From: Peter Zijlstra <peterz@infradead.org>
To: Patrick Bellasi <patrick.bellasi@arm.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>,
Ingo Molnar <mingo@kernel.org>,
linux-kernel <linux-kernel@vger.kernel.org>,
"Rafael J. Wysocki" <rjw@rjwysocki.net>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Morten Rasmussen <Morten.Rasmussen@arm.com>,
Paul Turner <pjt@google.com>, Ben Segall <bsegall@google.com>,
Thara Gopinath <thara.gopinath@linaro.org>,
pkondeti@codeaurora.org, Quentin Perret <quentin.perret@arm.com>,
Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Subject: Re: [PATCH v7 2/2] sched/fair: update scale invariance of PELT
Date: Tue, 29 Jan 2019 20:42:13 +0100 [thread overview]
Message-ID: <20190129194213.GA2979@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20190124140432.2kiprlxzw2cpf35f@e110439-lin>
On Thu, Jan 24, 2019 at 02:04:32PM +0000, Patrick Bellasi wrote:
> > So if I'm not mistaken we then have 3 cases:
> >
> > 1) runnable == util <= capacity
> >
> > no contention, idle
> >
> > 2) runnable == util > capacity
> >
> > no contention, no idle
> >
> > 3) runnable > util
> >
> > contention, no idle
> >
> > For 1) we can use: 'util'
> > For 2) we can use: 'capacity'
> > For 3) we can use: 'util * capacity >> 10'
> >
> > (note that 2 is a special case of 3 when u=1)
> >
> > This should work right?
>
> I think there is a case, similar to 2, in which the new 'util' could
> potentially be used. That's the case for example of a 20% (estimated)
> utilization task running alone on a 15% capacity CPU, for a single
> activation. In that case such a task will complete and be dequeued
> with:
>
> runnable == util > capacity
>
> The problem is that we need to be sure there was not contention... and
> that seems to be difficult to detect.
When there is contention runnable and util should diverge. Given this is
all discrete stuff, there's a few funnies, but who cares about those :-)
> > Now, instead of doing complicated things like that, you instead figure
> > that when there's no idle there's also no dequeue happening and we can
> > simply short-cut by skipping the entire thing, forgetting everything
> > about 2,3.
> >
> > Did I get that right?
>
> More or less... just saying that 1 is the only easy to detect scenario
> in which we are granted the utilization represents an actual bandwidth
> request and thus the only safe values to sample for estimated
> utilization. For the other cases, since anyway:
>
> util_est := max(max(ewma, last_util), util_avg)
>
> util_est will just keep representing a safe and actually measured
> lower-bound for the expected utilization of a task, without
> side-affecting the EWMA which has a "slow" update dynamic.
Right, so maybe we should expound the comment here a bit; but otherwise
I'm inclined to merge that v9 Vincent posted.
prev parent reply other threads:[~2019-01-29 19:42 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-20 10:55 [PATCH v7 0/2] sched/fair: update scale invariance of PELT Vincent Guittot
2018-11-20 10:55 ` [PATCH v7 1/2] sched/fair: move rq_of helper function Vincent Guittot
2018-11-20 10:55 ` [PATCH v7 2/2] sched/fair: update scale invariance of PELT Vincent Guittot
2018-11-28 9:54 ` Vincent Guittot
2018-11-28 10:02 ` Peter Zijlstra
2018-11-28 11:53 ` Patrick Bellasi
2018-11-28 13:33 ` Vincent Guittot
2018-11-28 13:35 ` Vincent Guittot
2018-11-28 14:40 ` Patrick Bellasi
2018-11-28 14:55 ` Vincent Guittot
2018-11-28 15:21 ` Patrick Bellasi
2018-11-28 15:42 ` Vincent Guittot
2018-11-28 16:35 ` Patrick Bellasi
2018-11-29 10:43 ` Vincent Guittot
2018-11-29 15:00 ` Patrick Bellasi
2018-11-29 16:19 ` Vincent Guittot
2019-01-10 15:30 ` Patrick Bellasi
2019-01-11 14:29 ` Vincent Guittot
2018-11-29 12:53 ` Peter Zijlstra
2018-11-29 15:13 ` Patrick Bellasi
2019-01-24 9:07 ` Peter Zijlstra
2019-01-24 14:04 ` Patrick Bellasi
2019-01-29 19:42 ` Peter Zijlstra [this message]
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=20190129194213.GA2979@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=Morten.Rasmussen@arm.com \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=patrick.bellasi@arm.com \
--cc=pjt@google.com \
--cc=pkondeti@codeaurora.org \
--cc=quentin.perret@arm.com \
--cc=rjw@rjwysocki.net \
--cc=srinivas.pandruvada@linux.intel.com \
--cc=thara.gopinath@linaro.org \
--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 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).