xfs: byte-base grant head reservation tracking

From: Dave Chinner <[email protected]>

Ever since the CIL and delayed logging was introduced, xfs_trans_committed_bulk() has been a purely CIL checkpoint completion function and not a transaction commit completion function. Now that we are adding log specific updates to this function, it really does not have anything to do with the transaction subsystem - it is really log and log item level functionality.

This should be part of the CIL code as it is the callback that moves log items from the CIL checkpoint to the AIL. Move it and rename it to xlog_cil_ail_insert().

Signed-off-by Dave Chinner <[email protected]>

---
 fs/xfs/xfs_log_cil.c    | 132 +++++++++++++++++++++++++++++++++++++++-
 fs/xfs/xfs_trans.c      | 129 ---------------------------------------
 fs/xfs/xfs_trans_priv.h |   3 -
 3 files changed, 131 insertions(+), 133 deletions(-)

fs/xfs/xfs_log_cil.c +131 -1

index eccbfb99e894..475a18493c37 100644
@@ -683,6 +683,136 @@ xlog_cil_insert_items(
 	}
 }
 
+static inline void
+xlog_cil_ail_insert_batch(
+	struct xfs_ail		*ailp,
+	struct xfs_ail_cursor	*cur,
+	struct xfs_log_item	**log_items,
+	int			nr_items,
+	xfs_lsn_t		commit_lsn)
+{
+	int	i;
+
+	spin_lock(&ailp->ail_lock);
+	/* xfs_trans_ail_update_bulk drops ailp->ail_lock */
+	xfs_trans_ail_update_bulk(ailp, cur, log_items, nr_items, commit_lsn);
+
+	for (i = 0; i < nr_items; i++) {
+		struct xfs_log_item *lip = log_items[i];
+
+		if (lip->li_ops->iop_unpin)
+			lip->li_ops->iop_unpin(lip, 0);
+	}
+}
+
+/*
+ * Take the checkpoint's log vector chain of items and insert the attached log
+ * items into the the AIL. This uses bulk insertion techniques to minimise AIL
+ * lock traffic.
+ *
+ * If we are called with the aborted flag set, it is because a log write during
+ * a CIL checkpoint commit has failed. In this case, all the items in the
+ * checkpoint have already gone through iop_committed and iop_committing, which
+ * means that checkpoint commit abort handling is treated exactly the same as an
+ * iclog write error even though we haven't started any IO yet. Hence in this
+ * case all we need to do is iop_committed processing, followed by an
+ * iop_unpin(aborted) call.
+ *
+ * The AIL cursor is used to optimise the insert process. If commit_lsn is not
+ * at the end of the AIL, the insert cursor avoids the need to walk the AIL to
+ * find the insertion point on every xfs_log_item_batch_insert() call. This
+ * saves a lot of needless list walking and is a net win, even though it
+ * slightly increases that amount of AIL lock traffic to set it up and tear it
+ * down.
+ */
+void
+xlog_cil_ail_insert(
+	struct xlog		*log,
+	struct list_head	*lv_chain,
+	xfs_lsn_t		commit_lsn,
+	bool			aborted)
+{
+#define LOG_ITEM_BATCH_SIZE	32
+	struct xfs_ail		*ailp = log->l_ailp;
+	struct xfs_log_item	*log_items[LOG_ITEM_BATCH_SIZE];
+	struct xfs_log_vec	*lv;
+	struct xfs_ail_cursor	cur;
+	int			i = 0;
+
+	spin_lock(&ailp->ail_lock);
+	xfs_trans_ail_cursor_last(ailp, &cur, commit_lsn);
+	spin_unlock(&ailp->ail_lock);
+
+	/* unpin all the log items */
+	list_for_each_entry(lv, lv_chain, lv_list) {
+		struct xfs_log_item	*lip = lv->lv_item;
+		xfs_lsn_t		item_lsn;
+
+		if (aborted)
+			set_bit(XFS_LI_ABORTED, &lip->li_flags);
+
+		if (lip->li_ops->flags & XFS_ITEM_RELEASE_WHEN_COMMITTED) {
+			lip->li_ops->iop_release(lip);
+			continue;
+		}
+
+		if (lip->li_ops->iop_committed)
+			item_lsn = lip->li_ops->iop_committed(lip, commit_lsn);
+		else
+			item_lsn = commit_lsn;
+
+		/* item_lsn of -1 means the item needs no further processing */
+		if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0)
+			continue;
+
+		/*
+		 * if we are aborting the operation, no point in inserting the
+		 * object into the AIL as we are in a shutdown situation.
+		 */
+		if (aborted) {
+			ASSERT(xlog_is_shutdown(ailp->ail_log));
+			if (lip->li_ops->iop_unpin)
+				lip->li_ops->iop_unpin(lip, 1);
+			continue;
+		}
+
+		if (item_lsn != commit_lsn) {
+
+			/*
+			 * Not a bulk update option due to unusual item_lsn.
+			 * Push into AIL immediately, rechecking the lsn once
+			 * we have the ail lock. Then unpin the item. This does
+			 * not affect the AIL cursor the bulk insert path is
+			 * using.
+			 */
+			spin_lock(&ailp->ail_lock);
+			if (XFS_LSN_CMP(item_lsn, lip->li_lsn) > 0)
+				xfs_trans_ail_update(ailp, lip, item_lsn);
+			else
+				spin_unlock(&ailp->ail_lock);
+			if (lip->li_ops->iop_unpin)
+				lip->li_ops->iop_unpin(lip, 0);
+			continue;
+		}
+
+		/* Item is a candidate for bulk AIL insert.  */
+		log_items[i++] = lv->lv_item;
+		if (i >= LOG_ITEM_BATCH_SIZE) {
+			xlog_cil_ail_insert_batch(ailp, &cur, log_items,
+					LOG_ITEM_BATCH_SIZE, commit_lsn);
+			i = 0;
+		}
+	}
+
+	/* make sure we insert the remainder! */
+	if (i)
+		xlog_cil_ail_insert_batch(ailp, &cur, log_items, i, commit_lsn);
+
+	spin_lock(&ailp->ail_lock);
+	xfs_trans_ail_cursor_done(&cur);
+	spin_unlock(&ailp->ail_lock);
+}
+
 static void
 xlog_cil_free_logvec(
 	struct list_head	*lv_chain)

@@ -792,7 +922,7 @@ xlog_cil_committed(
 		spin_unlock(&ctx->cil->xc_push_lock);
 	}
 
-	xfs_trans_committed_bulk(ctx->cil->xc_log->l_ailp, &ctx->lv_chain,
+	xlog_cil_ail_insert(ctx->cil->xc_log, &ctx->lv_chain,
 					ctx->start_lsn, abort);
 
 	xfs_extent_busy_sort(&ctx->busy_extents);

fs/xfs/xfs_trans.c +0 -129

index 7bd16fbff534..58c4e875eb12 100644
@@ -715,135 +715,6 @@ xfs_trans_free_items(
 	}
 }
 
-static inline void
-xfs_log_item_batch_insert(
-	struct xfs_ail		*ailp,
-	struct xfs_ail_cursor	*cur,
-	struct xfs_log_item	**log_items,
-	int			nr_items,
-	xfs_lsn_t		commit_lsn)
-{
-	int	i;
-
-	spin_lock(&ailp->ail_lock);
-	/* xfs_trans_ail_update_bulk drops ailp->ail_lock */
-	xfs_trans_ail_update_bulk(ailp, cur, log_items, nr_items, commit_lsn);
-
-	for (i = 0; i < nr_items; i++) {
-		struct xfs_log_item *lip = log_items[i];
-
-		if (lip->li_ops->iop_unpin)
-			lip->li_ops->iop_unpin(lip, 0);
-	}
-}
-
-/*
- * Bulk operation version of xfs_trans_committed that takes a log vector of
- * items to insert into the AIL. This uses bulk AIL insertion techniques to
- * minimise lock traffic.
- *
- * If we are called with the aborted flag set, it is because a log write during
- * a CIL checkpoint commit has failed. In this case, all the items in the
- * checkpoint have already gone through iop_committed and iop_committing, which
- * means that checkpoint commit abort handling is treated exactly the same
- * as an iclog write error even though we haven't started any IO yet. Hence in
- * this case all we need to do is iop_committed processing, followed by an
- * iop_unpin(aborted) call.
- *
- * The AIL cursor is used to optimise the insert process. If commit_lsn is not
- * at the end of the AIL, the insert cursor avoids the need to walk
- * the AIL to find the insertion point on every xfs_log_item_batch_insert()
- * call. This saves a lot of needless list walking and is a net win, even
- * though it slightly increases that amount of AIL lock traffic to set it up
- * and tear it down.
- */
-void
-xfs_trans_committed_bulk(
-	struct xfs_ail		*ailp,
-	struct list_head	*lv_chain,
-	xfs_lsn_t		commit_lsn,
-	bool			aborted)
-{
-#define LOG_ITEM_BATCH_SIZE	32
-	struct xfs_log_item	*log_items[LOG_ITEM_BATCH_SIZE];
-	struct xfs_log_vec	*lv;
-	struct xfs_ail_cursor	cur;
-	int			i = 0;
-
-	spin_lock(&ailp->ail_lock);
-	xfs_trans_ail_cursor_last(ailp, &cur, commit_lsn);
-	spin_unlock(&ailp->ail_lock);
-
-	/* unpin all the log items */
-	list_for_each_entry(lv, lv_chain, lv_list) {
-		struct xfs_log_item	*lip = lv->lv_item;
-		xfs_lsn_t		item_lsn;
-
-		if (aborted)
-			set_bit(XFS_LI_ABORTED, &lip->li_flags);
-
-		if (lip->li_ops->flags & XFS_ITEM_RELEASE_WHEN_COMMITTED) {
-			lip->li_ops->iop_release(lip);
-			continue;
-		}
-
-		if (lip->li_ops->iop_committed)
-			item_lsn = lip->li_ops->iop_committed(lip, commit_lsn);
-		else
-			item_lsn = commit_lsn;
-
-		/* item_lsn of -1 means the item needs no further processing */
-		if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0)
-			continue;
-
-		/*
-		 * if we are aborting the operation, no point in inserting the
-		 * object into the AIL as we are in a shutdown situation.
-		 */
-		if (aborted) {
-			ASSERT(xlog_is_shutdown(ailp->ail_log));
-			if (lip->li_ops->iop_unpin)
-				lip->li_ops->iop_unpin(lip, 1);
-			continue;
-		}
-
-		if (item_lsn != commit_lsn) {
-
-			/*
-			 * Not a bulk update option due to unusual item_lsn.
-			 * Push into AIL immediately, rechecking the lsn once
-			 * we have the ail lock. Then unpin the item. This does
-			 * not affect the AIL cursor the bulk insert path is
-			 * using.
-			 */
-			spin_lock(&ailp->ail_lock);
-			if (XFS_LSN_CMP(item_lsn, lip->li_lsn) > 0)
-				xfs_trans_ail_update(ailp, lip, item_lsn);
-			else
-				spin_unlock(&ailp->ail_lock);
-			if (lip->li_ops->iop_unpin)
-				lip->li_ops->iop_unpin(lip, 0);
-			continue;
-		}
-
-		/* Item is a candidate for bulk AIL insert.  */
-		log_items[i++] = lv->lv_item;
-		if (i >= LOG_ITEM_BATCH_SIZE) {
-			xfs_log_item_batch_insert(ailp, &cur, log_items,
-					LOG_ITEM_BATCH_SIZE, commit_lsn);
-			i = 0;
-		}
-	}
-
-	/* make sure we insert the remainder! */
-	if (i)
-		xfs_log_item_batch_insert(ailp, &cur, log_items, i, commit_lsn);
-
-	spin_lock(&ailp->ail_lock);
-	xfs_trans_ail_cursor_done(&cur);
-	spin_unlock(&ailp->ail_lock);
-}
-
 /*
  * Sort transaction items prior to running precommit operations. This will
  * attempt to order the items such that they will always be locked in the same

fs/xfs/xfs_trans_priv.h +0 -3

index d5400150358e..52a45f0a5ef1 100644
@@ -19,9 +19,6 @@ void	xfs_trans_add_item(struct xfs_trans *, struct xfs_log_item *);
 void	xfs_trans_del_item(struct xfs_log_item *);
 void	xfs_trans_unreserve_and_mod_sb(struct xfs_trans *tp);
 
-void	xfs_trans_committed_bulk(struct xfs_ail *ailp,
-				struct list_head *lv_chain,
-				xfs_lsn_t commit_lsn, bool aborted);
 /*
  * AIL traversal cursor.
  *

Signature · 1 line

2.36.1

From: Dave Chinner <[email protected]>

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.

