From: Peter Zijlstra <peterz@infradead.org>
To: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Ingo Molnar <mingo@kernel.org>,
linux-kernel <linux-kernel@vger.kernel.org>,
Tejun Heo <tj@kernel.org>, Josef Bacik <josef@toxicpanda.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Mike Galbraith <efault@gmx.de>, Paul Turner <pjt@google.com>,
Chris Mason <clm@fb.com>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Morten Rasmussen <morten.rasmussen@arm.com>,
Ben Segall <bsegall@google.com>, Yuyang Du <yuyang.du@intel.com>
Subject: Re: [PATCH -v2 12/18] sched/fair: Rewrite PELT migration propagation
Date: Tue, 10 Oct 2017 09:29:45 +0200 [thread overview]
Message-ID: <20171010072945.rjeuripvfksfpdcf@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <CAKfTPtAZqVbMKkSaH8TNVinykR4-dhZuOLr9DOOGt_toPqzeuw@mail.gmail.com>
On Mon, Oct 09, 2017 at 05:29:04PM +0200, Vincent Guittot wrote:
> On 9 October 2017 at 17:03, Vincent Guittot <vincent.guittot@linaro.org> wrote:
> > On 1 September 2017 at 15:21, Peter Zijlstra <peterz@infradead.org> wrote:
> >> +/*
> >> + * When on migration a sched_entity joins/leaves the PELT hierarchy, we need to
> >> + * propagate its contribution. The key to this propagation is the invariant
> >> + * that for each group:
> >> + *
> >> + * ge->avg == grq->avg (1)
> >> + *
> >> + * _IFF_ we look at the pure running and runnable sums. Because they
> >> + * represent the very same entity, just at different points in the hierarchy.
> >
> > I agree for the running part because only one entity can be running
> > but i'm not sure for the pure runnable sum because we can have
> > several runnable task in a cfs_rq but only one runnable group entity
> > to reflect them or I misunderstand (1)
The idea is that they (ge and grq) are the _same_ entity, just at
different levels in the hierarchy. If the grq is runnable, it is through
the ge.
As a whole, they don't care how many runnable tasks there are.
> > As an example, we have 2 always running task TA and TB so their
> > load_sum is LOAD_AVG_MAX for each task The grq->avg.load_sum = \Sum
> > se->avg.load_sum = 2*LOAD_AVG_MAX But the ge->avg.load_sum will be
> > only LOAD_AVG_MAX
> >
> > So If we apply directly the d(TB->avg.load_sum) on the group hierachy
> > and on ge->avg.load_sum in particular, the latter decreases to 0
> > whereas it should decrease only by half
> >
> > I have been able to see this wrong behavior with a rt-app json file
> >
> > so I think that we should instead remove only
> >
> > delta = se->avg.load_sum / grq->avg.load_sum * ge->avg.load_sum
>
> delta = se->avg.load_sum / (grq->avg.load_sum+se->avg.load_sum) *
> ge->avg.load_sum
>
> as the se has already been detached
>
> > We don't have grq->avg.load_sum but we can have a rough estimate with
> > grq->avg.load_avg/grq->weight
Hurm, I think I see what you're saying, let me ponder this more.
