lkml.org 
[lkml]   [2019]   [Nov]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
Date
SubjectRe: [PATCH v2] sched/freq: move call to cpufreq_update_util
On Tue, 12 Nov 2019 at 18:11, Valentin Schneider
<valentin.schneider@arm.com> wrote:
>
> Hi Vincent,
>
> I didn't see anything in that reply, was that just a spurious email?

there were a typo in one email address in the 1st message

>
> On 12/11/2019 15:05, Vincent Guittot wrote:
> > Le Tuesday 12 Nov 2019 à 15:48:13 (+0100), Vincent Guittot a écrit :
> >> 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_blocked_averages()
> >> 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,cpufreq}_util_change() 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@telus.net>
> >> Fixes: 039ae8bcf7a5 ("sched/fair: Fix O(nr_cgroups) in the load balancing path")
> >> Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
> >>
> >> ---
> >>
> >> I have just rebased the patch on latest tip/sched/core and made it a proper
> >> patchset after Doug reported that the problem has diseappeared according to
> >> his 1st results but tests results are not all based on the same v5.4-rcX
> >> and with menu instead of teo governor.
> >>
> >> kernel/sched/fair.c | 33 +++++++++++++++++++++------------
> >> 1 file changed, 21 insertions(+), 12 deletions(-)
> >>
> >> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> >> index e458f52..c93d534 100644
> >> --- a/kernel/sched/fair.c
> >> +++ b/kernel/sched/fair.c
> >> @@ -3508,9 +3508,6 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
> >> cfs_rq->load_last_update_time_copy = sa->last_update_time;
> >> #endif
> >>
> >> - if (decayed)
> >> - cfs_rq_util_change(cfs_rq, 0);
> >> -
> >> return decayed;
> >> }
> >>
> >> @@ -3620,8 +3617,12 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
> >> attach_entity_load_avg(cfs_rq, se, SCHED_CPUFREQ_MIGRATION);
> >> update_tg_load_avg(cfs_rq, 0);
> >>
> >> - } else if (decayed && (flags & UPDATE_TG))
> >> - update_tg_load_avg(cfs_rq, 0);
> >> + } else if (decayed) {
> >> + cfs_rq_util_change(cfs_rq, 0);
> >> +
> >> + if (flags & UPDATE_TG)
> >> + update_tg_load_avg(cfs_rq, 0);
> >> + }
> >> }
> >>
> >> #ifndef CONFIG_64BIT
> >> @@ -7484,6 +7485,7 @@ static void update_blocked_averages(int cpu)
> >> const struct sched_class *curr_class;
> >> struct rq_flags rf;
> >> bool done = true;
> >> + int decayed = 0;
> >>
> >> rq_lock_irqsave(rq, &rf);
> >> update_rq_clock(rq);
> >> @@ -7493,9 +7495,9 @@ static void update_blocked_averages(int cpu)
> >> * that RT, DL and IRQ signals have been updated before updating CFS.
> >> */
> >> curr_class = rq->curr->sched_class;
> >> - update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
> >> - update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
> >> - update_irq_load_avg(rq, 0);
> >> + decayed |= update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
> >> + decayed |= update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
> >> + decayed |= update_irq_load_avg(rq, 0);
> >>
> >> /* Don't need periodic decay once load/util_avg are null */
> >> if (others_have_blocked(rq))
> >> @@ -7529,6 +7531,9 @@ static void update_blocked_averages(int cpu)
> >> }
> >>
> >> update_blocked_load_status(rq, !done);
> >> +
> >> + if (decayed)
> >> + cpufreq_update_util(rq, 0);
> >> rq_unlock_irqrestore(rq, &rf);
> >> }
> >>
> >> @@ -7585,6 +7590,7 @@ static inline void update_blocked_averages(int cpu)
> >> struct cfs_rq *cfs_rq = &rq->cfs;
> >> const struct sched_class *curr_class;
> >> struct rq_flags rf;
> >> + int decayed = 0;
> >>
> >> rq_lock_irqsave(rq, &rf);
> >> update_rq_clock(rq);
> >> @@ -7594,13 +7600,16 @@ static inline void update_blocked_averages(int cpu)
> >> * that RT, DL and IRQ signals have been updated before updating CFS.
> >> */
> >> curr_class = rq->curr->sched_class;
> >> - update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
> >> - update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
> >> - update_irq_load_avg(rq, 0);
> >> + decayed |= update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
> >> + decayed |= update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
> >> + decayed |= update_irq_load_avg(rq, 0);
> >>
> >> - update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
> >> + decayed |= update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
> >>
> >> update_blocked_load_status(rq, cfs_rq_has_blocked(cfs_rq) || others_have_blocked(rq));
> >> +
> >> + if (decayed)
> >> + cpufreq_update_util(rq, 0);
> >> rq_unlock_irqrestore(rq, &rf);
> >> }
> >>
> >> --
> >> 2.7.4
> >>

\
 
 \ /
  Last update: 2019-11-12 18:21    [W:0.263 / U:1.060 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site