This is a note to let you know that I've just added the patch titled
xfs: tail updates only need to occur when LSN changes
to the 5.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
xfs-tail-updates-only-need-to-occur-when-lsn-changes.patch
and it can be found in the queue-5.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From foo@baz Wed Oct 26 04:49:40 PM CEST 2022
From: Chandan Babu R <chandan.babu@xxxxxxxxxx>
Date: Wed, 26 Oct 2022 11:58:37 +0530
Subject: xfs: tail updates only need to occur when LSN changes
To: gregkh@xxxxxxxxxxxxxxxxxxx
Cc: sashal@xxxxxxxxxx, mcgrof@xxxxxxxxxx, linux-xfs@xxxxxxxxxxxxxxx, stable@xxxxxxxxxxxxxxx, djwong@xxxxxxxxxx, chandan.babu@xxxxxxxxxx, amir73il@xxxxxxxxx, leah.rumancik@xxxxxxxxx
Message-ID: <20221026062843.927600-21-chandan.babu@xxxxxxxxxx>
From: Dave Chinner <dchinner@xxxxxxxxxx>
commit 8eb807bd839938b45bf7a97f0568d2a845ba6929 upstream.
We currently wake anything waiting on the log tail to move whenever
the log item at the tail of the log is removed. Historically this
was fine behaviour because there were very few items at any given
LSN. But with delayed logging, there may be thousands of items at
any given LSN, and we can't move the tail until they are all gone.
Hence if we are removing them in near tail-first order, we might be
waking up processes waiting on the tail LSN to change (e.g. log
space waiters) repeatedly without them being able to make progress.
This also occurs with the new sync push waiters, and can result in
thousands of spurious wakeups every second when under heavy direct
reclaim pressure.
To fix this, check that the tail LSN has actually changed on the
AIL before triggering wakeups. This will reduce the number of
spurious wakeups when doing bulk AIL removal and make this code much
more efficient.
Signed-off-by: Dave Chinner <dchinner@xxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: Brian Foster <bfoster@xxxxxxxxxx>
Reviewed-by: Allison Collins <allison.henderson@xxxxxxxxxx>
Reviewed-by: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
Signed-off-by: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
Acked-by: Darrick J. Wong <djwong@xxxxxxxxxx>
Signed-off-by: Chandan Babu R <chandan.babu@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
fs/xfs/xfs_inode_item.c | 18 ++++++++++++----
fs/xfs/xfs_trans_ail.c | 52 +++++++++++++++++++++++++++++++++---------------
fs/xfs/xfs_trans_priv.h | 4 +--
3 files changed, 51 insertions(+), 23 deletions(-)
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -732,19 +732,27 @@ xfs_iflush_done(
* holding the lock before removing the inode from the AIL.
*/
if (need_ail) {
- bool mlip_changed = false;
+ xfs_lsn_t tail_lsn = 0;
/* this is an opencoded batch version of xfs_trans_ail_delete */
spin_lock(&ailp->ail_lock);
list_for_each_entry(blip, &tmp, li_bio_list) {
if (INODE_ITEM(blip)->ili_logged &&
- blip->li_lsn == INODE_ITEM(blip)->ili_flush_lsn)
- mlip_changed |= xfs_ail_delete_one(ailp, blip);
- else {
+ blip->li_lsn == INODE_ITEM(blip)->ili_flush_lsn) {
+ /*
+ * xfs_ail_update_finish() only cares about the
+ * lsn of the first tail item removed, any
+ * others will be at the same or higher lsn so
+ * we just ignore them.
+ */
+ xfs_lsn_t lsn = xfs_ail_delete_one(ailp, blip);
+ if (!tail_lsn && lsn)
+ tail_lsn = lsn;
+ } else {
xfs_clear_li_failed(blip);
}
}
- xfs_ail_update_finish(ailp, mlip_changed);
+ xfs_ail_update_finish(ailp, tail_lsn);
}
/*
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -108,17 +108,25 @@ xfs_ail_next(
* We need the AIL lock in order to get a coherent read of the lsn of the last
* item in the AIL.
*/
+static xfs_lsn_t
+__xfs_ail_min_lsn(
+ struct xfs_ail *ailp)
+{
+ struct xfs_log_item *lip = xfs_ail_min(ailp);
+
+ if (lip)
+ return lip->li_lsn;
+ return 0;
+}
+
xfs_lsn_t
xfs_ail_min_lsn(
struct xfs_ail *ailp)
{
- xfs_lsn_t lsn = 0;
- struct xfs_log_item *lip;
+ xfs_lsn_t lsn;
spin_lock(&ailp->ail_lock);
- lip = xfs_ail_min(ailp);
- if (lip)
- lsn = lip->li_lsn;
+ lsn = __xfs_ail_min_lsn(ailp);
spin_unlock(&ailp->ail_lock);
return lsn;
@@ -683,11 +691,12 @@ xfs_ail_push_all_sync(
void
xfs_ail_update_finish(
struct xfs_ail *ailp,
- bool do_tail_update) __releases(ailp->ail_lock)
+ xfs_lsn_t old_lsn) __releases(ailp->ail_lock)
{
struct xfs_mount *mp = ailp->ail_mount;
- if (!do_tail_update) {
+ /* 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;
}
@@ -732,7 +741,7 @@ xfs_trans_ail_update_bulk(
xfs_lsn_t lsn) __releases(ailp->ail_lock)
{
struct xfs_log_item *mlip;
- int mlip_changed = 0;
+ xfs_lsn_t tail_lsn = 0;
int i;
LIST_HEAD(tmp);
@@ -747,9 +756,10 @@ xfs_trans_ail_update_bulk(
continue;
trace_xfs_ail_move(lip, lip->li_lsn, lsn);
+ if (mlip == lip && !tail_lsn)
+ tail_lsn = lip->li_lsn;
+
xfs_ail_delete(ailp, lip);
- if (mlip == lip)
- mlip_changed = 1;
} else {
trace_xfs_ail_insert(lip, 0, lsn);
}
@@ -760,15 +770,23 @@ xfs_trans_ail_update_bulk(
if (!list_empty(&tmp))
xfs_ail_splice(ailp, cur, &tmp, lsn);
- xfs_ail_update_finish(ailp, mlip_changed);
+ xfs_ail_update_finish(ailp, tail_lsn);
}
-bool
+/*
+ * Delete one log item from the AIL.
