xfs: align initial file allocations correctly
authorDave Chinner <dchinner@redhat.com>
Thu, 21 Nov 2013 23:41:16 +0000 (10:41 +1100)
committerBen Myers <bpm@sgi.com>
Wed, 11 Dec 2013 21:23:04 +0000 (15:23 -0600)
commitf9b395a8ef8f34d19cae2cde361e19c96e097fad
tree647d39c42d63704ae5b142edf76981d8dfd92256
parent8e825e3a02ff20973154559c33e662cacedc4458
xfs: align initial file allocations correctly

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>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ben Myers <bpm@sgi.com>
fs/xfs/xfs_bmap.c