ext4: limit number of scanned extents in status tree shrinker

Currently we scan extent status trees of inodes until we reclaim nr_to_scan
extents. This can however require a lot of scanning when there are lots
of delayed extents (as those cannot be reclaimed).

Change shrinker to work as shrinkers are supposed to and *scan* only
nr_to_scan extents regardless of how many extents did we actually
reclaim. We however need to be careful and avoid scanning each status
tree from the beginning - that could lead to a situation where we would
not be able to reclaim anything at all when first nr_to_scan extents in
the tree are always unreclaimable. We remember with each inode offset
where we stopped scanning and continue from there when we next come
across the inode.

Note that we also need to update places calling __es_shrink() manually
to pass reasonable nr_to_scan to have a chance of reclaiming anything and
not just 1.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fs/ext4/ext4.h

@@ -881,6 +881,9 @@ struct ext4_inode_info {
 	struct list_head i_es_list;
 	unsigned int i_es_all_nr;	/* protected by i_es_lock */
 	unsigned int i_es_shk_nr;	/* protected by i_es_lock */
+	ext4_lblk_t i_es_shrink_lblk;	/* Offset where we start searching for
+					   extents to shrink. Protected by
+					   i_es_lock  */
 
 	/* ialloc */
 	ext4_group_t	i_last_alloc_group;
@@ -1321,7 +1324,7 @@ struct ext4_sb_info {
 
 	/* Reclaim extents from extent status tree */
 	struct shrinker s_es_shrinker;
-	struct list_head s_es_list;
+	struct list_head s_es_list;	/* List of inodes with reclaimable extents */
 	long s_es_nr_inode;
 	struct ext4_es_stats s_es_stats;
 	struct mb_cache *s_mb_cache;

fs/ext4/extents_status.c

@@ -147,8 +147,7 @@ static struct kmem_cache *ext4_es_cachep;
 static int __es_insert_extent(struct inode *inode, struct extent_status *newes);
 static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 			      ext4_lblk_t end);
-static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
-				       int nr_to_scan);
+static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan);
 static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
 		       struct ext4_inode_info *locked_ei);
 
@@ -716,7 +715,7 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 retry:
 	err = __es_insert_extent(inode, &newes);
 	if (err == -ENOMEM && __es_shrink(EXT4_SB(inode->i_sb),
-					  1, EXT4_I(inode)))
+					  128, EXT4_I(inode)))
 		goto retry;
 	if (err == -ENOMEM && !ext4_es_is_delayed(&newes))
 		err = 0;
@@ -874,7 +873,7 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 				es->es_len = orig_es.es_len;
 				if ((err == -ENOMEM) &&
 				    __es_shrink(EXT4_SB(inode->i_sb),
-							1, EXT4_I(inode)))
+							128, EXT4_I(inode)))
 					goto retry;
 				goto out;
 			}
@@ -976,8 +975,6 @@ static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
 	spin_lock(&sbi->s_es_lock);
 	nr_to_walk = sbi->s_es_nr_inode;
 	while (nr_to_walk-- > 0) {
-		int shrunk;
-
 		if (list_empty(&sbi->s_es_list)) {
 			spin_unlock(&sbi->s_es_lock);
 			goto out;
@@ -985,7 +982,7 @@ static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
 		ei = list_first_entry(&sbi->s_es_list, struct ext4_inode_info,
 				      i_es_list);
 		/* Move the inode to the tail */
-		list_move(&ei->i_es_list, sbi->s_es_list.prev);
+		list_move_tail(&ei->i_es_list, &sbi->s_es_list);
 
 		/*
 		 * Normally we try hard to avoid shrinking precached inodes,
@@ -1007,13 +1004,10 @@ static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
 		 */
 		spin_unlock(&sbi->s_es_lock);
 
-		shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan);
+		nr_shrunk += es_reclaim_extents(ei, &nr_to_scan);
 		write_unlock(&ei->i_es_lock);
 
