diff options
| author | Josh Don <joshdon@google.com> | 2021-08-27 18:54:38 +0200 |
|---|---|---|
| committer | Peter Zijlstra <peterz@infradead.org> | 2021-10-05 15:51:35 +0200 |
| commit | a130e8fbc7de796eb6e680724d87f4737a26d0ac (patch) | |
| tree | 4adeb41642500b6aca5ddd2b1144a9785e2e591e /fs/proc | |
| parent | sched/core: Simplify core-wide task selection (diff) | |
| download | linux-a130e8fbc7de796eb6e680724d87f4737a26d0ac.tar.xz linux-a130e8fbc7de796eb6e680724d87f4737a26d0ac.zip | |
fs/proc/uptime.c: Fix idle time reporting in /proc/uptime
/proc/uptime reports idle time by reading the CPUTIME_IDLE field from
the per-cpu kcpustats. However, on NO_HZ systems, idle time is not
continually updated on idle cpus, leading this value to appear
incorrectly small.
/proc/stat performs an accounting update when reading idle time; we
can use the same approach for uptime.
With this patch, /proc/stat and /proc/uptime now agree on idle time.
Additionally, the following shows idle time tick up consistently on an
idle machine:
(while true; do cat /proc/uptime; sleep 1; done) | awk '{print $2-prev; prev=$2}'
Reported-by: Luigi Rizzo <lrizzo@google.com>
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lkml.kernel.org/r/20210827165438.3280779-1-joshdon@google.com
Diffstat (limited to 'fs/proc')
| -rw-r--r-- | fs/proc/stat.c | 4 | ||||
| -rw-r--r-- | fs/proc/uptime.c | 14 |
2 files changed, 11 insertions, 7 deletions
diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 6561a06ef905..4fb8729a68d4 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -24,7 +24,7 @@ #ifdef arch_idle_time -static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) +u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle; @@ -46,7 +46,7 @@ static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu) #else -static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) +u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle, idle_usecs = -1ULL; diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c index 5a1b228964fb..deb99bc9b7e6 100644 --- a/fs/proc/uptime.c +++ b/fs/proc/uptime.c @@ -12,18 +12,22 @@ static int uptime_proc_show(struct seq_file *m, void *v) { struct timespec64 uptime; struct timespec64 idle; - u64 nsec; + u64 idle_nsec; u32 rem; int i; - nsec = 0; - for_each_possible_cpu(i) - nsec += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE]; + idle_nsec = 0; + for_each_possible_cpu(i) { + struct kernel_cpustat kcs; + + kcpustat_cpu_fetch(&kcs, i); + idle_nsec += get_idle_time(&kcs, i); + } ktime_get_boottime_ts64(&uptime); timens_add_boottime(&uptime); - idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); + idle.tv_sec = div_u64_rem(idle_nsec, NSEC_PER_SEC, &rem); idle.tv_nsec = rem; seq_printf(m, "%lu.%02lu %lu.%02lu\n", (unsigned long) uptime.tv_sec, |