xfs: exact busy extent tracking

Update the extent tree in case we have to reuse a busy extent, so that it
always is kept uptodate.  This is done by replacing the busy list searches
with a new xfs_alloc_busy_reuse helper, which updates the busy extent tree
in case of a reuse.  This allows us to allow reusing metadata extents
unconditionally, and thus avoid log forces especially for allocation btree
blocks.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>

fs/xfs/linux-2.6/xfs_trace.h

@@ -1151,44 +1151,7 @@ TRACE_EVENT(xfs_bunmap,
 
 );
 
-#define XFS_BUSY_SYNC \
-	{ 0,	"async" }, \
-	{ 1,	"sync" }
-
-TRACE_EVENT(xfs_alloc_busy,
-	TP_PROTO(struct xfs_trans *trans, xfs_agnumber_t agno,
-		 xfs_agblock_t agbno, xfs_extlen_t len, int sync),
-	TP_ARGS(trans, agno, agbno, len, sync),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(struct xfs_trans *, tp)
-		__field(int, tid)
-		__field(xfs_agnumber_t, agno)
-		__field(xfs_agblock_t, agbno)
-		__field(xfs_extlen_t, len)
-		__field(int, sync)
-	),
-	TP_fast_assign(
-		__entry->dev = trans->t_mountp->m_super->s_dev;
-		__entry->tp = trans;
-		__entry->tid = trans->t_ticket->t_tid;
-		__entry->agno = agno;
-		__entry->agbno = agbno;
-		__entry->len = len;
-		__entry->sync = sync;
-	),
-	TP_printk("dev %d:%d trans 0x%p tid 0x%x agno %u agbno %u len %u %s",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->tp,
-		  __entry->tid,
-		  __entry->agno,
-		  __entry->agbno,
-		  __entry->len,
-		  __print_symbolic(__entry->sync, XFS_BUSY_SYNC))
-
-);
-
-TRACE_EVENT(xfs_alloc_unbusy,
+DECLARE_EVENT_CLASS(xfs_busy_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agblock_t agbno, xfs_extlen_t len),
 	TP_ARGS(mp, agno, agbno, len),
@@ -1210,36 +1173,16 @@ TRACE_EVENT(xfs_alloc_unbusy,
 		  __entry->agbno,
 		  __entry->len)
 );
-
-#define XFS_BUSY_STATES \
-	{ 0,	"missing" }, \
-	{ 1,	"found" }
-
-TRACE_EVENT(xfs_alloc_busysearch,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 xfs_agblock_t agbno, xfs_extlen_t len, int found),
-	TP_ARGS(mp, agno, agbno, len, found),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(xfs_agnumber_t, agno)
-		__field(xfs_agblock_t, agbno)
-		__field(xfs_extlen_t, len)
-		__field(int, found)
-	),
-	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
-		__entry->agbno = agbno;
-		__entry->len = len;
-		__entry->found = found;
-	),
-	TP_printk("dev %d:%d agno %u agbno %u len %u %s",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->agno,
-		  __entry->agbno,
-		  __entry->len,
-		  __print_symbolic(__entry->found, XFS_BUSY_STATES))
-);
+#define DEFINE_BUSY_EVENT(name) \
+DEFINE_EVENT(xfs_busy_class, name, \
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
+		 xfs_agblock_t agbno, xfs_extlen_t len), \
+	TP_ARGS(mp, agno, agbno, len))
+DEFINE_BUSY_EVENT(xfs_alloc_busy);
+DEFINE_BUSY_EVENT(xfs_alloc_busy_enomem);
+DEFINE_BUSY_EVENT(xfs_alloc_busy_force);
+DEFINE_BUSY_EVENT(xfs_alloc_busy_reuse);
+DEFINE_BUSY_EVENT(xfs_alloc_busy_clear);
 
 TRACE_EVENT(xfs_alloc_busy_trim,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,

fs/xfs/xfs_ag.h

@@ -187,7 +187,6 @@ struct xfs_busy_extent {
 	xfs_agnumber_t	agno;
 	xfs_agblock_t	bno;
 	xfs_extlen_t	length;
-	xlog_tid_t	tid;		/* transaction that created this */
 };
 
