[PATCH 10/10] mm: Clear shrinker bit if there are no objects related to memcg

[Kirill Tkhai <ktkhai@virtuozzo.com>]

To avoid further unneed calls of do_shrink_slab()
for shrinkers, which already do not have any charged
objects in a memcg, their bits have to be cleared.

This patch introduces new return value SHRINK_EMPTY,
which will be used in case of there is no charged
objects in shrinker. We can't use 0 instead of that,
as a shrinker may return 0, when it has very small
amount of objects.

To prevent race with parallel list lru add, we call
do_shrink_slab() once again, after the bit is cleared.
So, if there is a new object, we never miss it, and
the bit will be restored again.

The below test shows significant performance growths
after using the patchset:

$echo 1 > /sys/fs/cgroup/memory/memory.use_hierarchy
$mkdir /sys/fs/cgroup/memory/ct
$echo 4000M > /sys/fs/cgroup/memory/ct/memory.kmem.limit_in_bytes
$for i in `seq 0 4000`; do mkdir /sys/fs/cgroup/memory/ct/$i; echo $$ > /sys/fs/cgroup/memory/ct/$i/cgroup.procs; mkdir -p s/$i; mount -t tmpfs $i s/$i; touch s/$i/file; done

Then 4 drop_caches:
$time echo 3 > /proc/sys/vm/drop_caches

Times of drop_caches:

*Before (4 iterations)*
0.00user 6.80system 0:06.82elapsed 99%CPU
0.00user 4.61system 0:04.62elapsed 99%CPU
0.00user 4.61system 0:04.61elapsed 99%CPU
0.00user 4.61system 0:04.61elapsed 99%CPU

*After (4 iterations)*
0.00user 0.93system 0:00.94elapsed 99%CPU
0.00user 0.00system 0:00.01elapsed 80%CPU
0.00user 0.00system 0:00.01elapsed 80%CPU
0.00user 0.00system 0:00.01elapsed 81%CPU

4.61s/0.01s = 461 times faster.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
---
 fs/super.c               |    3 +++
 include/linux/shrinker.h |    1 +
 mm/vmscan.c              |   21 ++++++++++++++++++---
 mm/workingset.c          |    3 +++
 4 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/fs/super.c b/fs/super.c
index 1f3dc4eab409..788ea4e6a40b 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -133,6 +133,9 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 	total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc);
 	total_objects += list_lru_shrink_count(&sb->s_inode_lru, sc);
 
+	if (!total_objects)
+		return SHRINK_EMPTY;
+
 	total_objects = vfs_pressure_ratio(total_objects);
 	return total_objects;
 }
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 24aeed1bc332..b23180deb928 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -34,6 +34,7 @@ struct shrink_control {
 };
 
 #define SHRINK_STOP (~0UL)
+#define SHRINK_EMPTY (~0UL - 1)
 /*
  * A callback you can register to apply pressure to ageable caches.
  *
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e1fd16bc7a9b..1fc05e8bde04 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -387,6 +387,7 @@ void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int nr)
 {
 	struct shrinkers_map *map = SHRINKERS_MAP(memcg);
 
+	smp_mb__before_atomic(); /* Pairs with mb in shrink_slab() */
 	set_bit(nr, map->map[nid]);
 }
 #else /* CONFIG_MEMCG && !CONFIG_SLOB */
@@ -568,8 +569,8 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	long scanned = 0, next_deferred;
 
 	freeable = shrinker->count_objects(shrinker, shrinkctl);
-	if (freeable == 0)
-		return 0;
+	if (freeable == 0 || freeable == SHRINK_EMPTY)
+		return freeable;
 
 	/*
 	 * copy the current shrinker scan count into a local variable
@@ -708,6 +709,7 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 	if (!memcg_kmem_enabled() || memcg) {
 		struct shrinkers_map *map;
+		unsigned long ret;
 		int i;
 
 		map = rcu_dereference_protected(SHRINKERS_MAP(memcg), true);
@@ -724,7 +726,20 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 					clear_bit(i, map->map[nid]);
 					continue;
 				}
-				freed += do_shrink_slab(&sc, shrinker, priority);
+				if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
+					sc.nid = 0;
+				ret = do_shrink_slab(&sc, shrinker, priority);
+				if (ret == SHRINK_EMPTY) {
+					clear_bit(i, map->map[nid]);
+					/* pairs with mb in set_shrinker_bit() */
+					smp_mb__after_atomic();
+					ret = do_shrink_slab(&sc, shrinker, priority);
+					if (ret == SHRINK_EMPTY)
+						ret = 0;
+					else
+						set_bit(i, map->map[nid]);
+				}
+				freed += ret;
 
 				if (rwsem_is_contended(&shrinker_rwsem)) {
 					freed = freed ? : 1;
diff --git a/mm/workingset.c b/mm/workingset.c
index 62c9eb000c4f..dc05574f0a07 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -402,6 +402,9 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 	}
 	max_nodes = cache >> (RADIX_TREE_MAP_SHIFT - 3);
 
+	if (!nodes)
+		return SHRINK_EMPTY;
+
 	if (nodes <= max_nodes)
 		return 0;
 	return nodes - max_nodes;