Modify the AIL to calculate it's 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.

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.

Signed-off-by Dave Chinner <[email protected]>

---
 fs/xfs/libxfs/xfs_defer.c |   4 +-
 fs/xfs/xfs_log.c          | 135 ++-----------------------------
 fs/xfs/xfs_log.h          |   1 -
 fs/xfs/xfs_log_priv.h     |   2 +
 fs/xfs/xfs_trans_ail.c    | 165 +++++++++++++++++---------------------
 fs/xfs/xfs_trans_priv.h   |  33 ++++++--
 6 files changed, 110 insertions(+), 230 deletions(-)

fs/xfs/libxfs/xfs_defer.c +3 -1

index 5a321b783398..79c077078785 100644
@@ -12,12 +12,14 @@
 #include "xfs_mount.h"
 #include "xfs_defer.h"
 #include "xfs_trans.h"
+#include "xfs_trans_priv.h"
 #include "xfs_buf_item.h"
 #include "xfs_inode.h"
 #include "xfs_inode_item.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
 #include "xfs_log.h"
+#include "xfs_log_priv.h"
 #include "xfs_rmap.h"
 #include "xfs_refcount.h"
 #include "xfs_bmap.h"

@@ -439,7 +441,7 @@ xfs_defer_relog(
 		 * the log threshold once per call.
 		 */
 		if (threshold_lsn == NULLCOMMITLSN) {
-			threshold_lsn = xlog_grant_push_threshold(log, 0);
+			threshold_lsn = xfs_ail_push_target(log->l_ailp);
 			if (threshold_lsn == NULLCOMMITLSN)
 				break;
 		}

fs/xfs/xfs_log.c +5 -130

index 4b1c0a9c6368..c609c188bd8a 100644
@@ -30,10 +30,6 @@ xlog_alloc_log(
 	struct xfs_buftarg	*log_target,
 	xfs_daddr_t		blk_offset,
 	int			num_bblks);
-STATIC int
-xlog_space_left(
-	struct xlog		*log,
-	atomic64_t		*head);
 STATIC void
 xlog_dealloc_log(
 	struct xlog		*log);

@@ -51,10 +47,6 @@ xlog_state_get_iclog_space(
 	struct xlog_ticket	*ticket,
 	int			*logoffsetp);
 STATIC void
-xlog_grant_push_ail(
-	struct xlog		*log,
-	int			need_bytes);
-STATIC void
 xlog_sync(
 	struct xlog		*log,
 	struct xlog_in_core	*iclog,

@@ -242,42 +234,15 @@ xlog_grant_head_wake(
 {
 	struct xlog_ticket	*tic;
 	int			need_bytes;
-	bool			woken_task = false;
 
 	list_for_each_entry(tic, &head->waiters, t_queue) {
-
-		/*
-		 * There is a chance that the size of the CIL checkpoints in
-		 * progress at the last AIL push target calculation resulted in
-		 * limiting the target to the log head (l_last_sync_lsn) at the
-		 * time. This may not reflect where the log head is now as the
-		 * CIL checkpoints may have completed.
-		 *
-		 * Hence when we are woken here, it may be that the head of the
-		 * log that has moved rather than the tail. As the tail didn't
-		 * move, there still won't be space available for the
-		 * reservation we require.  However, if the AIL has already
-		 * pushed to the target defined by the old log head location, we
-		 * will hang here waiting for something else to update the AIL
-		 * push target.
-		 *
-		 * Therefore, if there isn't space to wake the first waiter on
-		 * the grant head, we need to push the AIL again to ensure the
-		 * target reflects both the current log tail and log head
-		 * position before we wait for the tail to move again.
-		 */
-
 		need_bytes = xlog_ticket_reservation(log, head, tic);
-		if (*free_bytes < need_bytes) {
-			if (!woken_task)
-				xlog_grant_push_ail(log, need_bytes);
+		if (*free_bytes < need_bytes)
 			return false;
-		}
 
 		*free_bytes -= need_bytes;
 		trace_xfs_log_grant_wake_up(log, tic);
 		wake_up_process(tic->t_task);
-		woken_task = true;
 	}
 
 	return true;

@@ -296,13 +261,15 @@ xlog_grant_head_wait(
 	do {
 		if (xlog_is_shutdown(log))
 			goto shutdown;
-		xlog_grant_push_ail(log, need_bytes);
 
 		__set_current_state(TASK_UNINTERRUPTIBLE);
 		spin_unlock(&head->lock);
 
 		XFS_STATS_INC(log->l_mp, xs_sleep_logspace);
 
+		/* Push on the AIL to free up all the log space. */
+		xfs_ail_push_all(log->l_ailp);
+
 		trace_xfs_log_grant_sleep(log, tic);
 		schedule();
 		trace_xfs_log_grant_wake(log, tic);

@@ -418,9 +385,6 @@ xfs_log_regrant(
 	 * of rolling transactions in the log easily.
 	 */
 	tic->t_tid++;
-
-	xlog_grant_push_ail(log, tic->t_unit_res);
-
 	tic->t_curr_res = tic->t_unit_res;
 	if (tic->t_cnt > 0)
 		return 0;

@@ -477,12 +441,7 @@ xfs_log_reserve(
 	ASSERT(*ticp == NULL);
 	tic = xlog_ticket_alloc(log, unit_bytes, cnt, permanent);
 	*ticp = tic;
-
-	xlog_grant_push_ail(log, tic->t_cnt ? tic->t_unit_res * tic->t_cnt
-					    : tic->t_unit_res);
-
 	trace_xfs_log_reserve(log, tic);
-
 	error = xlog_grant_head_check(log, &log->l_reserve_head, tic,
 				      &need_bytes);
 	if (error)

@@ -1337,7 +1296,7 @@ xlog_assign_tail_lsn(
  * shortcut invalidity asserts in this case so that we don't trigger them
  * falsely.
  */
-STATIC int
+int
 xlog_space_left(
 	struct xlog	*log,
 	atomic64_t	*head)

@@ -1678,89 +1637,6 @@ xlog_alloc_log(
 	return ERR_PTR(error);
 }	/* xlog_alloc_log */
 
-/*
- * Compute the LSN that we'd need to push the log tail towards in order to have
- * (a) enough on-disk log space to log the number of bytes specified, (b) at
- * least 25% of the log space free, and (c) at least 256 blocks free.  If the
- * log free space already meets all three thresholds, this function returns
- * NULLCOMMITLSN.
- */
-xfs_lsn_t
-xlog_grant_push_threshold(
-	struct xlog	*log,
-	int		need_bytes)
-{
-	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;
-
-	ASSERT(BTOBB(need_bytes) < log->l_logBBsize);
-
-	free_bytes = xlog_space_left(log, &log->l_reserve_head.grant);
-	free_blocks = BTOBBT(free_bytes);
-
-	/*
-	 * Set the threshold for the minimum number of free blocks in the
-	 * log to the maximum of what the caller needs, one quarter of the
-	 * log, and 256 blocks.
-	 */
-	free_threshold = BTOBB(need_bytes);
-	free_threshold = max(free_threshold, (log->l_logBBsize >> 2));
-	free_threshold = max(free_threshold, 256);
-	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;
-}
-
-/*
- * Push the tail of the log if we need to do so to maintain the free log space
- * thresholds set out by xlog_grant_push_threshold.  We may need to adopt a
- * policy which pushes on an lsn which is further along in the log once we
- * reach the high water mark.  In this manner, we would be creating a low water
- * mark.
- */
-STATIC void
-xlog_grant_push_ail(
-	struct xlog	*log,
-	int		need_bytes)
-{
-	xfs_lsn_t	threshold_lsn;
-
-	threshold_lsn = xlog_grant_push_threshold(log, need_bytes);
-	if (threshold_lsn == NULLCOMMITLSN || xlog_is_shutdown(log))
-		return;
-
-	/*
-	 * Get the transaction layer to kick the dirty buffers out to
-	 * disk asynchronously. No point in trying to do this if
-	 * the filesystem is shutting down.
-	 */
-	xfs_ail_push(log->l_ailp, threshold_lsn);
-}
-
 /*
  * Stamp cycle number in every block
  */

@@ -2725,7 +2601,6 @@ xlog_state_set_callback(
 		return;
 
 	atomic64_set(&log->l_last_sync_lsn, header_lsn);
-	xlog_grant_push_ail(log, 0);
 }
 
 /*

fs/xfs/xfs_log.h +0 -1

index 2728886c2963..6b6ee35b3885 100644
@@ -156,7 +156,6 @@ int	xfs_log_quiesce(struct xfs_mount *mp);
 void	xfs_log_clean(struct xfs_mount *mp);
 bool	xfs_log_check_lsn(struct xfs_mount *, xfs_lsn_t);
 
-xfs_lsn_t xlog_grant_push_threshold(struct xlog *log, int need_bytes);
 bool	  xlog_force_shutdown(struct xlog *log, uint32_t shutdown_flags);
 
 void xlog_use_incompat_feat(struct xlog *log);

fs/xfs/xfs_log_priv.h +2 -0

index 1bd2963e8fbd..91a8c74f4626 100644
@@ -573,6 +573,8 @@ xlog_assign_grant_head(atomic64_t *head, int cycle, int space)
 	atomic64_set(head, xlog_assign_grant_head_val(cycle, space));
 }
 
+int xlog_space_left(struct xlog	 *log, atomic64_t *head);
+
 /*
  * Committed Item List interfaces
  */

fs/xfs/xfs_trans_ail.c +18 -19

index d3a97a028560..243d6b05e5a9 100644
@@ -134,25 +134,6 @@ xfs_ail_min_lsn(
 	return 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

@@ -414,6 +395,57 @@ 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;
+

fs/xfs/xfs_trans_ail.c +26 -2

+		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)

@@ -422,7 +454,7 @@ xfsaild_push(
 	struct xfs_ail_cursor	cur;
 	struct xfs_log_item	*lip;
 	xfs_lsn_t		lsn;
-	xfs_lsn_t		target;
+	xfs_lsn_t		target = NULLCOMMITLSN;
 	long			tout;
 	int			stuck = 0;
 	int			flushing = 0;

@@ -454,21 +486,24 @@ 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);

fs/xfs/xfs_trans_ail.c +16 -67

 	}
 
+	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);
 

@@ -551,8 +586,9 @@ 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))

@@ -601,7 +637,7 @@ xfsaild(
 	set_freezable();
 
 	while (1) {
-		if (tout && tout <= 20)
+		if (tout)
 			set_current_state(TASK_KILLABLE);
 		else
 			set_current_state(TASK_INTERRUPTIBLE);

@@ -637,21 +673,9 @@ 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);
 			freezable_schedule();
 			tout = 0;

