lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20210121230621.654304-8-shy828301@gmail.com>
Date:   Thu, 21 Jan 2021 15:06:17 -0800
From:   Yang Shi <shy828301@...il.com>
To:     guro@...com, ktkhai@...tuozzo.com, shakeelb@...gle.com,
        david@...morbit.com, hannes@...xchg.org, mhocko@...e.com,
        akpm@...ux-foundation.org
Cc:     shy828301@...il.com, linux-mm@...ck.org,
        linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [v4 PATCH 07/11] mm: vmscan: add per memcg shrinker nr_deferred

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 ration 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.

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.

Signed-off-by: Yang Shi <shy828301@...il.com>
---
 include/linux/memcontrol.h |  7 +++---
 mm/vmscan.c                | 49 +++++++++++++++++++++++++-------------
 2 files changed, 36 insertions(+), 20 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 62b888b88a5f..e0384367e07d 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -93,12 +93,13 @@ struct 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[];
+	unsigned long *map;
+	atomic_long_t *nr_deferred;
 };
 
 /*
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 018e1beb24c9..722aa71b13b2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -192,11 +192,13 @@ static void free_shrinker_info_rcu(struct rcu_head *head)
 	kvfree(container_of(head, struct shrinker_info, rcu));
 }
 
-static int expand_one_shrinker_info(struct mem_cgroup *memcg,
-				   int size, int old_size)
+static int expand_one_shrinker_info(struct mem_cgroup *memcg, int nr_max,
+				    int m_size, int d_size,
+				    int old_m_size, int old_d_size)
 {
 	struct shrinker_info *new, *old;
 	int nid;
+	int size = m_size + d_size;
 
 	for_each_node(nid) {
 		old = rcu_dereference_protected(
@@ -209,9 +211,16 @@ 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->map = (unsigned long *)(new + 1);
+		new->nr_deferred = (atomic_long_t *)(new->map +
+					nr_max / BITS_PER_LONG + 1);
+
+		/* map: set all old bits, clear all new bits */
+		memset(new->map, (int)0xff, old_m_size);
+		memset((void *)new->map + old_m_size, 0, m_size - old_m_size);
+		/* nr_deferred: copy old values, clear all new values */
+		memcpy(new->nr_deferred, old->nr_deferred, old_d_size);
+		memset((void *)new->nr_deferred + old_d_size, 0, d_size - old_d_size);
 
 		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, new);
 		call_rcu(&old->rcu, free_shrinker_info_rcu);
@@ -226,9 +235,6 @@ 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 = rcu_dereference_protected(pn->shrinker_info, true);
@@ -242,12 +248,13 @@ 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 m_size, d_size = 0;
 
 	down_write(&shrinker_rwsem);
-	size = (shrinker_nr_max / BITS_PER_LONG + 1) * sizeof(unsigned long);
+	m_size = (shrinker_nr_max / BITS_PER_LONG + 1) * sizeof(unsigned long);
+	d_size = shrinker_nr_max * sizeof(atomic_long_t);
+	size = m_size + d_size;
+
 	for_each_node(nid) {
 		info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid);
 		if (!info) {
@@ -255,6 +262,9 @@ int alloc_shrinker_info(struct mem_cgroup *memcg)
 			ret = -ENOMEM;
 			break;
 		}
+		info->map = (unsigned long *)(info + 1);
+		info->nr_deferred = (atomic_long_t *)(info->map +
+					shrinker_nr_max / BITS_PER_LONG + 1);
 		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info);
 	}
 	up_write(&shrinker_rwsem);
@@ -266,10 +276,16 @@ static int expand_shrinker_info(int new_id)
 {
 	int size, old_size, ret = 0;
 	int new_nr_max = new_id + 1;
+	int m_size, d_size = 0;
+	int old_m_size, old_d_size = 0;
 	struct mem_cgroup *memcg;
 
-	size = (new_nr_max / BITS_PER_LONG + 1) * sizeof(unsigned long);
-	old_size = (shrinker_nr_max / BITS_PER_LONG + 1) * sizeof(unsigned long);
+	m_size = (new_nr_max / BITS_PER_LONG + 1) * sizeof(unsigned long);
+	d_size = new_nr_max * sizeof(atomic_long_t);
+	size = m_size + d_size;
+	old_m_size = (shrinker_nr_max / BITS_PER_LONG + 1) * sizeof(unsigned long);
+	old_d_size = shrinker_nr_max * sizeof(atomic_long_t);
+	old_size = old_m_size + old_d_size;
 	if (size <= old_size)
 		return 0;
 
@@ -278,9 +294,8 @@ static int expand_shrinker_info(int new_id)
 
 	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, new_nr_max, m_size, d_size,
+					       old_m_size, old_d_size);
 		if (ret) {
 			mem_cgroup_iter_break(NULL, memcg);
 			goto out;
-- 
2.26.2

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