Re: [PATCH] sched: Improve the accuracy of sched_stat_wait statistics for rt and dl
From: Zhang Qiao
Date: Tue Apr 16 2024 - 03:13:12 EST
ping.
在 2024/3/22 16:15, Zhang Qiao 写道:
> Where commit b9c88f752268 ("sched/fair: Improve the accuracy of
> sched_stat_wait statistics") fixed a wrong scenairio for cfs schedstat.
>
> This wrong scenario is also present for the RT task. For avoiding this
> scenario, add wait_start check in __update_stats_wait_end();
>
> Signed-off-by: Zhang Qiao <zhangqiao22@xxxxxxxxxx>
> ---
> kernel/sched/fair.c | 9 ---------
> kernel/sched/stats.c | 11 ++++++++++-
> 2 files changed, 10 insertions(+), 10 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 6a16129f9a5c..36c81fe0086b 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -1208,15 +1208,6 @@ update_stats_wait_end_fair(struct cfs_rq *cfs_rq, struct sched_entity *se)
>
> stats = __schedstats_from_se(se);
>
> - /*
> - * When the sched_schedstat changes from 0 to 1, some sched se
> - * maybe already in the runqueue, the se->statistics.wait_start
> - * will be 0.So it will let the delta wrong. We need to avoid this
> - * scenario.
> - */
> - if (unlikely(!schedstat_val(stats->wait_start)))
> - return;
> -
> if (entity_is_task(se))
> p = task_of(se);
>
> diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
> index 857f837f52cb..7077eb490c09 100644
> --- a/kernel/sched/stats.c
> +++ b/kernel/sched/stats.c
> @@ -20,8 +20,17 @@ void __update_stats_wait_start(struct rq *rq, struct task_struct *p,
> void __update_stats_wait_end(struct rq *rq, struct task_struct *p,
> struct sched_statistics *stats)
> {
> - u64 delta = rq_clock(rq) - schedstat_val(stats->wait_start);
> + u64 delta;
>
> + /*
> + * When the sched_schedstat changes from 0 to 1, some sched se
> + * maybe already in the runqueue, the stats->wait_start will be 0.
> + * So it will let the delta wrong. We need to avoid this scenario.
> + */
> + if (unlikely(!schedstat_val(stats->wait_start)))
> + return;
> +
> + delta = rq_clock(rq) - schedstat_val(stats->wait_start);
> if (p) {
> if (task_on_rq_migrating(p)) {
> /*
>