@@ -673,56 +697,6 @@ xfsaild(
 	return 0;
 }
 
-/*
- * 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.
  */

@@ -828,6 +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);
 }
 

fs/xfs/xfs_trans_priv.h +27 -6

index 52a45f0a5ef1..9a131e7fae94 100644
@@ -52,16 +52,18 @@ struct xfs_ail {
 	struct xlog		*ail_log;
 	struct task_struct	*ail_task;
 	struct list_head	ail_head;
-	xfs_lsn_t		ail_target;
-	xfs_lsn_t		ail_target_prev;
 	struct list_head	ail_cursors;
 	spinlock_t		ail_lock;
 	xfs_lsn_t		ail_last_pushed_lsn;
 	int			ail_log_flush;
+	unsigned long		ail_opstate;
 	struct list_head	ail_buf_list;
 	wait_queue_head_t	ail_empty;
 };
 
+/* Push all items out of the AIL immediately. */
+#define XFS_AIL_OPSTATE_PUSH_ALL	0u
+
 /*
  * From xfs_trans_ail.c
  */

@@ -98,10 +100,29 @@ void xfs_ail_update_finish(struct xfs_ail *ailp, xfs_lsn_t old_lsn)
 			__releases(ailp->ail_lock);
 void xfs_trans_ail_delete(struct xfs_log_item *lip, int shutdown_type);
 
-void			xfs_ail_push(struct xfs_ail *, xfs_lsn_t);
-void			xfs_ail_push_all(struct xfs_ail *);
-void			xfs_ail_push_all_sync(struct xfs_ail *);
-struct xfs_log_item	*xfs_ail_min(struct xfs_ail  *ailp);
+static inline void xfs_ail_push(struct xfs_ail *ailp)
+{
+	wake_up_process(ailp->ail_task);
+}
+
+static inline void xfs_ail_push_all(struct xfs_ail *ailp)
+{
+	if (!test_and_set_bit(XFS_AIL_OPSTATE_PUSH_ALL, &ailp->ail_opstate))
+		xfs_ail_push(ailp);
+}
+
+xfs_lsn_t		__xfs_ail_push_target(struct xfs_ail *ailp);
+static inline xfs_lsn_t xfs_ail_push_target(struct xfs_ail *ailp)
+{
+	xfs_lsn_t	lsn;
+
+	spin_lock(&ailp->ail_lock);
+	lsn = __xfs_ail_push_target(ailp);
+	spin_unlock(&ailp->ail_lock);
+	return lsn;
+}
+
+void			xfs_ail_push_all_sync(struct xfs_ail *ailp);
 xfs_lsn_t		xfs_ail_min_lsn(struct xfs_ail *ailp);
 
 struct xfs_log_item *	xfs_trans_ail_cursor_first(struct xfs_ail *ailp,

Signature · 1 line

2.36.1

Quoted 17 lines · Dave Chinner

From: Dave Chinner <[email protected]>

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.

Modify the AIL to calculate it's 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.

Quoted 28 lines

fs/xfs/xfs_trans_ail.c +24 -0

@@ -414,6 +395,57 @@ 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);
+
+	/*
+	 * Set the threshold for the minimum number of free blocks in the
+	 * log to the maximum of what the caller needs, one quarter of the

fs/xfs/xfs_trans_ail.c xfsaild_push_item( · line 425

Quoted 4 lines

fs/xfs/xfs_trans_ail.c +4 -0

+	 * log, and 256 blocks.
+	 */
+	free_threshold = log->l_logBBsize >> 2;
+	if (free_blocks >= free_threshold)

What happened to the "free_threshold = max(free_threshold, 256);" from the old code? Or is the documented 256 block minimum no longer necessary?

Quoted 15 lines

fs/xfs/xfs_trans_ail.c +4 -3

@@ -454,21 +486,24 @@ 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();

fs/xfs/xfs_trans_ail.c xfsaild_push( · line 497

Quoted 3 lines

fs/xfs/xfs_trans_ail.c +1 -2

-		target = ailp->ail_target;
-		ailp->ail_target_prev = target;
+		target = __xfs_ail_push_target(ailp);

Hmm. So now the AIL decides how far it ought to push itself: until 25% of the log is free if nobody's watching, or all the way to the end if there are xfs_ail_push_all_sync waiters or OPSTATE_PUSH_ALL is set because someone needs grant space?

So the xlog*grant* callers now merely wake up the AIL and let push whatever it will, instead of telling the AIL how far to push itself?

Does that mean that those grant callers might have to wait until the AIL empties itself?

Quoted 18 lines · Darrick J. Wong

Quoted 17 lines · Dave Chinner

From: Dave Chinner <[email protected]>

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.

Modify the AIL to calculate it's 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.

.....

Quoted 28 lines

Quoted 28 lines

fs/xfs/xfs_trans_ail.c +24 -0

@@ -414,6 +395,57 @@ 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);
+
+	/*
+	 * Set the threshold for the minimum number of free blocks in the
+	 * log to the maximum of what the caller needs, one quarter of the

Quoted 8 lines

fs/xfs/xfs_trans_ail.c xfsaild_push_item( · line 425

Quoted 4 lines

fs/xfs/xfs_trans_ail.c +4 -0

+	 * log, and 256 blocks.
+	 */
+	free_threshold = log->l_logBBsize >> 2;
+	if (free_blocks >= free_threshold)

What happened to the "free_threshold = max(free_threshold, 256);" from the old code? Or is the documented 256 block minimum no longer necessary?

Oh, I must have dropped the comment change when fixing the last round of rebase conflicts. The minimum of 256 blocks is largely useless because the even the smallest logs we create on tiny filesystems are around 1000 filesystem blocks in size. So a minimum free threshold of 128kB (256 BBs) is always going to be less than one quarter the size of the journal....

Quoted 16 lines

Quoted 16 lines

fs/xfs/xfs_trans_ail.c +4 -3

@@ -454,21 +486,24 @@ 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();

Quoted 8 lines

fs/xfs/xfs_trans_ail.c xfsaild_push( · line 497

Quoted 3 lines

fs/xfs/xfs_trans_ail.c +1 -2

-		target = ailp->ail_target;
-		ailp->ail_target_prev = target;
+		target = __xfs_ail_push_target(ailp);

Hmm. So now the AIL decides how far it ought to push itself: until 25% of the log is free if nobody's watching, or all the way to the end if there are xfs_ail_push_all_sync waiters or OPSTATE_PUSH_ALL is set because someone needs grant space?

Kind of. 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.

If the OPSTATE_PUSH_ALL flag is set, it will keep updating the push target until the log is empty every time it loops. THis is slightly different behaviour to the existing "push all" code which selects a LSN to push towards and it doesn't try to push beyond that even if new items are inserted into the AIL after the push_all has been triggered.

However, because push_all_sync() effectly waits until the AIL is empty (i.e. keep looping updating the push target until the AIL is empty), and async pushes never wait for it to complete, there is no practical difference between the current implementation and this one.

Quoted 2 lines

So the xlog*grant* callers now merely wake up the AIL and let push whatever it will, instead of telling the AIL how far to push itself?

Yes.

Quoted 2 lines

Does that mean that those grant callers might have to wait until the AIL empties itself?

No. The moment the log tail moves forward because of a removal from the tail of the AIL via xfs_ail_update_finish(), we call xlog_assign_tail_lsn_locked() to move the l_tail_lsn forwards and make grant space available, then we call xfs_log_space_wake() to wake up any grant waiters that are waiting on the space to be made available.

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...

Cheers,

Dave.

Signature · 2 lines

Dave Chinner
[email protected]

+int xlog_space_left(struct xlog *log, atomic64_t *head);

Quoted 4 lines

fs/xfs/xfs_trans_priv.h +4 -0

+static inline xfs_lsn_t xfs_ail_push_target(struct xfs_ail *ailp)
+{
+	xfs_lsn_t	lsn;
+

fs/xfs/xfs_trans_priv.h void xfs_ail_update_finish(struct xfs_ail *ailp, xfs_lsn_t old_lsn) · line 123

Quoted 5 lines

fs/xfs/xfs_trans_priv.h +5 -0

+	spin_lock(&ailp->ail_lock);
+	lsn = __xfs_ail_push_target(ailp);
+	spin_unlock(&ailp->ail_lock);
+	return lsn;
+}

Before this patch xfs_defer_relog called xlog_grant_push_threshold without the ail_lock, why is ail_lock needed now?

From: Dave Chinner <[email protected]>

Currently the AIL attempts to keep 25% of the "log space" free, where the current used space is tracked by the reserve grant head. That is, it tracks both physical space used plus the amount reserved by transactions in progress.

When we start tail pushing, we are trying to make space for new reservations by writing back older metadata and the log is generally physically full of dirty metadata, and reservations for modifications in flight take up whatever space the AIL can physically free up.

Hence we don't really need to take into account the reservation space that has been used - we just need to keep the log tail moving as fast as we can to free up space for more reservations to be made. We know exactly how much physical space the journal is consuming in the AIL (i.e. max LSN - min LSN) so we can base push thresholds directly on this state rather than have to look at grant head reservations to determine how much to physically push out of the log.

Signed-off-by Dave Chinner <[email protected]>

---
 fs/xfs/xfs_log_priv.h  | 18 ++++++++++++
 fs/xfs/xfs_trans_ail.c | 67 +++++++++++++++++++-----------------------
 2 files changed, 49 insertions(+), 36 deletions(-)

fs/xfs/xfs_log_priv.h +18 -0

index 91a8c74f4626..9f8c601a302b 100644
@@ -622,6 +622,24 @@ xlog_wait(
 
 int xlog_wait_on_iclog(struct xlog_in_core *iclog);
 
+/* Calculate the distance between two LSNs in bytes */
+static inline uint64_t
+xlog_lsn_sub(
+	struct xlog	*log,
+	xfs_lsn_t	high,
+	xfs_lsn_t	low)
+{
+	uint32_t	hi_cycle = CYCLE_LSN(high);
+	uint32_t	hi_block = BLOCK_LSN(high);
+	uint32_t	lo_cycle = CYCLE_LSN(low);
+	uint32_t	lo_block = BLOCK_LSN(low);
+
+	if (hi_cycle == lo_cycle)
+	       return BBTOB(hi_block - lo_block);
+	ASSERT((hi_cycle == lo_cycle + 1) || xlog_is_shutdown(log));
+	return (uint64_t)log->l_logsize - BBTOB(lo_block - hi_block);
+}
+
 /*
  * The LSN is valid so long as it is behind the current LSN. If it isn't, this
  * means that the next log record that includes this metadata could have a

fs/xfs/xfs_trans_ail.c +31 -36

index 243d6b05e5a9..d3dcb4942d6a 100644
@@ -398,52 +398,47 @@ xfsaild_push_item(
 /*
  * 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.
+ * threshold, this function returns the lowest LSN in the AIL to slowly keep
+ * writeback ticking over and the tail of the log moving forward.
  */
 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);
+	struct xlog		*log = ailp->ail_log;
+	struct xfs_log_item	*lip;
 
-	/*
-	 * Set the threshold for the minimum number of free blocks in the
-	 * log to the maximum of what the caller needs, one quarter of the
-	 * log, and 256 blocks.
-	 */
-	free_threshold = log->l_logBBsize >> 2;
-	if (free_blocks >= free_threshold)
+	xfs_lsn_t	target_lsn = 0;
+	xfs_lsn_t	max_lsn;
+	xfs_lsn_t	min_lsn;
+	int32_t		free_bytes;
+	uint32_t	target_block;
+	uint32_t	target_cycle;
+
+	lockdep_assert_held(&ailp->ail_lock);
+
+	lip = xfs_ail_max(ailp);
+	if (!lip)
+		return NULLCOMMITLSN;
+	max_lsn = lip->li_lsn;
+	min_lsn = __xfs_ail_min_lsn(ailp);
+
+	free_bytes = log->l_logsize - xlog_lsn_sub(log, max_lsn, min_lsn);
+	if (free_bytes >= log->l_logsize >> 2)
 		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;
+	target_cycle = CYCLE_LSN(min_lsn);
+	target_block = BLOCK_LSN(min_lsn) + (log->l_logBBsize >> 2);
+	if (target_block >= log->l_logBBsize) {
+		target_block -= log->l_logBBsize;
+		target_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;
+	target_lsn = xlog_assign_lsn(target_cycle, target_block);
 
-	return threshold_lsn;
+	/* Cap the target to the highest LSN known to be in the AIL. */
+	if (XFS_LSN_CMP(target_lsn, max_lsn) > 0)
+		return max_lsn;
+	return target_lsn;
 }
 
 static long

Signature · 1 line

2.36.1

Quoted 21 lines · Dave Chinner

From: Dave Chinner <[email protected]>

Currently the AIL attempts to keep 25% of the "log space" free, where the current used space is tracked by the reserve grant head. That is, it tracks both physical space used plus the amount reserved by transactions in progress.

