xfs: periodically relog deferred intent itemsdefer-ops-stalls_2020-06-24

There's a subtle design flaw in the deferred log item code that can lead
to pinning the log tail.  Taking up the defer ops chain examples from
the previous commit, we can get trapped in sequences like this:

Caller hands us a transaction t0 with D0-D3 attached.  The defer ops
chain will look like the following if the transaction rolls succeed:

t1: D0(t0), D1(t0), D2(t0), D3(t0)
t2: d4(t1), d5(t1), D1(t0), D2(t0), D3(t0)
t3: d5(t1), D1(t0), D2(t0), D3(t0)
...
t9: d9(t7), D3(t0)
t10: D3(t0)
t11: d10(t10), d11(t10)
t12: d11(t10)

In transaction 9, we finish d9 and try to roll to t10 while holding onto
an intent item for D3 that we logged in t0.

The previous commit changed the order in which we place new defer ops in
the defer ops processing chain to reduce the maximum chain length.  Now
make xfs_defer_finish_noroll capable of relogging the entire chain
periodically so that we can always move the log tail forward.  We do
this every seven loops, having observed that while most chains never
exceed seven items in length, the rest go far over that and seem to
be involved in most of the stall problems.

Callers are now required to ensure that the transaction reservation is
large enough to handle logging done items and new intent items for the
maximum possible chain length.  Most callers are careful to keep the
chain lengths low, so the overhead should be minimal.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>

7 files changed, 155 insertions, 0 deletions

diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 9e6412bd6845..15c84e11625d 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -361,6 +361,30 @@ xfs_defer_cancel_list(
 }
 
 /*
+ * Prevent a log intent item from pinning the tail of the log by logging a
+ * done item to release the intent item; and then log a new intent item.
+ * The caller should provide a fresh transaction and roll it after we're done.
+ */
+static void
+xfs_defer_relog(
+	struct xfs_trans		*tp,
+	struct list_head		*dfops)
+{
+	struct xfs_defer_pending	*dfp;
+
+	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
+
+	trace_xfs_defer_relog(tp, _RET_IP_);
+
+	list_for_each_entry(dfp, dfops, dfp_list) {
+		trace_xfs_defer_relog_intent(tp->t_mountp, dfp);
+		dfp->dfp_intent = xfs_trans_item_relog(dfp->dfp_intent, tp);
+	}
+
+	trace_xfs_defer_relog_done(tp, _RET_IP_);
+}
+
+/*
  * Log an intent-done item for the first pending intent, and finish the work
  * items.
  */
@@ -420,6 +444,7 @@ xfs_defer_finish_noroll(
 	struct xfs_trans		**tp)
 {
 	struct xfs_defer_pending	*dfp;
+	unsigned int			nr_rolls = 0;
 	int				error = 0;
 	LIST_HEAD(dop_pending);
 
@@ -445,6 +470,15 @@ xfs_defer_finish_noroll(
 		if (error)
 			goto out_shutdown;
 
+		/* Every few rolls we relog all the intent items. */
+		if (!(++nr_rolls % 7)) {
+			xfs_defer_relog(*tp, &dop_pending);
+
+			error = xfs_defer_trans_roll(tp);
+			if (error)
+				goto out_shutdown;
+		}
+
 		dfp = list_first_entry(&dop_pending, struct xfs_defer_pending,
 				       dfp_list);
 		error = xfs_defer_finish_one(*tp, dfp);
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 72d4f6d30ba5..d16f7e18271c 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -537,6 +537,30 @@ xfs_bui_item_match(
 	return BUI_ITEM(lip)->bui_format.bui_id == intent_id;
 }
 
