[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20210111154226.GG3524@suse.de>
Date: Mon, 11 Jan 2021 15:42:26 +0000
From: Mel Gorman <mgorman@...e.de>
To: Vincent Guittot <vincent.guittot@...aro.org>
Cc: mingo@...hat.com, peterz@...radead.org, juri.lelli@...hat.com,
dietmar.eggemann@....com, rostedt@...dmis.org, bsegall@...gle.com,
bristot@...hat.com, valentin.schneider@....com,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH 2/3 v2] sched/fair: don't set LBF_ALL_PINNED unnecessarily
On Thu, Jan 07, 2021 at 11:33:24AM +0100, Vincent Guittot wrote:
> Setting LBF_ALL_PINNED during active load balance is only valid when there
> is only 1 running task on the rq otherwise this ends up increasing the
> balance interval whereas other tasks could migrate after the next interval
> once they become cache-cold as an example.
>
> LBF_ALL_PINNED flag is now always set it by default. It is then cleared
> when we find one task that can be pulled when calling detach_tasks() or
> during active migration.
>
> Signed-off-by: Vincent Guittot <vincent.guittot@...aro.org>
When reviewing this, I found it curious that sched_nr_migrate_break is
a const instead of a #define. It's not clear why as it only appears to
exist in case sysctl_sched_nr_migrate is set higher than 32 to prevent
rq lock starvation.
With your patch, s/atleast/at least/ in the comments if there is another
version.
Otherwise, I didn't spot a real problem so
Acked-by: Mel Gorman <mgorman@...e.de>
--
Mel Gorman
SUSE Labs
Powered by blists - more mailing lists