, kstat_cpu(i).cpustat.nice); system = cputime64_add(system, kstat_cpu(i).cpustat.system); - idle = cputime64_add(idle, kstat_cpu(i).cpustat.idle); - idle = cputime64_add(idle, arch_idle_time(i)); - iowait = cputime64_add(iowait, kstat_cpu(i).cpustat.iowait); + idle = cputime64_add(idle, get_idle_time(i)); + iowait = cputime64_add(iowait, get_iowait_time(i)); irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq); softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq); steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal); @@ -76,14 +105,12 @@ static int show_stat(struct seq_file *p, (unsigned long long)cputime64_to_clock_t(guest), (unsigned long long)cputime64_to_clock_t(guest_nice)); for_each_online_cpu(i) { - /* Copy values here to work around gcc-2.95.3, gcc-2.96 */ user = kstat_cpu(i).cpustat.user; nice = kstat_cpu(i).cpustat.nice; system = kstat_cpu(i).cpustat.system; - idle = kstat_cpu(i).cpustat.idle; - idle = cputime64_add(idle, arch_idle_time(i)); - iowait = kstat_cpu(i).cpustat.iowait; + idle = get_idle_time(i); + iowait = get_iowait_time(i); irq = kstat_cpu(i).cpustat.irq; softirq = kstat_cpu(i).cpustat.softirq; steal = kstat_cpu(i).cpustat.steal; _ Patches currently in -mm which might be from mhocko@xxxxxxx are memcg-pin-execution-to-current-cpu-while-draining-stock.patch memcg-make-oom_lock-0-and-1-based-rather-than-coutner.patch linux-next.patch cputime-clean-up-cputime_to_usecs-and-usecs_to_cputime-macros.patch tick-fix-update_ts_time_stat-idle-accounting.patch nohz-do-not-update-idle-iowait-counters-from-get_cpu_idleiowait_time_us-if-not-asked.patch proc-consider-no_hz-when-printing-idle-and-iowait-times.patch mm-compaction-trivial-clean-up-in-acct_isolated.patch mm-change-isolate-mode-from-define-to-bitwise-type.patch mm-compaction-make-isolate_lru_page-filter-aware.patch mm-zone_reclaim-make-isolate_lru_page-filter-aware.patch mm-migration-clean-up-unmap_and_move.patch mm-page-writebackc-make-determine_dirtyable_memory-static-again.patch oom-avoid-killing-kthreads-if-they-assume-the-oom-killed-threads-mm.patch mm-vmscan-fix-force-scanning-small-targets-without-swap.patch mm-vmscan-drop-nr_force_scan-from-get_scan_count.patch memcg-rename-mem-variable-to-memcg.patch memcg-fix-oom-schedule_timeout.patch memcg-do-not-expose-uninitialized-mem_cgroup_per_node-to-world.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html