[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20201002141709.GX2628@hirez.programming.kicks-ass.net>
Date: Fri, 2 Oct 2020 16:17:09 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Vincent Donnefort <vincent.donnefort@....com>
Cc: tglx@...utronix.de, mingo@...nel.org, linux-kernel@...r.kernel.org,
bigeasy@...utronix.de, qais.yousef@....com, swood@...hat.com,
valentin.schneider@....com, juri.lelli@...hat.com,
vincent.guittot@...aro.org, dietmar.eggemann@....com,
rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de,
bristot@...hat.com
Subject: Re: [PATCH 5/9] sched/hotplug: Consolidate task migration on CPU
unplug
On Thu, Oct 01, 2020 at 06:12:30PM +0100, Vincent Donnefort wrote:
> On Mon, Sep 21, 2020 at 06:36:02PM +0200, Peter Zijlstra wrote:
>
> [...]
>
> > +
> > + [CPUHP_AP_SCHED_WAIT_EMPTY] = {
> > + .name = "sched:waitempty",
> > + .startup.single = NULL,
> > + .teardown.single = sched_cpu_wait_empty,
> > + },
> > +
> > /* Handle smpboot threads park/unpark */
>
> Unless I missed something, now that the wait has its own HP step, this
> patch can probably also get rid of the balance_hotplug_wait() in
> sched_cpu_deactivate() introduced by:
>
> [PATCH 4/9] sched/core: Wait for tasks being pushed away on hotplug
I'd think so. Consider it gone.
Powered by blists - more mailing lists