sched/cputime: Fix getrusage(RUSAGE_THREAD) with nohz_full
Sasha Levin
maintainerPATCH 1/1 sched/cputime: Fix getrusage(RUSAGE_THREAD) with nohz_full
From: Frederic Weisbecker <[email protected]>
[ Upstream commit e7f2be115f0746b969c0df14c0d182f65f005ca5 ]
getrusage(RUSAGE_THREAD) with nohz_full may return shorter utime/stime than the actual time.
task_cputime_adjusted() snapshots utime and stime and then adjust their sum to match the scheduler maintained cputime.sum_exec_runtime. Unfortunately in nohz_full, sum_exec_runtime is only updated once per second in the worst case, causing a discrepancy against utime and stime that can be updated anytime by the reader using vtime.
To fix this situation, perform an update of cputime.sum_exec_runtime when the cputime snapshot reports the task as actually running while the tick is disabled. The related overhead is then contained within the relevant situations.
--- include/linux/sched/cputime.h | 5 +++-- kernel/sched/cputime.c | 12 +++++++++--- 2 files changed, 12 insertions(+), 5 deletions(-)
include/linux/sched/cputime.h +3 -2
@@ -18,15 +18,16 @@#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void task_cputime (struct task_struct *t, +extern bool task_cputime (struct task_struct *t,u64 *utime,u64 *stime);extern u64 task_gtime (struct task_struct *t);#else -static inline void task_cputime (struct task_struct *t, +static inline bool task_cputime (struct task_struct *t,u64 *utime,u64 *stime) { *utime = t->utime; *stime = t->stime; +return false; }static inline u64 task_gtime (struct task_struct *t)
kernel/sched/cputime.c +9 -3
@@ -665,7 +665,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) .sum_exec_runtime = p->se.sum_exec_runtime, }; -task_cputime (p, &cputime.utime, &cputime.stime); +if (task_cputime (p, &cputime.utime, &cputime.stime)) + cputime.sum_exec_runtime =task_sched_runtime (p);cputime_adjust (&cputime, &p->prev_cputime, ut, st); }EXPORT_SYMBOL_GPL (task_cputime_adjusted);
@@ -858,19 +859,21 @@ u64 task_gtime(struct task_struct *t)* add up the pending nohz execution time since the last * cputime snapshot. */ -void task_cputime (struct task_struct *t,u64 *utime,u64 *stime) +bool task_cputime (struct task_struct *t,u64 *utime,u64 *stime) {struct vtime *vtime = &t->vtime;unsigned int seq;u64 delta; +int ret;if (!vtime_accounting_enabled ()) { *utime = t->utime; *stime = t->stime; -return ; +return false; } do { + ret = false; seq = read_seqcount_begin(&vtime->seqcount); *utime = t->utime;
@@ -880,6 +883,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)if (vtime->state ==VTIME_INACTIVE ||is_idle_task (t))continue ; + ret = true; delta =vtime_delta (vtime);/*
@@ -891,5 +895,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) else if (vtime->state == VTIME_SYS) *stime += vtime->stime + delta; }while (read_seqcount_retry (&vtime->seqcount, seq)); + +return ret; }#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
Signature · 1 line
2.33.0