From: Ingo Molnar <mingo@kernel.org>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Thara Gopinath <thara.gopinath@linaro.org>,
mingo@redhat.com, rui.zhang@intel.com,
linux-kernel@vger.kernel.org, amit.kachhap@gmail.com,
viresh.kumar@linaro.org, javi.merino@kernel.org,
edubezval@gmail.com, daniel.lezcano@linaro.org,
vincent.guittot@linaro.org, nicolas.dechesne@linaro.org,
bjorn.andersson@linaro.org, dietmar.eggemann@arm.com,
Quentin Perret <quentin.perret@arm.com>,
"Rafael J. Wysocki" <rjw@rjwysocki.net>
Subject: Re: [PATCH V2 0/3] Introduce Thermal Pressure
Date: Thu, 25 Apr 2019 19:44:25 +0200 [thread overview]
Message-ID: <20190425174425.GA121124@gmail.com> (raw)
In-Reply-To: <20190425173333.GA4081@gmail.com>
* Ingo Molnar <mingo@kernel.org> wrote:
>
> * Peter Zijlstra <peterz@infradead.org> wrote:
>
> > On Wed, Apr 17, 2019 at 08:29:32PM +0200, Ingo Molnar wrote:
> > > Assuming PeterZ & Rafael & Quentin doesn't hate the whole thermal load
> > > tracking approach.
> >
> > I seem to remember competing proposals, and have forgotten everything
> > about them; the cover letter also didn't have references to them or
> > mention them in any way.
> >
> > As to the averaging and period, I personally prefer a PELT signal with
> > the windows lined up, if that really is too short a window, then a PELT
> > like signal with a natural multiple of the PELT period would make sense,
> > such that the windows still line up nicely.
> >
> > Mixing different averaging methods and non-aligned windows just makes me
> > uncomfortable.
>
> Yeah, so the problem with PELT is that while it nicely approximates
> variable-period decay calculations with plain additions, shifts and table
> lookups (i.e. accelerates pow()), AFAICS the most important decay
> parameter is fixed: the speed of decay, the dampening factor, which is
> fixed at 32:
>
> Documentation/scheduler/sched-pelt.c
>
> #define HALFLIFE 32
>
> Right?
>
> Thara's numbers suggest that there's high sensitivity to the speed of
> decay. By using PELT we'd be using whatever averaging speed there is
> within PELT.
>
> Now we could make that parametric of course, but that would both
> complicate the PELT lookup code (one more dimension) and would negatively
> affect code generation in a number of places.
I missed the other solution, which is what you suggested: by
increasing/reducing the PELT window size we can effectively shift decay
speed and use just a single lookup table.
I.e. instead of the fixed period size of 1024 in accumulate_sum(), use
decay_load() directly but use a different (longer) window size from 1024
usecs to calculate 'periods', and make it a multiple of 1024.
This might just work out right: with a half-life of 32 the fastest decay
speed should be around ~20 msecs (?) - and Thara's numbers so far suggest
that the sweet spot averaging is significantly longer, at a couple of
hundred millisecs.
Thanks,
Ingo
next prev parent reply other threads:[~2019-04-25 17:44 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-04-16 19:38 [PATCH V2 0/3] Introduce Thermal Pressure Thara Gopinath
2019-04-16 19:38 ` [PATCH V2 1/3] Calculate " Thara Gopinath
2019-04-18 10:14 ` Quentin Perret
2019-04-24 4:13 ` Thara Gopinath
2019-04-24 16:38 ` Peter Zijlstra
2019-04-24 16:45 ` Peter Zijlstra
2019-04-25 10:57 ` Quentin Perret
2019-04-25 12:45 ` Vincent Guittot
2019-04-25 12:47 ` Quentin Perret
2019-04-26 14:17 ` Thara Gopinath
2019-05-08 12:41 ` Quentin Perret
2019-04-16 19:38 ` [PATCH V2 2/3] sched/fair: update cpu_capcity to reflect thermal pressure Thara Gopinath
2019-04-16 19:38 ` [PATCH V3 3/3] thermal/cpu-cooling: Update thermal pressure in case of a maximum frequency capping Thara Gopinath
2019-04-18 9:48 ` Quentin Perret
2019-04-23 22:38 ` Thara Gopinath
2019-04-24 15:56 ` Ionela Voinescu
2019-04-26 10:24 ` Thara Gopinath
2019-04-25 10:45 ` Quentin Perret
2019-04-25 12:04 ` Vincent Guittot
2019-04-25 12:50 ` Quentin Perret
2019-04-26 13:47 ` Thara Gopinath
2019-04-24 16:47 ` Peter Zijlstra
2019-04-17 5:36 ` [PATCH V2 0/3] Introduce Thermal Pressure Ingo Molnar
2019-04-17 5:55 ` Ingo Molnar
2019-04-17 17:28 ` Thara Gopinath
2019-04-17 17:18 ` Thara Gopinath
2019-04-17 18:29 ` Ingo Molnar
2019-04-18 0:07 ` Thara Gopinath
2019-04-18 9:22 ` Quentin Perret
2019-04-24 16:34 ` Peter Zijlstra
2019-04-25 17:33 ` Ingo Molnar
2019-04-25 17:44 ` Ingo Molnar [this message]
2019-04-26 7:08 ` Vincent Guittot
2019-04-26 8:35 ` Ingo Molnar
2019-04-24 15:57 ` Ionela Voinescu
2019-04-26 11:50 ` Thara Gopinath
2019-04-26 14:46 ` Ionela Voinescu
2019-04-29 13:29 ` Ionela Voinescu
2019-04-30 14:39 ` Ionela Voinescu
2019-04-30 16:10 ` Thara Gopinath
2019-05-02 10:44 ` Ionela Voinescu
2019-04-30 15:57 ` Thara Gopinath
2019-04-30 16:02 ` Thara Gopinath
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=20190425174425.GA121124@gmail.com \
--to=mingo@kernel.org \
--cc=amit.kachhap@gmail.com \
--cc=bjorn.andersson@linaro.org \
--cc=daniel.lezcano@linaro.org \
--cc=dietmar.eggemann@arm.com \
--cc=edubezval@gmail.com \
--cc=javi.merino@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=nicolas.dechesne@linaro.org \
--cc=peterz@infradead.org \
--cc=quentin.perret@arm.com \
--cc=rjw@rjwysocki.net \
--cc=rui.zhang@intel.com \
--cc=thara.gopinath@linaro.org \
--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 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).