]> err.no Git - linux-2.6/commit
[XFS] Fix inode allocation latency
authorDavid Chinner <dgc@sgi.com>
Fri, 23 Nov 2007 05:29:18 +0000 (16:29 +1100)
committerLachlan McIlroy <lachlan@redback.melbourne.sgi.com>
Thu, 7 Feb 2008 07:16:07 +0000 (18:16 +1100)
commit5d51eff4538bdfeb9b7a2ec030ee3b0980b067d2
tree27606a34eab830ccc9a066f14f598af0c0c9027c
parente4143a1cf5973e3443c0650fc4c35292d3b7baa8
[XFS] Fix inode allocation latency

The log force added in xfs_iget_core() has been a performance issue since
it was introduced for tight loops that allocate then unlink a single file.
under heavy writeback, this can introduce unnecessary latency due tothe
log I/o getting stuck behind bulk data writes.

Fix this latency problem by avoinding the need for the log force by moving
the place we mark linux inode dirty to the transaction commit rather than
on transaction completion.

This also closes a potential hole in the sync code where a linux inode is
not dirty between the time it is modified and the time the log buffer has
been written to disk.

SGI-PV: 972753
SGI-Modid: xfs-linux-melb:xfs-kern:30007a

Signed-off-by: David Chinner <dgc@sgi.com>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
fs/xfs/linux-2.6/xfs_iops.c
fs/xfs/xfs_iget.c
fs/xfs/xfs_inode.c
fs/xfs/xfs_inode.h
fs/xfs/xfs_inode_item.c