Re: [PATCH] sched/fair: Optimize select_idle_core
From: Vincent Guittot
Date: Fri Dec 06 2019 - 08:27:33 EST
On Fri, 6 Dec 2019 at 09:17, Srikar Dronamraju
<srikar@xxxxxxxxxxxxxxxxxx> wrote:
>
> * Vincent Guittot <vincent.guittot@xxxxxxxxxx> [2019-12-05 19:52:40]:
>
> > On Thu, 5 Dec 2019 at 18:52, Srikar Dronamraju
> > <srikar@xxxxxxxxxxxxxxxxxx> wrote:
> > >
> > > * Vincent Guittot <vincent.guittot@xxxxxxxxxx> [2019-12-05 18:27:51]:
> > >
> > > > Hi Srikar,
> > > >
> > > > On Thu, 5 Dec 2019 at 18:23, Srikar Dronamraju
> > > > <srikar@xxxxxxxxxxxxxxxxxx> wrote:
> > > > >
> > > > > Currently we loop through all threads of a core to evaluate if the core
> > > > > is idle or not. This is unnecessary. If a thread of a core is not
> > > > > idle, skip evaluating other threads of a core.
> > > >
> > > > I think that the goal is also to clear all CPUs of the core from the
> > > > cpumask of the loop above so it will not try the same core next time
> > > >
> > > > >
> > >
> > > That goal we still continue to maintain by the way of cpumask_andnot.
> > > i.e instead of clearing CPUs one at a time, we clear all the CPUs in the
> > > core at one shot.
> >
> > ah yes sorry, I have been to quick and overlooked the cpumask_andnot line
> >
>
> Just to reiterate why this is necessary.
> Currently, even if the first thread of a core is not idle, we iterate
> through all threads of the core and individually clear the CPU from the core
> mask.
>
> Collecting ticks on a Power 9 SMT 8 system around select_idle_core
> while running schbench shows us that
>
> (units are in ticks, hence lesser is better)
> Without patch
> N Min Max Median Avg Stddev
> x 130 151 1083 284 322.72308 144.41494
>
>
> With patch
> N Min Max Median Avg Stddev Improvement
> x 164 88 610 201 225.79268 106.78943 30.03%
Thanks for the figures. Might be good to include them in the commit message
Reviewed-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
>
> --
> Thanks and Regards
> Srikar Dronamraju
>