xfs: Introduce delayed logging core code
The delayed logging code only changes in-memory structures and as
such can be enabled and disabled with a mount option. Add the mount
option and emit a warning that this is an experimental feature that
should not be used in production yet.
We also need infrastructure to track committed items that have not
yet been written to the log. This is what the Committed Item List
(CIL) is for.
The log item also needs to be extended to track the current log
vector, the associated memory buffer and it's location in the Commit
Item List. Extend the log item and log vector structures to enable
this tracking.
To maintain the current log format for transactions with delayed
logging, we need to introduce a checkpoint transaction and a context
for tracking each checkpoint from initiation to transaction
completion. This includes adding a log ticket for tracking space
log required/used by the context checkpoint.
To track all the changes we need an io vector array per log item,
rather than a single array for the entire transaction. Using the new
log vector structure for this requires two passes - the first to
allocate the log vector structures and chain them together, and the
second to fill them out. This log vector chain can then be passed
to the CIL for formatting, pinning and insertion into the CIL.
Formatting of the log vector chain is relatively simple - it's just
a loop over the iovecs on each log vector, but it is made slightly
more complex because we re-write the iovec after the copy to point
back at the memory buffer we just copied into.
This code also needs to pin log items. If the log item is not
already tracked in this checkpoint context, then it needs to be
pinned. Otherwise it is already pinned and we don't need to pin it
again.
The only other complexity is calculating the amount of new log space
the formatting has consumed. This needs to be accounted to the
transaction in progress, and the accounting is made more complex
becase we need also to steal space from it for log metadata in the
checkpoint transaction. Calculate all this at insert time and update
all the tickets, counters, etc correctly.
Once we've formatted all the log items in the transaction, attach
the busy extents to the checkpoint context so the busy extents live
until checkpoint completion and can be processed at that point in
time. Transactions can then be freed at this point in time.
Now we need to issue checkpoints - we are tracking the amount of log space
used by the items in the CIL, so we can trigger background checkpoints when the
space usage gets to a certain threshold. Otherwise, checkpoints need ot be
triggered when a log synchronisation point is reached - a log force event.
Because the log write code already handles chained log vectors, writing the
transaction is trivial, too. Construct a transaction header, add it
to the head of the chain and write it into the log, then issue a
commit record write. Then we can release the checkpoint log ticket
and attach the context to the log buffer so it can be called during
Io completion to complete the checkpoint.
We also need to allow for synchronising multiple in-flight
checkpoints. This is needed for two things - the first is to ensure
that checkpoint commit records appear in the log in the correct
sequence order (so they are replayed in the correct order). The
second is so that xfs_log_force_lsn() operates correctly and only
flushes and/or waits for the specific sequence it was provided with.
To do this we need a wait variable and a list tracking the
checkpoint commits in progress. We can walk this list and wait for
the checkpoints to change state or complete easily, an this provides
the necessary synchronisation for correct operation in both cases.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 40d9595..ce558ef 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -655,7 +655,7 @@
* XFS_TRANS_SB_DIRTY will not be set when the transaction is updated but we
* still need to update the incore superblock with the changes.
*/
-STATIC void
+void
xfs_trans_unreserve_and_mod_sb(
xfs_trans_t *tp)
{
@@ -883,7 +883,7 @@
* they could be immediately flushed and we'd have to race with the flusher
* trying to pull the item from the AIL as we add it.
*/
-static void
+void
xfs_trans_item_committed(
struct xfs_log_item *lip,
xfs_lsn_t commit_lsn,
@@ -994,7 +994,7 @@
xfs_trans_unreserve_and_mod_sb(tp);
xfs_trans_unreserve_and_mod_dquots(tp);
- xfs_trans_free_items(tp, flags);
+ xfs_trans_free_items(tp, NULLCOMMITLSN, flags);
xfs_trans_free(tp);
}
@@ -1144,6 +1144,93 @@
return xfs_log_release_iclog(mp, commit_iclog);
}
+/*
+ * Walk the log items and allocate log vector structures for
+ * each item large enough to fit all the vectors they require.
