From: Jamie Lokier <jamie@shareable.org>
To: Linus Torvalds <torvalds@osdl.org>
Cc: Helge Hafting <helgehaf@aitel.hist.no>,
jw schultz <jw@pegasys.ws>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: raid0 slower than devices it is assembled of?
Date: Wed, 17 Dec 2003 19:22:44 +0000 [thread overview]
Message-ID: <20031217192244.GB12121@mail.shareable.org> (raw)
In-Reply-To: <Pine.LNX.4.58.0312160825570.1599@home.osdl.org>
Linus Torvalds wrote:
> My personal guess is that modern RAID0 stripes should be on the order of
> several MEGABYTES in size rather than the few hundred kB that most people
> use (not to mention the people who have 32kB stripes or smaller - they
> just kill their IO access patterns with that, and put the CPU at
> ridiculous strain).
If a large fs-level I/O transaction is split into lots of 32k
transactions by the RAID layer, many of those 32k transactions will be
contiguous on the disks.
That doesn't mean they're contiguous from the fs point of view, but
given that all modern hardware does scatter-gather, shouldn't the
contiguous transactions be merged before being sent to the disk?
It may strain the CPU (splitting and merging in a different order lots
of requests), but I don't see why it should kill I/O access patterns,
as they can be as large as if you had large stripes in the first place.
-- Jamie
next prev parent reply other threads:[~2003-12-17 19:23 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-12-15 13:34 raid0 slower than devices it is assembled of? Witold Krecicki
2003-12-15 15:44 ` Witold Krecicki
2003-12-16 4:01 ` jw schultz
2003-12-16 14:51 ` Helge Hafting
2003-12-16 16:42 ` Linus Torvalds
2003-12-16 20:58 ` Mike Fedyk
2003-12-16 21:11 ` Linus Torvalds
2003-12-17 10:53 ` Jörn Engel
2003-12-17 11:39 ` Peter Zaitsev
2003-12-17 16:01 ` Linus Torvalds
2003-12-17 18:37 ` Mike Fedyk
2003-12-17 21:55 ` bill davidsen
2003-12-17 17:02 ` bill davidsen
2003-12-17 20:14 ` Peter Zaitsev
2003-12-17 19:22 ` Jamie Lokier [this message]
2003-12-17 19:40 ` Linus Torvalds
2003-12-17 22:36 ` bill davidsen
2003-12-18 2:47 ` jw schultz
2003-12-17 22:29 ` bill davidsen
2003-12-18 2:18 ` jw schultz
2004-01-08 4:54 ` Greg Stark
2003-12-16 20:51 ` Andre Hedrick
2003-12-16 21:04 ` Andre Hedrick
2003-12-16 21:46 ` Witold Krecicki
2003-12-16 20:09 ` Witold Krecicki
2003-12-16 21:11 ` Adam Kropelin
2003-12-16 21:25 ` jw schultz
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=20031217192244.GB12121@mail.shareable.org \
--to=jamie@shareable.org \
--cc=helgehaf@aitel.hist.no \
--cc=jw@pegasys.ws \
--cc=linux-kernel@vger.kernel.org \
--cc=torvalds@osdl.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