From: "Keld Jørn Simonsen" <keld@keldix.com>
To: NeilBrown <neilb@suse.de>
Cc: Liam Kurmos <quantum.leaf@gmail.com>,
Roberto Spadim <roberto@spadim.com.br>,
Brad Campbell <lists2009@fnarfbargle.com>,
Drew <drew.kay@gmail.com>,
linux-raid@vger.kernel.org
Subject: Re: mdadm raid1 read performance
Date: Thu, 5 May 2011 13:10:06 +0200 [thread overview]
Message-ID: <20110505111006.GB11441@www2.open-std.org> (raw)
In-Reply-To: <20110505094538.0cef02cc@notabene.brown>
On Thu, May 05, 2011 at 09:45:38AM +1000, NeilBrown wrote:
> On Thu, 5 May 2011 00:08:59 +0100 Liam Kurmos <quantum.leaf@gmail.com> wrote:
>
> > as a separate question, what should be the theoretical performance of raid5?
>
> x(N-1)
>
> So a 4 drive RAID5 should read at 3 time the speed of a single drive.
Actually, theoretically, it should be more than that for reading, more like N minus
some overhead. In a raid5 stripe of 4 disks, when reading you do not read
the checksum block, and thus you should be able to have all 4 drives
occupied with reading real data. Some benchmarks back this up,
http://home.comcast.net/~jpiszcz/20080329-raid/
http://blog.jamponi.net/2008/07/raid56-and-10-benchmarks-on-26255_10.html
The latter reports a 3.44 times performance for raid5 reads with 4
disks, significantly over the N-1 = 3.0 mark.
For writing, you are correct with the N-1 formular.
best regards
keld
next prev parent reply other threads:[~2011-05-05 11:10 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-05-04 0:07 mdadm raid1 read performance Liam Kurmos
2011-05-04 0:57 ` John Robinson
2011-05-06 20:44 ` Leslie Rhorer
2011-05-06 21:56 ` Keld Jørn Simonsen
2011-05-04 0:58 ` NeilBrown
2011-05-04 5:30 ` Drew
2011-05-04 6:31 ` Brad Campbell
2011-05-04 7:42 ` Roberto Spadim
2011-05-04 23:08 ` Liam Kurmos
2011-05-04 23:35 ` Roberto Spadim
2011-05-04 23:36 ` Brad Campbell
2011-05-04 23:45 ` NeilBrown
2011-05-04 23:57 ` Roberto Spadim
2011-05-05 0:14 ` Liam Kurmos
2011-05-05 0:20 ` Liam Kurmos
2011-05-05 0:25 ` Roberto Spadim
2011-05-05 0:40 ` Liam Kurmos
2011-05-05 7:26 ` David Brown
2011-05-05 10:41 ` Keld Jørn Simonsen
2011-05-05 11:38 ` David Brown
2011-05-06 4:14 ` CoolCold
2011-05-06 7:29 ` David Brown
2011-05-06 21:05 ` Leslie Rhorer
2011-05-07 10:37 ` David Brown
2011-05-07 10:58 ` Keld Jørn Simonsen
2011-05-05 0:24 ` Roberto Spadim
2011-05-05 11:10 ` Keld Jørn Simonsen [this message]
2011-05-06 21:20 ` Leslie Rhorer
2011-05-06 21:53 ` Keld Jørn Simonsen
2011-05-07 3:17 ` Leslie Rhorer
2011-05-05 4:06 ` Roman Mamedov
2011-05-05 8:06 ` Nikolay Kichukov
2011-05-05 8:39 ` Liam Kurmos
2011-05-05 8:49 ` Liam Kurmos
2011-05-05 9:30 ` NeilBrown
2011-05-04 7:48 ` David Brown
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=20110505111006.GB11441@www2.open-std.org \
--to=keld@keldix.com \
--cc=drew.kay@gmail.com \
--cc=linux-raid@vger.kernel.org \
--cc=lists2009@fnarfbargle.com \
--cc=neilb@suse.de \
--cc=quantum.leaf@gmail.com \
--cc=roberto@spadim.com.br \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.