From: Andrew Dunn <andrew.g.dunn@gmail.com>
To: tfjellstrom@shaw.ca
Cc: Jon Nelson <jnelson-linux-raid@jamponi.net>,
LinuxRaid <linux-raid@vger.kernel.org>,
pernegger@gmail.com
Subject: Re: unbelievably bad performance: 2.6.27.37 and raid6
Date: Sun, 01 Nov 2009 14:37:51 -0500 [thread overview]
Message-ID: <4AEDE38F.3080408@gmail.com> (raw)
In-Reply-To: <200910311243.35126.tfjellstrom@shaw.ca>
Are we to expect some resolution in newer kernels?
I am going to rebuild my array (backup data and re-create) to modify the
chunk size this week. I hope to get a much higher performance when
increasing from 64k chunk size to 1024k.
Is there a way to modify chunk size in place or does the array need to
be re-created?
Thomas Fjellstrom wrote:
> On Sat October 31 2009, Jon Nelson wrote:
>
>> I have a 4 disk raid6. The disks are individually capable of (at
>> least) 75MB/s on average.
>> The raid6 looks like this:
>>
>> md0 : active raid6 sda4[0] sdc4[5] sdd4[4] sdb4[6]
>> 613409536 blocks super 1.1 level 6, 64k chunk, algorithm 2 [4/4]
>> [UUUU]
>>
>> The raid serves basically as an lvm physical volume.
>>
>> While rsyncing a file from an ext3 filesystem to a jfs filesystem, I
>> am observing speeds in the 10-15MB/s range.
>> That seems really really slow.
>>
>> Using vmstat, I see similar numbers (I'm averaging a bit, I'll see
>> lows of 6MB/s and highs of 18-20MB/s, but these are infrequent.)
>> The system is, for the most part, otherwise unloaded.
>>
>> I looked at stripe_cache_size and increased it to 384 - no difference.
>> blockdev --getra reports 256 for all involved raid components.
>> I'm using the deadline I/O scheduler.
>>
>> Am I crazy? Is 12.5MB/s (average) what I should expect, here? What
>> might I look at here?
>>
>>
>
> I can't say I see numbers that bad.. But I do get 1/3 or less of the
> performance with .29, .30, .31, and .32 than I get with .26. I haven't tried
> any other kernels as these are the only ones I've been able to grab from apt
> ;)
>
> I get something on the order of 100MB/s write and read with newer kernels,
> with really bursty behaviour, and with .26, its not as fast as it COULD be,
> but at least I get 200-300MB/s, which is reasonable.
>
> Now if your two file systems are on the same LVM VG, that could have an
> impact on performance.
>
>
--
Andrew Dunn
http://agdunn.net
next prev parent reply other threads:[~2009-11-01 19:37 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-10-31 15:55 unbelievably bad performance: 2.6.27.37 and raid6 Jon Nelson
2009-10-31 18:43 ` Thomas Fjellstrom
2009-11-01 19:37 ` Andrew Dunn [this message]
2009-11-01 19:41 ` Thomas Fjellstrom
2009-11-01 23:43 ` NeilBrown
2009-11-01 23:47 ` Thomas Fjellstrom
2009-11-01 23:53 ` Jon Nelson
2009-11-02 2:28 ` Neil Brown
2009-11-01 23:55 ` Andrew Dunn
2009-11-04 14:43 ` CoolCold
2009-10-31 19:59 ` Christian Pernegger
2009-11-02 19:39 ` Jon Nelson
2009-11-02 20:01 ` Christian Pernegger
2009-11-01 7:17 ` Kristleifur Daðason
2009-11-02 14:54 ` Bill Davidsen
2009-11-02 15:03 ` Jon Nelson
2009-11-03 5:36 ` NeilBrown
2009-11-03 6:09 ` Michael Evans
2009-11-03 6:28 ` NeilBrown
2009-11-03 6:39 ` Michael Evans
2009-11-03 6:46 ` Michael Evans
2009-11-03 9:16 ` NeilBrown
2009-11-03 13:07 ` Goswin von Brederlow
2009-11-03 16:28 ` Michael Evans
2009-11-03 19:26 ` Goswin von Brederlow
2009-11-02 18:51 ` Christian Pernegger
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=4AEDE38F.3080408@gmail.com \
--to=andrew.g.dunn@gmail.com \
--cc=jnelson-linux-raid@jamponi.net \
--cc=linux-raid@vger.kernel.org \
--cc=pernegger@gmail.com \
--cc=tfjellstrom@shaw.ca \
/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).