From: Robert Love <rml@tech9.net>
To: Martin Waitz <tali@admingilde.org>
Cc: Linus Torvalds <torvalds@transmeta.com>,
Andrew Morton <akpm@digeo.com>,
mingo@elte.hu, linux-kernel@vger.kernel.org
Subject: Re: [patch] "HT scheduler", sched-2.5.63-B3
Date: 06 Mar 2003 17:07:37 -0500 [thread overview]
Message-ID: <1046988457.715.37.camel@phantasy.awol.org> (raw)
In-Reply-To: <20030306220307.GA1326@admingilde.org>
On Thu, 2003-03-06 at 17:03, Martin Waitz wrote:
> RE: the patch, i think using sleep_avg is a wrong metric from the
> beginning.
Eh? It is as close to a heuristic of interactivity as I can think of.
> in addition, timeslices should be shortest for high priority processes
> (depending on dynamic prio, not static)
No, they should be longer. In some cases they should be nearly
infinitely long (which is sort of what we do with the reinsertion into
the active array for highly interactive tasks). We want interactive
tasks to always be able to run.
You may think they need shorter timeslice because they are I/O-bound.
Keep in mind they need not _use_ all their timeslice in one go, and
having a large timeslice ensures they have timeslice available when they
wake up and need to run.
Robert Love
next prev parent reply other threads:[~2003-03-06 21:56 UTC|newest]
Thread overview: 100+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-02-28 9:50 [patch] "HT scheduler", sched-2.5.63-B3 Ingo Molnar
2003-02-28 21:12 ` Andrew Morton
2003-02-28 21:23 ` Robert Love
2003-03-01 4:25 ` Andrew Morton
2003-03-06 3:20 ` Linus Torvalds
2003-03-06 7:45 ` Andrew Morton
2003-03-06 7:47 ` Ingo Molnar
2003-03-06 15:07 ` Linus Torvalds
2003-03-06 16:54 ` Ingo Molnar
2003-03-06 17:03 ` Linus Torvalds
2003-03-06 17:24 ` Ingo Molnar
2003-03-06 17:42 ` Linus Torvalds
2003-03-06 17:54 ` Ingo Molnar
2003-03-06 18:02 ` Linus Torvalds
2003-03-06 18:11 ` Ingo Molnar
2003-03-06 17:55 ` John Levon
2003-03-06 18:07 ` Linus Torvalds
2003-03-06 18:11 ` John Levon
2003-03-06 18:16 ` Linus Torvalds
2003-03-06 18:15 ` Ingo Molnar
2003-03-06 18:20 ` Linus Torvalds
2003-03-06 18:10 ` David S. Miller
2003-03-06 18:18 ` Ingo Molnar
2003-03-07 5:57 ` Ingo Molnar
2003-03-07 5:54 ` Shawn
2003-03-07 6:04 ` Ingo Molnar
2003-03-07 14:28 ` jlnance
2003-03-07 6:45 ` Aaron Lehmann
2003-03-07 6:50 ` Ingo Molnar
2003-03-07 7:00 ` Aaron Lehmann
2003-03-07 7:36 ` Ingo Molnar
2003-03-08 18:28 ` Aaron Lehmann
2003-03-07 7:00 ` Andrew Morton
2003-03-07 3:19 ` Horst von Brand
2003-03-06 15:37 ` Linus Torvalds
2003-03-06 16:01 ` Jeff Garzik
2003-03-06 16:51 ` Linus Torvalds
2003-03-06 17:11 ` Ingo Molnar
2003-03-06 17:52 ` jvlists
2003-03-06 18:27 ` Ingo Molnar
2003-03-07 8:15 ` Xavier Bestel
2003-03-06 23:18 ` Robert Love
2003-03-06 18:49 ` Alan Cox
2003-03-06 17:55 ` Linus Torvalds
2003-03-06 18:04 ` Ingo Molnar
2003-03-06 18:13 ` Martin J. Bligh
2003-03-06 18:26 ` Linus Torvalds
2003-03-08 0:05 ` Daniel Phillips
2003-03-06 17:58 ` Ingo Molnar
2003-03-06 17:17 ` Ingo Molnar
2003-03-06 18:06 ` Dimitrie O. Paun
2003-03-06 22:14 ` Martin J. Bligh
2003-03-06 22:31 ` Dimitrie O. Paun
2003-03-06 23:05 ` Robert Love
2003-03-06 23:33 ` Martin J. Bligh
2003-03-06 18:25 ` Alan Cox
2003-03-06 17:35 ` Linus Torvalds
2003-03-06 22:30 ` Eric Northup
2003-03-06 23:40 ` Martin J. Bligh
2003-03-07 0:02 ` Linus Torvalds
2003-03-07 0:09 ` Dimitrie O. Paun
2003-03-06 22:00 ` Bill Davidsen
2003-03-06 17:13 ` Ingo Molnar
2003-03-06 17:30 ` Linus Torvalds
2003-03-06 17:33 ` Ingo Molnar
2003-03-06 17:50 ` Ingo Molnar
2003-03-06 18:00 ` Linus Torvalds
2003-03-06 20:42 ` Andrew Morton
2003-03-06 22:18 ` Robert Love
2003-03-07 5:52 ` Ingo Molnar
2003-03-07 5:51 ` Shawn
2003-03-07 6:01 ` Ingo Molnar
2003-03-07 6:07 ` Andrew Morton
2003-03-07 6:15 ` Ingo Molnar
2003-03-07 10:19 ` Helge Hafting
2003-03-07 11:06 ` Ingo Molnar
2003-03-07 7:45 ` Mike Galbraith
2003-03-07 7:45 ` Ingo Molnar
[not found] ` <Pine.LNX.4.44.0303070842420.4572-100000@localhost.localdom ain>
2003-03-07 8:09 ` Mike Galbraith
2003-03-07 8:10 ` Andrew Morton
2003-03-07 8:26 ` Mike Galbraith
2003-03-07 8:15 ` Ingo Molnar
[not found] ` <Pine.LNX.4.44.0303070913370.5173-100000@localhost.localdom ain>
2003-03-07 8:34 ` Mike Galbraith
2003-03-07 8:31 ` Ingo Molnar
2003-03-06 22:03 ` Martin Waitz
2003-03-06 22:07 ` Robert Love [this message]
2003-03-06 22:35 ` Martin Waitz
2003-03-06 22:56 ` Robert Love
2003-03-06 23:27 ` Martin Waitz
2003-03-06 23:36 ` Robert Love
2003-03-07 10:39 ` Ingo Molnar
2003-03-07 10:27 ` Ingo Molnar
2003-03-06 6:58 ` [patch] "interactivity changes", sched-2.5.64-A4 Ingo Molnar
2003-03-06 10:00 ` Andrew Morton
2003-03-06 10:07 ` [patch] "interactivity changes", sched-2.5.64-A5 Ingo Molnar
2003-03-06 10:16 ` [patch] "HT scheduler", sched-2.5.63-B3 Chris Wedgwood
2003-03-06 10:18 ` Ingo Molnar
[not found] <5.2.0.9.2.20030307093435.01a8fe88@pop.gmx.net>
2003-03-07 9:30 ` Ingo Molnar
[not found] ` <Pine.LNX.4.44.0303071003060.6318-100000@localhost.localdom ain>
2003-03-07 9:38 ` Mike Galbraith
2003-03-10 19:53 Perez-Gonzalez, Inaky
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=1046988457.715.37.camel@phantasy.awol.org \
--to=rml@tech9.net \
--cc=akpm@digeo.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=tali@admingilde.org \
--cc=torvalds@transmeta.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).