ext4: introduce aging to extent status tree

Introduce a simple aging to extent status tree. Each extent has a
REFERENCED bit which gets set when the extent is used. Shrinker then
skips entries with referenced bit set and clears the bit. Thus
frequently used extents have higher chances of staying in memory.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

2 files changed, 48 insertions, 9 deletions

diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 3059649..e04d457 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -382,7 +382,7 @@ static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
 static int ext4_es_can_be_merged(struct extent_status *es1,
 				 struct extent_status *es2)
 {
-	if (ext4_es_status(es1) != ext4_es_status(es2))
+	if (ext4_es_type(es1) != ext4_es_type(es2))
 		return 0;
 
 	if (((__u64) es1->es_len) + es2->es_len > EXT_MAX_BLOCKS) {
@@ -425,6 +425,8 @@ ext4_es_try_to_merge_left(struct inode *inode, struct extent_status *es)
 	es1 = rb_entry(node, struct extent_status, rb_node);
 	if (ext4_es_can_be_merged(es1, es)) {
 		es1->es_len += es->es_len;
+		if (ext4_es_is_referenced(es))
+			ext4_es_set_referenced(es1);
 		rb_erase(&es->rb_node, &tree->root);
 		ext4_es_free_extent(inode, es);
 		es = es1;
@@ -447,6 +449,8 @@ ext4_es_try_to_merge_right(struct inode *inode, struct extent_status *es)
 	es1 = rb_entry(node, struct extent_status, rb_node);
 	if (ext4_es_can_be_merged(es, es1)) {
 		es->es_len += es1->es_len;
+		if (ext4_es_is_referenced(es1))
+			ext4_es_set_referenced(es);
 		rb_erase(node, &tree->root);
 		ext4_es_free_extent(inode, es1);
 	}
@@ -813,6 +817,8 @@ out:
 		es->es_lblk = es1->es_lblk;
 		es->es_len = es1->es_len;
 		es->es_pblk = es1->es_pblk;
+		if (!ext4_es_is_referenced(es))
+			ext4_es_set_referenced(es);
 		stats->es_stats_cache_hits++;
 	} else {
 		stats->es_stats_cache_misses++;
@@ -1252,11 +1258,17 @@ static int es_do_reclaim_extents(struct ext4_inode_info *ei, ext4_lblk_t end,
 		 * We can't reclaim delayed extent from status tree because
 		 * fiemap, bigallic, and seek_data/hole need to use it.
 		 */
-		if (!ext4_es_is_delayed(es)) {
-			rb_erase(&es->rb_node, &tree->root);
-			ext4_es_free_extent(inode, es);
-			(*nr_shrunk)++;
+		if (ext4_es_is_delayed(es))
+			goto next;
+		if (ext4_es_is_referenced(es)) {
+			ext4_es_clear_referenced(es);
+			goto next;
 		}
+
+		rb_erase(&es->rb_node, &tree->root);
+		ext4_es_free_extent(inode, es);
+		(*nr_shrunk)++;
+next:
 		if (!node)
 			goto out_wrap;
 		es = rb_entry(node, struct extent_status, rb_node);
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index e86b1f3..691b526 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -34,6 +34,7 @@ enum {
 	ES_UNWRITTEN_B,
 	ES_DELAYED_B,
 	ES_HOLE_B,
+	ES_REFERENCED_B,
 	ES_FLAGS
 };
 
@@ -44,6 +45,12 @@ enum {
 #define EXTENT_STATUS_UNWRITTEN (1 << ES_UNWRITTEN_B)
 #define EXTENT_STATUS_DELAYED	(1 << ES_DELAYED_B)
 #define EXTENT_STATUS_HOLE	(1 << ES_HOLE_B)
+#define EXTENT_STATUS_REFERENCED	(1 << ES_REFERENCED_B)
+
+#define ES_TYPE_MASK	((ext4_fsblk_t)(EXTENT_STATUS_WRITTEN | \
+			  EXTENT_STATUS_UNWRITTEN | \
+			  EXTENT_STATUS_DELAYED | \
+			  EXTENT_STATUS_HOLE) << ES_SHIFT)
 
 struct ext4_sb_info;
 struct ext4_extent;
@@ -93,24 +100,44 @@ static inline unsigned int ext4_es_status(struct extent_status *es)
 	return es->es_pblk >> ES_SHIFT;
 }
 
+static inline unsigned int ext4_es_type(struct extent_status *es)
+{
+	return (es->es_pblk & ES_TYPE_MASK) >> ES_SHIFT;
+}
+
 static inline int ext4_es_is_written(struct extent_status *es)
 {
-	return (ext4_es_status(es) & EXTENT_STATUS_WRITTEN) != 0;
+	return (ext4_es_type(es) & EXTENT_STATUS_WRITTEN) != 0;
 }
 
 static inline int ext4_es_is_unwritten(struct extent_status *es)
 {
-	return (ext4_es_status(es) & EXTENT_STATUS_UNWRITTEN) != 0;
+	return (ext4_es_type(es) & EXTENT_STATUS_UNWRITTEN) != 0;
 }
 
 static inline int ext4_es_is_delayed(struct extent_status *es)
 {
-	return (ext4_es_status(es) & EXTENT_STATUS_DELAYED) != 0;
+	return (ext4_es_type(es) & EXTENT_STATUS_DELAYED) != 0;
 }
 
 static inline int ext4_es_is_hole(struct extent_status *es)
 {
-	return (ext4_es_status(es) & EXTENT_STATUS_HOLE) != 0;
+	return (ext4_es_type(es) & EXTENT_STATUS_HOLE) != 0;
+}
+
+static inline void ext4_es_set_referenced(struct extent_status *es)
+{
+	es->es_pblk |= ((ext4_fsblk_t)EXTENT_STATUS_REFERENCED) << ES_SHIFT;
+}
+
+static inline void ext4_es_clear_referenced(struct extent_status *es)
+{
+	es->es_pblk &= ~(((ext4_fsblk_t)EXTENT_STATUS_REFERENCED) << ES_SHIFT);
+}
+
+static inline int ext4_es_is_referenced(struct extent_status *es)
+{
+	return (ext4_es_status(es) & EXTENT_STATUS_REFERENCED) != 0;
 }
 
 static inline ext4_fsblk_t ext4_es_pblock(struct extent_status *es)