When we start tail pushing, we are trying to make space for new reservations by writing back older metadata and the log is generally physically full of dirty metadata, and reservations for modifications in flight take up whatever space the AIL can physically free up.

Hence we don't really need to take into account the reservation space that has been used - we just need to keep the log tail moving as fast as we can to free up space for more reservations to be made. We know exactly how much physical space the journal is consuming in the AIL (i.e. max LSN - min LSN) so we can base push thresholds directly on this state rather than have to look at grant head reservations to determine how much to physically push out of the log.

Quoted 1 line

Signed-off-by Dave Chinner <[email protected]>

Makes sense, I think. Though I was wondering about the last patch -- pushing the AIL until it's empty when a trans_alloc can't find grant reservation could take a while on a slow storage.

Does this mean that
we're trading the incremental freeing-up of the existing code for potentially higher transaction allocation latency in the hopes that more threads can get reservation? Or does the "keep the AIL going" bits make up for that?

Quoted 22 lines · Darrick J. Wong

Quoted 21 lines · Dave Chinner

From: Dave Chinner <[email protected]>

Currently the AIL attempts to keep 25% of the "log space" free, where the current used space is tracked by the reserve grant head. That is, it tracks both physical space used plus the amount reserved by transactions in progress.

When we start tail pushing, we are trying to make space for new reservations by writing back older metadata and the log is generally physically full of dirty metadata, and reservations for modifications in flight take up whatever space the AIL can physically free up.

Hence we don't really need to take into account the reservation space that has been used - we just need to keep the log tail moving as fast as we can to free up space for more reservations to be made. We know exactly how much physical space the journal is consuming in the AIL (i.e. max LSN - min LSN) so we can base push thresholds directly on this state rather than have to look at grant head reservations to determine how much to physically push out of the log.

Quoted 5 lines

Quoted 1 line

Signed-off-by Dave Chinner <[email protected]>

Makes sense, I think. Though I was wondering about the last patch -- pushing the AIL until it's empty when a trans_alloc can't find grant reservation could take a while on a slow storage.

The push in the grant reservation code is not a blocking push - it just tells the AIL to start pushing everything, then it goes to sleep waiting for the tail to move and space to come available. The AIL behaviour is largely unchanged, especially if the application is running under even slight memory pressure as the inode shrinker will repeatedly kick the AIL push-all trigger regardless of consumed journal/grant space.

Quoted 5 lines

Does this mean that
we're trading the incremental freeing-up of the existing code for potentially higher transaction allocation latency in the hopes that more threads can get reservation? Or does the "keep the AIL going" bits make up for that?

So far I've typically measured slightly lower worst case latencies with this mechanism that with the existing "repeatedly push to 25% free" that we currently have. It's not really significant enough to make statements about (unlike cpu usage reductions or perf increases), but it does seem to be a bit better...

Cheers,

Dave.

Signature · 2 lines

Dave Chinner
[email protected]

Quoted 23 lines · Dave Chinner

Quoted 22 lines · Darrick J. Wong

Quoted 21 lines · Dave Chinner

From: Dave Chinner <[email protected]>

Currently the AIL attempts to keep 25% of the "log space" free, where the current used space is tracked by the reserve grant head. That is, it tracks both physical space used plus the amount reserved by transactions in progress.

When we start tail pushing, we are trying to make space for new reservations by writing back older metadata and the log is generally physically full of dirty metadata, and reservations for modifications in flight take up whatever space the AIL can physically free up.

Hence we don't really need to take into account the reservation space that has been used - we just need to keep the log tail moving as fast as we can to free up space for more reservations to be made. We know exactly how much physical space the journal is consuming in the AIL (i.e. max LSN - min LSN) so we can base push thresholds directly on this state rather than have to look at grant head reservations to determine how much to physically push out of the log.

Quoted 5 lines

Quoted 5 lines

Quoted 1 line

Signed-off-by Dave Chinner <[email protected]>

Makes sense, I think. Though I was wondering about the last patch -- pushing the AIL until it's empty when a trans_alloc can't find grant reservation could take a while on a slow storage.

Quoted 8 lines

The push in the grant reservation code is not a blocking push - it just tells the AIL to start pushing everything, then it goes to sleep waiting for the tail to move and space to come available. The AIL behaviour is largely unchanged, especially if the application is running under even slight memory pressure as the inode shrinker will repeatedly kick the AIL push-all trigger regardless of consumed journal/grant space.

Ok.

Quoted 11 lines

Quoted 5 lines

Does this mean that
we're trading the incremental freeing-up of the existing code for potentially higher transaction allocation latency in the hopes that more threads can get reservation? Or does the "keep the AIL going" bits make up for that?

So far I've typically measured slightly lower worst case latencies with this mechanism that with the existing "repeatedly push to 25% free" that we currently have. It's not really significant enough to make statements about (unlike cpu usage reductions or perf increases), but it does seem to be a bit better...

<nod>

--D

Quoted 6 lines

Cheers,

Dave.

Signature · 2 lines

Dave Chinner
[email protected]

From: Dave Chinner <[email protected]>

Whenever we write an iclog, we call xlog_assign_tail_lsn() to update the current tail before we write it into the iclog header. This means we have to take the AIL lock on every iclog write just to check if the tail of the log has moved.

This doesn't avoid races with log tail updates - the log tail could move immediately after we assign the tail to the iclog header and hence by the time the iclog reaches stable storage the tail LSN has moved forward in memory. Hence the log tail LSN in the iclog header is really just a point in time snapshot of the current state of the AIL.

With this in mind, if we simply update the in memory log->l_tail_lsn every time it changes in the AIL, there is no need to update the in memory value when we are writing it into an iclog - it will already be up-to-date in memory and checking the AIL again will not change this.

Hence xlog_state_release_iclog() does not need to check the AIL to update the tail lsn and can just sample it directly without needing to take the AIL lock.

Signed-off-by Dave Chinner <[email protected]>

---
 fs/xfs/xfs_log.c       |  5 ++---
 fs/xfs/xfs_trans_ail.c | 17 +++++++++++++++--
 2 files changed, 17 insertions(+), 5 deletions(-)

fs/xfs/xfs_log.c +2 -3

index c609c188bd8a..042744fe37b7 100644
@@ -530,7 +530,6 @@ xlog_state_release_iclog(
 	struct xlog_in_core	*iclog,
 	struct xlog_ticket	*ticket)
 {
-	xfs_lsn_t		tail_lsn;
 	bool			last_ref;
 
 	lockdep_assert_held(&log->l_icloglock);

@@ -545,8 +544,8 @@ xlog_state_release_iclog(
 	if ((iclog->ic_state == XLOG_STATE_WANT_SYNC ||
 	     (iclog->ic_flags & XLOG_ICL_NEED_FUA)) &&
 	    !iclog->ic_header.h_tail_lsn) {
-		tail_lsn = xlog_assign_tail_lsn(log->l_mp);
-		iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn);
+		iclog->ic_header.h_tail_lsn =
+				cpu_to_be64(atomic64_read(&log->l_tail_lsn));
 	}
 
 	last_ref = atomic_dec_and_test(&iclog->ic_refcnt);

fs/xfs/xfs_trans_ail.c +15 -2

index d3dcb4942d6a..5f40509877f7 100644
@@ -715,6 +715,13 @@ xfs_ail_push_all_sync(
 	finish_wait(&ailp->ail_empty, &wait);
 }
 
+/*
+ * Callers should pass the the original tail lsn so that we can detect if the
+ * tail has moved as a result of the operation that was performed. If the caller
+ * needs to force a tail LSN update, it should pass NULLCOMMITLSN to bypass the
+ * "did the tail LSN change?" checks. If the caller wants to avoid a tail update
+ * (e.g. it knows the tail did not change) it should pass an @old_lsn of 0.
+ */
 void
 xfs_ail_update_finish(
 	struct xfs_ail		*ailp,

@@ -799,10 +806,16 @@ xfs_trans_ail_update_bulk(
 
 	/*
 	 * If this is the first insert, wake up the push daemon so it can
-	 * actively scan for items to push.
+	 * actively scan for items to push. We also need to do a log tail
+	 * LSN update to ensure that it is correctly tracked by the log, so
+	 * set the tail_lsn to NULLCOMMITLSN so that xfs_ail_update_finish()
+	 * will see that the tail lsn has changed and will update the tail
+	 * appropriately.
 	 */
-	if (!mlip)
+	if (!mlip) {
 		wake_up_process(ailp->ail_task);
+		tail_lsn = NULLCOMMITLSN;
+	}
 
 	xfs_ail_update_finish(ailp, tail_lsn);
 }

Signature · 1 line

2.36.1

Quoted 14 lines · Dave Chinner

From: Dave Chinner <[email protected]>

Whenever we write an iclog, we call xlog_assign_tail_lsn() to update the current tail before we write it into the iclog header. This means we have to take the AIL lock on every iclog write just to check if the tail of the log has moved.

This doesn't avoid races with log tail updates - the log tail could move immediately after we assign the tail to the iclog header and hence by the time the iclog reaches stable storage the tail LSN has moved forward in memory. Hence the log tail LSN in the iclog header is really just a point in time snapshot of the current state of the AIL.

Quoted 5 lines

With this in mind, if we simply update the in memory log->l_tail_lsn every time it changes in the AIL, there is no need to update the in memory value when we are writing it into an iclog - it will already be up-to-date in memory and checking the AIL again will not change this.

This is too subtle for me to understand -- does the codebase already update l_tail_lsn? Does this patch make it do that?

Quoted 15 lines · Darrick J. Wong

Quoted 14 lines · Dave Chinner

From: Dave Chinner <[email protected]>

Whenever we write an iclog, we call xlog_assign_tail_lsn() to update the current tail before we write it into the iclog header. This means we have to take the AIL lock on every iclog write just to check if the tail of the log has moved.

This doesn't avoid races with log tail updates - the log tail could move immediately after we assign the tail to the iclog header and hence by the time the iclog reaches stable storage the tail LSN has moved forward in memory. Hence the log tail LSN in the iclog header is really just a point in time snapshot of the current state of the AIL.

Quoted 8 lines

Quoted 5 lines

With this in mind, if we simply update the in memory log->l_tail_lsn every time it changes in the AIL, there is no need to update the in memory value when we are writing it into an iclog - it will already be up-to-date in memory and checking the AIL again will not change this.

