xfs: AIL doesn't need manual pushing

We have a mechanism that checks the amount of log space remaining
available every time we make a transaction reservation. If the
amount of space is below a threshold (25% free) we push on the AIL
to tell it to do more work. To do this, we end up calculating the
LSN that the AIL needs to push to on every reservation and updating
the push target for the AIL with that new target LSN.

This is silly and expensive. The AIL is perfectly capable of
calculating the push target itself, and it will always be running
when the AIL contains objects.

What the target does is determine if the AIL needs to do
any work before it goes back to sleep. If we haven't run out of
reservation space or memory (or some other push all trigger), it
will simply go back to sleep for a while if there is more than 25%
of the journal space free without doing anything.

If there are items in the AIL at a lower LSN than the target, it
will try to push up to the target or to the point of getting stuck
before going back to sleep and trying again soon after.`

Hence we can modify the AIL to calculate it's own 25% push target
before it starts a push using the same reserve grant head based
calculation as is currently used, and remove all the places where we
ask the AIL to push to a new 25% free target. We can also drop the
minimum free space size of 256BBs from the calculation because the
25% of a minimum sized log is *always going to be larger than
256BBs.

This does still require a manual push in certain circumstances.
These circumstances arise when the AIL is not full, but the
reservation grants consume the entire of the free space in the log.
In this case, we still need to push on the AIL to free up space, so
when we hit this condition (i.e. reservation going to sleep to wait
on log space) we do a single push to tell the AIL it should empty
itself. This will keep the AIL moving as new reservations come in
and want more space, rather than keep queuing them and having to
push the AIL repeatedly.

The reason for using the "push all" when grant space runs out is
that we can run out of grant space when there is more than 25% of
the log free. Small logs are notorious for this, and we have a hack
in the log callback code (xlog_state_set_callback()) where we push
the AIL because the *head* moved) to ensure that we kick the AIL
when we consume space in it because that can push us over the "less
than 25% available" available that starts tail pushing back up
again.

Hence when we run out of grant space and are going to sleep, we have
to consider that the grant space may be consuming almost all the log
space and there is almost nothing in the AIL. In this situation, the
AIL pins the tail and moving the tail forwards is the only way the
grant space will come available, so we have to force the AIL to push
everything to guarantee grant space will eventually be returned.
Hence triggering a "push all" just before sleeping removes all the
nasty corner cases we have in other parts of the code that work
around the "we didn't ask the AIL to push enough to free grant
space" condition that leads to log space hangs...

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>

1 files changed, 71 insertions, 91 deletions

diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index e4c343096f95..a6b6fca1d138 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -135,25 +135,6 @@ xfs_ail_min_lsn(
 }
 
 /*
- * Return the maximum lsn held in the AIL, or zero if the AIL is empty.
- */
-static xfs_lsn_t
-xfs_ail_max_lsn(
-	struct xfs_ail		*ailp)
-{
-	xfs_lsn_t       	lsn = 0;
-	struct xfs_log_item	*lip;
-
-	spin_lock(&ailp->ail_lock);
-	lip = xfs_ail_max(ailp);
-	if (lip)
-		lsn = lip->li_lsn;
-	spin_unlock(&ailp->ail_lock);
-
-	return lsn;
-}
-
-/*
  * The cursor keeps track of where our current traversal is up to by tracking
  * the next item in the list for us. However, for this to be safe, removing an
  * object from the AIL needs to invalidate any cursor that points to it. hence
@@ -414,6 +395,56 @@ xfsaild_push_item(
 	return lip->li_ops->iop_push(lip, &ailp->ail_buf_list);
 }
 
+/*
+ * Compute the LSN that we'd need to push the log tail towards in order to have
+ * at least 25% of the log space free.  If the log free space already meets this
+ * threshold, this function returns NULLCOMMITLSN.
+ */
+xfs_lsn_t
+__xfs_ail_push_target(
+	struct xfs_ail		*ailp)
+{
+	struct xlog	*log = ailp->ail_log;
+	xfs_lsn_t	threshold_lsn = 0;
+	xfs_lsn_t	last_sync_lsn;
+	int		free_blocks;
+	int		free_bytes;
+	int		threshold_block;
+	int		threshold_cycle;
+	int		free_threshold;
+
+	free_bytes = xlog_space_left(log, &log->l_reserve_head.grant);
+	free_blocks = BTOBBT(free_bytes);
+
+	/*
+	 * The threshold for the minimum number of free blocks is one quarter of
+	 * the entire log space.
+	 */
+	free_threshold = log->l_logBBsize >> 2;
+	if (free_blocks >= free_threshold)
+		return NULLCOMMITLSN;
+
+	xlog_crack_atomic_lsn(&log->l_tail_lsn, &threshold_cycle,
+						&threshold_block);
+	threshold_block += free_threshold;
+	if (threshold_block >= log->l_logBBsize) {
+		threshold_block -= log->l_logBBsize;
+		threshold_cycle += 1;
+	}
+	threshold_lsn = xlog_assign_lsn(threshold_cycle,
+					threshold_block);
+	/*
+	 * Don't pass in an lsn greater than the lsn of the last
+	 * log record known to be on disk. Use a snapshot of the last sync lsn
+	 * so that it doesn't change between the compare and the set.
+	 */
+	last_sync_lsn = atomic64_read(&log->l_last_sync_lsn);
+	if (XFS_LSN_CMP(threshold_lsn, last_sync_lsn) > 0)
+		threshold_lsn = last_sync_lsn;
+
+	return threshold_lsn;
+}
+
 static long
 xfsaild_push(
 	struct xfs_ail		*ailp)
@@ -454,21 +485,24 @@ xfsaild_push(
 	 * capture updates that occur after the sync push waiter has gone to
 	 * sleep.
 	 */
-	if (waitqueue_active(&ailp->ail_empty)) {
+	if (test_bit(XFS_AIL_OPSTATE_PUSH_ALL, &ailp->ail_opstate) ||
+	    waitqueue_active(&ailp->ail_empty)) {
 		lip = xfs_ail_max(ailp);
 		if (lip)
 			target = lip->li_lsn;
+		else
+			clear_bit(XFS_AIL_OPSTATE_PUSH_ALL, &ailp->ail_opstate);
 	} else {
-		/* barrier matches the ail_target update in xfs_ail_push() */
-		smp_rmb();
-		target = ailp->ail_target;
-		ailp->ail_target_prev = target;
+		target = __xfs_ail_push_target(ailp);
 	}
 