 /*

fs/xfs/xfs_alloc.h

@@ -145,6 +145,10 @@ xfs_alloc_busy_clear(struct xfs_mount *mp, struct xfs_busy_extent *busyp);
 int
 xfs_alloc_busy_search(struct xfs_mount *mp, xfs_agnumber_t agno,
 	xfs_agblock_t bno, xfs_extlen_t len);
+
+void
+xfs_alloc_busy_reuse(struct xfs_mount *mp, xfs_agnumber_t agno,
+	xfs_agblock_t fbno, xfs_extlen_t flen, bool userdata);
 #endif	/* __KERNEL__ */
 
 /*

fs/xfs/xfs_alloc_btree.c

@@ -94,8 +94,8 @@ xfs_allocbt_alloc_block(
 		*stat = 0;
 		return 0;
 	}
-	if (xfs_alloc_busy_search(cur->bc_mp, cur->bc_private.a.agno, bno, 1))
-		xfs_trans_set_sync(cur->bc_tp);
+
+	xfs_alloc_busy_reuse(cur->bc_mp, cur->bc_private.a.agno, bno, 1, false);
 
 	xfs_trans_agbtree_delta(cur->bc_tp, 1);
 	new->s = cpu_to_be32(bno);
@@ -120,17 +120,6 @@ xfs_allocbt_free_block(
 	if (error)
 		return error;
 
-	/*
-	 * Since blocks move to the free list without the coordination used in
-	 * xfs_bmap_finish, we can't allow block to be available for
-	 * reallocation and non-transaction writing (user data) until we know
-	 * that the transaction that moved it to the free list is permanently
-	 * on disk. We track the blocks by declaring these blocks as "busy";
-	 * the busy list is maintained on a per-ag basis and each transaction
-	 * records which entries should be removed when the iclog commits to
-	 * disk. If a busy block is allocated, the iclog is pushed up to the
-	 * LSN that freed the block.
-	 */
 	xfs_alloc_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1);
 	xfs_trans_agbtree_delta(cur->bc_tp, -1);
 	return 0;

fs/xfs/xfs_log.c

@@ -3248,13 +3248,6 @@ xfs_log_ticket_get(
 	return ticket;
 }
 
-xlog_tid_t
-xfs_log_get_trans_ident(
-	struct xfs_trans	*tp)
-{
-	return tp->t_ticket->t_tid;
-}
-
 /*
  * Allocate and initialise a new log ticket.
  */

fs/xfs/xfs_log.h

@@ -189,8 +189,6 @@ void	  xlog_iodone(struct xfs_buf *);
 struct xlog_ticket *xfs_log_ticket_get(struct xlog_ticket *ticket);
 void	  xfs_log_ticket_put(struct xlog_ticket *ticket);
 
-xlog_tid_t xfs_log_get_trans_ident(struct xfs_trans *tp);
-
 void	xfs_log_commit_cil(struct xfs_mount *mp, struct xfs_trans *tp,
 				struct xfs_log_vec *log_vector,
 				xfs_lsn_t *commit_lsn, int flags);

fs/xfs/xfs_log_priv.h

@@ -146,6 +146,8 @@ static inline uint xlog_get_client_id(__be32 i)
 					   shutdown */
 #define XLOG_TAIL_WARN		0x10	/* log tail verify warning issued */
 
+typedef __uint32_t xlog_tid_t;
+
 #ifdef __KERNEL__
 /*
  * Below are states for covering allocation transactions.

fs/xfs/xfs_types.h

@@ -73,8 +73,6 @@ typedef	__int32_t	xfs_tid_t;	/* transaction identifier */
 typedef	__uint32_t	xfs_dablk_t;	/* dir/attr block number (in file) */
 typedef	__uint32_t	xfs_dahash_t;	/* dir/attr hash value */
 
-typedef __uint32_t	xlog_tid_t;	/* transaction ID type */
-
 /*
  * These types are 64 bits on disk but are either 32 or 64 bits in memory.
  * Disk based types: