From: Quentin Perret <qperret@google.com>
To: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: vincent.donnefort@arm.com, peterz@infradead.org,
mingo@redhat.com, vincent.guittot@linaro.org,
linux-kernel@vger.kernel.org, patrick.bellasi@matbug.net,
valentin.schneider@arm.com
Subject: Re: [PATCH v2 1/2] sched/fair: Fix task utilization accountability in compute_energy()
Date: Thu, 25 Feb 2021 11:58:27 +0000 [thread overview]
Message-ID: <YDeQ47Kfh8s/B0cn@google.com> (raw)
In-Reply-To: <f2f5cf8e-3a0b-7192-5293-bad576e7066b@arm.com>
On Thursday 25 Feb 2021 at 12:45:06 (+0100), Dietmar Eggemann wrote:
> I.e. since _task_util_est is always >= task_util during wakeup, cpu_util
> must be > cpu_util_est (by more than _task_util_est - task_util).
>
> I can see it for a CPU whose cpu_util has a fair amount of contributions
> from blocked tasks which cpu_util_est wouldn't have.
Yes I think this can manifest itself if there are tasks changing
behaviour, or on an idle CPU as its ue.enqueued will be 0 and we'll be
left with blocked util only.
Thanks,
Quentin
next prev parent reply other threads:[~2021-02-25 11:59 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-25 8:36 [PATCH v2 0/2] Fix task utilization accountability for EAS vincent.donnefort
2021-02-25 8:36 ` [PATCH v2 1/2] sched/fair: Fix task utilization accountability in compute_energy() vincent.donnefort
2021-02-25 8:52 ` Quentin Perret
2021-02-25 11:45 ` Dietmar Eggemann
2021-02-25 11:58 ` Quentin Perret [this message]
2021-02-25 16:23 ` Vincent Donnefort
2021-03-02 9:01 ` [tip: sched/core] " tip-bot2 for Vincent Donnefort
2021-03-03 9:49 ` tip-bot2 for Vincent Donnefort
2021-03-06 11:42 ` tip-bot2 for Vincent Donnefort
2021-02-25 8:36 ` [PATCH v2 2/2] sched/fair: use lsub_positive in cpu_util_next() vincent.donnefort
2021-02-25 8:53 ` Quentin Perret
2021-02-25 11:46 ` Dietmar Eggemann
2021-03-02 9:01 ` [tip: sched/core] " tip-bot2 for Vincent Donnefort
2021-03-03 9:49 ` tip-bot2 for Vincent Donnefort
2021-03-06 11:42 ` tip-bot2 for Vincent Donnefort
2021-02-25 17:29 ` [PATCH v2 0/2] Fix task utilization accountability for EAS Peter Zijlstra
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=YDeQ47Kfh8s/B0cn@google.com \
--to=qperret@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=patrick.bellasi@matbug.net \
--cc=peterz@infradead.org \
--cc=valentin.schneider@arm.com \
--cc=vincent.donnefort@arm.com \
--cc=vincent.guittot@linaro.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.