From: Patrick Bellasi <patrick.bellasi@arm.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org,
Ingo Molnar <mingo@redhat.com>, Tejun Heo <tj@kernel.org>,
"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
Vincent Guittot <vincent.guittot@linaro.org>,
Viresh Kumar <viresh.kumar@linaro.org>,
Paul Turner <pjt@google.com>,
Quentin Perret <quentin.perret@arm.com>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Morten Rasmussen <morten.rasmussen@arm.com>,
Juri Lelli <juri.lelli@redhat.com>, Todd Kjos <tkjos@google.com>,
Joel Fernandes <joelaf@google.com>,
Steve Muckle <smuckle@google.com>,
Suren Baghdasaryan <surenb@google.com>
Subject: Re: [PATCH v5 06/15] sched/core: uclamp: enforce last task UCLAMP_MAX
Date: Tue, 13 Nov 2018 07:14:24 -0800 [thread overview]
Message-ID: <20181113151424.GB7681@darkstar> (raw)
In-Reply-To: <20181111170848.GB3038@worktop>
On 11-Nov 18:08, Peter Zijlstra wrote:
> On Mon, Oct 29, 2018 at 06:33:01PM +0000, Patrick Bellasi wrote:
> > When a util_max clamped task sleeps, its clamp constraints are removed
> > from the CPU. However, the blocked utilization on that CPU can still be
> > higher than the max clamp value enforced while that task was running.
> >
> > The release of a util_max clamp when a CPU is going to be idle could
> > thus allow unwanted CPU frequency increases while tasks are not
> > running. This can happen, for example, when a frequency update is
> > triggered from another CPU of the same frequency domain.
> > In this case, when we aggregate the utilization of all the CPUs in a
> > shared frequency domain, schedutil can still see the full not clamped
> > blocked utilization of all the CPUs and thus, eventually, increase the
> > frequency.
>
> > @@ -810,6 +811,28 @@ static inline void uclamp_cpu_update(struct rq *rq, unsigned int clamp_id)
> > if (max_value >= SCHED_CAPACITY_SCALE)
> > break;
> > }
> > +
> > + /*
> > + * Just for the UCLAMP_MAX value, in case there are no RUNNABLE
> > + * task, we want to keep the CPU clamped to the last task's clamp
> > + * value. This is to avoid frequency spikes to MAX when one CPU, with
> > + * an high blocked utilization, sleeps and another CPU, in the same
> > + * frequency domain, do not see anymore the clamp on the first CPU.
> > + *
> > + * The UCLAMP_FLAG_IDLE is set whenever we detect, from the above
> > + * loop, that there are no more RUNNABLE taks on that CPU.
> > + * In this case we enforce the CPU util_max to that of the last
> > + * dequeued task.
> > + */
> > + if (max_value < 0) {
> > + if (clamp_id == UCLAMP_MAX) {
> > + rq->uclamp.flags |= UCLAMP_FLAG_IDLE;
> > + max_value = last_clamp_value;
> > + } else {
> > + max_value = uclamp_none(UCLAMP_MIN);
> > + }
> > + }
> > +
> > rq->uclamp.value[clamp_id] = max_value;
> > }
>
> *groan*, so it could be jet-lag, but I find the comment really hard to
> understand.
>
> Would not something like:
>
> /*
> * Avoid blocked utilization pushing up the frequency when we go
> * idle (which drops the max-clamp) by retaining the last known
> * max-clamp.
> */
>
> Be more clear?
It works: short and effective... will update in v6.
Thanks.