+	if (target == NULLCOMMITLSN)
+		goto out_done;
+
 	/* we're done if the AIL is empty or our push has reached the end */
 	lip = xfs_trans_ail_cursor_first(ailp, &cur, ailp->ail_last_pushed_lsn);
 	if (!lip)
-		goto out_done;
+		goto out_done_cursor;
 
 	XFS_STATS_INC(mp, xs_push_ail);
 
@@ -553,8 +587,9 @@ xfsaild_push(
 		lsn = lip->li_lsn;
 	}
 
-out_done:
+out_done_cursor:
 	xfs_trans_ail_cursor_done(&cur);
+out_done:
 	spin_unlock(&ailp->ail_lock);
 
 	if (xfs_buf_delwri_submit_nowait(&ailp->ail_buf_list))
@@ -603,7 +638,7 @@ xfsaild(
 	set_freezable();
 
 	while (1) {
-		if (tout && tout <= 20)
+		if (tout)
 			set_current_state(TASK_KILLABLE|TASK_FREEZABLE);
 		else
 			set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
@@ -639,21 +674,9 @@ xfsaild(
 			break;
 		}
 
+		/* Idle if the AIL is empty. */
 		spin_lock(&ailp->ail_lock);
-
-		/*
-		 * Idle if the AIL is empty and we are not racing with a target
-		 * update. We check the AIL after we set the task to a sleep
-		 * state to guarantee that we either catch an ail_target update
-		 * or that a wake_up resets the state to TASK_RUNNING.
-		 * Otherwise, we run the risk of sleeping indefinitely.
-		 *
-		 * The barrier matches the ail_target update in xfs_ail_push().
-		 */
-		smp_rmb();
-		if (!xfs_ail_min(ailp) &&
-		    ailp->ail_target == ailp->ail_target_prev &&
-		    list_empty(&ailp->ail_buf_list)) {
+		if (!xfs_ail_min(ailp) && list_empty(&ailp->ail_buf_list)) {
 			spin_unlock(&ailp->ail_lock);
 			schedule();
 			tout = 0;
@@ -676,56 +699,6 @@ xfsaild(
 }
 
 /*
- * This routine is called to move the tail of the AIL forward.  It does this by
- * trying to flush items in the AIL whose lsns are below the given
- * threshold_lsn.
- *
- * The push is run asynchronously in a workqueue, which means the caller needs
- * to handle waiting on the async flush for space to become available.
- * We don't want to interrupt any push that is in progress, hence we only queue
- * work if we set the pushing bit appropriately.
- *
- * We do this unlocked - we only need to know whether there is anything in the
- * AIL at the time we are called. We don't need to access the contents of
- * any of the objects, so the lock is not needed.
- */
-void
-xfs_ail_push(
-	struct xfs_ail		*ailp,
-	xfs_lsn_t		threshold_lsn)
-{
-	struct xfs_log_item	*lip;
-
-	lip = xfs_ail_min(ailp);
-	if (!lip || xlog_is_shutdown(ailp->ail_log) ||
-	    XFS_LSN_CMP(threshold_lsn, ailp->ail_target) <= 0)
-		return;
-
-	/*
-	 * Ensure that the new target is noticed in push code before it clears
-	 * the XFS_AIL_PUSHING_BIT.
-	 */
-	smp_wmb();
-	xfs_trans_ail_copy_lsn(ailp, &ailp->ail_target, &threshold_lsn);
-	smp_wmb();
-
-	wake_up_process(ailp->ail_task);
-}
-
-/*
- * Push out all items in the AIL immediately
- */
-void
-xfs_ail_push_all(
-	struct xfs_ail  *ailp)
-{
-	xfs_lsn_t       threshold_lsn = xfs_ail_max_lsn(ailp);
-
-	if (threshold_lsn)
-		xfs_ail_push(ailp, threshold_lsn);
-}
-
-/*
  * Push out all items in the AIL immediately and wait until the AIL is empty.
  */
 void
@@ -829,6 +802,13 @@ xfs_trans_ail_update_bulk(
 	if (!list_empty(&tmp))
 		xfs_ail_splice(ailp, cur, &tmp, lsn);
 
+	/*
+	 * If this is the first insert, wake up the push daemon so it can
+	 * actively scan for items to push.
+	 */
+	if (!mlip)
+		wake_up_process(ailp->ail_task);
+
 	xfs_ail_update_finish(ailp, tail_lsn);
 }