-		nr_shrunk += shrunk;
-		nr_to_scan -= shrunk;
-
-		if (nr_to_scan == 0)
+		if (nr_to_scan <= 0)
 			goto out;
 		spin_lock(&sbi->s_es_lock);
 	}
@@ -1029,7 +1023,7 @@ static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
 	}
 
 	if (locked_ei && nr_shrunk == 0)
-		nr_shrunk = __es_try_to_reclaim_extents(locked_ei, nr_to_scan);
+		nr_shrunk = es_reclaim_extents(locked_ei, &nr_to_scan);
 
 out:
 	scan_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
@@ -1224,27 +1218,33 @@ void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi)
 	unregister_shrinker(&sbi->s_es_shrinker);
 }
 
-static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
-				       int nr_to_scan)
+/*
+ * Shrink extents in given inode from ei->i_es_shrink_lblk till end. Scan at
+ * most *nr_to_scan extents, update *nr_to_scan accordingly.
+ *
+ * Return 0 if we hit end of tree / interval, 1 if we exhausted nr_to_scan.
+ * Increment *nr_shrunk by the number of reclaimed extents. Also update
+ * ei->i_es_shrink_lblk to where we should continue scanning.
+ */
+static int es_do_reclaim_extents(struct ext4_inode_info *ei, ext4_lblk_t end,
+				 int *nr_to_scan, int *nr_shrunk)
 {
 	struct inode *inode = &ei->vfs_inode;
 	struct ext4_es_tree *tree = &ei->i_es_tree;
-	struct rb_node *node;
 	struct extent_status *es;
-	unsigned long nr_shrunk = 0;
-	static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
-				      DEFAULT_RATELIMIT_BURST);
+	struct rb_node *node;
 
-	if (ei->i_es_shk_nr == 0)
+	es = __es_tree_search(&tree->root, ei->i_es_shrink_lblk);
+	if (!es)
+		goto out_wrap;
+	node = &es->rb_node;
+	while (*nr_to_scan > 0) {
+		if (es->es_lblk > end) {
+			ei->i_es_shrink_lblk = end + 1;
 			return 0;
+		}
 
-	if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED) &&
-	    __ratelimit(&_rs))
-		ext4_warning(inode->i_sb, "forced shrink of precached extents");
-
-	node = rb_first(&tree->root);
-	while (node != NULL) {
-		es = rb_entry(node, struct extent_status, rb_node);
+		(*nr_to_scan)--;
 		node = rb_next(&es->rb_node);
 		/*
 		 * We can't reclaim delayed extent from status tree because
@@ -1253,11 +1253,38 @@ static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
 		if (!ext4_es_is_delayed(es)) {
 			rb_erase(&es->rb_node, &tree->root);
 			ext4_es_free_extent(inode, es);
-			nr_shrunk++;
-			if (--nr_to_scan == 0)
-				break;
+			(*nr_shrunk)++;
 		}
+		if (!node)
+			goto out_wrap;
+		es = rb_entry(node, struct extent_status, rb_node);
 	}
-	tree->cache_es = NULL;
+	ei->i_es_shrink_lblk = es->es_lblk;
+	return 1;
+out_wrap:
+	ei->i_es_shrink_lblk = 0;
+	return 0;
+}
+
+static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan)
+{
+	struct inode *inode = &ei->vfs_inode;
+	int nr_shrunk = 0;
+	ext4_lblk_t start = ei->i_es_shrink_lblk;
+	static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
+
+	if (ei->i_es_shk_nr == 0)
+		return 0;
+
+	if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED) &&
+	    __ratelimit(&_rs))
+		ext4_warning(inode->i_sb, "forced shrink of precached extents");
+
+	if (!es_do_reclaim_extents(ei, EXT_MAX_BLOCKS, nr_to_scan, &nr_shrunk) &&
+	    start != 0)
+		es_do_reclaim_extents(ei, start - 1, nr_to_scan, &nr_shrunk);
+
+	ei->i_es_tree.cache_es = NULL;
 	return nr_shrunk;
 }

fs/ext4/super.c

@@ -874,6 +874,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	INIT_LIST_HEAD(&ei->i_es_list);
 	ei->i_es_all_nr = 0;
 	ei->i_es_shk_nr = 0;
+	ei->i_es_shrink_lblk = 0;
 	ei->i_reserved_data_blocks = 0;
 	ei->i_reserved_meta_blocks = 0;
 	ei->i_allocated_meta_blocks = 0;