From: Zhang Qiao <zhangqiao22@huawei.com>
To: Dietmar Eggemann <dietmar.eggemann@arm.com>,
Vincent Guittot <vincent.guittot@linaro.org>
Cc: <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>, <rkagan@amazon.de>
Subject: Re: [PATCH v2] sched/fair: sanitize vruntime of entity being migrated
Date: Thu, 9 Mar 2023 17:30:06 +0800 [thread overview]
Message-ID: <6a45bb5c-d851-d48d-44b1-cf533293a6d8@huawei.com> (raw)
In-Reply-To: <5250a0fc-3470-b313-0810-5d7a68c7cf50@arm.com>
在 2023/3/9 17:09, Dietmar Eggemann 写道:
> On 09/03/2023 09:37, Zhang Qiao wrote:
>>
>> 在 2023/3/8 20:55, Vincent Guittot 写道:
>>> Le mercredi 08 mars 2023 à 09:01:05 (+0100), Vincent Guittot a écrit :
>>>> On Tue, 7 Mar 2023 at 14:41, Zhang Qiao <zhangqiao22@huawei.com> wrote:
>
> [...]
>
>>>>> 在 2023/3/7 18:26, Vincent Guittot 写道:
>>>>>> On Mon, 6 Mar 2023 at 14:53, Vincent Guittot <vincent.guittot@linaro.org> wrote:
>>>>>>>
>>>>>>> On Mon, 6 Mar 2023 at 13:57, Zhang Qiao <zhangqiao22@huawei.com> wrote:
>
> [...]
>
>>> +static inline bool migrate_long_sleeper(struct sched_entity *se)
>>> +{
>>> + struct cfs_rq *cfs_rq;
>>> + u64 sleep_time;
>>> +
>>> + if (se->exec_start == 0)
>>
>> How about use `se->avg.last_update_time == 0` here?
>
> IMHO, both checks are not needed here since we're still dealing with the
> originating CPU of the migration. Both of them are set to 0 only at the
> end of migrate_task_rq_fair().
Yes, if place_entity() don't call migrate_long_sleeper(), the check can remove.
>
>
>>> + return false;
>>> +
>>> + cfs_rq = cfs_rq_of(se);
>>> + /*
>>> + * If the entity slept for a long time, don't even try to normalize its
>>> + * vruntime with the base as it may be too far off and might generate
>>> + * wrong decision because of s64 overflow.
>>> + * We estimate its sleep duration with the last update of se's pelt.
>>> + * The last update happened before sleeping. The cfs' pelt is not
>>> + * always updated when cfs is idle but this is not a problem because
>>> + * its min_vruntime is not updated too, so the situation can't get
>>> + * worse.
>>> + */
>>> + sleep_time = cfs_rq_last_update_time(cfs_rq) - se->avg.last_update_time;
>
> Looks like this doesn't work for asymmetric CPU capacity systems since
> we specifically do a sync_entity_load_avg() in select_task_rq_fair()
> (find_energy_efficient_cpu() for EAS and select_idle_sibling() for CAS)
> to sync cfs_rq and se (including their last_update_time).
>
> [...]
>
> .
>
next prev parent reply other threads:[~2023-03-09 9:30 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-06 13:24 [PATCH v2] sched/fair: sanitize vruntime of entity being migrated 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 [this message]
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
2023-03-17 16:08 Vincent Guittot
2023-03-18 7:45 ` Zhang Qiao
2023-03-20 12:29 ` Dietmar Eggemann
2023-03-20 13:26 ` Vincent Guittot
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
2023-03-24 4:05 ` Chen Yu
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=6a45bb5c-d851-d48d-44b1-cf533293a6d8@huawei.com \
--to=zhangqiao22@huawei.com \
--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=rkagan@amazon.de \
--cc=rostedt@goodmis.org \
--cc=vincent.guittot@linaro.org \
--cc=vschneid@redhat.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).