ext4: use percpu counter for extent cache count

Use a percpu counter rather than atomic types for shrinker accounting.
There's no need for ultimate accuracy in the shrinker, so this
should come a little more cheaply.  The percpu struct is somewhat
large, but there was a big gap before the cache-aligned
s_es_lru_lock anyway, and it fits nicely in there.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

fs/ext4/ext4.h

@@ -1268,7 +1268,6 @@ struct ext4_sb_info {
 	atomic_t s_mb_preallocated;
 	atomic_t s_mb_discarded;
 	atomic_t s_lock_busy;
-	atomic_t s_extent_cache_cnt;
 
 	/* locality groups */
 	struct ext4_locality_group __percpu *s_locality_groups;
@@ -1310,6 +1309,7 @@ struct ext4_sb_info {
 	/* Reclaim extents from extent status tree */
 	struct shrinker s_es_shrinker;
 	struct list_head s_es_lru;
+	struct percpu_counter s_extent_cache_cnt;
 	spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp;
 };
 

fs/ext4/extents_status.c

@@ -305,7 +305,7 @@ ext4_es_alloc_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len,
 	 */
 	if (!ext4_es_is_delayed(es)) {
 		EXT4_I(inode)->i_es_lru_nr++;
-		atomic_inc(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
+		percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
 	}
 
 	return es;
@@ -317,7 +317,7 @@ static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
 	if (!ext4_es_is_delayed(es)) {
 		BUG_ON(EXT4_I(inode)->i_es_lru_nr == 0);
 		EXT4_I(inode)->i_es_lru_nr--;
-		atomic_dec(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
+		percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
 	}
 
 	kmem_cache_free(ext4_es_cachep, es);
@@ -678,7 +678,7 @@ static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
 	int nr_to_scan = sc->nr_to_scan;
 	int ret, nr_shrunk = 0;
 
-	ret = atomic_read(&sbi->s_extent_cache_cnt);
+	ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
 	trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan, ret);
 
 	if (!nr_to_scan)
@@ -711,7 +711,7 @@ static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
 	list_splice_tail(&scanned, &sbi->s_es_lru);
 	spin_unlock(&sbi->s_es_lru_lock);
 
-	ret = atomic_read(&sbi->s_extent_cache_cnt);
+	ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
 	trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk, ret);
 	return ret;
 }

fs/ext4/super.c

@@ -783,6 +783,7 @@ static void ext4_put_super(struct super_block *sb)
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+	percpu_counter_destroy(&sbi->s_extent_cache_cnt);
 	brelse(sbi->s_sbh);
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < MAXQUOTAS; i++)
@@ -3688,6 +3689,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (!err) {
 		err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0);
 	}
+	if (!err) {
+		err = percpu_counter_init(&sbi->s_extent_cache_cnt, 0);
+	}
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "insufficient memory");
 		goto failed_mount3;
@@ -3993,6 +3997,7 @@ failed_mount3:
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+	percpu_counter_destroy(&sbi->s_extent_cache_cnt);
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
 failed_mount2: