summaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_log_cil.c
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2010-05-20 23:19:42 +1000
committerAlex Elder <aelder@sgi.com>2010-05-24 10:41:22 -0500
commitccf7c23fc129e75ef60e6f59f60a485b7a056598 (patch)
tree957539e31ee2a7155bbf9bb085ec1cb1d3432d3a /fs/xfs/xfs_log_cil.c
parentdf806158b0f6eb24247773b4a19b8b59d7217e59 (diff)
downloadop-kernel-dev-ccf7c23fc129e75ef60e6f59f60a485b7a056598.zip
op-kernel-dev-ccf7c23fc129e75ef60e6f59f60a485b7a056598.tar.gz
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_log_cil.c')
-rw-r--r--fs/xfs/xfs_log_cil.c45
1 files changed, 45 insertions, 0 deletions
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 9b21f80..bb17cc0 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -200,6 +200,15 @@ xlog_cil_insert(
ctx->nvecs += diff_iovecs;
/*
+ * If this is the first time the item is being committed to the CIL,
+ * store the sequence number on the log item so we can tell
+ * in future commits whether this is the first checkpoint the item is
+ * being committed into.
+ */
+ if (!item->li_seq)
+ item->li_seq = ctx->sequence;
+
+ /*
* Now transfer enough transaction reservation to the context ticket
* for the checkpoint. The context ticket is special - the unit
* reservation has to grow as well as the current reservation as we
@@ -325,6 +334,10 @@ xlog_cil_free_logvec(
* For more specific information about the order of operations in
* xfs_log_commit_cil() please refer to the comments in
* xfs_trans_commit_iclog().
+ *
+ * Called with the context lock already held in read mode to lock out
+ * background commit, returns without it held once background commits are
+ * allowed again.
*/
int
xfs_log_commit_cil(
@@ -678,3 +691,35 @@ restart:
spin_unlock(&cil->xc_cil_lock);
return commit_lsn;
}
+
+/*
+ * Check if the current log item was first committed in this sequence.
+ * We can't rely on just the log item being in the CIL, we have to check
+ * the recorded commit sequence number.
+ *
+ * Note: for this to be used in a non-racy manner, it has to be called with
+ * CIL flushing locked out. As a result, it should only be used during the
+ * transaction commit process when deciding what to format into the item.
+ */
+bool
+xfs_log_item_in_current_chkpt(
+ struct xfs_log_item *lip)
+{
+ struct xfs_cil_ctx *ctx;
+
+ if (!(lip->li_mountp->m_flags & XFS_MOUNT_DELAYLOG))
+ return false;
+ if (list_empty(&lip->li_cil))
+ return false;
+
+ ctx = lip->li_mountp->m_log->l_cilp->xc_ctx;
+
+ /*
+ * li_seq is written on the first commit of a log item to record the
+ * first checkpoint it is written to. Hence if it is different to the
+ * current sequence, we're in a new checkpoint.
+ */
+ if (XFS_LSN_CMP(lip->li_seq, ctx->sequence) != 0)
+ return false;
+ return true;
+}
OpenPOWER on IntegriCloud