Re: [PATCH v3] sched/fair: sanitize vruntime of entity being placed

[Vincent Guittot <vincent.guittot@linaro.org>]

On Thu, 2 Mar 2023 at 10:36, Zhang Qiao <zhangqiao22@huawei.com> wrote:
>
>
>
> 在 2023/2/27 22:37, Vincent Guittot 写道:
> > On Mon, 27 Feb 2023 at 09:43, Roman Kagan <rkagan@amazon.de> wrote:
> >>
> >> On Tue, Feb 21, 2023 at 06:26:11PM +0100, Vincent Guittot wrote:
> >>> On Tue, 21 Feb 2023 at 17:57, Roman Kagan <rkagan@amazon.de> wrote:
> >>>> What scares me, though, is that I've got a message from the test robot
> >>>> that this commit drammatically affected hackbench results, see the quote
> >>>> below.  I expected the commit not to affect any benchmarks.
> >>>>
> >>>> Any idea what could have caused this change?
> >>>
> >>> Hmm, It's most probably because se->exec_start is reset after a
> >>> migration and the condition becomes true for newly migrated task
> >>> whereas its vruntime should be after min_vruntime.
> >>>
> >>> We have missed this condition
> >>
> >> Makes sense to me.
> >>
> >> But what would then be the reliable way to detect a sched_entity which
> >> has slept for long and risks overflowing in .vruntime comparison?
> >
> > For now I don't have a better idea than adding the same check in
> > migrate_task_rq_fair()
>
> Hi, Vincent，
> I fixed this condition as you said, and the test results are as follows.
>
> testcase: hackbench -g 44 -f 20 --process --pipe -l 60000 -s 100
> version1: v6.2
> version2: v6.2 + commit 829c1651e9c4
> version3: v6.2 + commit 829c1651e9c4 + this patch
>
> -------------------------------------------------
>         version1        version2        version3
> test1   81.0            118.1           82.1
> test2   82.1            116.9           80.3
> test3   83.2            103.9           83.3
> avg(s)  82.1            113.0           81.9
>
> -------------------------------------------------
> After deal with the task migration case, the hackbench result has restored.
>
> The patch as follow, how does this look?
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index ff4dbbae3b10..3a88d20fd29e 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -4648,6 +4648,26 @@ static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
>  #endif
>  }
>
> +static inline u64 sched_sleeper_credit(struct sched_entity *se)
> +{
> +
> +       unsigned long thresh;
> +
> +       if (se_is_idle(se))
> +               thresh = sysctl_sched_min_granularity;
> +       else
> +               thresh = sysctl_sched_latency;
> +
> +       /*
> +        * Halve their sleep time's effect, to allow
> +        * for a gentler effect of sleepers:
> +        */
> +       if (sched_feat(GENTLE_FAIR_SLEEPERS))
> +               thresh >>= 1;
> +
> +       return thresh;
> +}
> +
>  static void
>  place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
>  {
> @@ -4664,23 +4684,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
>                 vruntime += sched_vslice(cfs_rq, se);
>
>         /* sleeps up to a single latency don't count. */
> -       if (!initial) {
> -               unsigned long thresh;
> -
> -               if (se_is_idle(se))
> -                       thresh = sysctl_sched_min_granularity;
> -               else
> -                       thresh = sysctl_sched_latency;
> -
> -               /*
> -                * Halve their sleep time's effect, to allow
> -                * for a gentler effect of sleepers:
> -                */
> -               if (sched_feat(GENTLE_FAIR_SLEEPERS))
> -                       thresh >>= 1;
> -
> -               vruntime -= thresh;
> -       }
> +       if (!initial)
> +               vruntime -= sched_sleeper_credit(se);
>
>         /*
>          * Pull vruntime of the entity being placed to the base level of
> @@ -4690,7 +4695,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
>          * inversed due to s64 overflow.
>          */
>         sleep_time = rq_clock_task(rq_of(cfs_rq)) - se->exec_start;
> -       if ((s64)sleep_time > 60LL * NSEC_PER_SEC)
> +       if (se->exec_start != 0 && (s64)sleep_time > 60LL * NSEC_PER_SEC)
>                 se->vruntime = vruntime;
>         else
>                 se->vruntime = max_vruntime(se->vruntime, vruntime);
> @@ -7634,8 +7639,12 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
>          */
>         if (READ_ONCE(p->__state) == TASK_WAKING) {
>                 struct cfs_rq *cfs_rq = cfs_rq_of(se);
> +               u64 sleep_time = rq_clock_task(rq_of(cfs_rq)) - se->exec_start;
>
> -               se->vruntime -= u64_u32_load(cfs_rq->min_vruntime);
> +               if ((s64)sleep_time > 60LL * NSEC_PER_SEC)

You also need to test (se->exec_start !=0) here because the task might
migrate another time before being scheduled. You should create a
helper function like below and use it in both place

static inline bool entity_long_sleep(se)
{
        struct cfs_rq *cfs_rq;
        u64 sleep_time;

        if (se->exec_start == 0)
                return false;

        cfs_rq = cfs_rq_of(se);
        sleep_time = rq_clock_task(rq_of(cfs_rq)) - se->exec_start;
        if ((s64)sleep_time > 60LL * NSEC_PER_SEC)
                return true;

        return false;
}


> +                       se->vruntime = -sched_sleeper_credit(se);
> +               else
> +                       se->vruntime -= u64_u32_load(cfs_rq->min_vruntime);
>         }
>
>         if (!task_on_rq_migrating(p)) {
>
>
>
> Thanks.
> Zhang Qiao.
>
> >
> >>
> >> Thanks,
> >> Roman.
> >>
> >>
> >>
> >> Amazon Development Center Germany GmbH
> >> Krausenstr. 38
> >> 10117 Berlin
> >> Geschaeftsfuehrung: Christian Schlaeger, Jonathan Weiss
> >> Eingetragen am Amtsgericht Charlottenburg unter HRB 149173 B
> >> Sitz: Berlin
> >> Ust-ID: DE 289 237 879
> >>
> >>
> >>
> > .
> >