+ *
+ * If this item was at the tail of the AIL, return the LSN of the log item so
+ * that we can use it to check if the LSN of the tail of the log has moved
+ * when finishing up the AIL delete process in xfs_ail_update_finish().
+ */
+xfs_lsn_t
xfs_ail_delete_one(
struct xfs_ail *ailp,
struct xfs_log_item *lip)
{
struct xfs_log_item *mlip = xfs_ail_min(ailp);
+ xfs_lsn_t lsn = lip->li_lsn;
trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn);
xfs_ail_delete(ailp, lip);
@@ -776,7 +794,9 @@ xfs_ail_delete_one(
clear_bit(XFS_LI_IN_AIL, &lip->li_flags);
lip->li_lsn = 0;
- return mlip == lip;
+ if (mlip == lip)
+ return lsn;
+ return 0;
}
/**
@@ -807,7 +827,7 @@ xfs_trans_ail_delete(
int shutdown_type)
{
struct xfs_mount *mp = ailp->ail_mount;
- bool need_update;
+ xfs_lsn_t tail_lsn;
if (!test_bit(XFS_LI_IN_AIL, &lip->li_flags)) {
spin_unlock(&ailp->ail_lock);
@@ -820,8 +840,8 @@ xfs_trans_ail_delete(
return;
}
- need_update = xfs_ail_delete_one(ailp, lip);
- xfs_ail_update_finish(ailp, need_update);
+ tail_lsn = xfs_ail_delete_one(ailp, lip);
+ xfs_ail_update_finish(ailp, tail_lsn);
}
int
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -91,8 +91,8 @@ xfs_trans_ail_update(
xfs_trans_ail_update_bulk(ailp, NULL, &lip, 1, lsn);
}
-bool xfs_ail_delete_one(struct xfs_ail *ailp, struct xfs_log_item *lip);
-void xfs_ail_update_finish(struct xfs_ail *ailp, bool do_tail_update)
+xfs_lsn_t xfs_ail_delete_one(struct xfs_ail *ailp, struct xfs_log_item *lip);
+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_ail *ailp, struct xfs_log_item *lip,
int shutdown_type);
Patches currently in stable-queue which might be from chandan.babu@xxxxxxxxxx are
queue-5.4/xfs-check-owner-of-dir3-blocks.patch
queue-5.4/xfs-throttle-commits-on-delayed-background-cil-push.patch
queue-5.4/xfs-factor-common-ail-item-deletion-code.patch
queue-5.4/xfs-remove-the-xfs_dq_logitem_t-typedef.patch
queue-5.4/xfs-fix-buffer-corruption-reporting-when-xfs_dir3_free_header_check-fails.patch
queue-5.4/xfs-xfs_buf_corruption_error-should-take-__this_address.patch
queue-5.4/xfs-open-code-insert-range-extent-split-helper.patch
queue-5.4/xfs-don-t-write-a-corrupt-unmount-record-to-force-summary-counter-recalc.patch
queue-5.4/xfs-check-owner-of-dir3-data-blocks.patch
queue-5.4/xfs-factor-out-quotaoff-intent-ail-removal-and-memory-free.patch
queue-5.4/xfs-trylock-underlying-buffer-on-dquot-flush.patch
queue-5.4/xfs-remove-the-xfs_disk_dquot_t-and-xfs_dquot_t.patch
queue-5.4/xfs-add-a-function-to-deal-with-corrupt-buffers-post-verifiers.patch
queue-5.4/xfs-fix-use-after-free-on-cil-context-on-shutdown.patch
queue-5.4/xfs-tail-updates-only-need-to-occur-when-lsn-changes.patch
queue-5.4/xfs-use-scnprintf-for-avoiding-potential-buffer-overflow.patch
queue-5.4/xfs-move-inode-flush-to-the-sync-workqueue.patch
queue-5.4/xfs-lower-cil-flush-limit-for-large-logs.patch
queue-5.4/xfs-rework-collapse-range-into-an-atomic-operation.patch
queue-5.4/xfs-remove-the-xfs_qoff_logitem_t-typedef.patch
queue-5.4/xfs-fix-unmount-hang-and-memory-leak-on-shutdown-during-quotaoff.patch
queue-5.4/xfs-preserve-default-grace-interval-during-quotacheck.patch
queue-5.4/xfs-replace-function-declaration-by-actual-definition.patch
queue-5.4/xfs-rework-insert-range-into-an-atomic-operation.patch
queue-5.4/xfs-factor-out-a-new-xfs_log_force_inode-helper.patch
queue-5.4/xfs-reflink-should-force-the-log-out-if-mounted-with-wsync.patch
