From: Con Kolivas <kernel@kolivas.org>
To: utz lehmann <lkml@s2y4n2c.de>
Cc: LKML <linux-kernel@vger.kernel.org>, Ingo Molnar <mingo@elte.hu>,
rlrevell@joe-job.com, paul@linuxaudiosystems.com, joq@io.com,
CK Kernel <ck@vds.kolivas.org>, Andrew Morton <akpm@osdl.org>,
alexn@dsv.su.se
Subject: Re: [PATCH]sched: Isochronous class v2 for unprivileged soft rt scheduling
Date: Sat, 22 Jan 2005 10:48:44 +1100 [thread overview]
Message-ID: <41F194DC.40603@kolivas.org> (raw)
In-Reply-To: <1106350245.4442.5.camel@segv.aura.of.mankind>
[-- Attachment #1: Type: text/plain, Size: 894 bytes --]
utz lehmann wrote:
> Hi
>
> I dislike the behavior of the SCHED_ISO patch that iso tasks are
> degraded to SCHED_NORMAL if they exceed the limit.
> IMHO it's better to throttle them at the iso_cpu limit.
>
> I have modified Con's iso2 patch to do this. If iso_cpu > 50 iso tasks
> only get stalled for 1 tick (1ms on x86).
Some tasks are so cache intensive they would make almost no forward
progress running for only 1ms.
> Fortunately there is a currently unused task prio (MAX_RT_PRIO-1) [1]. I
Your implementation is not correct. The "prio" field of real time tasks
is determined by MAX_RT_PRIO-1-rt_priority. Therefore you're limiting
the best real time priority, not the other way around.
Throttling them for only 1ms will make it very easy to starve the system
with 1 or more short running (<1ms) SCHED_NORMAL tasks running. Lower
priority tasks will never run.
Cheers,
Con
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 256 bytes --]
next prev parent reply other threads:[~2005-01-21 23:53 UTC|newest]
Thread overview: 198+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-01-19 22:39 [PATCH]sched: Isochronous class v2 for unprivileged soft rt scheduling Con Kolivas
2005-01-20 0:16 ` utz lehmann
2005-01-20 0:33 ` Con Kolivas
2005-01-20 4:26 ` utz lehmann
2005-01-20 5:55 ` Con Kolivas
2005-01-20 17:54 ` Alexander Nyberg
2005-01-20 20:27 ` Con Kolivas
2005-01-20 0:53 ` Con Kolivas
2005-01-20 1:32 ` Jack O'Quin
2005-01-20 2:06 ` Con Kolivas
2005-01-20 2:45 ` Jack O'Quin
2005-01-20 4:07 ` Con Kolivas
2005-01-20 4:57 ` Jack O'Quin
2005-01-20 5:05 ` Gene Heskett
2005-01-20 5:59 ` Con Kolivas
2005-01-20 6:35 ` Con Kolivas
2005-01-20 15:19 ` Jack O'Quin
2005-01-20 15:42 ` Paul Davis
2005-01-20 16:47 ` Jack O'Quin
2005-01-20 17:25 ` Ingo Molnar
2005-01-22 0:09 ` Jack O'Quin
2005-01-22 16:54 ` Ingo Molnar
2005-01-22 21:23 ` Jack O'Quin
2005-01-23 2:06 ` Nick Piggin
2005-01-23 2:58 ` Chris Wright
2005-01-24 8:59 ` Ingo Molnar
2005-01-24 9:55 ` Paolo Ciarrocchi
2005-01-24 10:29 ` Nick Piggin
2005-01-24 10:46 ` Ingo Molnar
2005-01-24 12:58 ` [patch, 2.6.11-rc2] sched: /proc/sys/kernel/rt_cpu_limit tunable Ingo Molnar
2005-01-24 13:34 ` Ingo Molnar
2005-01-24 13:53 ` Con Kolivas
2005-01-24 14:01 ` [ck] " Con Kolivas
[not found] ` <87k6q2umla.fsf@sulphur.joq.us>
2005-01-25 6:28 ` Nick Piggin
2005-01-25 14:12 ` Ingo Molnar
2005-01-25 8:37 ` Ingo Molnar
2005-01-25 21:36 ` Jack O'Quin
2005-01-25 21:49 ` Ingo Molnar
2005-01-25 21:55 ` Chris Wright
2005-01-25 21:57 ` Ingo Molnar
2005-01-25 22:03 ` Chris Wright
2005-01-25 22:08 ` Ingo Molnar
2005-01-25 22:16 ` Chris Wright
2005-01-25 22:44 ` Bill Rugolsky Jr.
