From: Nick Piggin <nickpiggin@yahoo.com.au>
To: Andrew Morton <akpm@osdl.org>
Cc: alexeyk@mysql.com, linuxram@us.ibm.com, peter@mysql.com,
linux-kernel@vger.kernel.org, axboe@suse.de
Subject: Re: Random file I/O regressions in 2.6 [patch+results]
Date: Fri, 21 May 2004 17:31:46 +1000 [thread overview]
Message-ID: <40ADB062.8050005@yahoo.com.au> (raw)
In-Reply-To: <20040520152305.3dbfa00b.akpm@osdl.org>
Andrew Morton wrote:
> Open questions are:
>
> a) Why is 2.6 write coalescing so superior to 2.4?
>
> b) Why is 2.6 issuing more read requests, for less data?
>
> c) Why is Alexey seeing dissimilar results?
>
Interesting. I am not too familiar with 2.4's IO scheduler,
but 2.6's have pretty comprehensive merging systems. Could
that be helping, Jens? Or is 2.4 pretty equivalent?
What about things like maximum request size for 2.4 vs 2.6
for example? This is another thing that can have an impact,
especially for writes.
I'll take a guess at b, and say it could be as-iosched.c.
Another thing might be that 2.6 has smaller nr_requests than
2.4, although you are unlikely to hid the read side limit
with only 16 threads if they are doing sync IO.
As for question c, has Alexey confirmed that it is indeed
2.6-bk which has problems?
next prev parent reply other threads:[~2004-05-22 0:13 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-05-02 19:57 Random file I/O regressions in 2.6 Alexey Kopytov
2004-05-03 11:14 ` Nick Piggin
2004-05-03 18:08 ` Andrew Morton
2004-05-03 20:22 ` Ram Pai
2004-05-03 20:57 ` Andrew Morton
2004-05-03 21:37 ` Peter Zaitsev
2004-05-03 21:50 ` Ram Pai
2004-05-03 22:01 ` Peter Zaitsev
2004-05-03 21:59 ` Andrew Morton
2004-05-03 22:07 ` Ram Pai
2004-05-03 23:58 ` Nick Piggin
2004-05-04 0:10 ` Andrew Morton
2004-05-04 0:19 ` Nick Piggin
2004-05-04 0:50 ` Ram Pai
2004-05-04 6:29 ` Andrew Morton
2004-05-04 15:03 ` Ram Pai
2004-05-04 19:39 ` Ram Pai
2004-05-04 19:48 ` Andrew Morton
2004-05-04 19:58 ` Ram Pai
2004-05-04 21:51 ` Ram Pai
2004-05-04 22:29 ` Ram Pai
2004-05-04 23:01 ` Alexey Kopytov
2004-05-04 23:20 ` Andrew Morton
2004-05-05 22:04 ` Alexey Kopytov
2004-05-06 8:43 ` Andrew Morton
2004-05-06 18:13 ` Peter Zaitsev
2004-05-06 21:49 ` Andrew Morton
2004-05-06 23:49 ` Nick Piggin
2004-05-07 1:29 ` Peter Zaitsev
2004-05-10 19:50 ` Ram Pai
2004-05-10 20:21 ` Andrew Morton
2004-05-10 22:39 ` Ram Pai
2004-05-10 23:07 ` Andrew Morton
2004-05-11 20:51 ` Ram Pai
2004-05-11 21:17 ` Andrew Morton
2004-05-13 20:41 ` Ram Pai
2004-05-17 17:30 ` Random file I/O regressions in 2.6 [patch+results] Ram Pai
2004-05-20 1:06 ` Alexey Kopytov
2004-05-20 1:31 ` Ram Pai
2004-05-21 19:32 ` Alexey Kopytov
2004-05-20 5:49 ` Andrew Morton
2004-05-20 21:59 ` Andrew Morton
2004-05-20 22:23 ` Andrew Morton
2004-05-21 7:31 ` Nick Piggin [this message]
2004-05-21 7:50 ` Jens Axboe
2004-05-21 8:40 ` Nick Piggin
2004-05-21 8:56 ` Spam: " Andrew Morton
2004-05-21 22:24 ` Alexey Kopytov
2004-05-21 21:13 ` Alexey Kopytov
2004-05-26 4:43 ` Alexey Kopytov
2004-05-11 22:26 ` Random file I/O regressions in 2.6 Bill Davidsen
2004-05-04 1:15 ` Andrew Morton
2004-05-04 11:39 ` Nick Piggin
2004-05-04 8:27 ` Arjan van de Ven
2004-05-04 8:47 ` Andrew Morton
2004-05-04 8:50 ` Arjan van de Ven
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=40ADB062.8050005@yahoo.com.au \
--to=nickpiggin@yahoo.com.au \
--cc=akpm@osdl.org \
--cc=alexeyk@mysql.com \
--cc=axboe@suse.de \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxram@us.ibm.com \
--cc=peter@mysql.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