+ * Note that this format differs from the old log vector format in
+ * that there is no transaction header in these log vectors.
+ */
+STATIC struct xfs_log_vec *
+xfs_trans_alloc_log_vecs(
+ xfs_trans_t *tp)
+{
+ xfs_log_item_desc_t *lidp;
+ struct xfs_log_vec *lv = NULL;
+ struct xfs_log_vec *ret_lv = NULL;
+
+ lidp = xfs_trans_first_item(tp);
+
+ /* Bail out if we didn't find a log item. */
+ if (!lidp) {
+ ASSERT(0);
+ return NULL;
+ }
+
+ while (lidp != NULL) {
+ struct xfs_log_vec *new_lv;
+
+ /* Skip items which aren't dirty in this transaction. */
+ if (!(lidp->lid_flags & XFS_LID_DIRTY)) {
+ lidp = xfs_trans_next_item(tp, lidp);
+ continue;
+ }
+
+ /* Skip items that do not have any vectors for writing */
+ lidp->lid_size = IOP_SIZE(lidp->lid_item);
+ if (!lidp->lid_size) {
+ lidp = xfs_trans_next_item(tp, lidp);
+ continue;
+ }
+
+ new_lv = kmem_zalloc(sizeof(*new_lv) +
+ lidp->lid_size * sizeof(struct xfs_log_iovec),
+ KM_SLEEP);
+
+ /* The allocated iovec region lies beyond the log vector. */
+ new_lv->lv_iovecp = (struct xfs_log_iovec *)&new_lv[1];
+ new_lv->lv_niovecs = lidp->lid_size;
+ new_lv->lv_item = lidp->lid_item;
+ if (!ret_lv)
+ ret_lv = new_lv;
+ else
+ lv->lv_next = new_lv;
+ lv = new_lv;
+ lidp = xfs_trans_next_item(tp, lidp);
+ }
+
+ return ret_lv;
+}
+
+static int
+xfs_trans_commit_cil(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ xfs_lsn_t *commit_lsn,
+ int flags)
+{
+ struct xfs_log_vec *log_vector;
+ int error;
+
+ /*
+ * Get each log item to allocate a vector structure for
+ * the log item to to pass to the log write code. The
+ * CIL commit code will format the vector and save it away.
+ */
+ log_vector = xfs_trans_alloc_log_vecs(tp);
+ if (!log_vector)
+ return ENOMEM;
+
+ error = xfs_log_commit_cil(mp, tp, log_vector, commit_lsn, flags);
+ if (error)
+ return error;
+
+ current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+
+ /* xfs_trans_free_items() unlocks them first */
+ xfs_trans_free_items(tp, *commit_lsn, 0);
+ xfs_trans_free(tp);
+ return 0;
+}
/*
* xfs_trans_commit
@@ -1204,7 +1291,11 @@
xfs_trans_apply_sb_deltas(tp);
xfs_trans_apply_dquot_deltas(tp);
- error = xfs_trans_commit_iclog(mp, tp, &commit_lsn, flags);
+ if (mp->m_flags & XFS_MOUNT_DELAYLOG)
+ error = xfs_trans_commit_cil(mp, tp, &commit_lsn, flags);
+ else
+ error = xfs_trans_commit_iclog(mp, tp, &commit_lsn, flags);
+
if (error == ENOMEM) {
xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR);
error = XFS_ERROR(EIO);
@@ -1242,7 +1333,7 @@
error = XFS_ERROR(EIO);
}
current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
- xfs_trans_free_items(tp, error ? XFS_TRANS_ABORT : 0);
+ xfs_trans_free_items(tp, NULLCOMMITLSN, error ? XFS_TRANS_ABORT : 0);
xfs_trans_free(tp);
XFS_STATS_INC(xs_trans_empty);
@@ -1320,7 +1411,7 @@
/* mark this thread as no longer being in a transaction */
current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
- xfs_trans_free_items(tp, flags);
+ xfs_trans_free_items(tp, NULLCOMMITLSN, flags);
xfs_trans_free(tp);
}