From: Joel Fernandes <joel@joelfernandes.org>
To: Daniel Bristot de Oliveira <bristot@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Juri Lelli <juri.lelli@redhat.com>,
Vincent Guittot <vincent.guittot@linaro.org>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Steven Rostedt <rostedt@goodmis.org>,
Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
Daniel Bristot de Oliveira <bristot@redhat.com>,
Valentin Schneider <vschneid@redhat.com>,
linux-kernel@vger.kernel.org,
Luca Abeni <luca.abeni@santannapisa.it>,
Tommaso Cucinotta <tommaso.cucinotta@santannapisa.it>,
Thomas Gleixner <tglx@linutronix.de>,
Vineeth Pillai <vineeth@bitbyteword.org>,
Shuah Khan <skhan@linuxfoundation.org>,
Phil Auld <pauld@redhat.com>
Subject: Re: [PATCH v5 6/7] sched/deadline: Deferrable dl server
Date: Wed, 8 Nov 2023 02:42:16 +0000 [thread overview]
Message-ID: <20231108024216.GB2992223@google.com> (raw)
In-Reply-To: <d6811957-1cb7-489d-a3da-f38622d7f515@kernel.org>
On Tue, Nov 07, 2023 at 12:58:48PM +0100, Daniel Bristot de Oliveira wrote:
[...]
> >> One more consideration I guess is, because the server is throttled
> >> till 0-laxity time, it is possible that if CFS sleeps even a bit
> >> (after the DL-server is unthrottled), then it will be pushed out to a
> >> full current deadline + period due to CBS. In such a situation, if
> >> CFS-server is the only DL task running, it might starve RT for a bit
> >> more time.
> >>
> >> Example, say CFS runtime is 0.3s and period is 1s. At 0.7s, 0-laxity
> >> timer fires. CFS runs for 0.29s, then sleeps for 0.005s and wakes up
> >> at 0.295s (its remaining runtime is 0.01s at this point which is < the
> >> "time till deadline" of 0.005s). Now the runtime of the CFS-server
> >> will be replenished to the full 3s (due to CBS) and the deadline
> >> pushed out. The end result is the total runtime that the CFS-server
> >> actually gets is 0.0595s (though yes it did sleep for 5ms in between,
> >> still that's tiny -- say if it briefly blocked on a kernel mutex).
> >
> > Blah, I got lost in decimal points. Here's the example again:
> >
> > Say CFS-server runtime is 0.3s and period is 1s.
> >
> > At 0.7s, 0-laxity timer fires. CFS runs for 0.29s, then sleeps for
> > 0.005s and wakes up at 0.295s (its remaining runtime is 0.01s at this
> > point which is < the "time till deadline" of 0.005s)
> >
> > Now the runtime of the CFS-server will be replenished to the full 0.3s
> > (due to CBS) and the deadline
> > pushed out.
> >
> > The end result is, the total runtime that the CFS-server actually gets
> > is 0.595s (though yes it did sleep for 5ms in between, still that's
> > tiny -- say if it briefly blocked on a kernel mutex). That's almost
> > double the allocated runtime.
>
> I think I got what you mean, and I think I took for granted that we were
> doing overload control on the replenishment, but it seems that we are not..
>
> I just got back from a doct appt, I will do a proper reply later today.
Ah ok! Thanks Daniel! And hope the appointment went well.
