From: Vincent Guittot <vincent.guittot@linaro.org>
To: Valentin Schneider <valentin.schneider@arm.com>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
gaku.inami.xh@renesas.com,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCHv4 12/12] sched/core: Disable SD_PREFER_SIBLING on asymmetric cpu capacity domains
Date: Fri, 10 Aug 2018 11:30:18 +0200 [thread overview]
Message-ID: <CAKfTPtCfzpbcxzbMiOxd3kXWaES2+ai6vUEXET0++5W-mWDUdA@mail.gmail.com> (raw)
In-Reply-To: <b7c78d65-ab85-36ce-6da6-d10e5113c4a3@arm.com>
On Mon, 6 Aug 2018 at 12:53, Valentin Schneider
<valentin.schneider@arm.com> wrote:
>
> Hi,
>
> On 06/08/18 11:20, Vincent Guittot wrote:
> > Hi Valentin,
> >
> > On Tue, 31 Jul 2018 at 14:33, Valentin Schneider
> > <valentin.schneider@arm.com> wrote:
> >>
> >> Hi,
> >>
> >> On 31/07/18 13:17, Vincent Guittot wrote:
> >> [...]
> >>>>
> >>>> This can easily happen with SD_PREFER_SIBLING enabled too so I wouldn't
> >>>> say that this patch breaks anything that isn't broken already. In fact
> >>>> we this happening with and without this patch applied.
> >>>
> >>> At least for the use case above, this doesn't happen when
> >>> SD_PREFER_SIBLING is set
> >>>
> >>
> >> On my HiKey960 I can see coscheduling on a big CPU while a LITTLE is free
> >> with **and** without SD_PREFER_SIBLING. Having it set only means that in
> >> some cases the imbalance will be re-classified as group_overloaded instead
> >> of group_misfit_task, so we'll skip the misfit logic when we shouldn't (this
> >> happens on Juno for instance).
> >
> > Can you give more details about your test case ?
> >
>
> I've been running the same test case as presented in the cover letter on
> my HiKey960 but with sched_switch tracing and with no tasksets. I've just
> re-run the testcase with tasksets and I get similar results (i.e. a big
> with coscheduling while a LITTLE is free) with or without the flag.
>
> >>
> >> It does nothing for the "1 task per CPU" problem that Morten described above.
> >> When you have this little amount of tasks, load isn't very relevant, but it
> >> skews the load-balancer into thinking the LITTLE CPUs are more busy than
> >> the bigs even though there's an idle one in the lot.
ok. I meant that without misfit patch, SD_PREFER_SIBLING ensures 1
task per CPU and no co scheduling. But co scheduling appears with
misfit task patchset
Vincent
> >>
> >>>>
> >>>> Morten
next prev parent reply other threads:[~2018-08-10 9:30 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-04 10:17 [PATCHv4 00/12] sched/fair: Migrate 'misfit' tasks on asymmetric capacity systems Morten Rasmussen
2018-07-04 10:17 ` [PATCHv4 01/12] sched: Add static_key for asymmetric cpu capacity optimizations Morten Rasmussen
2018-07-31 10:59 ` Peter Zijlstra
2018-08-02 15:15 ` Morten Rasmussen
2018-09-10 10:13 ` [tip:sched/core] sched/topology: Add static_key for asymmetric CPU " tip-bot for Morten Rasmussen
2018-07-04 10:17 ` [PATCHv4 02/12] sched/fair: Add group_misfit_task load-balance type Morten Rasmussen
2018-09-10 10:13 ` [tip:sched/core] sched/fair: Add 'group_misfit_task' " tip-bot for Morten Rasmussen
2018-07-04 10:17 ` [PATCHv4 03/12] sched: Add sched_group per-cpu max capacity Morten Rasmussen
