All of lore.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@infradead.org>
To: Dave Chinner <david@fromorbit.com>
Cc: Martin Boutin <martboutin@gmail.com>,
	"Kernel.org-Linux-RAID" <linux-raid@vger.kernel.org>,
	Eric Sandeen <sandeen@redhat.com>,
	"Kernel.org-Linux-EXT4" <linux-ext4@vger.kernel.org>,
	xfs-oss <xfs@oss.sgi.com>
Subject: Re: Filesystem writes on RAID5 too slow
Date: Fri, 22 Nov 2013 01:21:36 -0800	[thread overview]
Message-ID: <20131122092136.GD32568@infradead.org> (raw)
In-Reply-To: <20131121234116.GD6502@dastard>

> From: Dave Chinner <dchinner@redhat.com>
> 
> The function xfs_bmap_isaeof() is used to indicate that an
> allocation is occurring at or past the end of file, and as such
> should be aligned to the underlying storage geometry if possible.
> 
> Commit 27a3f8f ("xfs: introduce xfs_bmap_last_extent") changed the
> behaviour of this function for empty files - it turned off
> allocation alignment for this case accidentally. Hence large initial
> allocations from direct IO are not getting correctly aligned to the
> underlying geometry, and that is cause write performance to drop in
> alignment sensitive configurations.
> 
> Fix it by considering allocation into empty files as requiring
> aligned allocation again.
> 
> Signed-off-by: Dave Chinner <dchinner@redhat.com>

Ooops.  The fix looks good,

Reviewed-by: Christoph Hellwig <hch@lst.de>


Might be worth cooking up a test for this, scsi_debug can expose
geometry, and we already have it wired to to large sector size
testing in xfstests.


WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@infradead.org>
To: Dave Chinner <david@fromorbit.com>
Cc: Martin Boutin <martboutin@gmail.com>,
	"Kernel.org-Linux-RAID" <linux-raid@vger.kernel.org>,
	xfs-oss <xfs@oss.sgi.com>,
	"Kernel.org-Linux-EXT4" <linux-ext4@vger.kernel.org>,
	Eric Sandeen <sandeen@redhat.com>
Subject: Re: Filesystem writes on RAID5 too slow
Date: Fri, 22 Nov 2013 01:21:36 -0800	[thread overview]
Message-ID: <20131122092136.GD32568@infradead.org> (raw)
In-Reply-To: <20131121234116.GD6502@dastard>

> From: Dave Chinner <dchinner@redhat.com>
> 
> The function xfs_bmap_isaeof() is used to indicate that an
> allocation is occurring at or past the end of file, and as such
> should be aligned to the underlying storage geometry if possible.
> 
> Commit 27a3f8f ("xfs: introduce xfs_bmap_last_extent") changed the
> behaviour of this function for empty files - it turned off
> allocation alignment for this case accidentally. Hence large initial
> allocations from direct IO are not getting correctly aligned to the
> underlying geometry, and that is cause write performance to drop in
> alignment sensitive configurations.
> 
> Fix it by considering allocation into empty files as requiring
> aligned allocation again.
> 
> Signed-off-by: Dave Chinner <dchinner@redhat.com>

Ooops.  The fix looks good,

Reviewed-by: Christoph Hellwig <hch@lst.de>


Might be worth cooking up a test for this, scsi_debug can expose
geometry, and we already have it wired to to large sector size
testing in xfstests.

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

  reply	other threads:[~2013-11-22  9:21 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-11-18 16:02 Filesystem writes on RAID5 too slow Martin Boutin
2013-11-18 18:28 ` Eric Sandeen
2013-11-18 18:28   ` Eric Sandeen
2013-11-19  0:57   ` Dave Chinner
2013-11-21  9:11     ` Martin Boutin
2013-11-21  9:11       ` Martin Boutin
2013-11-21  9:26       ` Dave Chinner
2013-11-21  9:26         ` Dave Chinner
2013-11-21  9:50         ` Martin Boutin
2013-11-21 13:31           ` Martin Boutin
2013-11-21 13:31             ` Martin Boutin
2013-11-21 16:35             ` Martin Boutin
2013-11-21 16:35               ` Martin Boutin
2013-11-22  9:23               ` Christoph Hellwig
2013-11-21 23:41             ` Dave Chinner
2013-11-21 23:41               ` Dave Chinner
2013-11-22  9:21               ` Christoph Hellwig [this message]
2013-11-22  9:21                 ` Christoph Hellwig
2013-11-22 22:40                 ` Dave Chinner
2013-11-22 22:40                   ` Dave Chinner
2013-11-23  8:41                   ` Christoph Hellwig
2013-11-23  8:41                     ` Christoph Hellwig
2013-11-24 23:21                     ` Dave Chinner
2013-11-24 23:21                       ` Dave Chinner
2013-11-22 13:33               ` Martin Boutin
2013-12-10 19:18               ` Christoph Hellwig
2013-12-10 19:18                 ` Christoph Hellwig
2013-12-11  0:27                 ` Dave Chinner
2013-12-11  0:27                   ` Dave Chinner
2013-12-11 19:09                   ` Ben Myers
2013-11-18 18:41 ` Roman Mamedov
2013-11-18 19:25   ` Roman Mamedov

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=20131122092136.GD32568@infradead.org \
    --to=hch@infradead.org \
    --cc=david@fromorbit.com \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-raid@vger.kernel.org \
    --cc=martboutin@gmail.com \
    --cc=sandeen@redhat.com \
    --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.