Linux-Fsdevel Archive on lore.kernel.org
 help / color / Atom feed
From: Dave Chinner <david@fromorbit.com>
To: linux-xfs@vger.kernel.org
Cc: linux-mm@kvack.org, linux-fsdevel@vger.kernel.org
Subject: [PATCH 07/26] xfs: tail updates only need to occur when LSN changes
Date: Wed,  9 Oct 2019 14:21:05 +1100
Message-ID: <20191009032124.10541-8-david@fromorbit.com> (raw)
In-Reply-To: <20191009032124.10541-1-david@fromorbit.com>

From: Dave Chinner <dchinner@redhat.com>

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@redhat.com>
---
 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(-)

diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index ab12e526540a..0d5eee456b0c 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -731,19 +731,27 @@ 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);
 	}
 
 	/*
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 656819523bbd..685a21cd24c0 100644
--- 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;
@@ -681,11 +689,12 @@ 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;
 	}
@@ -730,7 +739,7 @@ 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);
 
@@ -745,9 +754,10 @@ 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);
 		}
@@ -758,15 +768,23 @@ 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);
@@ -774,7 +792,9 @@ 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;
 }
 
 /**
@@ -805,7 +825,7 @@ 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);
@@ -818,8 +838,8 @@ 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
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index 64ffa746730e..35655eac01a6 100644
--- 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);
-- 
2.23.0.rc1


