From: Peter Zijlstra <peterz@infradead.org>
To: Patrick Bellasi <patrick.bellasi@arm.com>
Cc: Juri Lelli <Juri.Lelli@arm.com>,
Viresh Kumar <viresh.kumar@linaro.org>,
Rafael Wysocki <rjw@rjwysocki.net>,
Ingo Molnar <mingo@redhat.com>,
linaro-kernel@lists.linaro.org, linux-pm@vger.kernel.org,
linux-kernel@vger.kernel.org,
Vincent Guittot <vincent.guittot@linaro.org>,
Robin Randhawa <robin.randhawa@arm.com>,
Steve Muckle <smuckle.linux@gmail.com>,
tkjos@google.com, Morten Rasmussen <morten.rasmussen@arm.com>
Subject: Re: [PATCH] cpufreq: schedutil: add up/down frequency transition rate limits
Date: Mon, 21 Nov 2016 16:34:06 +0100 [thread overview]
Message-ID: <20161121153406.GA3174@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <20161121152606.GI3092@twins.programming.kicks-ass.net>
On Mon, Nov 21, 2016 at 04:26:06PM +0100, Peter Zijlstra wrote:
> > For example, a task running 30 [ms] every 100 [ms] is a ~300 util_avg
> > task. With PELT, we get a signal which range between [120,550] with an
> > average of ~300 which is instead completely ignored. By capping the
> > decay we will get:
> >
> > decay_cap [ms] range average
> > 0 120:550 300
> > 64 140:560 310
> > 32 320:660 430
> >
> > which means that still the raw PELT signal is wobbling and never
> > provides a consistent response to drive decisions.
> >
> > Thus, a "predictor" should be something which sample information from
> > PELT to provide a more consistent view, a sort of of low-pass filter
> > on top of the "dynamic metric" which is PELT.
Note that a simple low-pass IIR filter will only shrink the wobble, not
take it out entirely. Or rather, if you make it so strong as to take the
entire wobble out, it'll likely react like molasses.
next prev parent reply other threads:[~2016-11-21 15:34 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-11-17 5:18 [PATCH] cpufreq: schedutil: add up/down frequency transition rate limits Viresh Kumar
2016-11-21 10:08 ` Viresh Kumar
2016-11-21 10:19 ` Peter Zijlstra
2016-11-21 10:48 ` Viresh Kumar
2016-11-21 11:12 ` Peter Zijlstra
2016-11-21 11:30 ` Viresh Kumar
2016-11-21 11:48 ` Peter Zijlstra
2016-11-21 12:14 ` Juri Lelli
2016-11-21 12:26 ` Peter Zijlstra
2016-11-21 13:53 ` Juri Lelli
2016-11-21 14:17 ` Peter Zijlstra
2016-11-21 14:37 ` Juri Lelli
2016-11-21 14:43 ` Peter Zijlstra
2016-11-21 14:59 ` Juri Lelli
2016-11-22 9:27 ` Vincent Guittot
2016-11-22 11:03 ` Patrick Bellasi
2016-11-21 14:59 ` Patrick Bellasi
2016-11-21 15:26 ` Peter Zijlstra
2016-11-21 15:34 ` Peter Zijlstra [this message]
2016-11-21 16:24 ` Patrick Bellasi
2016-11-21 16:46 ` Peter Zijlstra
2016-11-21 20:53 ` Rafael J. Wysocki
2016-12-29 3:24 ` Wanpeng Li
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=20161121153406.GA3174@twins.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=Juri.Lelli@arm.com \
--cc=linaro-kernel@lists.linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=morten.rasmussen@arm.com \
--cc=patrick.bellasi@arm.com \
--cc=rjw@rjwysocki.net \
--cc=robin.randhawa@arm.com \
--cc=smuckle.linux@gmail.com \
--cc=tkjos@google.com \
--cc=vincent.guittot@linaro.org \
--cc=viresh.kumar@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.