From: Daniel Phillips <phillips@innominate.de>
To: Chris Mason <mason@suse.com>, linux-kernel@vger.kernel.org
Subject: Re: [RFC] changes to buffer.c (was Test12 ll_rw_block error)
Date: Thu, 28 Dec 2000 16:49:14 +0100 [thread overview]
Message-ID: <3A4B60FA.FD05ED4C@innominate.de> (raw)
In-Reply-To: <3A4A505A.3CF8A8BB@innominate.de> <18670000.977950159@coffee>
Chris Mason wrote:
>
> On Wednesday, December 27, 2000 21:26:02 +0100 Daniel Phillips
> <phillips@innominate.de> wrote:
>
> > Hi Chris. I took your patch for a test drive under dbench and it seems
> > impressively stable under load, but there are performance problems.
> >
> > Test machine: 64 meg, 500 Mhz K6, IDE, Ext2, Blocksize=4K
> > Without patch: 9.5 MB/sec, 11 min 6 secs
> > With patch: 3.12 MB/sec, 33 min 51 sec
> >
>
> Cool, thanks for the testing. Which benchmark are you using? bonnie and
> dbench don't show any changes on my scsi disks, I'll give IDE a try as well.
Chris, this was an error, I had accidently booted the wrong kernel. The
'With patch' results above are for 2.2.16, not your patch.
With correct results you are looking much better:
Test machine: 64 meg, 500 Mhz K6, IDE, Ext2, Blocksize=4K
Test: dbench 48
pre13 without patch: 9.5 MB/sec 11 min 6 secs
pre13 with patch: 8.9 MB/sec 11 min 46 secs
2.2.16: 3.1 MB/sec 33 min 51 sec
This benchmark doesn't seem to suffer a lot from noise, so the 7%
slowdown with your patch likely real.
We've come a long way from 2.2.16, haven't we? I'll run some of these
tests against 2.2 pre19 kernels and maybe fan the flames of the 2.2/2.4
competition a little.
--
Daniel
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/
next prev parent reply other threads:[~2000-12-28 16:22 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <3A398F84.2CD3039D@thebarn.com>
2000-12-15 6:20 ` Test12 ll_rw_block error Linus Torvalds
2000-12-15 7:00 ` Alexander Viro
2000-12-15 9:14 ` Chris Mason
2000-12-17 0:54 ` Russell Cattelan
2000-12-17 12:20 ` Chris Mason
2000-12-15 10:51 ` Stephen C. Tweedie
2000-12-15 19:04 ` Linus Torvalds
2000-12-17 1:08 ` Russell Cattelan
2000-12-18 11:44 ` Stephen C. Tweedie
2000-12-17 2:38 ` Marcelo Tosatti
2000-12-18 11:46 ` Stephen C. Tweedie
2000-12-19 14:05 ` Marcelo Tosatti
2000-12-19 16:43 ` Daniel Phillips
2000-12-19 17:18 ` Marcelo Tosatti
2000-12-19 17:40 ` Christoph Hellwig
2000-12-21 23:25 ` [RFC] changes to buffer.c (was Test12 ll_rw_block error) Chris Mason
2000-12-22 0:19 ` Marcelo Tosatti
2000-12-22 2:20 ` Andreas Dilger
2000-12-22 0:38 ` Marcelo Tosatti
2000-12-22 13:56 ` Chris Mason
2000-12-22 16:45 ` Daniel Phillips
2000-12-22 19:35 ` Chris Mason
2000-12-22 15:07 ` Chris Mason
2000-12-22 19:52 ` Marcelo Tosatti
2000-12-22 23:18 ` Chris Mason
2000-12-22 23:26 ` Marcelo Tosatti
2000-12-23 18:21 ` Chris Mason
2000-12-23 19:02 ` Linus Torvalds
2000-12-23 19:25 ` Chris Mason
2000-12-23 15:47 ` Daniel Phillips
2000-12-27 0:57 ` Chris Mason
2000-12-26 23:18 ` Marcelo Tosatti
2000-12-27 20:26 ` Daniel Phillips
2000-12-27 20:49 ` Chris Mason
2000-12-28 15:49 ` Daniel Phillips [this message]
2000-12-28 19:19 ` Chris Mason
2000-12-28 19:29 ` Linus Torvalds
2000-12-29 16:03 ` Chris Mason
2000-12-29 16:21 ` Marcelo Tosatti
2000-12-29 18:33 ` Alexander Viro
2001-01-05 15:54 ` Chris Mason
2001-01-05 15:43 ` Marcelo Tosatti
2001-01-05 17:49 ` Daniel Phillips
2001-01-05 17:52 ` Chris Mason
2001-01-05 19:51 ` Chris Mason
2001-01-05 18:32 ` Marcelo Tosatti
2001-01-05 20:29 ` Rik van Riel
2001-01-05 18:43 ` Marcelo Tosatti
2001-01-05 20:37 ` Rik van Riel
2001-01-05 21:08 ` Chris Mason
2001-01-05 18:09 ` Juergen Schneider
2000-12-29 17:58 ` Daniel Phillips
2001-01-02 15:49 ` Chris Mason
2000-12-22 1:54 ` Alexander Viro
2000-12-22 13:49 ` Chris Mason
2000-12-17 0:51 ` Test12 ll_rw_block error Russell Cattelan
2000-12-17 0:21 ` Russell Cattelan
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=3A4B60FA.FD05ED4C@innominate.de \
--to=phillips@innominate.de \
--cc=linux-kernel@vger.kernel.org \
--cc=mason@suse.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).