+/* Relog an intent item to push the log tail forward. */
+static struct xfs_log_item *
+xfs_bui_item_relog(
+	struct xfs_log_item		*intent,
+	struct xfs_trans		*tp)
+{
+	struct xfs_bud_log_item		*budp;
+	struct xfs_bui_log_item		*buip;
+	struct xfs_map_extent		*extp;
+
+	extp = BUI_ITEM(intent)->bui_format.bui_extents;
+
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	budp = xfs_trans_get_bud(tp, BUI_ITEM(intent));
+	set_bit(XFS_LI_DIRTY, &budp->bud_item.li_flags);
+
+	buip = xfs_bui_init(tp->t_mountp);
+	memcpy(buip->bui_format.bui_extents, extp, sizeof(*extp));
+	atomic_set(&buip->bui_next_extent, 1);
+	xfs_trans_add_item(tp, &buip->bui_item);
+	set_bit(XFS_LI_DIRTY, &buip->bui_item.li_flags);
+	return &buip->bui_item;
+}
+
 static const struct xfs_item_ops xfs_bui_item_ops = {
 	.iop_size	= xfs_bui_item_size,
 	.iop_format	= xfs_bui_item_format,
@@ -544,6 +568,7 @@ static const struct xfs_item_ops xfs_bui_item_ops = {
 	.iop_release	= xfs_bui_item_release,
 	.iop_recover	= xfs_bui_item_recover,
 	.iop_match	= xfs_bui_item_match,
+	.iop_relog	= xfs_bui_item_relog,
 };
 
 /*
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 951855364eae..5f239af43046 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -646,6 +646,34 @@ xfs_efi_item_match(
 	return EFI_ITEM(lip)->efi_format.efi_id == intent_id;
 }
 
+/* Relog an intent item to push the log tail forward. */
+static struct xfs_log_item *
+xfs_efi_item_relog(
+	struct xfs_log_item		*intent,
+	struct xfs_trans		*tp)
+{
+	struct xfs_efd_log_item		*efdp;
+	struct xfs_efi_log_item		*efip;
+	struct xfs_extent		*extp;
+	unsigned int			count;
+
+	count = EFI_ITEM(intent)->efi_format.efi_nextents;
+	extp = EFI_ITEM(intent)->efi_format.efi_extents;
+
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	efdp = xfs_trans_get_efd(tp, EFI_ITEM(intent), count);
+	efdp->efd_next_extent = count;
+	memcpy(efdp->efd_format.efd_extents, extp, count * sizeof(*extp));
+	set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
+
+	efip = xfs_efi_init(tp->t_mountp, count);
+	memcpy(efip->efi_format.efi_extents, extp, count * sizeof(*extp));
+	atomic_set(&efip->efi_next_extent, count);
+	xfs_trans_add_item(tp, &efip->efi_item);
+	set_bit(XFS_LI_DIRTY, &efip->efi_item.li_flags);
+	return &efip->efi_item;
+}
+
 static const struct xfs_item_ops xfs_efi_item_ops = {
 	.iop_size	= xfs_efi_item_size,
 	.iop_format	= xfs_efi_item_format,
@@ -653,6 +681,7 @@ static const struct xfs_item_ops xfs_efi_item_ops = {
 	.iop_release	= xfs_efi_item_release,
 	.iop_recover	= xfs_efi_item_recover,
 	.iop_match	= xfs_efi_item_match,
+	.iop_relog	= xfs_efi_item_relog,
 };
 
 /*
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 69699d22b254..54f29431f175 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -565,6 +565,32 @@ xfs_cui_item_match(
 	return CUI_ITEM(lip)->cui_format.cui_id == intent_id;
 }
 
+/* Relog an intent item to push the log tail forward. */
+static struct xfs_log_item *
+xfs_cui_item_relog(
+	struct xfs_log_item		*intent,
+	struct xfs_trans		*tp)
+{
+	struct xfs_cud_log_item		*cudp;
+	struct xfs_cui_log_item		*cuip;
+	struct xfs_phys_extent		*extp;
+	unsigned int			count;
+
+	count = CUI_ITEM(intent)->cui_format.cui_nextents;
+	extp = CUI_ITEM(intent)->cui_format.cui_extents;
+
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	cudp = xfs_trans_get_cud(tp, CUI_ITEM(intent));
+	set_bit(XFS_LI_DIRTY, &cudp->cud_item.li_flags);
+
+	cuip = xfs_cui_init(tp->t_mountp, count);
+	memcpy(cuip->cui_format.cui_extents, extp, count * sizeof(*extp));
+	atomic_set(&cuip->cui_next_extent, count);
+	xfs_trans_add_item(tp, &cuip->cui_item);
+	set_bit(XFS_LI_DIRTY, &cuip->cui_item.li_flags);
+	return &cuip->cui_item;
+}
+
 static const struct xfs_item_ops xfs_cui_item_ops = {
 	.iop_size	= xfs_cui_item_size,
 	.iop_format	= xfs_cui_item_format,
@@ -572,6 +598,7 @@ static const struct xfs_item_ops xfs_cui_item_ops = {
 	.iop_release	= xfs_cui_item_release,
 	.iop_recover	= xfs_cui_item_recover,
 	.iop_match	= xfs_cui_item_match,
+	.iop_relog	= xfs_cui_item_relog,
 };
 
