Linux RAID subsystem development
 help / color / mirror / Atom feed
From: Peter Landmann <sfrazt@googlemail.com>
To: linux-raid@vger.kernel.org
Subject: Re: RAID 5 doesn't scale
Date: Wed, 3 Apr 2013 20:36:49 +0000 (UTC)	[thread overview]
Message-ID: <loom.20130403T223431-541@post.gmane.org> (raw)
In-Reply-To: 515C73B3.5060704@arcor.de


> 
> On 04/03/2013 03:18 PM, Stan Hoeppner wrote:
> 
> > You didn't mention your stripe_cache_size value.  It'll make a lot of
> > difference.  Make sure it's at least 4096.  The default is 256.
> 
> I'm not getting it - why would stripe cache size matter in a random
> read/write test? If the disks are large enough and the pattern is really
> random, the cache should hardly ever be hit (s_c_z = 4096 =^ 16MB cache
> per disk, that's 0.01% of disk size for a 160GB SSD).
> 
> I read that Peter confirmed the influence of stripe_cache_size, but I'd
> like to understand why it matters in this case.
> 
> Martin


I'm very sorry but now i can't confirm anymore that stripe_cache_size helps.

My test was to short. With every minute the IOPS decrease. So 
stripe_cache_size does only help for very short tests. 

I will provide details in another post.

Peter



  reply	other threads:[~2013-04-03 20:36 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-04-03 11:00 RAID 5 doesn't scale Peter Landmann
2013-04-03 11:21 ` Benjamin ESTRABAUD
2013-04-03 18:34   ` Martin Wilck
2013-04-03 20:38     ` Peter Landmann
2013-04-04 13:40       ` Benjamin ESTRABAUD
2013-04-03 13:18 ` Stan Hoeppner
2013-04-03 15:23   ` keld
2013-04-03 15:31   ` Peter Landmann
2013-04-03 18:35     ` Stan Hoeppner
2013-04-03 18:23   ` Martin Wilck
2013-04-03 20:36     ` Peter Landmann [this message]
2013-04-03 21:19       ` Peter Landmann
2013-04-03 21:24       ` Stan Hoeppner
2013-04-03 21:29         ` Peter Landmann
2013-04-03 21:15     ` Stan Hoeppner
2013-04-03 19:56   ` Roy Sigurd Karlsbakk
2013-04-03 21:12   ` Peter Landmann

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=loom.20130403T223431-541@post.gmane.org \
    --to=sfrazt@googlemail.com \
    --cc=linux-raid@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