From: Roger Luethi <rl@hellgate.ch>
To: Thomas Molina <tmolina@cablespeed.com>
Cc: William Lee Irwin III <wli@holomorphy.com>,
Linus Torvalds <torvalds@osdl.org>,
Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: 2.6.0 performance problems
Date: Wed, 31 Dec 2003 00:46:43 +0100 [thread overview]
Message-ID: <20031230234643.GB8412@k3.hellgate.ch> (raw)
In-Reply-To: <Pine.LNX.4.58.0312301524220.3152@localhost.localdomain>
On Tue, 30 Dec 2003 16:14:13 -0500, Thomas Molina wrote:
> I also get 90+ percent iowait under 2.6 and 0 iowait in 2.4. I'm not sure
> how the alleged suckiness of 2.6 paging fits into this. On this system
It is not alleged. It is real, but the badness is not universal. I was
afraid I'd have to add another category, but fortunately it seems bk
export matches qsbench: Major regressions neither between test2 and
test3 nor between 2.4 and 2.6.
I'm still interested to learn whether 2.5.39 is a major regression
(fixed later) for bk export, although that might have been due to the
qs specific reference patterns, I haven't looked into it. At least for
qsbench the spike is confirmed though, even with different parameters.
Roger
next prev parent reply other threads:[~2003-12-30 23:47 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-12-29 22:07 2.6.0 performance problems Thomas Molina
2003-12-29 22:21 ` Linus Torvalds
2003-12-29 22:58 ` Thomas Molina
2003-12-29 23:04 ` Linus Torvalds
2003-12-30 14:14 ` Thomas Molina
2003-12-30 14:39 ` William Lee Irwin III
2003-12-30 21:14 ` Thomas Molina
2003-12-30 21:23 ` Linus Torvalds
2003-12-31 0:50 ` Thomas Molina
2003-12-31 1:01 ` Linus Torvalds
2003-12-31 1:34 ` Andrew Morton
2003-12-31 11:25 ` bert hubert
2003-12-30 21:35 ` William Lee Irwin III
2003-12-30 23:46 ` Roger Luethi [this message]
2003-12-30 18:20 ` Linus Torvalds
2003-12-29 23:14 ` Martin Schlemmer
2003-12-30 5:09 ` William Lee Irwin III
2003-12-30 10:27 ` Thomas Molina
2003-12-29 23:25 ` David B. Stevens
2003-12-29 23:05 ` Thomas Molina
2003-12-29 23:43 ` Martin Schlemmer
2003-12-30 0:17 ` Thomas Molina
2003-12-30 1:23 ` Martin Schlemmer
2003-12-30 1:27 ` Dave Jones
2003-12-30 1:37 ` Martin Schlemmer
2003-12-30 1:40 ` Dave Jones
2003-12-30 1:49 ` Thomas Molina
2003-12-30 2:03 ` Mike Fedyk
2004-01-03 19:37 ` Bill Davidsen
2003-12-30 1:25 ` Roger Luethi
2003-12-30 1:37 ` Thomas Molina
2003-12-30 19:21 ` Andy Isaacson
2003-12-30 19:40 ` William Lee Irwin III
2003-12-30 22:24 ` Roger Luethi
2003-12-31 0:33 ` Thomas Molina
2003-12-31 10:17 ` Roger Luethi
2003-12-31 11:21 ` Jens Axboe
2003-12-31 21:03 ` Roger Luethi
2004-01-01 1:27 ` Thomas Molina
2004-01-01 10:23 ` Roger Luethi
2004-01-01 23:09 ` Roger Luethi
2004-01-02 10:11 ` Jens Axboe
2003-12-30 1:27 ` Thomas Molina
2003-12-30 2:53 ` Thomas Molina
-- strict thread matches above, loose matches on Subject: below --
2003-12-30 11:41 Samium Gromoff
2004-01-03 19:54 ` Bill Davidsen
[not found] ` <200312300855.00741.edt@aei.ca>
2004-01-05 12:33 ` Samium Gromoff
2004-01-05 15:09 ` Ed Tomlinson
2004-01-06 2:23 ` David Lang
2004-01-06 14:44 ` Samium Gromoff
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=20031230234643.GB8412@k3.hellgate.ch \
--to=rl@hellgate.ch \
--cc=linux-kernel@vger.kernel.org \
--cc=tmolina@cablespeed.com \
--cc=torvalds@osdl.org \
--cc=wli@holomorphy.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.