Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Yang Shi <shy828301@gmail.com>
To:     guro@fb.com, ktkhai@virtuozzo.com, vbabka@suse.cz,
        shakeelb@google.com, david@fromorbit.com, hannes@cmpxchg.org,
        mhocko@suse.com, akpm@linux-foundation.org
Cc:     shy828301@gmail.com, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [v9 PATCH 09/13] mm: vmscan: add per memcg shrinker nr_deferred
Date:   Wed, 10 Mar 2021 09:45:59 -0800
Message-Id: <20210310174603.5093-10-shy828301@gmail.com>
In-Reply-To: <20210310174603.5093-1-shy828301@gmail.com>
References: <20210310174603.5093-1-shy828301@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Currently the number of deferred objects are per shrinker, but some slabs, for
example, vfs inode/dentry cache are per memcg, this would result in poor
isolation among memcgs.

The deferred objects typically are generated by __GFP_NOFS allocations, one
memcg with excessive __GFP_NOFS allocations may blow up deferred objects, then
other innocent memcgs may suffer from over shrink, excessive reclaim latency,
etc.

For example, two workloads run in memcgA and memcgB respectively, workload in
B is vfs heavy workload.  Workload in A generates excessive deferred objects,
then B's vfs cache might be hit heavily (drop half of caches) by B's limit
reclaim or global reclaim.

We observed this hit in our production environment which was running vfs heavy
workload shown as the below tracing log:

<...>-409454 [016] .... 28286961.747146: mm_shrink_slab_start: super_cache_scan+0x0/0x1a0 ffff9a83046f3458:
nid: 1 objects to shrink 3641681686040 gfp_flags GFP_HIGHUSER_MOVABLE|__GFP_ZERO pgs_scanned 1 lru_pgs 15721
cache items 246404277 delta 31345 total_scan 123202138
<...>-409454 [022] .... 28287105.928018: mm_shrink_slab_end: super_cache_scan+0x0/0x1a0 ffff9a83046f3458:
nid: 1 unused scan count 3641681686040 new scan count 3641798379189 total_scan 602
last shrinker return val 123186855

The vfs cache and page cache ratio was 10:1 on this machine, and half of caches
were dropped.  This also resulted in significant amount of page caches were
dropped due to inodes eviction.

Make nr_deferred per memcg for memcg aware shrinkers would solve the unfairness
and bring better isolation.

The following patch will add nr_deferred to parent memcg when memcg offline.
To preserve nr_deferred when reparenting memcgs to root, root memcg needs
shrinker_info allocated too.

When memcg is not enabled (!CONFIG_MEMCG or memcg disabled), the shrinker's
nr_deferred would be used.  And non memcg aware shrinkers use shrinker's
nr_deferred all the time.

Acked-by: Roman Gushchin <guro@fb.com>
Acked-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Yang Shi <shy828301@gmail.com>
---
 include/linux/memcontrol.h |  7 +++--
 mm/vmscan.c                | 60 ++++++++++++++++++++++++++------------
 2 files changed, 46 insertions(+), 21 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 308a202f1de2..42a4facb5b7c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -97,12 +97,13 @@ struct batched_lruvec_stat {
 };
 
 /*
- * Bitmap of shrinker::id corresponding to memcg-aware shrinkers,
- * which have elements charged to this memcg.
+ * Bitmap and deferred work of shrinker::id corresponding to memcg-aware
+ * shrinkers, which have elements charged to this memcg.
  */
 struct shrinker_info {
 	struct rcu_head rcu;
-	unsigned long map[];
+	atomic_long_t *nr_deferred;
+	unsigned long *map;
 };
 
 /*
diff --git a/mm/vmscan.c b/mm/vmscan.c
index d0876970601e..ae82afe6cec6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -187,11 +187,17 @@ static DECLARE_RWSEM(shrinker_rwsem);
 #ifdef CONFIG_MEMCG
 static int shrinker_nr_max;
 
+/* The shrinker_info is expanded in a batch of BITS_PER_LONG */
 static inline int shrinker_map_size(int nr_items)
 {
 	return (DIV_ROUND_UP(nr_items, BITS_PER_LONG) * sizeof(unsigned long));
 }
 
