xfs: cache unlinked pointers in an rhashtable

Use a rhashtable to cache the unlinked list incore.  This should speed
up unlinked processing considerably when there are a lot of inodes on
the unlinked list because iunlink_remove no longer has to traverse an
entire bucket list to find which inode points to the one being removed.

The incore list structure records "X.next_unlinked = Y" relations, with
the rhashtable using Y to index the records.  This makes finding the
inode X that points to a inode Y very quick.  If our cache fails to find
anything we can always fall back on the old method.

FWIW this drastically reduces the amount of time it takes to remove
inodes from the unlinked list.  I wrote a program to open a lot of
O_TMPFILE files and then close them in the same order, which takes
a very long time if we have to traverse the unlinked lists.  With the
ptach, I see:

+ /d/t/tmpfile/tmpfile
Opened 193531 files in 6.33s.
Closed 193531 files in 5.86s

real    0m12.192s
user    0m0.064s
sys     0m11.619s
+ cd /
+ umount /mnt

real    0m0.050s
user    0m0.004s
sys     0m0.030s

And without the patch:

+ /d/t/tmpfile/tmpfile
Opened 193588 files in 6.35s.
Closed 193588 files in 751.61s

real    12m38.853s
user    0m0.084s
sys     12m34.470s
+ cd /
+ umount /mnt

real    0m0.086s
user    0m0.000s
sys     0m0.060s
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>

fs/xfs/libxfs/xfs_errortag.h

@@ -54,7 +54,8 @@
 #define XFS_ERRTAG_BUF_LRU_REF				31
 #define XFS_ERRTAG_FORCE_SCRUB_REPAIR			32
 #define XFS_ERRTAG_FORCE_SUMMARY_RECALC			33
-#define XFS_ERRTAG_MAX					34
+#define XFS_ERRTAG_IUNLINK_FALLBACK			34
+#define XFS_ERRTAG_MAX					35
 
 /*
  * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -93,5 +94,6 @@
 #define XFS_RANDOM_BUF_LRU_REF				2
 #define XFS_RANDOM_FORCE_SCRUB_REPAIR			1
 #define XFS_RANDOM_FORCE_SUMMARY_RECALC			1
+#define XFS_RANDOM_IUNLINK_FALLBACK			(XFS_RANDOM_DEFAULT/10)
 
 #endif /* __XFS_ERRORTAG_H_ */

fs/xfs/xfs_error.c

@@ -51,6 +51,7 @@ static unsigned int xfs_errortag_random_default[] = {
 	XFS_RANDOM_BUF_LRU_REF,
 	XFS_RANDOM_FORCE_SCRUB_REPAIR,
 	XFS_RANDOM_FORCE_SUMMARY_RECALC,
+	XFS_RANDOM_IUNLINK_FALLBACK,
 };
 
 struct xfs_errortag_attr {
@@ -159,6 +160,7 @@ XFS_ERRORTAG_ATTR_RW(log_item_pin,	XFS_ERRTAG_LOG_ITEM_PIN);
 XFS_ERRORTAG_ATTR_RW(buf_lru_ref,	XFS_ERRTAG_BUF_LRU_REF);
 XFS_ERRORTAG_ATTR_RW(force_repair,	XFS_ERRTAG_FORCE_SCRUB_REPAIR);
 XFS_ERRORTAG_ATTR_RW(bad_summary,	XFS_ERRTAG_FORCE_SUMMARY_RECALC);
+XFS_ERRORTAG_ATTR_RW(iunlink_fallback,	XFS_ERRTAG_IUNLINK_FALLBACK);
 
 static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(noerror),
@@ -195,6 +197,7 @@ static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(buf_lru_ref),
 	XFS_ERRORTAG_ATTR_LIST(force_repair),
 	XFS_ERRORTAG_ATTR_LIST(bad_summary),
+	XFS_ERRORTAG_ATTR_LIST(iunlink_fallback),
 	NULL,
 };
 

fs/xfs/xfs_inode.h

@@ -500,4 +500,7 @@ extern struct kmem_zone	*xfs_inode_zone;
 
 bool xfs_inode_verify_forks(struct xfs_inode *ip);
 
+int xfs_iunlink_init(struct xfs_perag *pag);
+void xfs_iunlink_destroy(struct xfs_perag *pag);
+
 #endif	/* __XFS_INODE_H__ */

fs/xfs/xfs_mount.c

@@ -149,6 +149,7 @@ xfs_free_perag(
 		spin_unlock(&mp->m_perag_lock);
 		ASSERT(pag);
 		ASSERT(atomic_read(&pag->pag_ref) == 0);
+		xfs_iunlink_destroy(pag);
 		xfs_buf_hash_destroy(pag);
 		mutex_destroy(&pag->pag_ici_reclaim_lock);
 		call_rcu(&pag->rcu_head, __xfs_free_perag);
@@ -227,6 +228,9 @@ xfs_initialize_perag(
 		/* first new pag is fully initialized */
 		if (first_initialised == NULLAGNUMBER)
 			first_initialised = index;
+		error = xfs_iunlink_init(pag);
+		if (error)
+			goto out_hash_destroy;
 	}
 
 	index = xfs_set_inode_alloc(mp, agcount);
@@ -249,6 +253,7 @@ xfs_initialize_perag(
 		if (!pag)
 			break;
 		xfs_buf_hash_destroy(pag);
+		xfs_iunlink_destroy(pag);
 		mutex_destroy(&pag->pag_ici_reclaim_lock);
 		kmem_free(pag);
 	}

fs/xfs/xfs_mount.h

@@ -396,6 +396,13 @@ typedef struct xfs_perag {
 
 	/* reference count */
 	uint8_t			pagf_refcount_level;
+
+	/*
+	 * Unlinked inode information.  This incore information reflects
+	 * data stored in the AGI, so callers must hold the AGI buffer lock
+	 * or have some other means to control concurrency.
+	 */
+	struct rhashtable	pagi_unlinked_hash;
 } xfs_perag_t;
 
 static inline struct xfs_ag_resv *

fs/xfs/xfs_trace.h

@@ -3447,6 +3447,7 @@ DEFINE_EVENT(xfs_ag_inode_class, name, \
 	TP_ARGS(ip))
 DEFINE_AGINODE_EVENT(xfs_iunlink);
 DEFINE_AGINODE_EVENT(xfs_iunlink_remove);
+DEFINE_AG_EVENT(xfs_iunlink_map_prev_fallback);
 
 #endif /* _TRACE_XFS_H */