This is too subtle for me to understand -- does the codebase already update l_tail_lsn? Does this patch make it do that?

tl;dr: if the AIL is empty, log->l_tail_lsn is not updated on the first insert of a new item into the AILi and hence is stale. xlog_state_release_iclog() currently works around that by calling xlog_assign_tail_lsn() to get the tail lsn from the AIL. This change makes sure log->l_tail_lsn is always up to date.

In more detail:

The tail update occurs in xfs_ail_update_finish(), but only if we pass in a non-zero tail_lsn. xfs_trans_ail_update_bulk() will only set a non-zero tail_lsn if it moves the log item at the tail of the log (i.e. we relog the tail item and move it forwards in the AIL).

Hence if we pass a non-zero tail_lsn to xfs_ail_update_finish(), it indicates it needs to check it against the LSN of the item currently at the tail of the AIL. If the tail LSN has not changed, we do nothing, if it has changed, then we call xlog_assign_tail_lsn_locked() to update the log tail.

The problem with the current code is that if the AIL is empty when we insert the first item, we've actually moved the log tail but we do not update the log tail (i.e. tail_lsn is zero in this case). If we then release an iclog for writing at this point in time, the tail lsn it writes into the iclog header would be wrong - it does not reflect the log tail as defined by the AIL and the checkpoint that has just been committed.

Hence xlog_state_release_iclog() called xlog_assign_tail_lsn() to ensure that it checked that the tail LSN it applies to the iclog reflects the current state of the AIL. i.e. it checks if there is an item in the AIL, and if so, grabs the tail_lsn from the AIL. This works around the fact the AIL doesn't update the log tail on the first insert.

Hence what this patch does is have xfs_trans_ail_update_bulk set the tail_lsn passed to xfs_ail_update_finish() to NULLCOMMITLSN when it does the first insert into the AIL. NULLCOMMITLSN is a non-zero value that won't match with the LSN of items we just inserted into the AIL, and hence xfs_ail_update_finish() will go an update the log tail in this case.

Hence we close the hole when the log->l_tail_lsn is incorrect after the first insert into the AIL, and hence we no longer need to update the log->l_tail_lsn when reading it into the iclog header - log->l_tail_lsn is always up to date, and so we can now just read it in xlog_state_release_iclog() rather than having to grab the AIL lock and checking the AIL to update log->l_tail_lsn with the correct tail value from iclog IO submission....

Cheers,

Dave.

Signature · 2 lines

Dave Chinner
[email protected]

Quoted 66 lines · Dave Chinner

Quoted 15 lines · Darrick J. Wong

Quoted 14 lines · Dave Chinner

From: Dave Chinner <[email protected]>

Whenever we write an iclog, we call xlog_assign_tail_lsn() to update the current tail before we write it into the iclog header. This means we have to take the AIL lock on every iclog write just to check if the tail of the log has moved.

This doesn't avoid races with log tail updates - the log tail could move immediately after we assign the tail to the iclog header and hence by the time the iclog reaches stable storage the tail LSN has moved forward in memory. Hence the log tail LSN in the iclog header is really just a point in time snapshot of the current state of the AIL.

Quoted 8 lines

Quoted 5 lines

With this in mind, if we simply update the in memory log->l_tail_lsn every time it changes in the AIL, there is no need to update the in memory value when we are writing it into an iclog - it will already be up-to-date in memory and checking the AIL again will not change this.

This is too subtle for me to understand -- does the codebase already update l_tail_lsn? Does this patch make it do that?

tl;dr: if the AIL is empty, log->l_tail_lsn is not updated on the first insert of a new item into the AILi and hence is stale. xlog_state_release_iclog() currently works around that by calling xlog_assign_tail_lsn() to get the tail lsn from the AIL. This change makes sure log->l_tail_lsn is always up to date.

In more detail:

The tail update occurs in xfs_ail_update_finish(), but only if we pass in a non-zero tail_lsn. xfs_trans_ail_update_bulk() will only set a non-zero tail_lsn if it moves the log item at the tail of the log (i.e. we relog the tail item and move it forwards in the AIL).

Hence if we pass a non-zero tail_lsn to xfs_ail_update_finish(), it indicates it needs to check it against the LSN of the item currently at the tail of the AIL. If the tail LSN has not changed, we do nothing, if it has changed, then we call xlog_assign_tail_lsn_locked() to update the log tail.

The problem with the current code is that if the AIL is empty when we insert the first item, we've actually moved the log tail but we do not update the log tail (i.e. tail_lsn is zero in this case). If we then release an iclog for writing at this point in time, the tail lsn it writes into the iclog header would be wrong - it does not reflect the log tail as defined by the AIL and the checkpoint that has just been committed.

Hence xlog_state_release_iclog() called xlog_assign_tail_lsn() to ensure that it checked that the tail LSN it applies to the iclog reflects the current state of the AIL. i.e. it checks if there is an item in the AIL, and if so, grabs the tail_lsn from the AIL. This works around the fact the AIL doesn't update the log tail on the first insert.

Hence what this patch does is have xfs_trans_ail_update_bulk set the tail_lsn passed to xfs_ail_update_finish() to NULLCOMMITLSN when it does the first insert into the AIL. NULLCOMMITLSN is a non-zero value that won't match with the LSN of items we just inserted into the AIL, and hence xfs_ail_update_finish() will go an update the log tail in this case.

Quoted 7 lines

Hence we close the hole when the log->l_tail_lsn is incorrect after the first insert into the AIL, and hence we no longer need to update the log->l_tail_lsn when reading it into the iclog header - log->l_tail_lsn is always up to date, and so we can now just read it in xlog_state_release_iclog() rather than having to grab the AIL lock and checking the AIL to update log->l_tail_lsn with the correct tail value from iclog IO submission....

Ahhh, ok, I get it now. Thanks for the explanation.

--D

Quoted 6 lines

Cheers,

Dave.

Signature · 2 lines

Dave Chinner
[email protected]

From: Dave Chinner <[email protected]>

The current implementation of xlog_assign_tail_lsn() assumes that when the AIL is empty, the log tail matches the LSN of the last written commit record. This is recorded in xlog_state_set_callback() as log->l_last_sync_lsn when the iclog state changes to XLOG_STATE_CALLBACK. This change is then immediately followed by running the callbacks on the iclog which then insert the log items into the AIL at the "commit lsn" of that checkpoint.

The AIL tracks log items via the start record LSN of the checkpoint, not the commit record LSN. THis is because we can pipeline multiple checkpoints, and so the start record of checkpoint N+1 can be written before the commit record of checkpoint N. i.e:

     start N			commit N
	+-------------+------------+----------------+
		  start N+1			commit N+1

The tail of the log cannot be moved to the LSN of commit N when all the items of that checkpoint are written back, because then the start record for N+1 is no longer in the active portion of the log and recovery will fail/corrupt the filesystem.

Hence when all the log items in checkpoint N are written back, the tail of the log most now only move as far forwards as the start LSN of checkpoint N+1.

Hence we cannot use the maximum start record LSN the AIL sees as a replacement the pointer to the current head of the on-disk log records. However, we currently only use the l_last_sync_lsn when the AIL is empty - when there is no start LSN remaining, the tail of the log moves to the LSN of the last commit record as this is where recovery needs to start searching for recoverable records. THe next checkpoint will have a start record LSN that is higher than l_last_sync_lsn, and so everything still works correctly when new checkpoints are written to an otherwise empty log.

l_last_sync_lsn is an atomic variable because it is currently updated when an iclog with callbacks attached moves to the CALLBACK state. While we hold the icloglock at this point, we don't hold the AIL lock. When we assign the log tail, we hold the AIL lock, not the icloglock because we have to look up the AIL. Hence it is an atomic variable so it's not bound to a specific lock context.

However, the iclog callbacks are only used for CIL checkpoints. We don't use callbacks with unmount record writes, so the l_last_sync_lsn variable only gets updated when we are processing CIL checkpoint callbacks. And those callbacks run under AIL lock contexts, not icloglock context. The CIL checkpoint already knows what the LSN of the iclog the commit record was written to (obtained when written into the iclog before submission) and so we can update the l_last_sync_lsn under the AIL lock in this callback. No other iclog callbacks will run until the currently executing one completes, and hence we can update the l_last_sync_lsn under the AIL lock safely.

This means l_last_sync_lsn can move to the AIL as the "ail_head_lsn" and it can be used to replace the atomic l_last_sync_lsn in the iclog code. This makes tracking the log tail belong entirely to the AIL, rather than being smeared across log, iclog and AIL state and locking.

Signed-off-by Dave Chinner <[email protected]>

---
 fs/xfs/xfs_log.c         | 81 +++++-----------------------------------
 fs/xfs/xfs_log_cil.c     | 54 ++++++++++++++++++++-------
 fs/xfs/xfs_log_priv.h    |  9 ++---
 fs/xfs/xfs_log_recover.c | 19 +++++-----
 fs/xfs/xfs_trace.c       |  1 +
 fs/xfs/xfs_trace.h       |  8 ++--
 fs/xfs/xfs_trans_ail.c   | 26 +++++++++++--
 fs/xfs/xfs_trans_priv.h  | 13 +++++++
 8 files changed, 102 insertions(+), 109 deletions(-)

fs/xfs/xfs_log.c +9 -72

index 042744fe37b7..e420591b1a8a 100644
@@ -1237,47 +1237,6 @@ xfs_log_cover(
 	return error;
 }
 
-/*
- * We may be holding the log iclog lock upon entering this routine.
- */
-xfs_lsn_t
-xlog_assign_tail_lsn_locked(
-	struct xfs_mount	*mp)
-{
-	struct xlog		*log = mp->m_log;
-	struct xfs_log_item	*lip;
-	xfs_lsn_t		tail_lsn;
-
-	assert_spin_locked(&mp->m_ail->ail_lock);
-
-	/*
-	 * To make sure we always have a valid LSN for the log tail we keep
-	 * track of the last LSN which was committed in log->l_last_sync_lsn,
-	 * and use that when the AIL was empty.
-	 */
-	lip = xfs_ail_min(mp->m_ail);
-	if (lip)
-		tail_lsn = lip->li_lsn;
-	else
-		tail_lsn = atomic64_read(&log->l_last_sync_lsn);
-	trace_xfs_log_assign_tail_lsn(log, tail_lsn);
-	atomic64_set(&log->l_tail_lsn, tail_lsn);
-	return tail_lsn;
-}
-
-xfs_lsn_t
-xlog_assign_tail_lsn(
-	struct xfs_mount	*mp)
-{
-	xfs_lsn_t		tail_lsn;
-
-	spin_lock(&mp->m_ail->ail_lock);
-	tail_lsn = xlog_assign_tail_lsn_locked(mp);
-	spin_unlock(&mp->m_ail->ail_lock);
-
-	return tail_lsn;
-}
-
 /*
  * Return the space in the log between the tail and the head.  The head
  * is passed in the cycle/bytes formal parms.  In the special case where

@@ -1511,7 +1470,6 @@ xlog_alloc_log(
 	log->l_prev_block  = -1;
 	/* log->l_tail_lsn = 0x100000000LL; cycle = 1; current block = 0 */
 	xlog_assign_atomic_lsn(&log->l_tail_lsn, 1, 0);
-	xlog_assign_atomic_lsn(&log->l_last_sync_lsn, 1, 0);
 	log->l_curr_cycle  = 1;	    /* 0 is bad since this is initial value */
 
 	if (xfs_has_logv2(mp) && mp->m_sb.sb_logsunit > 1)

