Re: [RFC/RFT][PATCH 6/7] sched: idle: Predict idle duration before stopping the tick
From: Rafael J. Wysocki
Date: Tue Mar 06 2018 - 03:17:27 EST
On Tuesday, March 6, 2018 12:27:01 AM CET Rik van Riel wrote:
> On Sun, 2018-03-04 at 23:28 +0100, Rafael J. Wysocki wrote:
> >
> > +++ linux-pm/kernel/sched/idle.c
> > @@ -188,13 +188,14 @@ static void cpuidle_idle_call(void)
> > } else {
> > unsigned int duration_us;
> >
> > - tick_nohz_idle_go_idle(true);
> > - rcu_idle_enter();
> > -
> > /*
> > * Ask the cpuidle framework to choose a convenient
> > idle state.
> > */
> > next_state = cpuidle_select(drv, dev, &duration_us);
> > +
> > + tick_nohz_idle_go_idle(duration_us > USEC_PER_SEC /
> > HZ);
> > + rcu_idle_enter();
> > +
> > entered_state = call_cpuidle(drv, dev, next_state);
>
> When the expected idle period is short enough
> that the timer is not stopped, does it make
> sense to still call rcu_idle_enter?
>
> Should rcu_idle_enter also be conditional on
> the expected idle period?
Well, that would be the next step. :-)