[Top] [All Lists]

Re: Filesystem writes on RAID5 too slow

To: Dave Chinner <david@xxxxxxxxxxxxx>
Subject: Re: Filesystem writes on RAID5 too slow
From: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Date: Fri, 22 Nov 2013 01:21:36 -0800
Cc: Martin Boutin <martboutin@xxxxxxxxx>, "Kernel.org-Linux-RAID" <linux-raid@xxxxxxxxxxxxxxx>, Eric Sandeen <sandeen@xxxxxxxxxx>, "Kernel.org-Linux-EXT4" <linux-ext4@xxxxxxxxxxxxxxx>, xfs-oss <xfs@xxxxxxxxxxx>
Delivered-to: xfs@xxxxxxxxxxx
In-reply-to: <20131121234116.GD6502@dastard>
References: <CACtJ3HZxp6xEjY_wOucCcqX4scNzEGuiAsovQYObJS9whtYJsQ@xxxxxxxxxxxxxx> <528A5C45.4080906@xxxxxxxxxx> <20131119005740.GY6188@dastard> <CACtJ3Ha3C7JNi5VZRnNMn+-okNheygmbj=j9AnUMvfzfZjNwug@xxxxxxxxxxxxxx> <20131121092606.GU11434@dastard> <CACtJ3HZAsOtmLArMWraygfQxpGymtZjr+a_reXv8o6LJzoMbvw@xxxxxxxxxxxxxx> <CACtJ3Ha5P2Heu4qiEEk6c4g+tKyR=RrD-4E-Cqj+bP8YDjKQ6w@xxxxxxxxxxxxxx> <20131121234116.GD6502@dastard>
User-agent: Mutt/1.5.21 (2010-09-15)
> From: Dave Chinner <dchinner@xxxxxxxxxx>
> 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@xxxxxxxxxx>

Ooops.  The fix looks good,

Reviewed-by: Christoph Hellwig <hch@xxxxxx>

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.

<Prev in Thread] Current Thread [Next in Thread>