@@ -2562,44 +2520,23 @@ xlog_get_lowest_lsn(
 	return lowest_lsn;
 }
 
-/*
- * Completion of a iclog IO does not imply that a transaction has completed, as
- * transactions can be large enough to span many iclogs. We cannot change the
- * tail of the log half way through a transaction as this may be the only
- * transaction in the log and moving the tail to point to the middle of it
- * will prevent recovery from finding the start of the transaction. Hence we
- * should only update the last_sync_lsn if this iclog contains transaction
- * completion callbacks on it.
- *
- * We have to do this before we drop the icloglock to ensure we are the only one
- * that can update it.
- *
- * If we are moving the last_sync_lsn forwards, we also need to ensure we kick
- * the reservation grant head pushing. This is due to the fact that the push
- * target is bound by the current last_sync_lsn value. Hence if we have a large
- * amount of log space bound up in this committing transaction then the
- * last_sync_lsn value may be the limiting factor preventing tail pushing from
- * freeing space in the log. Hence once we've updated the last_sync_lsn we
- * should push the AIL to ensure the push target (and hence the grant head) is
- * no longer bound by the old log head location and can move forwards and make
- * progress again.
- */
 static void
 xlog_state_set_callback(
 	struct xlog		*log,
 	struct xlog_in_core	*iclog,
 	xfs_lsn_t		header_lsn)
 {
+	/*
+	 * If there are no callbacks on this iclog, we can mark it clean
+	 * immediately and return. Otherwise we need to run the
+	 * callbacks.
+	 */
+	if (list_empty(&iclog->ic_callbacks)) {
+		xlog_state_clean_iclog(log, iclog);
+		return;
+	}
 	trace_xlog_iclog_callback(iclog, _RET_IP_);
 	iclog->ic_state = XLOG_STATE_CALLBACK;
-
-	ASSERT(XFS_LSN_CMP(atomic64_read(&log->l_last_sync_lsn),
-			   header_lsn) <= 0);
-
-	if (list_empty_careful(&iclog->ic_callbacks))
-		return;
-
-	atomic64_set(&log->l_last_sync_lsn, header_lsn);
 }
 
 /*

fs/xfs/xfs_log_cil.c +0 -0

index 475a18493c37..843764d40232 100644

fs/xfs/xfs_log_cil.c +39 -13

+ * checkpoints, and so the start record of checkpoint N+1 can be
+ * written before the commit record of checkpoint N. i.e:
+ *
+ *   start N			commit N
+ *	+-------------+------------+----------------+
+ *		  start N+1			commit N+1
+ *
+ * The tail of the log cannot be moved to the LSN of commit N when all
+ * the items of that checkpoint are written back, because then the
+ * start record for N+1 is no longer in the active portion of the log
+ * and recovery will fail/corrupt the filesystem.
+ *
+ * Hence when all the log items in checkpoint N are written back, the
+ * tail of the log most now only move as far forwards as the start LSN
+ * of checkpoint N+1.
+ *
  * If we are called with the aborted flag set, it is because a log write during
  * a CIL checkpoint commit has failed. In this case, all the items in the
  * checkpoint have already gone through iop_committed and iop_committing, which

@@ -727,24 +745,33 @@ xlog_cil_ail_insert_batch(
  */
 void
 xlog_cil_ail_insert(
-	struct xlog		*log,
-	struct list_head	*lv_chain,
-	xfs_lsn_t		commit_lsn,
+	struct xfs_cil_ctx	*ctx,
 	bool			aborted)
 {
 #define LOG_ITEM_BATCH_SIZE	32
-	struct xfs_ail		*ailp = log->l_ailp;
+	struct xfs_ail		*ailp = ctx->cil->xc_log->l_ailp;
 	struct xfs_log_item	*log_items[LOG_ITEM_BATCH_SIZE];
 	struct xfs_log_vec	*lv;
 	struct xfs_ail_cursor	cur;
 	int			i = 0;
 
+	/*
+	 * Update the AIL head LSN with the commit record LSN of this
+	 * checkpoint. As iclogs are always completed in order, this should
+	 * always be the same (as iclogs can contain multiple commit records) or
+	 * higher LSN than the current head. We do this before insertion of the
+	 * items so that log space checks during insertion will reflect the
+	 * space that this checkpoint has already consumed.
+	 */
+	ASSERT(XFS_LSN_CMP(ctx->commit_lsn, ailp->ail_head_lsn) >= 0 ||
+			aborted);
 	spin_lock(&ailp->ail_lock);
-	xfs_trans_ail_cursor_last(ailp, &cur, commit_lsn);
+	ailp->ail_head_lsn = ctx->commit_lsn;
+	xfs_trans_ail_cursor_last(ailp, &cur, ctx->start_lsn);
 	spin_unlock(&ailp->ail_lock);
 
 	/* unpin all the log items */
-	list_for_each_entry(lv, lv_chain, lv_list) {
+	list_for_each_entry(lv, &ctx->lv_chain, lv_list) {
 		struct xfs_log_item	*lip = lv->lv_item;
 		xfs_lsn_t		item_lsn;
 

@@ -757,9 +784,10 @@ xlog_cil_ail_insert(
 		}
 
 		if (lip->li_ops->iop_committed)
-			item_lsn = lip->li_ops->iop_committed(lip, commit_lsn);
+			item_lsn = lip->li_ops->iop_committed(lip,
+					ctx->start_lsn);
 		else
-			item_lsn = commit_lsn;
+			item_lsn = ctx->start_lsn;
 
 		/* item_lsn of -1 means the item needs no further processing */
 		if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0)

@@ -776,7 +804,7 @@ xlog_cil_ail_insert(
 			continue;
 		}
 
-		if (item_lsn != commit_lsn) {
+		if (item_lsn != ctx->start_lsn) {
 
 			/*
 			 * Not a bulk update option due to unusual item_lsn.

@@ -799,14 +827,15 @@ xlog_cil_ail_insert(
 		log_items[i++] = lv->lv_item;
 		if (i >= LOG_ITEM_BATCH_SIZE) {
 			xlog_cil_ail_insert_batch(ailp, &cur, log_items,
-					LOG_ITEM_BATCH_SIZE, commit_lsn);
+					LOG_ITEM_BATCH_SIZE, ctx->start_lsn);
 			i = 0;
 		}
 	}
 
 	/* make sure we insert the remainder! */
 	if (i)
-		xlog_cil_ail_insert_batch(ailp, &cur, log_items, i, commit_lsn);
+		xlog_cil_ail_insert_batch(ailp, &cur, log_items, i,
+				ctx->start_lsn);
 
 	spin_lock(&ailp->ail_lock);
 	xfs_trans_ail_cursor_done(&cur);

@@ -922,8 +951,7 @@ xlog_cil_committed(
 		spin_unlock(&ctx->cil->xc_push_lock);
 	}
 
-	xlog_cil_ail_insert(ctx->cil->xc_log, &ctx->lv_chain,
-					ctx->start_lsn, abort);
+	xlog_cil_ail_insert(ctx, abort);
 
 	xfs_extent_busy_sort(&ctx->busy_extents);
 	xfs_extent_busy_clear(mp, &ctx->busy_extents,

fs/xfs/xfs_log_priv.h +3 -6

index 9f8c601a302b..5f4358f18224 100644
@@ -426,13 +426,10 @@ struct xlog {
 	int			l_prev_block;   /* previous logical log block */
 
 	/*
-	 * l_last_sync_lsn and l_tail_lsn are atomics so they can be set and
-	 * read without needing to hold specific locks. To avoid operations
-	 * contending with other hot objects, place each of them on a separate
-	 * cacheline.
+	 * l_tail_lsn is atomic so it can be set and read without needing to
+	 * hold specific locks. To avoid operations contending with other hot
+	 * objects, it on a separate cacheline.
 	 */
-	/* lsn of last LR on disk */
-	atomic64_t		l_last_sync_lsn ____cacheline_aligned_in_smp;
 	/* lsn of 1st LR with unflushed * buffers */
 	atomic64_t		l_tail_lsn ____cacheline_aligned_in_smp;
 

fs/xfs/xfs_log_recover.c +9 -10

index 9e0e7ff76e02..d9997714f975 100644
@@ -1177,8 +1177,8 @@ xlog_check_unmount_rec(
 			 */
 			xlog_assign_atomic_lsn(&log->l_tail_lsn,
 					log->l_curr_cycle, after_umount_blk);
-			xlog_assign_atomic_lsn(&log->l_last_sync_lsn,
-					log->l_curr_cycle, after_umount_blk);
+			log->l_ailp->ail_head_lsn =
+					atomic64_read(&log->l_tail_lsn);
 			*tail_blk = after_umount_blk;
 
 			*clean = true;

@@ -1212,7 +1212,7 @@ xlog_set_state(
 	if (bump_cycle)
 		log->l_curr_cycle++;
 	atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn));
-	atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn));
+	log->l_ailp->ail_head_lsn = be64_to_cpu(rhead->h_lsn);
 	xlog_assign_grant_head(&log->l_reserve_head.grant, log->l_curr_cycle,
 					BBTOB(log->l_curr_block));
 	xlog_assign_grant_head(&log->l_write_head.grant, log->l_curr_cycle,

@@ -3294,14 +3294,13 @@ xlog_do_recover(
 
 	/*
 	 * We now update the tail_lsn since much of the recovery has completed
-	 * and there may be space available to use.  If there were no extent
-	 * or iunlinks, we can free up the entire log and set the tail_lsn to
-	 * be the last_sync_lsn.  This was set in xlog_find_tail to be the
-	 * lsn of the last known good LR on disk.  If there are extent frees
-	 * or iunlinks they will have some entries in the AIL; so we look at
-	 * the AIL to determine how to set the tail_lsn.
+	 * and there may be space available to use.  If there were no extent or
+	 * iunlinks, we can free up the entire log.  This was set in
+	 * xlog_find_tail to be the lsn of the last known good LR on disk.  If
+	 * there are extent frees or iunlinks they will have some entries in the
+	 * AIL; so we look at the AIL to determine how to set the tail_lsn.
 	 */
-	xlog_assign_tail_lsn(mp);
+	xfs_ail_assign_tail_lsn(log->l_ailp);
 
 	/*
 	 * Now that we've finished replaying all buffer and inode updates,

fs/xfs/xfs_trace.c +1 -0

index d269ef57ff01..dcf9af0108c1 100644
@@ -22,6 +22,7 @@
 #include "xfs_trans.h"
 #include "xfs_log.h"
 #include "xfs_log_priv.h"
+#include "xfs_trans_priv.h"
 #include "xfs_buf_item.h"
 #include "xfs_quota.h"
 #include "xfs_dquot_item.h"

fs/xfs/xfs_trace.h +4 -4

index f9057af6e0c8..886cde292c95 100644
@@ -1383,19 +1383,19 @@ TRACE_EVENT(xfs_log_assign_tail_lsn,
 		__field(dev_t, dev)
 		__field(xfs_lsn_t, new_lsn)
 		__field(xfs_lsn_t, old_lsn)
-		__field(xfs_lsn_t, last_sync_lsn)
+		__field(xfs_lsn_t, head_lsn)
 	),
 	TP_fast_assign(
 		__entry->dev = log->l_mp->m_super->s_dev;
 		__entry->new_lsn = new_lsn;
 		__entry->old_lsn = atomic64_read(&log->l_tail_lsn);
-		__entry->last_sync_lsn = atomic64_read(&log->l_last_sync_lsn);
+		__entry->head_lsn = log->l_ailp->ail_head_lsn;
 	),
-	TP_printk("dev %d:%d new tail lsn %d/%d, old lsn %d/%d, last sync %d/%d",
+	TP_printk("dev %d:%d new tail lsn %d/%d, old lsn %d/%d, head lsn %d/%d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  CYCLE_LSN(__entry->new_lsn), BLOCK_LSN(__entry->new_lsn),
 		  CYCLE_LSN(__entry->old_lsn), BLOCK_LSN(__entry->old_lsn),
-		  CYCLE_LSN(__entry->last_sync_lsn), BLOCK_LSN(__entry->last_sync_lsn))
+		  CYCLE_LSN(__entry->head_lsn), BLOCK_LSN(__entry->head_lsn))
 )
 
