Re: [PATCH v3] sched,fair: skip newidle_balance if a wakeup is pending

[Rik van Riel <riel@surriel.com>]

[-- Attachment #1: Type: text/plain, Size: 1286 bytes --]

On Thu, 2021-04-22 at 10:37 +0200, Vincent Guittot wrote:
> On Wed, 21 Apr 2021 at 19:27, Vincent Guittot
> <vincent.guittot@linaro.org> wrote:
> > 
> > > -       if (pulled_task)
> > > +       /*
> > > +        * If we are no longer idle, do not let the time spent
> > > here pull
> > > +        * down this_rq->avg_idle. That could lead to
> > > newidle_balance not
> > > +        * doing enough work, and the CPU actually going idle.
> > > +        */
> > > +       if (pulled_task || this_rq->ttwu_pending)
> > 
> I confirmed that the line above generate hackbench regression on my
> large arm64 system (2 * 112 CPUs)
> I'm testing hackbench with various number of group : 1, 2, 4, 16, 32,
> 64, 128, 256 but I have only put the 2 results which significantly
> regress. The other ones are in the +/-1% variation range
> 
> hackbench -g $group
> 
> group    v5.12-rc8+tip    w/ this patch          w/ this patch
> without
> the line above
> 64       2.862(+/- 9%)    2.952(+/-11%) -3%      2.807(+/- 7%) +2%
> 128      3.334(+/-10%)    3.561-+/-13%) -7%      3.181(+/- 6%) +4%

OK, I guess this part of the patch needs additional work.

I'll send a v4 with just the first two changes.

Thank you for running those tests.

-- 
All Rights Reversed.

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 488 bytes --]