From: Brad Campbell <brad@fnarfbargle.com>
To: Liam Kurmos <quantum.leaf@gmail.com>
Cc: Roberto Spadim <roberto@spadim.com.br>,
Brad Campbell <lists2009@fnarfbargle.com>,
Drew <drew.kay@gmail.com>, NeilBrown <neilb@suse.de>,
linux-raid@vger.kernel.org
Subject: Re: mdadm raid1 read performance
Date: Thu, 05 May 2011 07:36:13 +0800 [thread overview]
Message-ID: <4DC1E2ED.6070201@fnarfbargle.com> (raw)
In-Reply-To: <BANLkTikQTKPuY+Mg8h9ZOkJPoEQ-jGTeLg@mail.gmail.com>
On 05/05/11 07:08, Liam Kurmos wrote:
> Thanks to all who replied on this.
>
> I somewhat naively assumed that having 2 disks with the same data
> would mean a similar read speed to raid0 should be the norm (and i
> think this is a very popular miss-conception).
> I was neglecting the seek time to skip alternate blocks which i guess
> must the flaw.
>
> In theory though if i was reading a larger file, couldn't one disk
> start reading at the beginning to a buffer and one start reading from
> half way ( assuming 2 disks) and hence get close to 2x single disk
> speed?
>
> as a separate question, what should be the theoretical performance of raid5?
>
> in my tests i read 1GB and throw away the data.
> dd if=/dev/md0 of=/dev/null bs=1M count=1000
>
> With 4 fairly fast hdd's i get
>
> raid0: ~540MB/s
> raid10: 220MB/s
> raid5: ~165MB/s
> raid1: ~140MB/s (single disk speed)
>
> for 4 disks raid0 seems like suicide, but for my system drive the
> speed advantage is so great im tempted to try it anyway and try and
> use rsync to keep constant back up.
>
Try RAID10 with the far layout. It should give you streaming reads the same as RAID0
Brad
next prev parent reply other threads:[~2011-05-04 23:36 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 [this message]
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
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=4DC1E2ED.6070201@fnarfbargle.com \
--to=brad@fnarfbargle.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 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).