[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20160621124740.GN30921@twins.programming.kicks-ass.net>
Date: Tue, 21 Jun 2016 14:47:40 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Vincent Guittot <vincent.guittot@...aro.org>
Cc: Yuyang Du <yuyang.du@...el.com>, Ingo Molnar <mingo@...nel.org>,
linux-kernel <linux-kernel@...r.kernel.org>,
Mike Galbraith <umgwanakikbuti@...il.com>,
Benjamin Segall <bsegall@...gle.com>,
Paul Turner <pjt@...gle.com>,
Morten Rasmussen <morten.rasmussen@....com>,
Dietmar Eggemann <dietmar.eggemann@....com>,
Matt Fleming <matt@...eblueprint.co.uk>
Subject: Re: [PATCH 4/4] sched,fair: Fix PELT integrity for new tasks
On Tue, Jun 21, 2016 at 02:36:46PM +0200, Vincent Guittot wrote:
> On 21 June 2016 at 13:43, Peter Zijlstra <peterz@...radead.org> wrote:
> > On Mon, Jun 20, 2016 at 11:23:39AM +0200, Vincent Guittot wrote:
> >
> >> Don't we have to do a complete attach with attach_task_cfs_rq instead
> >> of just the load_avg ? to set also depth ?
> >
> > Hmm, yes, your sched_set_group() change seems to have munged this.
> >
>
> I think that it was done by the attach_task_cfs_rq during the activate_task.
> Now, the attach is done in post_init_entity_util_avg. Can't we just
> set the depth in post_init_entity_util_avg ?
Yes, I actually had that patch for a little while.
But since its cgroup specific, I felt it should be in the cgroup code,
hence the current patch.
Powered by blists - more mailing lists