--
#include <best/regards.h>
Patrick Bellasi
next prev parent reply other threads:[~2018-11-13 15:14 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-29 18:32 [PATCH v5 00/15] Add utilization clamping support Patrick Bellasi
2018-10-29 18:32 ` [PATCH v5 01/15] sched/core: uclamp: extend sched_setattr to support utilization clamping Patrick Bellasi
2018-10-29 19:33 ` Randy Dunlap
2018-11-07 12:09 ` Peter Zijlstra
2018-10-29 18:32 ` [PATCH v5 02/15] sched/core: make sched_setattr able to tune the current policy Patrick Bellasi
2018-11-07 12:11 ` Peter Zijlstra
2018-11-07 13:50 ` Patrick Bellasi
2018-11-07 13:58 ` Peter Zijlstra
2018-10-29 18:32 ` [PATCH v5 03/15] sched/core: uclamp: map TASK's clamp values into CPU's clamp groups Patrick Bellasi
2018-11-07 12:19 ` Peter Zijlstra
2018-11-07 14:19 ` Patrick Bellasi
2018-11-07 14:42 ` Peter Zijlstra
2018-11-07 14:56 ` Patrick Bellasi
2018-11-07 13:16 ` Peter Zijlstra
2018-11-07 13:57 ` Patrick Bellasi
2018-11-07 14:14 ` Peter Zijlstra
2018-11-07 13:35 ` Peter Zijlstra
2018-11-07 14:48 ` Patrick Bellasi
2018-11-07 14:55 ` Peter Zijlstra
2018-11-07 15:04 ` Patrick Bellasi
2018-11-07 13:44 ` Peter Zijlstra
2018-11-07 14:24 ` Patrick Bellasi
2018-11-07 14:44 ` Peter Zijlstra
2018-11-07 14:58 ` Patrick Bellasi
2018-11-07 14:37 ` Peter Zijlstra
2018-11-07 14:53 ` Patrick Bellasi
2018-10-29 18:32 ` [PATCH v5 04/15] sched/core: uclamp: add CPU's clamp groups accounting Patrick Bellasi
2018-10-29 18:42 ` Patrick Bellasi
2018-10-29 18:32 ` [PATCH v5 04/15] sched/core: uclamp: add CPU's clamp groups refcounting Patrick Bellasi
2018-11-11 16:47 ` Peter Zijlstra
2018-11-13 15:11 ` Patrick Bellasi
2018-11-22 14:20 ` Patrick Bellasi
2018-10-29 18:33 ` [PATCH v5 05/15] sched/core: uclamp: update CPU's refcount on clamp changes Patrick Bellasi
2018-10-29 18:33 ` [PATCH v5 06/15] sched/core: uclamp: enforce last task UCLAMP_MAX Patrick Bellasi
2018-11-11 17:08 ` Peter Zijlstra
2018-11-13 15:14 ` Patrick Bellasi [this message]
2018-10-29 18:33 ` [PATCH v5 07/15] sched/core: uclamp: add clamp group bucketing support Patrick Bellasi
2018-11-12 0:09 ` Peter Zijlstra
2018-11-13 15:29 ` Patrick Bellasi
2018-10-29 18:33 ` [PATCH v5 08/15] sched/core: uclamp: add system default clamps Patrick Bellasi
2018-10-29 18:33 ` [PATCH v5 09/15] sched/cpufreq: uclamp: add utilization clamping for FAIR tasks Patrick Bellasi
2018-11-07 11:38 ` Patrick Bellasi
2018-10-29 18:33 ` [PATCH v5 10/15] sched/cpufreq: uclamp: add utilization clamping for RT tasks Patrick Bellasi
2018-10-29 18:33 ` [PATCH v5 11/15] sched/core: uclamp: extend CPU's cgroup controller Patrick Bellasi
2018-10-29 18:33 ` [PATCH v5 12/15] sched/core: uclamp: propagate parent clamps Patrick Bellasi
2018-10-29 18:33 ` [PATCH v5 13/15] sched/core: uclamp: map TG's clamp values into CPU's clamp groups Patrick Bellasi
2018-10-29 18:33 ` [PATCH v5 14/15] sched/core: uclamp: use TG's clamps to restrict Task's clamps Patrick Bellasi
2018-10-29 18:47 ` Patrick Bellasi
2018-10-29 18:33 ` [PATCH v5 14/15] sched/core: uclamp: use TG's clamps to restrict TASK's clamps Patrick Bellasi
2018-10-29 18:33 ` [PATCH v5 15/15] sched/core: uclamp: update CPU's refcount on TG's clamp changes Patrick Bellasi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20181113151424.GB7681@darkstar \
--to=patrick.bellasi@arm.com \
--cc=dietmar.eggemann@arm.com \
--cc=joelaf@google.com \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=morten.rasmussen@arm.com \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=quentin.perret@arm.com \
--cc=rafael.j.wysocki@intel.com \
--cc=smuckle@google.com \
--cc=surenb@google.com \
--cc=tj@kernel.org \
--cc=tkjos@google.com \
--cc=vincent.guittot@linaro.org \
--cc=viresh.kumar@linaro.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).