Re: [PATCH v2] sched/core: forced idle accounting

[Peter Zijlstra]

On Tue, Nov 09, 2021 at 02:59:00PM -0800, Josh Don wrote:
> On Tue, Nov 9, 2021 at 3:15 AM Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> >
> > On Mon, Oct 18, 2021 at 01:34:28PM -0700, Josh Don wrote:
> > > @@ -5804,6 +5830,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
> > >               }
> > >       }
> > >
> > > +     if (rq->core->core_forceidle_count) {
> >
> > Does this want to be something like:
> >
> >         if (schedstat_enabled() && .. ) ?
> >
> > afaict without schedstat on this is dead code.
> >
> 
> Makes sense to me, and similarly we can bail out of sched_core_tick()
> early in the disabled case.

Ok, I already changed the patch to include the above, lemme also edit
sched_core_tick().