  parent reply index

Thread overview: 87+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-09  3:20 [PATCH V2 00/26] mm, xfs: non-blocking inode reclaim Dave Chinner
2019-10-09  3:20 ` [PATCH 01/26] xfs: Lower CIL flush limit for large logs Dave Chinner
2019-10-11 12:39   ` Brian Foster
2019-10-30 17:08   ` Darrick J. Wong
2019-10-09  3:21 ` [PATCH 02/26] xfs: Throttle commits on delayed background CIL push Dave Chinner
2019-10-11 12:38   ` Brian Foster
2019-10-09  3:21 ` [PATCH 03/26] xfs: don't allow log IO to be throttled Dave Chinner
2019-10-11  9:35   ` Christoph Hellwig
2019-10-11 12:39   ` Brian Foster
2019-10-30 17:14   ` Darrick J. Wong
2019-10-09  3:21 ` [PATCH 04/26] xfs: Improve metadata buffer reclaim accountability Dave Chinner
2019-10-11 12:39   ` Brian Foster
2019-10-11 12:57     ` Christoph Hellwig
2019-10-11 23:14       ` Dave Chinner
2019-10-11 23:13     ` Dave Chinner
2019-10-12 12:05       ` Brian Foster
2019-10-13  3:14         ` Dave Chinner
2019-10-14 13:05           ` Brian Foster
2019-10-30 17:25   ` Darrick J. Wong
2019-10-30 21:43     ` Dave Chinner
2019-10-31  3:06       ` Darrick J. Wong
2019-10-31 20:50         ` Dave Chinner
2019-10-31 21:05           ` Darrick J. Wong
2019-10-31 21:22             ` Christoph Hellwig
2019-11-03 21:26             ` Dave Chinner
2019-11-04 23:08               ` Darrick J. Wong
2019-10-09  3:21 ` [PATCH 05/26] xfs: correctly acount for reclaimable slabs Dave Chinner
2019-10-11 12:39   ` Brian Foster
2019-10-30 17:16   ` Darrick J. Wong
2019-10-09  3:21 ` [PATCH 06/26] xfs: synchronous AIL pushing Dave Chinner
2019-10-11  9:42   ` Christoph Hellwig
2019-10-11 12:40   ` Brian Foster
2019-10-11 23:15     ` Dave Chinner
2019-10-09  3:21 ` Dave Chinner [this message]
2019-10-11  9:50   ` [PATCH 07/26] xfs: tail updates only need to occur when LSN changes Christoph Hellwig
2019-10-11 12:40   ` Brian Foster
2019-10-09  3:21 ` [PATCH 08/26] mm: directed shrinker work deferral Dave Chinner
2019-10-14  8:46   ` Christoph Hellwig
2019-10-14 13:06     ` Brian Foster
2019-10-18  7:59     ` Dave Chinner
2019-10-09  3:21 ` [PATCH 09/26] shrinkers: use defer_work for GFP_NOFS sensitive shrinkers Dave Chinner
2019-10-09  3:21 ` [PATCH 10/26] mm: factor shrinker work calculations Dave Chinner
2019-10-09  3:21 ` [PATCH 11/26] shrinker: defer work only to kswapd Dave Chinner
2019-10-09  3:21 ` [PATCH 12/26] shrinker: clean up variable types and tracepoints Dave Chinner
2019-10-09  3:21 ` [PATCH 13/26] mm: reclaim_state records pages reclaimed, not slabs Dave Chinner
2019-10-09  3:21 ` [PATCH 14/26] mm: back off direct reclaim on excessive shrinker deferral Dave Chinner
2019-10-11 16:21   ` Matthew Wilcox
2019-10-11 23:20     ` Dave Chinner
2019-10-09  3:21 ` [PATCH 15/26] mm: kswapd backoff for shrinkers Dave Chinner
2019-10-09  3:21 ` [PATCH 16/26] xfs: synchronous AIL pushing Dave Chinner
2019-10-11 10:18   ` Christoph Hellwig
2019-10-11 15:29     ` Brian Foster
2019-10-11 23:27       ` Dave Chinner
2019-10-12 12:08         ` Brian Foster
2019-10-09  3:21 ` [PATCH 17/26] xfs: don't block kswapd in inode reclaim Dave Chinner
2019-10-11 15:29   ` Brian Foster
2019-10-09  3:21 ` [PATCH 18/26] xfs: reduce kswapd blocking on inode locking Dave Chinner
2019-10-11 10:29   ` Christoph Hellwig
2019-10-09  3:21 ` [PATCH 19/26] xfs: kill background reclaim work Dave Chinner
2019-10-11 10:31   ` Christoph Hellwig
2019-10-09  3:21 ` [PATCH 20/26] xfs: use AIL pushing for inode reclaim IO Dave Chinner
2019-10-11 17:38   ` Brian Foster
2019-10-09  3:21 ` [PATCH 21/26] xfs: remove mode from xfs_reclaim_inodes() Dave Chinner
2019-10-11 10:39   ` Christoph Hellwig
2019-10-14 13:07   ` Brian Foster
2019-10-09  3:21 ` [PATCH 22/26] xfs: track reclaimable inodes using a LRU list Dave Chinner
2019-10-11 10:42   ` Christoph Hellwig
2019-10-14 13:07   ` Brian Foster
2019-10-09  3:21 ` [PATCH 23/26] xfs: reclaim inodes from the LRU Dave Chinner
2019-10-11 10:56   ` Christoph Hellwig
2019-10-30 23:25     ` Dave Chinner
2019-10-09  3:21 ` [PATCH 24/26] xfs: remove unusued old inode reclaim code Dave Chinner
2019-10-09  3:21 ` [PATCH 25/26] xfs: rework unreferenced inode lookups Dave Chinner
2019-10-11 12:55   ` Christoph Hellwig
2019-10-11 13:39     ` Peter Zijlstra
2019-10-11 23:38     ` Dave Chinner
2019-10-14 13:07   ` Brian Foster
2019-10-17  1:24     ` Dave Chinner
2019-10-17  7:57       ` Brian Foster
2019-10-18 20:29         ` Dave Chinner
2019-10-09  3:21 ` [PATCH 26/26] xfs: use xfs_ail_push_all_sync in xfs_reclaim_inodes Dave Chinner
2019-10-11  9:55   ` Christoph Hellwig
2019-10-09  7:06 ` [PATCH V2 00/26] mm, xfs: non-blocking inode reclaim Christoph Hellwig
2019-10-11 19:03 ` Josef Bacik
2019-10-11 23:48   ` Dave Chinner
2019-10-12  0:19     ` Josef Bacik
2019-10-12  0:48       ` Dave Chinner

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191009032124.10541-8-david@fromorbit.com \
    --to=david@fromorbit.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-xfs@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \
		linux-fsdevel@vger.kernel.org
	public-inbox-index linux-fsdevel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-fsdevel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git