 /*
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index 11520e1d352f..149aa190b958 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -588,6 +588,32 @@ xfs_rui_item_match(
 	return RUI_ITEM(lip)->rui_format.rui_id == intent_id;
 }
 
+/* Relog an intent item to push the log tail forward. */
+static struct xfs_log_item *
+xfs_rui_item_relog(
+	struct xfs_log_item		*intent,
+	struct xfs_trans		*tp)
+{
+	struct xfs_rud_log_item		*rudp;
+	struct xfs_rui_log_item		*ruip;
+	struct xfs_map_extent		*extp;
+	unsigned int			count;
+
+	count = RUI_ITEM(intent)->rui_format.rui_nextents;
+	extp = RUI_ITEM(intent)->rui_format.rui_extents;
+
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	rudp = xfs_trans_get_rud(tp, RUI_ITEM(intent));
+	set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags);
+
+	ruip = xfs_rui_init(tp->t_mountp, count);
+	memcpy(ruip->rui_format.rui_extents, extp, count * sizeof(*extp));
+	atomic_set(&ruip->rui_next_extent, count);
+	xfs_trans_add_item(tp, &ruip->rui_item);
+	set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags);
+	return &ruip->rui_item;
+}
+
 static const struct xfs_item_ops xfs_rui_item_ops = {
 	.iop_size	= xfs_rui_item_size,
 	.iop_format	= xfs_rui_item_format,
@@ -595,6 +621,7 @@ static const struct xfs_item_ops xfs_rui_item_ops = {
 	.iop_release	= xfs_rui_item_release,
 	.iop_recover	= xfs_rui_item_recover,
 	.iop_match	= xfs_rui_item_match,
+	.iop_relog	= xfs_rui_item_relog,
 };
 
 /*
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 50c478374a31..2c5df8315351 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2384,6 +2384,8 @@ DEFINE_DEFER_EVENT(xfs_defer_trans_roll);
 DEFINE_DEFER_EVENT(xfs_defer_trans_abort);
 DEFINE_DEFER_EVENT(xfs_defer_finish);
 DEFINE_DEFER_EVENT(xfs_defer_finish_done);
+DEFINE_DEFER_EVENT(xfs_defer_relog);
+DEFINE_DEFER_EVENT(xfs_defer_relog_done);
 
 DEFINE_DEFER_ERROR_EVENT(xfs_defer_trans_roll_error);
 DEFINE_DEFER_ERROR_EVENT(xfs_defer_finish_error);
@@ -2392,6 +2394,7 @@ DEFINE_DEFER_PENDING_EVENT(xfs_defer_create_intent);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_cancel_list);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_finish);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_abort);
+DEFINE_DEFER_PENDING_EVENT(xfs_defer_relog_intent);
 
 #define DEFINE_BMAP_FREE_DEFERRED_EVENT DEFINE_PHYS_EXTENT_DEFERRED_EVENT
 DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_bmap_free_defer);
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 78fa4267bb8e..d82873159dd5 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -83,6 +83,8 @@ struct xfs_item_ops {
 	int (*iop_recover)(struct xfs_log_item *lip,
 			   struct xfs_defer_capture **dfcp);
 	bool (*iop_match)(struct xfs_log_item *item, uint64_t id);
+	struct xfs_log_item *(*iop_relog)(struct xfs_log_item *intent,
+			struct xfs_trans *tp);
 };
 
 /*
@@ -250,4 +252,12 @@ void		xfs_trans_buf_copy_type(struct xfs_buf *dst_bp,
 
 extern kmem_zone_t	*xfs_trans_zone;
 
+static inline struct xfs_log_item *
+xfs_trans_item_relog(
+	struct xfs_log_item	*lip,
+	struct xfs_trans	*tp)
+{
+	return lip->li_ops->iop_relog(lip, tp);
+}
+
 #endif	/* __XFS_TRANS_H__ */