2005-01-26 5:12 ` Jack O'Quin
2005-01-26 7:27 ` Ingo Molnar
2005-01-26 11:02 ` [patch, 2.6.11-rc2] sched: RLIMIT_RT_CPU feature, -D7 Ingo Molnar
2005-01-25 13:56 ` [patch, 2.6.11-rc2] sched: RLIMIT_RT_CPU_RATIO feature Ingo Molnar
2005-01-25 14:06 ` Con Kolivas
2005-01-25 22:18 ` Peter Williams
2005-01-25 22:26 ` Peter Williams
2005-01-26 10:08 ` [patch, 2.6.11-rc2] sched: RLIMIT_RT_CPU feature, -D7 Ingo Molnar
2005-01-26 14:22 ` Jack O'Quin
2005-01-26 16:18 ` [ck] " Cal
2005-01-26 16:29 ` Cal
2005-01-26 16:41 ` Jack O'Quin
2005-01-26 17:57 ` Cal
2005-01-26 18:57 ` Jack O'Quin
2005-01-27 2:03 ` Cal
2005-01-27 8:51 ` [patch, 2.6.11-rc2] sched: RLIMIT_RT_CPU feature, -D8 Ingo Molnar
2005-01-27 12:48 ` Cal
2005-01-27 16:31 ` Mike Galbraith
2005-01-26 21:28 ` [patch, 2.6.11-rc2] sched: RLIMIT_RT_CPU feature, -D7 Peter Williams
2005-01-26 21:44 ` Peter Williams
2005-01-26 9:20 ` [patch, 2.6.11-rc2] sched: RLIMIT_RT_CPU_RATIO feature Ingo Molnar
2005-01-31 23:03 ` Peter Williams
2005-02-01 10:11 ` [patch] sys_setpriority() euid semantics fix Ingo Molnar
2005-02-01 21:46 ` Peter Williams
2005-01-26 5:24 ` [patch, 2.6.11-rc2] sched: RLIMIT_RT_CPU_RATIO feature Jack O'Quin
2005-01-26 7:04 ` Ingo Molnar
2005-01-26 22:27 ` Jack O'Quin
2005-01-26 23:29 ` Nick Piggin
2005-01-27 2:31 ` Jack O'Quin
2005-01-27 3:26 ` Nick Piggin
2005-01-27 5:15 ` Jack O'Quin
2005-01-27 5:54 ` Nick Piggin
2005-01-27 8:35 ` Ingo Molnar
2005-01-27 8:59 ` Ingo Molnar
2005-01-27 11:35 ` Ingo Molnar
2005-02-02 5:10 ` Jack O'Quin
2005-02-02 11:10 ` Bill Huey
2005-02-02 16:44 ` Jack O'Quin
2005-02-02 21:14 ` Bill Huey
2005-02-02 21:20 ` Bill Huey
2005-02-02 21:21 ` Ingo Molnar
2005-02-02 21:34 ` Bill Huey
2005-02-02 22:59 ` Paul Davis
2005-02-03 2:46 ` Bill Huey
2005-02-03 14:20 ` Paul Davis
2005-02-03 20:19 ` Con Kolivas
2005-02-03 20:47 ` Ingo Molnar
2005-02-03 21:15 ` Paul Davis
2005-02-03 21:28 ` Ingo Molnar
2005-02-03 21:41 ` Paul Davis
2005-02-03 21:59 ` Ingo Molnar
2005-02-03 22:24 ` Paul Davis
2005-02-03 22:26 ` Ingo Molnar
2005-02-04 0:36 ` Tristan Wibberley
2005-02-03 21:48 ` Peter Williams
2005-02-04 16:41 ` Jack O'Quin
2005-02-04 21:38 ` Peter Williams
2005-02-03 21:41 ` Ingo Molnar
2005-02-03 23:01 ` Bill Huey
2005-02-11 21:27 ` Lee Revell
2005-02-02 21:54 ` Peter Williams
2005-02-02 23:03 ` Paul Davis
2005-02-02 23:46 ` Peter Williams
2005-02-03 1:13 ` Jack O'Quin
2005-02-03 3:10 ` Peter Williams
2005-02-03 3:56 ` Jack O'Quin
2005-02-03 21:36 ` Ingo Molnar
2005-02-04 0:35 ` Chris Wright
2005-02-04 17:21 ` Jack O'Quin
2005-02-03 2:54 ` Bill Huey
2005-02-03 3:25 ` Peter Williams
2005-02-02 11:37 ` Ingo Molnar
2005-02-02 16:01 ` Jack O'Quin
2005-02-02 18:59 ` Lee Revell
2005-02-02 19:31 ` Jack O'Quin
2005-02-02 20:29 ` Ingo Molnar
2005-02-02 22:45 ` Jack O'Quin
2005-02-02 20:17 ` Ingo Molnar
2005-01-27 20:01 ` Lee Revell
