From: Vincent Guittot <vincent.guittot@linaro.org>
To: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Zhang Qiao <zhangqiao22@huawei.com>,
linux-kernel@vger.kernel.org, mingo@redhat.com,
peterz@infradead.org, juri.lelli@redhat.com, rostedt@goodmis.org,
bsegall@google.com, mgorman@suse.de, bristot@redhat.com,
vschneid@redhat.com
Subject: Re: [PATCH v2] sched/fair: sanitize vruntime of entity being migrated
Date: Mon, 20 Mar 2023 14:26:35 +0100 [thread overview]
Message-ID: <CAKfTPtADr6ds6kmfE73J-33fT6mkziGZ4=x45rpwmGhv-u1f2A@mail.gmail.com> (raw)
In-Reply-To: <df2cccda-1550-b06b-aa74-e0f054e9fb9d@arm.com>
On Mon, 20 Mar 2023 at 13:29, Dietmar Eggemann <dietmar.eggemann@arm.com> wrote:
>
> On 18/03/2023 08:45, Zhang Qiao wrote:
> >
> >
> > 在 2023/3/18 0:08, Vincent Guittot 写道:
> >> Commit 829c1651e9c4 ("sched/fair: sanitize vruntime of entity being placed")
> >> fixes an overflowing bug, but ignore a case that se->exec_start is reset
> >> after a migration.
> >>
> >> For fixing this case, we delay the reset of se->exec_start after
> >> placing the entity which se->exec_start to detect long sleeping task.
> >>
> >> In order to take into account a possible divergence between the clock_task
> >> of 2 rqs, we increase the threshold to around 104 days.
> >>
> >>
> >> Fixes: 829c1651e9c4 ("sched/fair: sanitize vruntime of entity being placed")
> >> Signed-off-by: Zhang Qiao <zhangqiao22@huawei.com>
> >> Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
> >> ---
> >>
> >> My last proposal was not yet correct as the exec_start was not always
> >> reset after migrating a task. I finally found this solution which keeps
> >> the long sleep detection to one place as well as the reset of se->exec_start.
> >>
> >
> > Tested-by: Zhang Qiao <zhangqiao22@huawei.com>
> >
> > I have retested it with this version, and the result is fine.
> >
> > -------
> >
> > Performance counter stats for 'hackbench -g 44 -f 20 --process --pipe -l 60000 -s 100' (10 runs):
> >
> > 80.10 +- 1.22 seconds time elapsed ( +- 1.53% )
>
> [...]
>
> >> @@ -8701,7 +8734,7 @@ static void attach_task(struct rq *rq, struct task_struct *p)
> >> lockdep_assert_rq_held(rq);
> >>
> >> WARN_ON_ONCE(task_rq(p) != rq);
> >> - activate_task(rq, p, ENQUEUE_NOCLOCK);
> >> + activate_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_MIGRATED);
> >> check_preempt_curr(rq, p, 0);
>
> Why not:
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index b9bc1ab67aaa..96dd3a62e683 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -7674,7 +7674,10 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
> se->vruntime -= u64_u32_load(cfs_rq->min_vruntime);
> }
>
> - if (!task_on_rq_migrating(p)) {
> + if (task_on_rq_migrating(p)) {
> + /* We have migrated, no longer consider this task hot */
> + se->exec_start = 0;
mainly to keep the clear of se->exec_start = 0 in one place to ease
the maintenance
> + } else {
> remove_entity_load_avg(se);
>
> /*
> @@ -8726,7 +8729,7 @@ static void attach_task(struct rq *rq, struct task_struct *p)
> lockdep_assert_rq_held(rq);
>
> WARN_ON_ONCE(task_rq(p) != rq);
> - activate_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_MIGRATED);
> + activate_task(rq, p, ENQUEUE_NOCLOCK);
> check_preempt_curr(rq, p, 0);
> }
>
>
> entity_is_long_sleeper() will bail early for these rq-migrating tasks
> for which a long-sleep test would make little sense anyway.
