All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: mingo@kernel.org, mgorman@suse.de, juri.lelli@redhat.com,
	vincent.guittot@linaro.org, rostedt@goodmis.org,
	bsegall@google.com, bristot@redhat.com, joshdon@google.com,
	valentin.schneider@arm.com, linux-kernel@vger.kernel.org,
	greg@kroah.com
Subject: Re: [PATCH 9/9] sched,fair: Alternative sched_slice()
Date: Fri, 26 Mar 2021 15:07:06 +0100	[thread overview]
Message-ID: <20210326140706.GH4746@worktop.programming.kicks-ass.net> (raw)
In-Reply-To: <6c36c39a-d2da-a110-3f83-fda70a73a1fd@arm.com>

On Fri, Mar 26, 2021 at 01:08:44PM +0100, Dietmar Eggemann wrote:
> On 26/03/2021 11:34, Peter Zijlstra wrote:
> > The current sched_slice() seems to have issues; there's two possible
> > things that could be improved:
> > 
> >  - the 'nr_running' used for __sched_period() is daft when cgroups are
> >    considered. Using the RQ wide h_nr_running seems like a much more
> >    consistent number.
> > 
> >  - (esp) cgroups can slice it real fine, which makes for easy
> >    over-scheduling, ensure min_gran is what the name says.
> 
> So ALT_PERIOD considers all runnable CFS tasks now and BASE_SLICE
> guarantees min_gran as a floor for cgroup (hierarchies) with small
> weight value(s)?

Pretty much.

The previous cfs_rq->nr_running is just how many runnable thingies there
are in whatever cgroup you happen to be in on our CPU, not counting its
child cgroups nor whatever is upwards. Which is a pretty arbitrary
value.

By always using h_nr_running of the root, we get a consistent number and
the period is the same for all tasks on the CPU.

And yes, low weight cgroups, or even just a nice -20 and 19 task
together would result in *tiny* slices, which then leads to
over-scheduling. So by only scaling the part between period and
min_gran, we still get a variable slice, but also avoid the worst cases.


  reply	other threads:[~2021-03-26 14:09 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-26 10:33 [PATCH 0/9] sched: Clean up SCHED_DEBUG Peter Zijlstra
2021-03-26 10:33 ` [PATCH 1/9] sched/numa: Allow runtime enabling/disabling of NUMA balance without SCHED_DEBUG Peter Zijlstra
2021-03-26 10:33 ` [PATCH 2/9] sched: Remove sched_schedstats sysctl out from under SCHED_DEBUG Peter Zijlstra
2021-03-26 10:33 ` [PATCH 3/9] sched: Dont make LATENCYTOP select SCHED_DEBUG Peter Zijlstra
2021-03-26 10:33 ` [PATCH 4/9] sched: Move SCHED_DEBUG to debugfs Peter Zijlstra
2021-03-26 11:06   ` Greg KH
2021-04-07 10:46   ` Valentin Schneider
2021-04-07 12:26     ` Peter Zijlstra
2021-04-07 12:57       ` Valentin Schneider
2021-03-26 10:33 ` [PATCH 5/9] sched,preempt: Move preempt_dynamic to debug.c Peter Zijlstra
2021-03-26 10:33 ` [PATCH 6/9] debugfs: Implement debugfs_create_str() Peter Zijlstra
2021-03-26 11:05   ` Greg KH
2021-03-26 11:18     ` Peter Zijlstra
2021-03-26 11:30       ` Greg KH
2021-03-26 11:38         ` [PATCH v2 " Peter Zijlstra
2021-03-26 12:18           ` Greg KH
2021-03-26 12:53           ` Rasmus Villemoes
2021-03-26 12:57             ` Greg KH
2021-03-26 13:10               ` Rasmus Villemoes
2021-03-26 14:12                 ` Peter Zijlstra
2021-03-26 14:19                   ` Greg KH
2021-03-26 14:22             ` Peter Zijlstra
2021-03-26 14:58               ` Rasmus Villemoes
2021-03-26 15:19                 ` Peter Zijlstra
2021-03-27 10:41                   ` Greg KH
2021-03-26 14:50   ` [PATCH v3 " Peter Zijlstra
2021-03-27 10:42     ` Greg KH
2021-03-27 22:24   ` [PATCH " Al Viro
2021-03-28  0:33     ` Steven Rostedt
2021-03-26 10:33 ` [PATCH 7/9] sched,debug: Convert sysctl sched_domains to debugfs Peter Zijlstra
2021-03-26 13:11   ` Dietmar Eggemann
2021-04-07 10:46   ` Valentin Schneider
2021-04-07 12:18     ` Peter Zijlstra
2021-03-26 10:34 ` [PATCH 8/9] sched: Move /proc/sched_debug " Peter Zijlstra
2021-03-26 11:05   ` Greg KH
2021-03-26 10:34 ` [PATCH 9/9] sched,fair: Alternative sched_slice() Peter Zijlstra
2021-03-26 12:08   ` Dietmar Eggemann
2021-03-26 14:07     ` Peter Zijlstra [this message]
2021-03-26 15:37   ` Vincent Guittot
2021-03-26 18:30     ` Peter Zijlstra

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=20210326140706.GH4746@worktop.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=bristot@redhat.com \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=greg@kroah.com \
    --cc=joshdon@google.com \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=valentin.schneider@arm.com \
    --cc=vincent.guittot@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.