From: Jens Axboe <axboe@suse.de>
To: Lou Langholtz <ldl@aros.net>
Cc: Con Kolivas <kernel@kolivas.org>,
Marc-Christian Petersen <m.c.p@wolk-project.de>,
Felipe Alfaro Solana <felipe_alfaro@linuxmail.org>,
LKML <linux-kernel@vger.kernel.org>,
mingo@elte.hu
Subject: Re: Ingo Molnar and Con Kolivas 2.6 scheduler patches
Date: Sat, 26 Jul 2003 18:40:58 +0200 [thread overview]
Message-ID: <20030726164058.GD518@suse.de> (raw)
In-Reply-To: <3F22AF7E.1080601@aros.net>
On Sat, Jul 26 2003, Lou Langholtz wrote:
> Con Kolivas wrote:
>
> >. . .
> >Actually this is not strange to me. It has become obvious that the
> >problems with interactivity that have evolved in 2.5 are not scheduler
> >related. Just try plugging in all the old 2.4 O(1) scheduler settings into
> >the current scheduler and you will see that it still performs badly. What
> >exactly is the cause is a mystery but seems to be more a combination of
> >factors with a careful look at the way the vm behaves being part of that.
> >. . .
> >
> Any chance that the problem may be due to the block layer system (and
> block driver(s)) getting more cycles than it should? Particularly with
Not likely
> the out-of-band like work queue scheduling? That would at least explain
If anything, 2.6 will unplug sooner than 2.4. 2.4 will unplug only when
someone does a wait_on_buffer/page, 2.6 will unplug when:
- queued requests exceed unplug threshold, 4 requests
- unplug timeout, 3ms
- someone doing wait_on_page/buffer
Can't rule out a bug of course, the horrible audio skips I've seen in
2.6 are not io related though. Block layer will only do out of band
unplugs for the timer unplug, and even that could be superceded by a new
request entering the queue (or someone doing wait_bla)
> the scheduling oddities I'm seeing with 2.6.0-test1 after a minute of so
> of intense I/O.
CPU or disk scheduling oddities?
People should try booting with elevator=deadline to see if it changes
anything for these types of workloads, AS is really not optimal for that
at all.
--
Jens Axboe
next prev parent reply other threads:[~2003-07-26 16:39 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-07-26 9:30 Ingo Molnar and Con Kolivas 2.6 scheduler patches Felipe Alfaro Solana
2003-07-26 9:46 ` Marc-Christian Petersen
2003-07-26 10:02 ` Ismael Valladolid Torres
2003-07-26 10:10 ` Eugene Teo
2003-07-26 11:24 ` Ed Sweetman
2003-07-26 17:00 ` Rahul Karnik
2003-07-27 15:46 ` Daniel Phillips
2003-07-26 16:52 ` Diego Calleja García
2003-07-26 18:35 ` Andrew Morton
2003-07-26 23:01 ` Diego Calleja García
2003-07-28 9:38 ` Felipe Alfaro Solana
2003-07-28 10:37 ` Måns Rullgård
2003-07-28 17:06 ` Diego Calleja García
2003-07-27 2:38 ` Con Kolivas
2003-07-27 7:39 ` Willy Tarreau
2003-07-27 9:12 ` Ingo Molnar
2003-07-27 11:54 ` Con Kolivas
2003-07-27 20:18 ` Daniel Phillips
2003-07-26 22:05 ` Ed Sweetman
2003-08-01 15:38 ` Daniel Phillips
2003-07-31 23:02 ` Ed Sweetman
2003-07-27 2:39 ` Ed Sweetman
2003-07-29 13:56 ` Timothy Miller
2003-07-29 13:57 ` Con Kolivas
2003-07-29 15:30 ` Timothy Miller
2003-07-29 15:52 ` Helge Hafting
2003-07-29 16:26 ` Timothy Miller
2003-07-30 14:46 ` Daniel Phillips
2003-07-29 15:40 ` Timothy Miller
2003-07-30 16:17 ` Daniel Phillips
2003-08-08 21:09 ` Bill Huey
2003-08-06 21:28 ` Rob Landley
2003-08-07 9:34 ` Helge Hafting
2003-08-07 15:42 ` Daniel Phillips
2003-08-07 20:45 ` William Lee Irwin III
2003-08-07 20:51 ` Rob Landley
2003-08-07 21:40 ` Ed Sweetman
2003-08-07 22:17 ` William Lee Irwin III
2003-08-08 0:01 ` Rob Landley
2003-08-09 20:52 ` George Anzinger
2003-08-14 0:24 ` Rob Landley
2003-08-14 8:01 ` George Anzinger
2003-08-16 9:10 ` Rob Landley
2003-08-16 14:29 ` APM and 2.5.75 not resuming properly Jamie Lokier
2003-08-16 15:03 ` Stephen Rothwell
2003-08-16 16:12 ` Jamie Lokier
2003-08-16 20:43 ` Rob Landley
2003-08-13 3:38 ` Ingo Molnar and Con Kolivas 2.6 scheduler patches George Anzinger
2003-08-08 6:08 ` Daniel Phillips
2003-07-26 12:08 ` Ismael Valladolid Torres
2003-07-26 14:54 ` Con Kolivas
2003-07-26 14:49 ` Con Kolivas
2003-07-26 14:47 ` Con Kolivas
2003-07-26 16:42 ` Lou Langholtz
2003-07-26 16:40 ` Jens Axboe [this message]
2003-07-26 18:19 ` William Lee Irwin III
2003-07-26 18:31 ` Felipe Alfaro Solana
2003-07-26 19:20 ` William Lee Irwin III
2003-07-26 19:47 ` William Lee Irwin III
2003-07-27 9:24 ` Ingo Molnar
2003-07-27 9:57 ` Con Kolivas
2003-07-27 10:02 ` Ingo Molnar
2003-07-27 10:19 ` Con Kolivas
2003-07-28 22:44 ` Timothy Miller
2003-07-26 14:44 Downing, Thomas
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=20030726164058.GD518@suse.de \
--to=axboe@suse.de \
--cc=felipe_alfaro@linuxmail.org \
--cc=kernel@kolivas.org \
--cc=ldl@aros.net \
--cc=linux-kernel@vger.kernel.org \
--cc=m.c.p@wolk-project.de \
--cc=mingo@elte.hu \
/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).