Re: [PATCH v3] sched/freq: move call to cpufreq_update_util

[Vincent Guittot]

On Thu, 14 Nov 2019 at 17:23, Dietmar Eggemann <dietmar.eggemann@xxxxxxx> wrote:
>
> On 13.11.19 21:21, Vincent Guittot wrote:
> > update_cfs_rq_load_avg() calls cfs_rq_util_change() everytime pelt decays,
> > which might be inefficient when cpufreq driver has rate limitation.
> >
> > When a task is attached on a CPU, we have call path:
> >
> > update_load_avg()
> >   update_cfs_rq_load_avg()
> >     cfs_rq_util_change -- > trig frequency update
> >   attach_entity_load_avg()
> >     cfs_rq_util_change -- > trig frequency update
> >
> > The 1st frequency update will not take into account the utilization of the
> > newly attached task and the 2nd one might be discard because of rate
> > limitation of the cpufreq driver.
> >
> > update_cfs_rq_load_avg() is only called by update_blocked_averages()
> > and update_load_avg() so we can move the call to
> > cfs_rq_util_change/cpufreq_update_util() into these 2 functions. It's also
> > interesting to notice that update_load_avg() already calls directly
> > cfs_rq_util_change() for !SMP case.
> >
> > This changes will also ensure that cpufreq_update_util() is called even
> > when there is no more CFS rq in the leaf_cfs_rq_list to update but only
> > irq, rt or dl pelt signals.
> >
> > Reported-by: Doug Smythies <dsmythies@xxxxxxxxx>
> > Fixes: 039ae8bcf7a5 ("sched/fair: Fix O(nr_cgroups) in the load balancing path")
> > Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
>
> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
>
> > ---
> >
> > changes for v3:
> > - fix typo
> > - test the decay of root cfs_rq even for !CONFIG_FAIR_GROUP_SCHED case
>
> nit: s/!CONFIG_FAIR_GROUP_SCHED/CONFIG_FAIR_GROUP_SCHED
>
> [...]
>
> > @@ -7543,6 +7544,7 @@ static void update_blocked_averages(int cpu)
> >       const struct sched_class *curr_class;
> >       struct rq_flags rf;
> >       bool done = true;
> > +     int decayed;
> >
> >       rq_lock_irqsave(rq, &rf);
> >       update_rq_clock(rq);
> > @@ -7552,9 +7554,9 @@ static void update_blocked_averages(int cpu)
> >        * that RT, DL and IRQ signals have been updated before updating CFS.
> >        */
>
> tip/sched/urgent's b90f7c9d2198 ("sched/pelt: Fix update of blocked PELT
> ordering") adds this comment to both update_blocked_averages()
> implementations. It mentions explicitly that update_cfs_rq_load_avg()
> can call cpufreq_update_util(). Something this patch changes. Might be
> good to update the comments with this patch as well.

yes.

>
> [...]