 DECLARE_EVENT_CLASS(xfs_file_class,

fs/xfs/xfs_trans_ail.c +22 -4

index 5f40509877f7..fe3f8b80e687 100644
@@ -715,6 +715,26 @@ xfs_ail_push_all_sync(
 	finish_wait(&ailp->ail_empty, &wait);
 }
 
+void
+__xfs_ail_assign_tail_lsn(
+	struct xfs_ail		*ailp)
+{
+	struct xlog		*log = ailp->ail_log;
+	xfs_lsn_t		tail_lsn;
+
+	assert_spin_locked(&ailp->ail_lock);
+
+	if (xlog_is_shutdown(log))
+		return;
+
+	tail_lsn = __xfs_ail_min_lsn(ailp);
+	if (!tail_lsn)
+		tail_lsn = ailp->ail_head_lsn;
+
+	trace_xfs_log_assign_tail_lsn(log, tail_lsn);
+	atomic64_set(&log->l_tail_lsn, tail_lsn);
+}
+
 /*
  * Callers should pass the the original tail lsn so that we can detect if the
  * tail has moved as a result of the operation that was performed. If the caller

@@ -729,15 +749,13 @@ xfs_ail_update_finish(
 {
 	struct xlog		*log = ailp->ail_log;
 
-	/* if the tail lsn hasn't changed, don't do updates or wakeups. */
+	/* If the tail lsn hasn't changed, don't do updates or wakeups. */
 	if (!old_lsn || old_lsn == __xfs_ail_min_lsn(ailp)) {
 		spin_unlock(&ailp->ail_lock);
 		return;
 	}
 
-	if (!xlog_is_shutdown(log))
-		xlog_assign_tail_lsn_locked(log->l_mp);
-
+	__xfs_ail_assign_tail_lsn(ailp);
 	if (list_empty(&ailp->ail_head))
 		wake_up_all(&ailp->ail_empty);
 	spin_unlock(&ailp->ail_lock);

fs/xfs/xfs_trans_priv.h +13 -0

index 9a131e7fae94..6541a6c3ea22 100644
@@ -55,6 +55,7 @@ struct xfs_ail {
 	struct list_head	ail_cursors;
 	spinlock_t		ail_lock;
 	xfs_lsn_t		ail_last_pushed_lsn;
+	xfs_lsn_t		ail_head_lsn;
 	int			ail_log_flush;
 	unsigned long		ail_opstate;
 	struct list_head	ail_buf_list;

@@ -135,6 +136,18 @@ struct xfs_log_item *	xfs_trans_ail_cursor_next(struct xfs_ail *ailp,
 					struct xfs_ail_cursor *cur);
 void			xfs_trans_ail_cursor_done(struct xfs_ail_cursor *cur);
 
+void			__xfs_ail_assign_tail_lsn(struct xfs_ail *ailp);
+
+static inline void
+xfs_ail_assign_tail_lsn(
+	struct xfs_ail		*ailp)
+{
+
+	spin_lock(&ailp->ail_lock);
+	__xfs_ail_assign_tail_lsn(ailp);
+	spin_unlock(&ailp->ail_lock);
+}
+
 #if BITS_PER_LONG != 64
 static inline void
 xfs_trans_ail_copy_lsn(

Signature · 1 line

2.36.1

From: Dave Chinner <[email protected]>

The function is called from a single place, and it isn't just setting the iclog state to XLOG_STATE_CALLBACK - it can mark iclogs clean, which moves tehm to states after CALLBACK. Hence the function

is now badly named, and should just be folded into the caller where the iclog completion logic makes a whole lot more sense.

Signed-off-by Dave Chinner <[email protected]>

---
 fs/xfs/xfs_log.c | 31 +++++++++++--------------------
 1 file changed, 11 insertions(+), 20 deletions(-)

fs/xfs/xfs_log.c +11 -20

index e420591b1a8a..5b7c91a42edf 100644
@@ -2520,25 +2520,6 @@ xlog_get_lowest_lsn(
 	return lowest_lsn;
 }
 
-static void
-xlog_state_set_callback(
-	struct xlog		*log,
-	struct xlog_in_core	*iclog,
-	xfs_lsn_t		header_lsn)
-{
-	/*
-	 * If there are no callbacks on this iclog, we can mark it clean
-	 * immediately and return. Otherwise we need to run the
-	 * callbacks.
-	 */
-	if (list_empty(&iclog->ic_callbacks)) {
-		xlog_state_clean_iclog(log, iclog);
-		return;
-	}
-	trace_xlog_iclog_callback(iclog, _RET_IP_);
-	iclog->ic_state = XLOG_STATE_CALLBACK;
-}
-
 /*
  * Return true if we need to stop processing, false to continue to the next
  * iclog. The caller will need to run callbacks if the iclog is returned in the

@@ -2570,7 +2551,17 @@ xlog_state_iodone_process_iclog(
 		lowest_lsn = xlog_get_lowest_lsn(log);
 		if (lowest_lsn && XFS_LSN_CMP(lowest_lsn, header_lsn) < 0)
 			return false;
-		xlog_state_set_callback(log, iclog, header_lsn);
+		/*
+		 * If there are no callbacks on this iclog, we can mark it clean
+		 * immediately and return. Otherwise we need to run the
+		 * callbacks.
+		 */
+		if (list_empty(&iclog->ic_callbacks)) {
+			xlog_state_clean_iclog(log, iclog);
+			return false;
+		}
+		trace_xlog_iclog_callback(iclog, _RET_IP_);
+		iclog->ic_state = XLOG_STATE_CALLBACK;
 		return false;
 	default:
 		/*

Signature · 1 line

2.36.1

From: Dave Chinner <[email protected]>

Currently we track space used in the log by grant heads. These store the reserved space as a physical log location and combine both space reserved for future use with space already used in the log in a single variable. The amount of space consumed in the log is then calculated as the distance between the log tail and the grant head.

The problem with tracking the grant head as a physical location comes from the fact that it tracks both log cycle count and offset into the log in bytes in a single 64 bit variable. because the cycle count on disk is a 32 bit number, this also limits the offset into the log to 32 bits. ANd because that is in bytes, we are limited to being able to track only 2GB of log space in the grant head.

Hence to support larger physical logs, we need to track used space differently in the grant head. We no longer use the grant head for guiding AIL pushing, so the only thing it is now used for is determining if we've run out of reservation space via the calculation in xlog_space_left().

What we really need to do is move the grant heads away from tracking physical space in the log. The issue here is that space consumed in the log is not directly tracked by the current mechanism - the space consumed in the log by grant head reservations gets returned to the free pool by the tail of the log moving forward. i.e. the space isn't directly tracked or calculated, but the used grant space gets "freed" as the physical limits of the log are updated without actually needing to update the grant heads.

Hence to move away from implicit, zero-update log space tracking we need to explicitly track the amount of physical space the log actually consumes separately to the in-memory reservations for operations that will be committed to the journal. Luckily, we already track the information we need to calculate this in the AIL itself.

That is, the space currently consumed by the journal is the maximum LSN that the AIL has seen minus the current log tail. As we update both of these items dynamically as the head and tail of the log moves, we always know exactly how much space the journal consumes.

This means that we also know exactly how much space the currently active reservations require, and exactly how much free space we have remaining for new reservations to be made. Most importantly, we know what these spaces are indepedently of the physical locations of the head and tail of the log.

Hence by separating out the physical space consumed by the journal, we can now track reservations in the grant heads purely as a byte count, and the log can be considered full when the tail space + reservation space exceeds the size of the log. This means we can use the full 64 bits of grant head space for reservation space, completely removing the 32 bit byte count limitation on log size that they impose.

Hence the first step in this conversion is to track and update the "log tail space" every time the AIL tail or maximum seen LSN changes.

Signed-off-by Dave Chinner <[email protected]>

---
 fs/xfs/xfs_log_cil.c   | 9 ++++++---
 fs/xfs/xfs_log_priv.h  | 1 +
 fs/xfs/xfs_trans_ail.c | 9 ++++++---
 3 files changed, 13 insertions(+), 6 deletions(-)

fs/xfs/xfs_log_cil.c +3 -1

index 843764d40232..e482ae9fc01c 100644
@@ -761,14 +761,17 @@ xlog_cil_ail_insert(
 	 * always be the same (as iclogs can contain multiple commit records) or
 	 * higher LSN than the current head. We do this before insertion of the
 	 * items so that log space checks during insertion will reflect the
-	 * space that this checkpoint has already consumed.
+	 * space that this checkpoint has already consumed.  We call
+	 * xfs_ail_update_finish() so that tail space and space-based wakeups
+	 * will be recalculated appropriately.

fs/xfs/xfs_log_cil.c +0 -0

 	/* unpin all the log items */
 	list_for_each_entry(lv, &ctx->lv_chain, lv_list) {

fs/xfs/xfs_log_priv.h +1 -0

index 5f4358f18224..8a005cb08a02 100644
@@ -435,6 +435,7 @@ struct xlog {
 
 	struct xlog_grant_head	l_reserve_head;
 	struct xlog_grant_head	l_write_head;
+	uint64_t		l_tail_space;
 
 	struct xfs_kobj		l_kobj;
 

fs/xfs/xfs_trans_ail.c +6 -3

index fe3f8b80e687..5d0ddd6d68e9 100644
@@ -731,6 +731,8 @@ __xfs_ail_assign_tail_lsn(
 	if (!tail_lsn)
 		tail_lsn = ailp->ail_head_lsn;
 
+	WRITE_ONCE(log->l_tail_space,
+			xlog_lsn_sub(log, ailp->ail_head_lsn, tail_lsn));
 	trace_xfs_log_assign_tail_lsn(log, tail_lsn);
 	atomic64_set(&log->l_tail_lsn, tail_lsn);
 }

@@ -738,9 +740,10 @@ __xfs_ail_assign_tail_lsn(
 /*
  * Callers should pass the the original tail lsn so that we can detect if the
  * tail has moved as a result of the operation that was performed. If the caller
- * needs to force a tail LSN update, it should pass NULLCOMMITLSN to bypass the
- * "did the tail LSN change?" checks. If the caller wants to avoid a tail update
- * (e.g. it knows the tail did not change) it should pass an @old_lsn of 0.
+ * needs to force a tail space update, it should pass NULLCOMMITLSN to bypass
+ * the "did the tail LSN change?" checks. If the caller wants to avoid a tail
+ * update (e.g. it knows the tail did not change) it should pass an @old_lsn of
+ * 0.
  */
 void
 xfs_ail_update_finish(

Signature · 1 line

2.36.1

From: Dave Chinner <[email protected]>

Because we are going to need them soon. API change only, no logic changes.

