From: Andi Kleen <ak@suse.de>
To: arjan@fenrus.demon.nl
Cc: linux-kernel@vger.kernel.org
Subject: Re: performance of O_DIRECT on md/lvm
Date: 20 Jan 2002 23:11:35 +0100 [thread overview]
Message-ID: <p73ofjoisfc.fsf@oldwotan.suse.de> (raw)
In-Reply-To: <p734rlg90ga.fsf@oldwotan.suse.de.suse.lists.linux.kernel> <m16SPj2-000OVeC@amadeus.home.nl.suse.lists.linux.kernel>
In-Reply-To: arjan@fenrus.demon.nl's message of "20 Jan 2002 22:46:12 +0100"
arjan@fenrus.demon.nl writes:
> In article <p734rlg90ga.fsf@oldwotan.suse.de> you wrote:
>
> > I think an optional readahead mode for O_DIRECT would be useful.
>
> I disagree. O_DIRECT says "do not cache. period. I know what I'm doing"
> and the kernel should respect that imho. After all we have sys_readahead for
> the other part...
Problem with sys_readahead is that it doesn't work for big IO sizes.
e.g. you read in big blocks. You have to do readahead(next block);
read(directfd, ..., big-block);
The readahead comes to early in this case; it would be better if it is
done in the middle of read of big-block based on the request size.
Otherwise you risk additional seeks when you overflow the 'read window',
which is all to easy this way.
-Andi
next parent reply other threads:[~2002-01-20 22:11 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <p734rlg90ga.fsf@oldwotan.suse.de.suse.lists.linux.kernel>
[not found] ` <m16SPj2-000OVeC@amadeus.home.nl.suse.lists.linux.kernel>
2002-01-20 22:11 ` Andi Kleen [this message]
[not found] <200201181743.g0IHhO226012@street-vision.com.suse.lists.linux.kernel>
[not found] ` <3C48607C.35D3DDFF@redhat.com.suse.lists.linux.kernel>
[not found] ` <20020120201603.L21279@athlon.random.suse.lists.linux.kernel>
2002-01-20 21:28 ` performance of O_DIRECT on md/lvm Andi Kleen
2002-01-20 21:42 ` arjan
2002-01-21 1:12 ` Andrea Arcangeli
2002-01-21 5:35 ` Benjamin LaHaise
2002-01-21 14:41 ` Andrea Arcangeli
2002-01-18 17:43 Justin Cormack
2002-01-18 17:50 ` Arjan van de Ven
2002-01-20 19:16 ` Andrea Arcangeli
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=p73ofjoisfc.fsf@oldwotan.suse.de \
--to=ak@suse.de \
--cc=arjan@fenrus.demon.nl \
--cc=linux-kernel@vger.kernel.org \
/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