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

Groups > linux.kernel > #1697763

Re: [Eas-dev] [PATCH V4 0/3] sched: cpufreq: Allow remote callbacks

Show all headers | View raw

On 26-07-17, 23:23, Joel Fernandes (Google) wrote:
> Ok, but the "heavy" in init_entity_runnable_average means for load,
> not the util_avg. The util_avg is what's used for frequency scaling
> IIUC and is set to 0 in that function no?

That's because the task isn't enqueued yet and so don't have any
utilization. The last line of that routine is a comment which says:

/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */

But once the task is enqueued, this load_avg will get considered for
sure :)

> > The application was written by Steve (all credit goes to him) before
> > he left Linaro, but I did test it with ftrace. What I saw with ftrace
> > was that the freq isn't reevaluated for almost an entire tick many
> > times because we enqueued the task remotely. And that changes with
> > this series.
> >
> >> > The reason being that this patchset only targets a corner case, where
> >> > following are required to be true to improve performance and that
> >> > doesn't happen too often with these tests:
> >> >
> >> > - Task is migrated to another CPU.
> >> > - The task has maximum demand initially, and should take the CPU to
> >>
> >> Just to make the cover-letter more clear and also confirming with you
> >> I understand the above usecase, maybe in the future this can reworded
> >> from "initially" to "before the migration" and "take the CPU" to "take
> >> the target CPU of the migration" ?
> >
> > I can reword it a bit, but the test case wasn't really migrating
> > anything and was looking only at the initial loads.
> 
> Ok, I wasn't talking about the synthetic test in the second part of my
> email above but about the explanation you gave about Galleryfling
> improvement (that the migration of a task with high utilization
> doesn't update the target frequency) which makes sense to me so we are
> on the same page about that.

Okay, great.

-- 
viresh

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

Thread

[PATCH V4 0/3] sched: cpufreq: Allow remote callbacks Viresh Kumar <viresh.kumar@linaro.org> - 2017-07-26 11:30 +0200
  [PATCH V4 2/3] cpufreq: schedutil: Process remote callback for shared policies Viresh Kumar <viresh.kumar@linaro.org> - 2017-07-26 11:30 +0200
    Re: [Eas-dev] [PATCH V4 2/3] cpufreq: schedutil: Process remote  callback for shared policies "Joel Fernandes (Google)" <joel.opensrc@gmail.com> - 2017-07-27 07:50 +0200
  [PATCH V4 1/3] sched: cpufreq: Allow remote cpufreq callbacks Viresh Kumar <viresh.kumar@linaro.org> - 2017-07-26 11:30 +0200
    Re: [PATCH V4 1/3] sched: cpufreq: Allow remote cpufreq callbacks "Rafael J. Wysocki" <rjw@rjwysocki.net> - 2017-07-26 20:00 +0200
      Re: [PATCH V4 1/3] sched: cpufreq: Allow remote cpufreq callbacks Viresh Kumar <viresh.kumar@linaro.org> - 2017-07-27 05:30 +0200
    Re: [Eas-dev] [PATCH V4 1/3] sched: cpufreq: Allow remote cpufreq callbacks "Joel Fernandes (Google)" <joel.opensrc@gmail.com> - 2017-07-27 07:40 +0200
      Re: [Eas-dev] [PATCH V4 1/3] sched: cpufreq: Allow remote cpufreq  callbacks Viresh Kumar <viresh.kumar@linaro.org> - 2017-07-27 08:00 +0200
        Re: [Eas-dev] [PATCH V4 1/3] sched: cpufreq: Allow remote cpufreq callbacks "Joel Fernandes (Google)" <joel.opensrc@gmail.com> - 2017-07-27 08:20 +0200
          Re: [Eas-dev] [PATCH V4 1/3] sched: cpufreq: Allow remote cpufreq  callbacks Viresh Kumar <viresh.kumar@linaro.org> - 2017-07-27 09:20 +0200
            Re: [Eas-dev] [PATCH V4 1/3] sched: cpufreq: Allow remote cpufreq  callbacks Peter Zijlstra <peterz@infradead.org> - 2017-07-27 11:20 +0200
            Re: [Eas-dev] [PATCH V4 1/3] sched: cpufreq: Allow remote cpufreq callbacks "Joel Fernandes (Google)" <joel.opensrc@gmail.com> - 2017-07-28 05:40 +0200
    Re: [PATCH V4 1/3] sched: cpufreq: Allow remote cpufreq callbacks Peter Zijlstra <peterz@infradead.org> - 2017-07-27 12:00 +0200
  [PATCH V4 3/3] cpufreq: governor: Process remote callback for shared policies Viresh Kumar <viresh.kumar@linaro.org> - 2017-07-26 11:30 +0200
  Re: [Eas-dev] [PATCH V4 0/3] sched: cpufreq: Allow remote callbacks "Joel Fernandes (Google)" <joel.opensrc@gmail.com> - 2017-07-27 07:20 +0200
    Re: [Eas-dev] [PATCH V4 0/3] sched: cpufreq: Allow remote callbacks Viresh Kumar <viresh.kumar@linaro.org> - 2017-07-27 07:50 +0200
      Re: [Eas-dev] [PATCH V4 0/3] sched: cpufreq: Allow remote callbacks "Joel Fernandes (Google)" <joel.opensrc@gmail.com> - 2017-07-27 08:30 +0200
        Re: [Eas-dev] [PATCH V4 0/3] sched: cpufreq: Allow remote callbacks Viresh Kumar <viresh.kumar@linaro.org> - 2017-07-27 09:20 +0200
        Re: [Eas-dev] [PATCH V4 0/3] sched: cpufreq: Allow remote callbacks Juri Lelli <juri.lelli@arm.com> - 2017-07-27 09:30 +0200
          Re: [Eas-dev] [PATCH V4 0/3] sched: cpufreq: Allow remote callbacks "Joel Fernandes (Google)" <joel.opensrc@gmail.com> - 2017-07-28 05:50 +0200

csiph-web