[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAKfTPtATBXgp47=gv=yVQ0rox9qr1H3DOXCSngmcZvAmqt-GTg@mail.gmail.com>
Date: Fri, 26 Jul 2019 10:41:30 +0200
From: Vincent Guittot <vincent.guittot@...aro.org>
To: Srikar Dronamraju <srikar@...ux.vnet.ibm.com>
Cc: linux-kernel <linux-kernel@...r.kernel.org>,
Ingo Molnar <mingo@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Quentin Perret <quentin.perret@....com>,
Dietmar Eggemann <dietmar.eggemann@....com>,
Morten Rasmussen <Morten.Rasmussen@....com>,
Phil Auld <pauld@...hat.com>
Subject: Re: [PATCH 2/5] sched/fair: rename sum_nr_running to sum_h_nr_running
On Fri, 26 Jul 2019 at 04:17, Srikar Dronamraju
<srikar@...ux.vnet.ibm.com> wrote:
>
> * Vincent Guittot <vincent.guittot@...aro.org> [2019-07-19 09:58:22]:
>
> > sum_nr_running will track rq->nr_running task and sum_h_nr_running
> > will track cfs->h_nr_running so we can use both to detect when other
> > scheduling class are running and preempt CFS.
> >
> > There is no functional changes.
> >
> > Signed-off-by: Vincent Guittot <vincent.guittot@...aro.org>
> > ---
> >
> > ld_moved = 0;
> > - if (busiest->nr_running > 1) {
> > + if (busiest->cfs.h_nr_running > 1) {
>
> We should be looking for nr_running here.
> There could be only one cfs task but that may not be the current running
> task, so it could be a good one to be picked for load balancing.
>
> No?
Yes you're right.
That's what i have done on the new version that I'm preparing
>
> > /*
> > * Attempt to move tasks. If find_busiest_group has found
> > * an imbalance but busiest->nr_running <= 1, the group is
> > --
> > 2.7.4
> >
>
> --
> Thanks and Regards
> Srikar Dronamraju
>
Powered by blists - more mailing lists