aboutsummaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_buf_item.c
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2010-05-20 09:19:42 -0400
committerAlex Elder <aelder@sgi.com>2010-05-24 11:41:22 -0400
commitccf7c23fc129e75ef60e6f59f60a485b7a056598 (patch)
tree957539e31ee2a7155bbf9bb085ec1cb1d3432d3a /fs/xfs/xfs_buf_item.c
parentdf806158b0f6eb24247773b4a19b8b59d7217e59 (diff)
xfs: Ensure inode allocation buffers are fully replayed
With delayed logging, we can get inode allocation buffers in the same transaction inode unlink buffers. We don't currently mark inode allocation buffers in the log, so inode unlink buffers take precedence over allocation buffers. The result is that when they are combined into the same checkpoint, only the unlinked inode chain fields are replayed, resulting in uninitialised inode buffers being detected when the next inode modification is replayed. To fix this, we need to ensure that we do not set the inode buffer flag in the buffer log item format flags if the inode allocation has not already hit the log. To avoid requiring a change to log recovery, we really need to make this a modification that relies only on in-memory sate. We can do this by checking during buffer log formatting (while the CIL cannot be flushed) if we are still in the same sequence when we commit the unlink transaction as the inode allocation transaction. If we are, then we do not add the inode buffer flag to the buffer log format item flags. This means the entire buffer will be replayed, not just the unlinked fields. We do this while CIL flusheѕ are locked out to ensure that we don't race with the sequence numbers changing and hence fail to put the inode buffer flag in the buffer format flags when we really need to. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
Diffstat (limited to 'fs/xfs/xfs_buf_item.c')
-rw-r--r--fs/xfs/xfs_buf_item.c14
1 files changed, 14 insertions, 0 deletions
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index bcbb66150838..02a80984aa05 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -254,6 +254,20 @@ xfs_buf_item_format(
254 vecp++; 254 vecp++;
255 nvecs = 1; 255 nvecs = 1;
256 256
257 /*
258 * If it is an inode buffer, transfer the in-memory state to the
259 * format flags and clear the in-memory state. We do not transfer
260 * this state if the inode buffer allocation has not yet been committed
261 * to the log as setting the XFS_BLI_INODE_BUF flag will prevent
262 * correct replay of the inode allocation.
263 */
264 if (bip->bli_flags & XFS_BLI_INODE_BUF) {
265 if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
266 xfs_log_item_in_current_chkpt(&bip->bli_item)))
267 bip->bli_format.blf_flags |= XFS_BLF_INODE_BUF;
268 bip->bli_flags &= ~XFS_BLI_INODE_BUF;
269 }
270
257 if (bip->bli_flags & XFS_BLI_STALE) { 271 if (bip->bli_flags & XFS_BLI_STALE) {
258 /* 272 /*
259 * The buffer is stale, so all we need to log 273 * The buffer is stale, so all we need to log