From: Dietmar Eggemann <dietmar.eggemann@arm.com>
To: Patrick Bellasi <patrick.bellasi@arm.com>,
Vincent Guittot <vincent.guittot@linaro.org>
Cc: Juri Lelli <juri.lelli@redhat.com>,
linux-kernel <linux-kernel@vger.kernel.org>,
linux-pm <linux-pm@vger.kernel.org>,
Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>, Tejun Heo <tj@kernel.org>,
"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
Viresh Kumar <viresh.kumar@linaro.org>,
Paul Turner <pjt@google.com>,
Morten Rasmussen <morten.rasmussen@arm.com>,
Todd Kjos <tkjos@google.com>, Joel Fernandes <joelaf@google.com>,
Steve Muckle <smuckle@google.com>,
Suren Baghdasaryan <surenb@google.com>
Subject: Re: [PATCH v3 06/14] sched/cpufreq: uclamp: add utilization clamping for RT tasks
Date: Thu, 16 Aug 2018 12:34:05 +0200 [thread overview]
Message-ID: <1b72b94c-5411-4b95-01a6-49ac978acbd5@arm.com> (raw)
In-Reply-To: <20180813150112.GE2605@e110439-lin>
On 08/13/2018 05:01 PM, Patrick Bellasi wrote:
> On 13-Aug 16:06, Vincent Guittot wrote:
>> On Mon, 13 Aug 2018 at 14:49, Patrick Bellasi <patrick.bellasi@arm.com> wrote:
>>> On 13-Aug 14:07, Vincent Guittot wrote:
>>>> On Mon, 13 Aug 2018 at 12:12, Patrick Bellasi <patrick.bellasi@arm.com> wrote:
>
> [...]
>
>>> Yes I agree that the current behavior is not completely clean... still
>>> the question is: do you reckon the problem I depicted above, i.e. RT
>>> workloads eclipsing the min_util required by lower priority classes?
>>
>> As said above, I don't think that there is a problem that is specific
>> to cross class scheduling that can't also happen in the same class.
>>
>> Regarding your example:
>> task TA util=40% with uclamp_min 50%
>> task TB util=10% with uclamp_min 0%
>>
>> If TA and TB are cfs, util=50% and it doesn't seem to be a problem
>> whereas TB will steal some bandwidth to TA and delay it (and i even
>> don't speak about the impact of the nice priority of TB)
>> If TA is cfs and TB is rt, Why util=50% is now a problem for TA ?
>
> You right, in the current implementation, where we _do not_
> distinguish among scheduling classes it's not possible to get a
> reasonable implementation of a per sched class clamping.
>
>>> To a certain extend I see this problem similar to the rt/dl/irq pressure
>>> in defining cpu_capacity, isn't it?
>
> However, I still think that higher priority classes eclipsing the
> clamping of lower priority classes can still be a problem.
>
> In your example above, the main difference between TA and TB being on
> the same class or different classes is that in the second case TB
> is granted to always preempt TA. We can end up with a non boosted RT
> task consuming all the boosted bandwidth required by a CFS task.
>
> This does not happen, apart maybe for the corner case of really
> different nice values, if the tasks are both CFS, since the fair
> scheduler will grant some progress for both of them.
>
> Thus, given the current implementation, I think it makes sense to drop
> the UCLAMP_SCHED_CLASS policy and stick with a more clean and
> consistent design.
I agree with everything said in this thread so far.
So in case you skip UCLAMP_SCHED_CLASS [(B) combine the clamped
utilizations] in v4, you will only provide [A) clamp the combined
utilization]?
I assume that we don't have to guard the util clamping for rt tasks
behind a disabled by default sched feature because all runnable rt tasks
will have util_min = SCHED_CAPACITY_SCALE by default?
> I'll then see if it makes sense to add a dedicated patch on top of the
> series to add a proper per-class clamp tracking.
I assume if you introduce this per-class clamping you will switch to use
the UCLAMP_SCHED_CLASS approach?
