Received-SPF: pass (google.com: domain of linux-kernel+bounces-39050-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Precedence: bulk
MIME-Version: 1.0
References: <20240105222014.1025040-1-qyousef@layalina.io> <20240105222014.1025040-2-qyousef@layalina.io>
 <213f94df-cc36-4281-805d-9f56cbfef796@arm.com> <CAKfTPtCfYcD_zPr7PqgL5hRYny=n3KW8hr6GY8q7zkoyRN7gQg@mail.gmail.com>
 <20240124224616.wcrexeb2evkugbak@airbuntu>
In-Reply-To: <20240124224616.wcrexeb2evkugbak@airbuntu>
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Thu, 25 Jan 2024 18:44:14 +0100
Message-ID: <CAKfTPtDnxsOS0je9DgMc5ZCLPXA6QRLz14t6o_ht7rvxbAbc9A@mail.gmail.com>
Subject: Re: [PATCH v4 1/2] sched/fair: Check a task has a fitting cpu when
 updating misfit
To: Qais Yousef <qyousef@layalina.io>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>, Ingo Molnar <mingo@kernel.org>, 
	Peter Zijlstra <peterz@infradead.org>, linux-kernel@vger.kernel.org, 
	Pierre Gondois <Pierre.Gondois@arm.com>
Content-Type: text/plain; charset="UTF-8"

On Wed, 24 Jan 2024 at 23:46, Qais Yousef <qyousef@layalina.io> wrote:
>
> On 01/23/24 09:32, Vincent Guittot wrote:
>
> > > > @@ -9583,9 +9630,7 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
> > > >   */
> > > >  static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd)
> > > >  {
> > > > -     return rq->misfit_task_load &&
> > > > -             (arch_scale_cpu_capacity(rq->cpu) < rq->rd->max_cpu_capacity ||
> > > > -              check_cpu_capacity(rq, sd));
> > > > +     return rq->misfit_task_load && check_cpu_capacity(rq, sd);

Coming back to this:
With your change above, misfit can't kick an idle load balance and
must wait for the cpu capacity being noticeably reduced by something
else

> > >
> > > You removed 'arch_scale_cpu_capacity(rq->cpu) <
> > > rq->rd->max_cpu_capacity' here. Why? I can see that with the standard
> > > setup (max CPU capacity equal 1024) which is what we probably use 100%
> > > of the time now. It might get useful again when Vincent will introduce
> > > his 'user space system pressure' implementation?
> >
> > That's interesting because I'm doing the opposite in the user space
> > system pressure that I'm preparing:
> > I keep something similar to (arch_scale_cpu_capacity(rq->cpu) <
> > rq->rd->max_cpu_capacity but I remove check_cpu_capacity(rq, sd) which
> > seems to be useless because it's already used earlier in
> > nohz_balancer_kick()
>
> Okay. I need to look at your patches anyway. I can potentially rebase on top of
> your series.
>
>
> Cheers
>
> --
> Qais Yousef