>
> Plus move_queued_task() (e.g. from sched_exex()) would be covered as well.
next prev parent reply other threads:[~2023-03-20 13:27 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-17 16:08 [PATCH v2] sched/fair: sanitize vruntime of entity being migrated Vincent Guittot
2023-03-18 7:45 ` Zhang Qiao
2023-03-20 12:29 ` Dietmar Eggemann
2023-03-20 13:26 ` Vincent Guittot [this message]
2023-03-21 10:02 ` Peter Zijlstra
2023-03-21 10:29 ` Dietmar Eggemann
2023-03-21 10:49 ` Peter Zijlstra
2023-03-21 11:12 ` Vincent Guittot
2023-03-21 11:13 ` Dietmar Eggemann
2023-03-21 12:26 ` Peter Zijlstra
2023-03-21 12:28 ` Peter Zijlstra
2023-03-21 12:38 ` Vincent Guittot
2023-03-22 9:07 ` [tip: sched/urgent] sched/fair: Sanitize " tip-bot2 for Vincent Guittot
2023-03-24 4:05 ` [PATCH v2] sched/fair: sanitize " Chen Yu
-- strict thread matches above, loose matches on Subject: below --
2023-03-06 13:24 Zhang Qiao
2023-03-06 13:53 ` Vincent Guittot
2023-03-07 10:26 ` Vincent Guittot
2023-03-07 11:05 ` Zhang Qiao
2023-03-07 13:41 ` Zhang Qiao
2023-03-08 8:01 ` Vincent Guittot
2023-03-08 12:55 ` Vincent Guittot
2023-03-09 8:37 ` Zhang Qiao
2023-03-09 9:09 ` Dietmar Eggemann
2023-03-09 9:30 ` Zhang Qiao
2023-03-09 10:48 ` Vincent Guittot
2023-03-09 14:23 ` Zhang Qiao
2023-03-07 2:16 ` kernel test robot
2023-03-07 12:45 ` Dietmar Eggemann
2023-03-07 14:06 ` Zhang Qiao
2023-03-09 9:43 ` Zhang Qiao
2023-03-08 14:33 ` Chen Yu
2023-03-09 13:05 ` Peter Zijlstra
2023-03-09 13:34 ` Vincent Guittot
2023-03-09 14:28 ` Peter Zijlstra
2023-03-09 14:36 ` Peter Zijlstra
2023-03-09 15:14 ` Vincent Guittot
2023-03-10 14:29 ` Vincent Guittot
2023-03-11 9:57 ` Zhang Qiao
2023-03-13 14:23 ` Vincent Guittot
2023-03-14 11:03 ` Zhang Qiao
2023-03-14 13:26 ` Vincent Guittot
2023-03-14 13:38 ` Zhang Qiao
2023-03-14 13:39 ` Vincent Guittot
2023-03-14 15:32 ` Vincent Guittot
2023-03-15 9:16 ` Zhang Qiao
2023-03-15 15:30 ` Vincent Guittot
2023-03-13 9:06 ` Dietmar Eggemann
2023-03-13 18:17 ` Dietmar Eggemann
2023-03-14 7:41 ` Vincent Guittot
2023-03-14 12:07 ` Peter Zijlstra
2023-03-14 13:24 ` Vincent Guittot
2023-03-14 17:16 ` Peter Zijlstra
2023-03-15 7:18 ` Vincent Guittot
2023-03-15 8:42 ` Vincent Guittot
2023-03-15 10:15 ` Dietmar Eggemann
2023-03-15 10:21 ` Vincent Guittot
2023-03-15 13:35 ` Dietmar Eggemann
2023-03-15 15:32 ` Vincent Guittot
2023-03-14 13:29 ` Dietmar Eggemann
2023-03-14 13:37 ` Dietmar Eggemann
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CAKfTPtADr6ds6kmfE73J-33fT6mkziGZ4=x45rpwmGhv-u1f2A@mail.gmail.com' \
--to=vincent.guittot@linaro.org \
--cc=bristot@redhat.com \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=vschneid@redhat.com \
--cc=zhangqiao22@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).