Signed-off-by Dave Chinner <[email protected]>

---
 fs/xfs/xfs_log.c      | 157 +++++++++++++++++++++---------------------
 fs/xfs/xfs_log_priv.h |   2 -
 2 files changed, 77 insertions(+), 82 deletions(-)

fs/xfs/xfs_log.c +77 -80

index 5b7c91a42edf..459c0f438c89 100644
@@ -136,10 +136,10 @@ xlog_prepare_iovec(
 static void
 xlog_grant_sub_space(
 	struct xlog		*log,
-	atomic64_t		*head,
+	struct xlog_grant_head	*head,
 	int			bytes)
 {
-	int64_t	head_val = atomic64_read(head);
+	int64_t	head_val = atomic64_read(&head->grant);
 	int64_t new, old;
 
 	do {

@@ -155,17 +155,17 @@ xlog_grant_sub_space(
 
 		old = head_val;
 		new = xlog_assign_grant_head_val(cycle, space);
-		head_val = atomic64_cmpxchg(head, old, new);
+		head_val = atomic64_cmpxchg(&head->grant, old, new);
 	} while (head_val != old);
 }
 
 static void
 xlog_grant_add_space(
 	struct xlog		*log,
-	atomic64_t		*head,
+	struct xlog_grant_head	*head,
 	int			bytes)
 {
-	int64_t	head_val = atomic64_read(head);
+	int64_t	head_val = atomic64_read(&head->grant);
 	int64_t new, old;
 
 	do {

@@ -184,7 +184,7 @@ xlog_grant_add_space(
 
 		old = head_val;
 		new = xlog_assign_grant_head_val(cycle, space);
-		head_val = atomic64_cmpxchg(head, old, new);
+		head_val = atomic64_cmpxchg(&head->grant, old, new);
 	} while (head_val != old);
 }
 

@@ -197,6 +197,63 @@ xlog_grant_head_init(
 	spin_lock_init(&head->lock);
 }
 
+/*
+ * Return the space in the log between the tail and the head.  The head
+ * is passed in the cycle/bytes formal parms.  In the special case where
+ * the reserve head has wrapped passed the tail, this calculation is no
+ * longer valid.  In this case, just return 0 which means there is no space
+ * in the log.  This works for all places where this function is called
+ * with the reserve head.  Of course, if the write head were to ever
+ * wrap the tail, we should blow up.  Rather than catch this case here,
+ * we depend on other ASSERTions in other parts of the code.   XXXmiken
+ *
+ * If reservation head is behind the tail, we have a problem. Warn about it,
+ * but then treat it as if the log is empty.
+ *
+ * If the log is shut down, the head and tail may be invalid or out of whack, so
+ * shortcut invalidity asserts in this case so that we don't trigger them
+ * falsely.
+ */
+static int
+xlog_grant_space_left(
+	struct xlog		*log,
+	struct xlog_grant_head	*head)
+{
+	int			tail_bytes;
+	int			tail_cycle;
+	int			head_cycle;
+	int			head_bytes;
+
+	xlog_crack_grant_head(&head->grant, &head_cycle, &head_bytes);
+	xlog_crack_atomic_lsn(&log->l_tail_lsn, &tail_cycle, &tail_bytes);
+	tail_bytes = BBTOB(tail_bytes);
+	if (tail_cycle == head_cycle && head_bytes >= tail_bytes)
+		return log->l_logsize - (head_bytes - tail_bytes);
+	if (tail_cycle + 1 < head_cycle)
+		return 0;
+
+	/* Ignore potential inconsistency when shutdown. */
+	if (xlog_is_shutdown(log))
+		return log->l_logsize;
+
+	if (tail_cycle < head_cycle) {
+		ASSERT(tail_cycle == (head_cycle - 1));
+		return tail_bytes - head_bytes;
+	}
+
+	/*
+	 * The reservation head is behind the tail. In this case we just want to
+	 * return the size of the log as the amount of space left.
+	 */
+	xfs_alert(log->l_mp, "xlog_grant_space_left: head behind tail");
+	xfs_alert(log->l_mp, "  tail_cycle = %d, tail_bytes = %d",
+		  tail_cycle, tail_bytes);
+	xfs_alert(log->l_mp, "  GH   cycle = %d, GH   bytes = %d",
+		  head_cycle, head_bytes);
+	ASSERT(0);
+	return log->l_logsize;
+}
+
 STATIC void
 xlog_grant_head_wake_all(
 	struct xlog_grant_head	*head)

@@ -277,7 +334,7 @@ xlog_grant_head_wait(
 		spin_lock(&head->lock);
 		if (xlog_is_shutdown(log))
 			goto shutdown;
-	} while (xlog_space_left(log, &head->grant) < need_bytes);
+	} while (xlog_grant_space_left(log, head) < need_bytes);
 
 	list_del_init(&tic->t_queue);
 	return 0;

@@ -322,7 +379,7 @@ xlog_grant_head_check(
 	 * otherwise try to get some space for this transaction.
 	 */
 	*need_bytes = xlog_ticket_reservation(log, head, tic);
-	free_bytes = xlog_space_left(log, &head->grant);
+	free_bytes = xlog_grant_space_left(log, head);
 	if (!list_empty_careful(&head->waiters)) {
 		spin_lock(&head->lock);
 		if (!xlog_grant_head_wake(log, head, &free_bytes) ||

@@ -396,7 +453,7 @@ xfs_log_regrant(
 	if (error)
 		goto out_error;
 
-	xlog_grant_add_space(log, &log->l_write_head.grant, need_bytes);
+	xlog_grant_add_space(log, &log->l_write_head, need_bytes);
 	trace_xfs_log_regrant_exit(log, tic);
 	xlog_verify_grant_tail(log);
 	return 0;

@@ -447,8 +504,8 @@ xfs_log_reserve(
 	if (error)
 		goto out_error;
 
-	xlog_grant_add_space(log, &log->l_reserve_head.grant, need_bytes);
-	xlog_grant_add_space(log, &log->l_write_head.grant, need_bytes);
+	xlog_grant_add_space(log, &log->l_reserve_head, need_bytes);
+	xlog_grant_add_space(log, &log->l_write_head, need_bytes);
 	trace_xfs_log_reserve_exit(log, tic);
 	xlog_verify_grant_tail(log);
 	return 0;

@@ -1114,7 +1171,7 @@ xfs_log_space_wake(
 		ASSERT(!xlog_in_recovery(log));
 
 		spin_lock(&log->l_write_head.lock);
-		free_bytes = xlog_space_left(log, &log->l_write_head.grant);
+		free_bytes = xlog_grant_space_left(log, &log->l_write_head);
 		xlog_grant_head_wake(log, &log->l_write_head, &free_bytes);
 		spin_unlock(&log->l_write_head.lock);
 	}

@@ -1123,7 +1180,7 @@ xfs_log_space_wake(
 		ASSERT(!xlog_in_recovery(log));
 
 		spin_lock(&log->l_reserve_head.lock);
-		free_bytes = xlog_space_left(log, &log->l_reserve_head.grant);
+		free_bytes = xlog_grant_space_left(log, &log->l_reserve_head);
 		xlog_grant_head_wake(log, &log->l_reserve_head, &free_bytes);
 		spin_unlock(&log->l_reserve_head.lock);
 	}

@@ -1237,64 +1294,6 @@ xfs_log_cover(
 	return error;
 }
 
-/*
- * Return the space in the log between the tail and the head.  The head
- * is passed in the cycle/bytes formal parms.  In the special case where
- * the reserve head has wrapped passed the tail, this calculation is no
- * longer valid.  In this case, just return 0 which means there is no space
- * in the log.  This works for all places where this function is called
- * with the reserve head.  Of course, if the write head were to ever
- * wrap the tail, we should blow up.  Rather than catch this case here,
- * we depend on other ASSERTions in other parts of the code.   XXXmiken
- *
- * If reservation head is behind the tail, we have a problem. Warn about it,
- * but then treat it as if the log is empty.
- *
- * If the log is shut down, the head and tail may be invalid or out of whack, so
- * shortcut invalidity asserts in this case so that we don't trigger them
- * falsely.
- */
-int
-xlog_space_left(
-	struct xlog	*log,
-	atomic64_t	*head)
-{
-	int		tail_bytes;
-	int		tail_cycle;
-	int		head_cycle;
-	int		head_bytes;
-
-	xlog_crack_grant_head(head, &head_cycle, &head_bytes);
-	xlog_crack_atomic_lsn(&log->l_tail_lsn, &tail_cycle, &tail_bytes);
-	tail_bytes = BBTOB(tail_bytes);
-	if (tail_cycle == head_cycle && head_bytes >= tail_bytes)
-		return log->l_logsize - (head_bytes - tail_bytes);
-	if (tail_cycle + 1 < head_cycle)
-		return 0;
-
-	/* Ignore potential inconsistency when shutdown. */
-	if (xlog_is_shutdown(log))
-		return log->l_logsize;
-
-	if (tail_cycle < head_cycle) {
-		ASSERT(tail_cycle == (head_cycle - 1));
-		return tail_bytes - head_bytes;
-	}
-
-	/*
-	 * The reservation head is behind the tail. In this case we just want to
-	 * return the size of the log as the amount of space left.
-	 */
-	xfs_alert(log->l_mp, "xlog_space_left: head behind tail");
-	xfs_alert(log->l_mp, "  tail_cycle = %d, tail_bytes = %d",
-		  tail_cycle, tail_bytes);
-	xfs_alert(log->l_mp, "  GH   cycle = %d, GH   bytes = %d",
-		  head_cycle, head_bytes);
-	ASSERT(0);
-	return log->l_logsize;
-}
-
-
 static void
 xlog_ioend_work(
 	struct work_struct	*work)

@@ -1883,8 +1882,8 @@ xlog_sync(
 	if (ticket) {
 		ticket->t_curr_res -= roundoff;
 	} else {
-		xlog_grant_add_space(log, &log->l_reserve_head.grant, roundoff);
-		xlog_grant_add_space(log, &log->l_write_head.grant, roundoff);
+		xlog_grant_add_space(log, &log->l_reserve_head, roundoff);
+		xlog_grant_add_space(log, &log->l_write_head, roundoff);
 	}
 
 	/* put cycle number in every block */

@@ -2815,17 +2814,15 @@ xfs_log_ticket_regrant(
 	if (ticket->t_cnt > 0)
 		ticket->t_cnt--;
 
-	xlog_grant_sub_space(log, &log->l_reserve_head.grant,
-					ticket->t_curr_res);
-	xlog_grant_sub_space(log, &log->l_write_head.grant,
-					ticket->t_curr_res);
+	xlog_grant_sub_space(log, &log->l_reserve_head, ticket->t_curr_res);
+	xlog_grant_sub_space(log, &log->l_write_head, ticket->t_curr_res);
 	ticket->t_curr_res = ticket->t_unit_res;
 
 	trace_xfs_log_ticket_regrant_sub(log, ticket);
 
 	/* just return if we still have some of the pre-reserved space */
 	if (!ticket->t_cnt) {
-		xlog_grant_add_space(log, &log->l_reserve_head.grant,
+		xlog_grant_add_space(log, &log->l_reserve_head,
 				     ticket->t_unit_res);
 		trace_xfs_log_ticket_regrant_exit(log, ticket);
 

@@ -2873,8 +2870,8 @@ xfs_log_ticket_ungrant(
 		bytes += ticket->t_unit_res*ticket->t_cnt;
 	}
 
-	xlog_grant_sub_space(log, &log->l_reserve_head.grant, bytes);
-	xlog_grant_sub_space(log, &log->l_write_head.grant, bytes);
+	xlog_grant_sub_space(log, &log->l_reserve_head, bytes);
+	xlog_grant_sub_space(log, &log->l_write_head, bytes);
 
 	trace_xfs_log_ticket_ungrant_exit(log, ticket);
 

fs/xfs/xfs_log_priv.h +0 -2

index 8a005cb08a02..86b5959b5ef2 100644
@@ -571,8 +571,6 @@ xlog_assign_grant_head(atomic64_t *head, int cycle, int space)
 	atomic64_set(head, xlog_assign_grant_head_val(cycle, space));
 }
 
-int xlog_space_left(struct xlog	 *log, atomic64_t *head);
-
 /*
  * Committed Item List interfaces
  */

Signature · 1 line

2.36.1