From: Arjan van de Ven <arjan@infradead.org>
To: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Ingo Oeser <ioe-lkml@rameria.de>,
linux-kernel@vger.kernel.org, Andrew Morton <akpm@osdl.org>,
Marr <marr@flex.com>,
reiserfs-dev@namesys.com
Subject: Re: Drastic Slowdown of 'fseek()' Calls From 2.4 to 2.6 -- VMM Change?
Date: Sun, 26 Feb 2006 15:11:20 +0100 [thread overview]
Message-ID: <1140963081.2934.21.camel@laptopd505.fenrus.org> (raw)
In-Reply-To: <4401B233.7050308@yahoo.com.au>
On Mon, 2006-02-27 at 00:50 +1100, Nick Piggin wrote:
>
> Not really. The app is not silly if it does an fseek() then a _write_.
> Writing page sized and aligned chunks should not require previously
> uptodate pagecache, so doing a pre-read like this is a complete waste.
>
> Actually glibc tries to turn this pre-read off if the seek is to a page
> aligned offset, presumably to handle this case. However a big write
> would only have to RMW the first and last partial pages, so pre-reading
> 128KB in this case is wrong.
>
> And I would also say a 4K read is wrong as well, because a big read will
> be less efficient due to the extra syscall and small IO.
I can very much see the point of issuing a sys_readahead instead.....
next prev parent reply other threads:[~2006-02-26 14:11 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-02-24 20:22 Drastic Slowdown of 'fseek()' Calls From 2.4 to 2.6 -- VMM Change? Marr
2006-02-25 5:16 ` Andrew Morton
2006-02-26 13:07 ` Ingo Oeser
2006-02-26 13:50 ` Nick Piggin
2006-02-26 14:11 ` Arjan van de Ven [this message]
2006-02-27 20:52 ` Hans Reiser
2006-02-28 0:34 ` Nick Piggin
2006-02-28 18:42 ` Hans Reiser
2006-02-28 18:51 ` Hans Reiser
2006-02-27 20:24 ` Marr
2006-02-27 21:53 ` Hans Reiser
2006-02-28 0:03 ` Bill Davidsen
2006-02-28 18:38 ` Hans Reiser
2006-03-05 23:02 ` Readahead value 128K? (was Re: Drastic Slowdown of 'fseek()' Calls From 2.4 to 2.6 -- VMM Change?) Linda Walsh
2006-03-07 19:53 ` Marr
2006-03-07 21:15 ` Linda Walsh
2006-03-12 21:53 ` Marr
2006-03-12 22:15 ` Mark Lord
2006-03-13 4:36 ` Marr
2006-03-13 14:41 ` Mark Lord
2006-03-13 18:15 ` Hans Reiser
2006-03-13 20:00 ` Marr
[not found] <5JRJO-6Al-7@gated-at.bofh.it>
2006-02-24 23:31 ` Drastic Slowdown of 'fseek()' Calls From 2.4 to 2.6 -- VMM Change? Robert Hancock
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=1140963081.2934.21.camel@laptopd505.fenrus.org \
--to=arjan@infradead.org \
--cc=akpm@osdl.org \
--cc=ioe-lkml@rameria.de \
--cc=linux-kernel@vger.kernel.org \
--cc=marr@flex.com \
--cc=nickpiggin@yahoo.com.au \
--cc=reiserfs-dev@namesys.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).