next prev parent reply other threads:[~2017-10-10 7:30 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-09-01 13:20 [PATCH -v2 00/18] sched/fair: A bit of a cgroup/PELT overhaul Peter Zijlstra
2017-09-01 13:21 ` [PATCH -v2 01/18] sched/fair: Clean up calc_cfs_shares() Peter Zijlstra
2017-09-01 13:21 ` [PATCH -v2 02/18] sched/fair: Add comment to calc_cfs_shares() Peter Zijlstra
2017-09-28 10:03 ` Morten Rasmussen
2017-09-29 11:35 ` Peter Zijlstra
2017-09-29 13:03 ` Morten Rasmussen
2017-09-01 13:21 ` [PATCH -v2 03/18] sched/fair: Cure calc_cfs_shares() vs reweight_entity() Peter Zijlstra
2017-09-29 9:04 ` Morten Rasmussen
2017-09-29 11:38 ` Peter Zijlstra
2017-09-29 13:00 ` Morten Rasmussen
2017-09-01 13:21 ` [PATCH -v2 04/18] sched/fair: Remove se->load.weight from se->avg.load_sum Peter Zijlstra
2017-09-29 15:26 ` Morten Rasmussen
2017-09-29 16:39 ` Peter Zijlstra
2017-09-01 13:21 ` [PATCH -v2 05/18] sched/fair: Change update_load_avg() arguments Peter Zijlstra
2017-09-01 13:21 ` [PATCH -v2 06/18] sched/fair: Move enqueue migrate handling Peter Zijlstra
2017-09-01 13:21 ` [PATCH -v2 07/18] sched/fair: Rename {en,de}queue_entity_load_avg() Peter Zijlstra
2017-09-01 13:21 ` [PATCH -v2 08/18] sched/fair: Introduce {en,de}queue_load_avg() Peter Zijlstra
2017-09-01 13:21 ` [PATCH -v2 09/18] sched/fair: More accurate reweight_entity() Peter Zijlstra
2017-09-01 13:21 ` [PATCH -v2 10/18] sched/fair: Use reweight_entity() for set_user_nice() Peter Zijlstra
2017-09-01 13:21 ` [PATCH -v2 11/18] sched/fair: Rewrite cfs_rq->removed_*avg Peter Zijlstra
2017-09-01 13:21 ` [PATCH -v2 12/18] sched/fair: Rewrite PELT migration propagation Peter Zijlstra
2017-10-09 8:08 ` Morten Rasmussen
2017-10-09 9:45 ` Peter Zijlstra
2017-10-18 12:45 ` Morten Rasmussen
2017-10-30 13:35 ` Peter Zijlstra
2017-10-09 15:03 ` Vincent Guittot
2017-10-09 15:29 ` Vincent Guittot
2017-10-10 7:29 ` Peter Zijlstra [this message]
2017-10-10 7:44 ` Vincent Guittot
2017-10-13 15:22 ` Vincent Guittot
2017-10-13 20:41 ` Peter Zijlstra
2017-10-15 12:01 ` Vincent Guittot
2017-10-16 13:55 ` Vincent Guittot
2017-10-19 15:04 ` Vincent Guittot
2017-10-30 17:20 ` Peter Zijlstra
2017-10-31 11:14 ` Vincent Guittot
2017-10-31 15:01 ` Peter Zijlstra
2017-10-31 16:38 ` Vincent Guittot
2017-11-16 14:09 ` [PATCH v3] sched: Update runnable propagation rule Vincent Guittot
2017-11-16 14:21 ` [PATCH v4] " Vincent Guittot
2017-12-06 11:40 ` Peter Zijlstra
2017-12-06 17:10 ` Ingo Molnar
2017-12-06 20:29 ` [tip:sched/core] sched/fair: Update and fix the " tip-bot for Vincent Guittot
2017-09-01 13:21 ` [PATCH -v2 13/18] sched/fair: Propagate an effective runnable_load_avg Peter Zijlstra
2017-10-02 17:46 ` Dietmar Eggemann
2017-10-03 8:50 ` Peter Zijlstra
2017-10-03 9:29 ` Dietmar Eggemann
2017-10-03 12:26 ` Dietmar Eggemann
2017-09-01 13:21 ` [PATCH -v2 14/18] sched/fair: Synchonous PELT detach on load-balance migrate Peter Zijlstra
2017-09-01 13:21 ` [PATCH -v2 15/18] sched/fair: Align PELT windows between cfs_rq and its se Peter Zijlstra
2017-10-04 19:27 ` Dietmar Eggemann
2017-10-06 13:02 ` Peter Zijlstra
2017-10-09 12:15 ` Dietmar Eggemann
2017-10-09 12:19 ` Peter Zijlstra
2017-09-01 13:21 ` [PATCH -v2 16/18] sched/fair: More accurate async detach Peter Zijlstra
2017-09-01 13:21 ` [PATCH -v2 17/18] sched/fair: Calculate runnable_weight slightly differently Peter Zijlstra
2017-09-01 13:21 ` [PATCH -v2 18/18] sched/fair: Update calc_group_*() comments 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=20171010072945.rjeuripvfksfpdcf@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=bsegall@google.com \
--cc=clm@fb.com \
--cc=dietmar.eggemann@arm.com \
--cc=efault@gmx.de \
--cc=josef@toxicpanda.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=morten.rasmussen@arm.com \
--cc=pjt@google.com \
--cc=tj@kernel.org \
--cc=torvalds@linux-foundation.org \
--cc=vincent.guittot@linaro.org \
--cc=yuyang.du@intel.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).