2018-09-10 10:14 ` [tip:sched/core] sched/fair: Add sched_group per-CPU " tip-bot for Morten Rasmussen
2018-07-04 10:17 ` [PATCHv4 04/12] sched/fair: Consider misfit tasks when load-balancing Morten Rasmussen
2018-09-10 10:14 ` [tip:sched/core] " tip-bot for Morten Rasmussen
2018-07-04 10:17 ` [PATCHv4 05/12] sched/fair: Kick nohz balance if rq->misfit_task_load Morten Rasmussen
2018-09-10 10:15 ` [tip:sched/core] " tip-bot for Valentin Schneider
2018-07-04 10:17 ` [PATCHv4 06/12] sched/fair: Change prefer_sibling type to bool Morten Rasmussen
2018-09-10 10:15 ` [tip:sched/core] sched/fair: Change 'prefer_sibling' " tip-bot for Valentin Schneider
2018-07-04 10:17 ` [PATCHv4 07/12] sched: Change root_domain->overload type to int Morten Rasmussen
2018-09-10 10:16 ` [tip:sched/core] sched/core: " tip-bot for Valentin Schneider
2018-07-04 10:17 ` [PATCHv4 08/12] sched: Wrap rq->rd->overload accesses with READ/WRITE_ONCE Morten Rasmussen
2018-09-10 10:17 ` [tip:sched/core] sched/fair: Wrap rq->rd->overload accesses with READ/WRITE_ONCE() tip-bot for Valentin Schneider
2018-07-04 10:17 ` [PATCHv4 09/12] sched/fair: Set rq->rd->overload when misfit Morten Rasmussen
2018-09-10 10:17 ` [tip:sched/core] " tip-bot for Valentin Schneider
2018-07-04 10:17 ` [PATCHv4 10/12] sched/fair: Don't move tasks to lower capacity cpus unless necessary Morten Rasmussen
2018-09-10 10:18 ` [tip:sched/core] sched/fair: Don't move tasks to lower capacity CPUs " tip-bot for Chris Redpath
2018-07-04 10:17 ` [PATCHv4 11/12] sched/core: Disable SD_ASYM_CPUCAPACITY for root_domains without asymmetry Morten Rasmussen
2018-07-05 13:31 ` Quentin Perret
2018-07-05 14:13 ` Morten Rasmussen
2018-07-05 15:03 ` Quentin Perret
2018-07-20 13:54 ` Morten Rasmussen
2018-07-04 10:17 ` [PATCHv4 12/12] sched/core: Disable SD_PREFER_SIBLING on asymmetric cpu capacity domains Morten Rasmussen
2018-07-06 10:18 ` Vincent Guittot
2018-07-06 14:31 ` Morten Rasmussen
2018-07-31 12:17 ` Vincent Guittot
2018-07-31 12:33 ` Valentin Schneider
2018-08-06 10:20 ` Vincent Guittot
2018-08-06 10:53 ` Valentin Schneider
2018-08-10 9:30 ` Vincent Guittot [this message]
2018-09-10 10:18 ` [tip:sched/core] sched/core: Disable SD_PREFER_SIBLING on asymmetric CPU " tip-bot for Morten Rasmussen
2018-07-06 10:18 ` [PATCHv4 00/12] sched/fair: Migrate 'misfit' tasks on asymmetric capacity systems Vincent Guittot
2018-07-09 15:08 ` Morten Rasmussen
2018-07-26 17:14 ` Valentin Schneider
2018-07-30 14:30 ` Dietmar Eggemann
2018-07-31 12:13 ` Vincent Guittot
2018-07-31 12:14 ` Dietmar Eggemann
2018-07-31 12:11 ` Vincent Guittot
2018-07-31 12:00 ` Peter Zijlstra
2018-07-31 12:10 ` Valentin Schneider
2018-07-31 12:50 ` Morten Rasmussen
2018-08-17 1:57 ` Joel Fernandes
2018-08-20 2:50 ` Gaku Inami
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=CAKfTPtCfzpbcxzbMiOxd3kXWaES2+ai6vUEXET0++5W-mWDUdA@mail.gmail.com \
--to=vincent.guittot@linaro.org \
--cc=dietmar.eggemann@arm.com \
--cc=gaku.inami.xh@renesas.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=morten.rasmussen@arm.com \
--cc=peterz@infradead.org \
--cc=valentin.schneider@arm.com \
/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).