2005-01-28 6:38 ` Ingo Molnar
2005-01-28 8:09 ` Jack O'Quin
2005-01-28 8:08 ` Ingo Molnar
2005-01-28 8:35 ` Jack O'Quin
2005-01-28 8:40 ` Ingo Molnar
2005-01-28 9:01 ` Jack O'Quin
2005-01-28 9:11 ` Ingo Molnar
2005-01-29 0:44 ` Lee Revell
2005-01-28 9:51 ` Mike Galbraith
2005-01-28 22:16 ` Peter Williams
2005-01-28 22:19 ` Ingo Molnar
2005-01-29 7:02 ` Jack O'Quin
2005-01-31 22:29 ` Bill Davidsen
2005-02-01 0:39 ` Bill Huey
2005-01-25 5:16 ` [PATCH]sched: Isochronous class v2 for unprivileged soft rt scheduling Jack O'Quin
2005-01-25 15:09 ` Ingo Molnar
2005-01-23 20:48 ` Jack O'Quin
2005-01-23 22:57 ` Con Kolivas
2005-01-24 1:06 ` Jack O'Quin
2005-01-24 1:09 ` Con Kolivas
2005-01-24 4:45 ` Jack O'Quin
2005-01-24 4:53 ` Jack O'Quin
2005-01-24 6:28 ` Jack O'Quin
2005-01-24 6:35 ` Con Kolivas
2005-01-24 6:57 ` Jack O'Quin
2005-01-24 22:58 ` Con Kolivas
2005-01-25 3:55 ` Con Kolivas
2005-01-25 13:05 ` Con Kolivas
2005-01-25 14:38 ` Con Kolivas
2005-01-25 18:36 ` Jack O'Quin
2005-01-25 20:52 ` Rui Nuno Capela
2005-01-24 21:46 ` Con Kolivas
2005-01-23 7:38 ` Jack O'Quin
2005-01-23 7:41 ` Con Kolivas
2005-01-24 6:30 ` Jack O'Quin
2005-01-24 20:55 ` Ingo Molnar
2005-01-20 21:59 ` Peter Chubb
2005-01-21 0:30 ` Jack O'Quin
2005-01-22 14:06 ` Paul Davis
2005-01-20 17:49 ` ross
2005-01-20 19:07 ` Lee Revell
2005-01-20 23:17 ` Con Kolivas
2005-01-21 7:48 ` Ingo Molnar
2005-02-07 3:09 ` Werner Almesberger
2005-02-07 3:27 ` Jack O'Quin
2005-02-07 3:27 ` Con Kolivas
2005-01-20 9:06 ` Rui Nuno Capela
2005-01-20 17:09 ` Rui Nuno Capela
2005-01-20 19:32 ` Jack O'Quin
2005-01-21 9:18 ` Rui Nuno Capela
2005-01-21 16:23 ` Con Kolivas
2005-01-21 16:40 ` Jack O'Quin
2005-01-22 0:06 ` Con Kolivas
2005-01-22 6:18 ` Jack O'Quin
2005-01-22 6:19 ` Con Kolivas
2005-01-22 6:48 ` Con Kolivas
2005-01-22 6:50 ` Con Kolivas
2005-01-22 7:09 ` Con Kolivas
2005-01-22 20:22 ` Jack O'Quin
2005-01-23 1:02 ` Con Kolivas
2005-01-23 3:02 ` Jack O'Quin
2005-01-23 4:29 ` Con Kolivas
2005-01-23 4:46 ` Jack O'Quin
2005-01-23 4:50 ` Con Kolivas
2005-01-23 7:37 ` Mike Galbraith
2005-01-23 13:57 ` Paul Davis
2005-01-23 1:31 ` Con Kolivas
2005-01-23 1:41 ` Paul Davis
2005-01-23 1:56 ` Con Kolivas
2005-01-23 4:50 ` Jack O'Quin
2005-01-21 23:30 ` utz lehmann
2005-01-21 23:48 ` Con Kolivas [this message]
2005-01-22 0:28 ` utz lehmann
2005-01-22 3:52 ` Con Kolivas
2005-01-22 6:15 ` Jack O'Quin
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=41F194DC.40603@kolivas.org \
--to=kernel@kolivas.org \
--cc=akpm@osdl.org \
--cc=alexn@dsv.su.se \
--cc=ck@vds.kolivas.org \
--cc=joq@io.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lkml@s2y4n2c.de \
--cc=mingo@elte.hu \
--cc=paul@linuxaudiosystems.com \
--cc=rlrevell@joe-job.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 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.