- Joel
next prev parent reply other threads:[~2023-11-08 2:42 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-11-04 10:59 [PATCH v5 0/7] SCHED_DEADLINE server infrastructure Daniel Bristot de Oliveira
2023-11-04 10:59 ` [PATCH v5 1/7] sched: Unify runtime accounting across classes Daniel Bristot de Oliveira
2023-11-15 9:04 ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2023-11-04 10:59 ` [PATCH v5 2/7] sched/deadline: Collect sched_dl_entity initialization Daniel Bristot de Oliveira
2023-11-15 9:04 ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2023-11-04 10:59 ` [PATCH v5 3/7] sched/deadline: Move bandwidth accounting into {en,de}queue_dl_entity Daniel Bristot de Oliveira
2023-11-15 9:04 ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2023-11-04 10:59 ` [PATCH v5 4/7] sched/deadline: Introduce deadline servers Daniel Bristot de Oliveira
2023-11-15 9:04 ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2023-11-04 10:59 ` [PATCH v5 5/7] sched/fair: Add trivial fair server Daniel Bristot de Oliveira
2023-11-06 14:24 ` Peter Zijlstra
2023-11-06 14:26 ` Daniel Bristot de Oliveira
2023-11-04 10:59 ` [PATCH v5 6/7] sched/deadline: Deferrable dl server Daniel Bristot de Oliveira
2023-11-06 14:55 ` Peter Zijlstra
2023-11-06 17:05 ` Daniel Bristot de Oliveira
2023-11-06 19:32 ` Joel Fernandes
2023-11-06 21:32 ` Joel Fernandes
2023-11-06 21:37 ` Joel Fernandes
2023-11-07 11:58 ` Daniel Bristot de Oliveira
2023-11-08 2:42 ` Joel Fernandes [this message]
2023-11-07 16:47 ` Steven Rostedt
2023-11-07 17:35 ` Steven Rostedt
2023-11-07 17:46 ` Steven Rostedt
2023-11-07 17:54 ` Steven Rostedt
2023-11-07 19:32 ` Steven Rostedt
2023-11-07 20:07 ` Steven Rostedt
2023-11-07 17:37 ` Daniel Bristot de Oliveira
2023-11-07 18:50 ` Daniel Bristot de Oliveira
2023-11-08 3:20 ` Joel Fernandes
2023-11-08 8:01 ` Daniel Bristot de Oliveira
2023-11-08 18:25 ` Joel Fernandes
2023-11-08 12:44 ` Peter Zijlstra
2023-11-08 12:50 ` Peter Zijlstra
2023-11-08 14:52 ` Daniel Bristot de Oliveira
2023-11-08 13:46 ` Daniel Bristot de Oliveira
2023-11-08 13:58 ` Daniel Bristot de Oliveira
2023-11-08 15:14 ` Juri Lelli
2023-11-08 16:57 ` Peter Zijlstra
2023-11-08 2:37 ` Joel Fernandes
2023-11-07 7:30 ` Daniel Bristot de Oliveira
2023-11-07 16:37 ` Steven Rostedt
2023-11-13 15:05 ` kernel test robot
2024-03-20 0:03 ` Joel Fernandes
2024-03-20 19:24 ` Daniel Bristot de Oliveira
2024-03-21 16:15 ` Joel Fernandes
2024-03-23 14:37 ` Joel Fernandes
2024-04-05 14:35 ` Daniel Bristot de Oliveira
2024-04-08 17:11 ` Steven Rostedt
2023-11-04 10:59 ` [PATCH v5 7/7] sched/fair: Fair server interface Daniel Bristot de Oliveira
2023-11-04 15:18 ` kernel test robot
2023-11-05 0:55 ` kernel test robot
2023-11-06 15:40 ` Peter Zijlstra
2023-11-06 16:29 ` Daniel Bristot de Oliveira
2023-11-07 8:16 ` Peter Zijlstra
2023-11-07 14:06 ` Daniel Bristot de Oliveira
2023-11-07 14:44 ` Peter Zijlstra
2023-11-07 12:38 ` Peter Zijlstra
2023-11-07 13:24 ` Daniel Bristot de Oliveira
2024-01-19 1:49 ` Joel Fernandes
2024-01-19 1:55 ` Joel Fernandes
2024-01-22 14:14 ` Daniel Bristot de Oliveira
2024-01-23 15:39 ` Joel Fernandes
2024-01-23 15:44 ` Joel Fernandes
2024-02-13 2:13 ` Joel Fernandes
2024-02-13 2:21 ` Joel Fernandes
2024-02-14 14:23 ` Daniel Bristot de Oliveira
2024-02-15 13:57 ` Joel Fernandes
2024-02-15 17:27 ` Daniel Bristot de Oliveira
2024-02-15 17:41 ` Joel Fernandes
2024-04-04 17:43 ` Daniel Bristot de Oliveira
2023-12-08 21:47 ` [PATCH v5 0/7] SCHED_DEADLINE server infrastructure Joel Fernandes
2024-02-19 7:33 ` Huang, Ying
2024-02-19 10:23 ` Daniel Bristot de Oliveira
2024-02-20 3:28 ` Huang, Ying
2024-02-20 8:31 ` Daniel Bristot de Oliveira
2024-02-20 8:41 ` Huang, Ying
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=20231108024216.GB2992223@google.com \
--to=joel@joelfernandes.org \
--cc=bristot@kernel.org \
--cc=bristot@redhat.com \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luca.abeni@santannapisa.it \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=pauld@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=skhan@linuxfoundation.org \
--cc=tglx@linutronix.de \
--cc=tommaso.cucinotta@santannapisa.it \
--cc=vincent.guittot@linaro.org \
--cc=vineeth@bitbyteword.org \
--cc=vschneid@redhat.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