All of lore.kernel.org
 help / color / mirror / Atom feed
From: Eric Sandeen <sandeen@sandeen.net>
To: Kasper Sandberg <postmaster@metanurb.dk>
Cc: "Dave Chinner" <david@fromorbit.com>, Asdo <asdo@shiftmail.org>,
	linux-raid <linux-raid@vger.kernel.org>,
	"Kristleifur Daðason" <kristleifur@gmail.com>,
	"Gabor Gombas" <gombasg@sztaki.hu>,
	xfs@oss.sgi.com
Subject: Re: Disappointing performance of copy (MD raid + XFS)
Date: Tue, 15 Dec 2009 10:53:23 -0600	[thread overview]
Message-ID: <4B27BF03.6090602@sandeen.net> (raw)
In-Reply-To: <1260895872.7209.46.camel@localhost>

Kasper Sandberg wrote:
> On Fri, 2009-12-11 at 14:26 +1100, Dave Chinner wrote:
>> On Fri, Dec 11, 2009 at 02:41:32AM +0100, Asdo wrote:
>>> I have checked the other problem I had which I was mentioning, that I  
> <snip>
>>> Also with noalign and rotorstep at 255 the stripe_cache_size stays  
>>> usually in the lower half (below 16000 out of 32000) while with defaults  
>>> it's stuck for most of the time at the maximum and processes are stuck  
>>> sleeping in MD locks for this reason.
>> That really does sound like a misaligned filesystem - the stripe
>> cache will grow larger the more RMW cycles that need to be
>> performed...
> Sorry to interrupt, I would very much like to see if my array/xfs is
> properly aligned and all that stuff which has been mentioned inhere,
> could any of you please post the things required to check? filesystem is
> straight on md raid6, debian lenny.
> 
> 
> <snip>
> 

use xfs_info on your mountpoint, and compare the stripe unit and width
to what md tells you.  xfs_info stripe unit/width output is in fs blocks
units.

-Eric

WARNING: multiple messages have this Message-ID (diff)
From: Eric Sandeen <sandeen@sandeen.net>
To: Kasper Sandberg <postmaster@metanurb.dk>
Cc: "Gabor Gombas" <gombasg@sztaki.hu>,
	xfs@oss.sgi.com, linux-raid <linux-raid@vger.kernel.org>,
	"Kristleifur Daðason" <kristleifur@gmail.com>,
	Asdo <asdo@shiftmail.org>
Subject: Re: Disappointing performance of copy (MD raid + XFS)
Date: Tue, 15 Dec 2009 10:53:23 -0600	[thread overview]
Message-ID: <4B27BF03.6090602@sandeen.net> (raw)
In-Reply-To: <1260895872.7209.46.camel@localhost>

Kasper Sandberg wrote:
> On Fri, 2009-12-11 at 14:26 +1100, Dave Chinner wrote:
>> On Fri, Dec 11, 2009 at 02:41:32AM +0100, Asdo wrote:
>>> I have checked the other problem I had which I was mentioning, that I  
> <snip>
>>> Also with noalign and rotorstep at 255 the stripe_cache_size stays  
>>> usually in the lower half (below 16000 out of 32000) while with defaults  
>>> it's stuck for most of the time at the maximum and processes are stuck  
>>> sleeping in MD locks for this reason.
>> That really does sound like a misaligned filesystem - the stripe
>> cache will grow larger the more RMW cycles that need to be
>> performed...
> Sorry to interrupt, I would very much like to see if my array/xfs is
> properly aligned and all that stuff which has been mentioned inhere,
> could any of you please post the things required to check? filesystem is
> straight on md raid6, debian lenny.
> 
> 
> <snip>
> 

use xfs_info on your mountpoint, and compare the stripe unit and width
to what md tells you.  xfs_info stripe unit/width output is in fs blocks
units.

-Eric

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

  reply	other threads:[~2009-12-15 16:53 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-12-10  0:39 Disappointing performance of copy (MD raid + XFS) Asdo
2009-12-10  0:39 ` Asdo
2009-12-10  0:57 ` Asdo
2009-12-10  0:57   ` Asdo
2009-12-10  1:16   ` Asdo
2009-12-10  1:16     ` Asdo
2009-12-10  4:16 ` Eric Sandeen
2009-12-10  4:16   ` Eric Sandeen
2009-12-11  1:41   ` Asdo
2009-12-11  1:41     ` Asdo
2009-12-11  3:20     ` Eric Sandeen
2009-12-11  3:20       ` Eric Sandeen
2009-12-11  3:26     ` Dave Chinner
2009-12-15 16:51       ` Kasper Sandberg
2009-12-15 16:53         ` Eric Sandeen [this message]
2009-12-15 16:53           ` Eric Sandeen
2009-12-10  7:28 ` Gabor Gombas
2009-12-10  7:28   ` Gabor Gombas
2009-12-10  9:44 ` Kristleifur Daðason
2009-12-10  9:44   ` Kristleifur Daðason

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=4B27BF03.6090602@sandeen.net \
    --to=sandeen@sandeen.net \
    --cc=asdo@shiftmail.org \
    --cc=david@fromorbit.com \
    --cc=gombasg@sztaki.hu \
    --cc=kristleifur@gmail.com \
    --cc=linux-raid@vger.kernel.org \
    --cc=postmaster@metanurb.dk \
    --cc=xfs@oss.sgi.com \
    /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.