next prev parent reply other threads:[~2018-08-16 10:34 UTC|newest]
Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-08-06 16:39 [PATCH v3 00/14] Add utilization clamping support Patrick Bellasi
2018-08-06 16:39 ` [PATCH v3 01/14] sched/core: uclamp: extend sched_setattr to support utilization clamping Patrick Bellasi
2018-08-06 16:50 ` Randy Dunlap
2018-08-09 8:39 ` Patrick Bellasi
2018-08-09 15:20 ` Randy Dunlap
2018-08-07 9:59 ` Juri Lelli
2018-08-13 12:14 ` Patrick Bellasi
2018-08-13 12:27 ` Juri Lelli
2018-08-07 12:35 ` Juri Lelli
2018-08-09 9:14 ` Patrick Bellasi
2018-08-09 9:50 ` Juri Lelli
2018-08-09 15:23 ` Patrick Bellasi
2018-08-10 7:50 ` Juri Lelli
2018-08-17 10:34 ` Quentin Perret
2018-08-17 10:57 ` Patrick Bellasi
2018-08-17 11:14 ` Quentin Perret
2018-08-06 16:39 ` [PATCH v3 02/14] sched/core: uclamp: map TASK's clamp values into CPU's clamp groups Patrick Bellasi
2018-08-14 11:25 ` Pavan Kondeti
2018-08-14 15:21 ` Patrick Bellasi
2018-08-06 16:39 ` [PATCH v3 03/14] sched/core: uclamp: add CPU's clamp groups accounting Patrick Bellasi
2018-08-14 15:44 ` Dietmar Eggemann
2018-08-14 16:49 ` Patrick Bellasi
2018-08-15 9:37 ` Dietmar Eggemann
2018-08-15 10:54 ` Patrick Bellasi
2018-08-15 10:59 ` Dietmar Eggemann
2018-08-16 13:32 ` Patrick Bellasi
2018-08-16 13:37 ` Quentin Perret
2018-08-16 13:45 ` Dietmar Eggemann
2018-08-16 14:21 ` Quentin Perret
2018-08-16 15:00 ` Dietmar Eggemann
2018-08-17 11:04 ` Patrick Bellasi
2018-08-06 16:39 ` [PATCH v3 04/14] sched/core: uclamp: update CPU's refcount on clamp changes Patrick Bellasi
2018-08-15 15:02 ` Dietmar Eggemann
2018-08-16 13:22 ` Patrick Bellasi
2018-08-06 16:39 ` [PATCH v3 05/14] sched/cpufreq: uclamp: add utilization clamping for FAIR tasks Patrick Bellasi
2018-08-08 13:18 ` Vincent Guittot
2018-08-09 15:30 ` Patrick Bellasi
2018-08-15 15:30 ` Dietmar Eggemann
2018-08-16 13:53 ` Patrick Bellasi
2018-08-06 16:39 ` [PATCH v3 06/14] sched/cpufreq: uclamp: add utilization clamping for RT tasks Patrick Bellasi
2018-08-07 13:26 ` Juri Lelli
2018-08-09 15:34 ` Patrick Bellasi
2018-08-09 16:03 ` Vincent Guittot
2018-08-13 10:12 ` Patrick Bellasi
2018-08-13 10:50 ` Juri Lelli
2018-08-13 12:07 ` Vincent Guittot
2018-08-13 12:09 ` Vincent Guittot
2018-08-13 12:49 ` Patrick Bellasi
2018-08-13 14:06 ` Vincent Guittot
2018-08-13 15:01 ` Patrick Bellasi
2018-08-16 10:34 ` Dietmar Eggemann [this message]
2018-08-16 13:40 ` Patrick Bellasi
2018-08-07 13:54 ` Quentin Perret
2018-08-09 15:41 ` Patrick Bellasi
2018-08-09 15:55 ` Quentin Perret
2018-08-13 10:17 ` Patrick Bellasi
2018-08-06 16:39 ` [PATCH v3 07/14] sched/core: uclamp: enforce last task UCLAMP_MAX Patrick Bellasi
2018-08-16 15:43 ` Dietmar Eggemann
2018-08-16 16:47 ` Patrick Bellasi
2018-08-16 17:10 ` Dietmar Eggemann
2018-08-16 17:27 ` Patrick Bellasi
2018-08-16 17:20 ` Patrick Bellasi
2018-08-06 16:39 ` [PATCH v3 08/14] sched/core: uclamp: extend cpu's cgroup controller Patrick Bellasi
2018-08-17 12:21 ` Dietmar Eggemann
2018-08-17 14:24 ` Patrick Bellasi
2018-08-06 16:39 ` [PATCH v3 09/14] sched/core: uclamp: propagate parent clamps Patrick Bellasi
2018-08-16 9:09 ` Pavan Kondeti
2018-08-16 14:07 ` Patrick Bellasi
2018-08-17 13:43 ` Dietmar Eggemann
2018-08-17 14:45 ` Patrick Bellasi
2018-08-17 15:50 ` Dietmar Eggemann
2018-08-20 10:01 ` Dietmar Eggemann
2018-08-20 12:28 ` Patrick Bellasi
2018-08-06 16:39 ` [PATCH v3 10/14] sched/core: uclamp: map TG's clamp values into CPU's clamp groups Patrick Bellasi
2018-08-06 16:39 ` [PATCH v3 11/14] sched/core: uclamp: use TG's clamps to restrict Task's clamps Patrick Bellasi
2018-08-06 16:39 ` [PATCH v3 12/14] sched/core: uclamp: add system default clamps Patrick Bellasi
2018-08-16 9:13 ` Pavan Kondeti
2018-08-16 14:37 ` Patrick Bellasi
2018-08-20 10:18 ` Dietmar Eggemann
2018-08-20 12:27 ` Patrick Bellasi
2018-08-06 16:39 ` [PATCH v3 13/14] sched/core: uclamp: update CPU's refcount on TG's clamp changes Patrick Bellasi
2018-08-06 16:39 ` [PATCH v3 14/14] sched/core: uclamp: use percentage clamp values 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=1b72b94c-5411-4b95-01a6-49ac978acbd5@arm.com \
--to=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=patrick.bellasi@arm.com \
--cc=peterz@infradead.org \
--cc=pjt@google.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).