Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1743124

Re: [PATCH v2 2/2] cpufreq: schedutil: consolidate capacity margin calculation

From Leo Yan <leo.yan@linaro.org>
Newsgroups linux.kernel
Subject Re: [PATCH v2 2/2] cpufreq: schedutil: consolidate capacity margin calculation
Date 2017-10-02 13:20 +0200
Message-ID <uw6Vs-6CK-11@gated-at.bofh.it> (permalink)
References <uvWW6-sI-7@gated-at.bofh.it> <uvWW6-sI-5@gated-at.bofh.it> <uvXp7-RI-1@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


Hi Joel,

On Sun, Oct 01, 2017 at 06:02:24PM -0700, Joel Fernandes wrote:
> Hi Leo,
> 
> On Sun, Oct 1, 2017 at 5:30 PM, Leo Yan <leo.yan@linaro.org> wrote:
> > Scheduler CFS class has variable 'capacity_margin' to calculate the
> 
> s/calculate/represent/ ?
> 
> > capacity margin, and schedutil governor also needs to compensate the
> > same margin for frequency tipping point. Below are formulas used in
> > CFS class and schedutil governor separately:
> >
> > CFS:       U` = U * capacity_margin / 1024 = U * 1.25
> 
> You should mention in the commit message, at the moment
> capacity_margin is 1280 which makes U` = 1.25.
> 
> > Schedutil: U` = U + U >> 2 = U + U * 0.25  = U * 1.25
> >
> > This patch consolidates the capacity margin calculation so let
> > schedutil to use same formula with CFS class. As result this can avoid
> 
> As a result.
> 
> > the mismatch issue between schedutil and CFS class after change
> > 'capacity_margin' to other values.
> 
> This didn't make sense to me. May be you meant:
> 
> This patch consolidates the usage of the capacity margin value and
> lets schedutil use the same formula as the CFS class. Thus we can
> avoid the mismatch between schedutil and CFS class if
> 'capacity_margin' is changed to other values in the future.

Yeah, thanks for the suggestion. And accept all upper comment.
Will refine for new patch.

Thanks,
Leo Yan

> > Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
> > Cc: Morten Rasmussen <morten.rasmussen@arm.com>
> > Cc: Chris Redpath <Chris.Redpath@arm.com>
> > Cc: Joel Fernandes <joelaf@google.com>
> > Cc: Vincent Guittot <vincent.guittot@linaro.org>
> > Cc: Patrick Bellasi <patrick.bellasi@arm.com>
> > Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
> > Signed-off-by: Leo Yan <leo.yan@linaro.org>
> > ---
> >  kernel/sched/cpufreq_schedutil.c | 6 ++++--
> >  kernel/sched/sched.h             | 1 +
> >  2 files changed, 5 insertions(+), 2 deletions(-)
> >
> > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > index 9209d83..13cc243 100644
> > --- a/kernel/sched/cpufreq_schedutil.c
> > +++ b/kernel/sched/cpufreq_schedutil.c
> > @@ -155,7 +155,8 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
> >   *
> >   * next_freq = C * curr_freq * util_raw / max
> >   *
> > - * Take C = 1.25 for the frequency tipping point at (util / max) = 0.8.
> > + * Take C = capacity_margin / 1024 = 1.25, so it's for the frequency tipping
> > + * point at (util / max) = 0.8.
> 
> The above comment assumes capacity_margin is 1280. If for any reason
> the capacity_margin is changed to something else, then the comment
> wont make sense anymore.
> 
> thanks,
> 
> - Joel

Back to linux.kernel | Previous | NextPrevious in thread | Find similar | Unroll thread


Thread

[PATCH v2 2/2] cpufreq: schedutil: consolidate capacity margin calculation Leo Yan <leo.yan@linaro.org> - 2017-10-02 02:40 +0200
  Re: [PATCH v2 2/2] cpufreq: schedutil: consolidate capacity margin calculation Joel Fernandes <joelaf@google.com> - 2017-10-02 03:10 +0200
    Re: [PATCH v2 2/2] cpufreq: schedutil: consolidate capacity margin  calculation Leo Yan <leo.yan@linaro.org> - 2017-10-02 13:20 +0200

csiph-web