[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20201209090507.GM3371@techsingularity.net>
Date: Wed, 9 Dec 2020 09:05:07 +0000
From: Mel Gorman <mgorman@...hsingularity.net>
To: "Li, Aubrey" <aubrey.li@...ux.intel.com>
Cc: Vincent Guittot <vincent.guittot@...aro.org>,
Peter Ziljstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
LKML <linux-kernel@...r.kernel.org>,
Barry Song <song.bao.hua@...ilicon.com>,
Juri Lelli <juri.lelli@...hat.com>,
Valentin Schneider <valentin.schneider@....com>,
Linux-ARM <linux-arm-kernel@...ts.infradead.org>
Subject: Re: [PATCH 2/4] sched/fair: Move avg_scan_cost calculations under
SIS_PROP
On Wed, Dec 09, 2020 at 01:28:11PM +0800, Li, Aubrey wrote:
> >> nr = div_u64(span_avg, avg_cost);
> >> else
> >> nr = 4;
> >> - }
> >> -
> >> - time = cpu_clock(this);
> >>
> >> - cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
> >> + time = cpu_clock(this);
> >> + }
> >>
> >> for_each_cpu_wrap(cpu, cpus, target) {
> >> if (!--nr)
>
> nr is the key of this throttling mechanism, need to be placed under sched_feat(SIS_PROP) as well.
>
It isn't necessary as nr in initialised to INT_MAX if !SIS_PROP.
--
Mel Gorman
SUSE Labs
Powered by blists - more mailing lists