+static inline int shrinker_defer_size(int nr_items)
+{
+	return (round_up(nr_items, BITS_PER_LONG) * sizeof(atomic_long_t));
+}
+
 static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg,
 						     int nid)
 {
@@ -200,10 +206,12 @@ static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg,
 }
 
 static int expand_one_shrinker_info(struct mem_cgroup *memcg,
-				    int size, int old_size)
+				    int map_size, int defer_size,
+				    int old_map_size, int old_defer_size)
 {
 	struct shrinker_info *new, *old;
 	int nid;
+	int size = map_size + defer_size;
 
 	for_each_node(nid) {
 		old = shrinker_info_protected(memcg, nid);
@@ -215,9 +223,16 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg,
 		if (!new)
 			return -ENOMEM;
 
-		/* Set all old bits, clear all new bits */
-		memset(new->map, (int)0xff, old_size);
-		memset((void *)new->map + old_size, 0, size - old_size);
+		new->nr_deferred = (atomic_long_t *)(new + 1);
+		new->map = (void *)new->nr_deferred + defer_size;
+
+		/* map: set all old bits, clear all new bits */
+		memset(new->map, (int)0xff, old_map_size);
+		memset((void *)new->map + old_map_size, 0, map_size - old_map_size);
+		/* nr_deferred: copy old values, clear all new values */
+		memcpy(new->nr_deferred, old->nr_deferred, old_defer_size);
+		memset((void *)new->nr_deferred + old_defer_size, 0,
+		       defer_size - old_defer_size);
 
 		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, new);
 		kvfree_rcu(old, rcu);
@@ -232,9 +247,6 @@ void free_shrinker_info(struct mem_cgroup *memcg)
 	struct shrinker_info *info;
 	int nid;
 
-	if (mem_cgroup_is_root(memcg))
-		return;
-
 	for_each_node(nid) {
 		pn = mem_cgroup_nodeinfo(memcg, nid);
 		info = shrinker_info_protected(memcg, nid);
@@ -247,12 +259,12 @@ int alloc_shrinker_info(struct mem_cgroup *memcg)
 {
 	struct shrinker_info *info;
 	int nid, size, ret = 0;
-
-	if (mem_cgroup_is_root(memcg))
-		return 0;
+	int map_size, defer_size = 0;
 
 	down_write(&shrinker_rwsem);
-	size = shrinker_map_size(shrinker_nr_max);
+	map_size = shrinker_map_size(shrinker_nr_max);
+	defer_size = shrinker_defer_size(shrinker_nr_max);
+	size = map_size + defer_size;
 	for_each_node(nid) {
 		info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid);
 		if (!info) {
@@ -260,6 +272,8 @@ int alloc_shrinker_info(struct mem_cgroup *memcg)
 			ret = -ENOMEM;
 			break;
 		}
+		info->nr_deferred = (atomic_long_t *)(info + 1);
+		info->map = (void *)info->nr_deferred + defer_size;
 		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info);
 	}
 	up_write(&shrinker_rwsem);
@@ -267,15 +281,21 @@ int alloc_shrinker_info(struct mem_cgroup *memcg)
 	return ret;
 }
 
+static inline bool need_expand(int nr_max)
+{
+	return round_up(nr_max, BITS_PER_LONG) >
+	       round_up(shrinker_nr_max, BITS_PER_LONG);
+}
+
 static int expand_shrinker_info(int new_id)
 {
-	int size, old_size, ret = 0;
+	int ret = 0;
 	int new_nr_max = new_id + 1;
+	int map_size, defer_size = 0;
+	int old_map_size, old_defer_size = 0;
 	struct mem_cgroup *memcg;
 
-	size = shrinker_map_size(new_nr_max);
-	old_size = shrinker_map_size(shrinker_nr_max);
-	if (size <= old_size)
+	if (!need_expand(new_nr_max))
 		goto out;
 
 	if (!root_mem_cgroup)
@@ -283,11 +303,15 @@ static int expand_shrinker_info(int new_id)
 
 	lockdep_assert_held(&shrinker_rwsem);
 
+	map_size = shrinker_map_size(new_nr_max);
+	defer_size = shrinker_defer_size(new_nr_max);
+	old_map_size = shrinker_map_size(shrinker_nr_max);
+	old_defer_size = shrinker_defer_size(shrinker_nr_max);
+
 	memcg = mem_cgroup_iter(NULL, NULL, NULL);
 	do {
-		if (mem_cgroup_is_root(memcg))
-			continue;
-		ret = expand_one_shrinker_info(memcg, size, old_size);
+		ret = expand_one_shrinker_info(memcg, map_size, defer_size,
+					       old_map_size, old_defer_size);
 		if (ret) {
 			mem_cgroup_iter_break(NULL, memcg);
 			goto out;
-- 
2.26.2