summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2017-02-22 15:41:08 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-02-22 16:41:27 -0800
commit290b6a58b78be709e734d7fbeb1aa0416d9d41bc (patch)
treecbddb86cb214bc93f6f2c338d284d789a3910172
parentaf3b5f8764a270165195d8b9520d913a268c0062 (diff)
Revert "slub: move synchronize_sched out of slab_mutex on shrink"
Patch series "slab: make memcg slab destruction scalable", v3. With kmem cgroup support enabled, kmem_caches can be created and destroyed frequently and a great number of near empty kmem_caches can accumulate if there are a lot of transient cgroups and the system is not under memory pressure. When memory reclaim starts under such conditions, it can lead to consecutive deactivation and destruction of many kmem_caches, easily hundreds of thousands on moderately large systems, exposing scalability issues in the current slab management code. I've seen machines which end up with hundred thousands of caches and many millions of kernfs_nodes. The current code is O(N^2) on the total number of caches and has synchronous rcu_barrier() and synchronize_sched() in cgroup offline / release path which is executed while holding cgroup_mutex. Combined, this leads to very expensive and slow cache destruction operations which can easily keep running for half a day. This also messes up /proc/slabinfo along with other cache iterating operations. seq_file operates on 4k chunks and on each 4k boundary tries to seek to the last position in the list. With a huge number of caches on the list, this becomes very slow and very prone to the list content changing underneath it leading to a lot of missing and/or duplicate entries. This patchset addresses the scalability problem. * Add root and per-memcg lists. Update each user to use the appropriate list. * Make rcu_barrier() for SLAB_DESTROY_BY_RCU caches globally batched and asynchronous. * For dying empty slub caches, remove the sysfs files after deactivation so that we don't end up with millions of sysfs files without any useful information on them. This patchset contains the following nine patches. 0001-Revert-slub-move-synchronize_sched-out-of-slab_mutex.patch 0002-slub-separate-out-sysfs_slab_release-from-sysfs_slab.patch 0003-slab-remove-synchronous-rcu_barrier-call-in-memcg-ca.patch 0004-slab-reorganize-memcg_cache_params.patch 0005-slab-link-memcg-kmem_caches-on-their-associated-memo.patch 0006-slab-implement-slab_root_caches-list.patch 0007-slab-introduce-__kmemcg_cache_deactivate.patch 0008-slab-remove-synchronous-synchronize_sched-from-memcg.patch 0009-slab-remove-slub-sysfs-interface-files-early-for-emp.patch 0010-slab-use-memcg_kmem_cache_wq-for-slab-destruction-op.patch 0001 reverts an existing optimization to prepare for the following changes. 0002 is a prep patch. 0003 makes rcu_barrier() in release path batched and asynchronous. 0004-0006 separate out the lists. 0007-0008 replace synchronize_sched() in slub destruction path with call_rcu_sched(). 0009 removes sysfs files early for empty dying caches. 0010 makes destruction work items use a workqueue with limited concurrency. This patch (of 10): Revert 89e364db71fb5e ("slub: move synchronize_sched out of slab_mutex on shrink"). With kmem cgroup support enabled, kmem_caches can be created and destroyed frequently and a great number of near empty kmem_caches can accumulate if there are a lot of transient cgroups and the system is not under memory pressure. When memory reclaim starts under such conditions, it can lead to consecutive deactivation and destruction of many kmem_caches, easily hundreds of thousands on moderately large systems, exposing scalability issues in the current slab management code. This is one of the patches to address the issue. Moving synchronize_sched() out of slab_mutex isn't enough as it's still inside cgroup_mutex. The whole deactivation / release path will be updated to avoid all synchronous RCU operations. Revert this insufficient optimization in preparation to ease future changes. Link: http://lkml.kernel.org/r/20170117235411.9408-2-tj@kernel.org Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Jay Vana <jsvana@fb.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--mm/slab.c4
-rw-r--r--mm/slab.h2
-rw-r--r--mm/slab_common.c27
-rw-r--r--mm/slob.c2
-rw-r--r--mm/slub.c19
5 files changed, 23 insertions, 31 deletions
diff --git a/mm/slab.c b/mm/slab.c
index be977ef6e718..8a0e3392f181 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2315,7 +2315,7 @@ out:
return nr_freed;
}
-int __kmem_cache_shrink(struct kmem_cache *cachep)
+int __kmem_cache_shrink(struct kmem_cache *cachep, bool deactivate)
{
int ret = 0;
int node;
@@ -2335,7 +2335,7 @@ int __kmem_cache_shrink(struct kmem_cache *cachep)
int __kmem_cache_shutdown(struct kmem_cache *cachep)
{
- return __kmem_cache_shrink(cachep);
+ return __kmem_cache_shrink(cachep, false);
}
void __kmem_cache_release(struct kmem_cache *cachep)
diff --git a/mm/slab.h b/mm/slab.h
index 2fa824335a50..d07563f37f33 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -167,7 +167,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size,
int __kmem_cache_shutdown(struct kmem_cache *);
void __kmem_cache_release(struct kmem_cache *);
-int __kmem_cache_shrink(struct kmem_cache *);
+int __kmem_cache_shrink(struct kmem_cache *, bool);
void slab_kmem_cache_release(struct kmem_cache *);
struct seq_file;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index f266b0de1e92..4a999d749d2b 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -582,29 +582,6 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
get_online_cpus();
get_online_mems();
-#ifdef CONFIG_SLUB
- /*
- * In case of SLUB, we need to disable empty slab caching to
- * avoid pinning the offline memory cgroup by freeable kmem
- * pages charged to it. SLAB doesn't need this, as it
- * periodically purges unused slabs.
- */
- mutex_lock(&slab_mutex);
- list_for_each_entry(s, &slab_caches, list) {
- c = is_root_cache(s) ? cache_from_memcg_idx(s, idx) : NULL;
- if (c) {
- c->cpu_partial = 0;
- c->min_partial = 0;
- }
- }
- mutex_unlock(&slab_mutex);
- /*
- * kmem_cache->cpu_partial is checked locklessly (see
- * put_cpu_partial()). Make sure the change is visible.
- */
- synchronize_sched();
-#endif
-
mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list) {
if (!is_root_cache(s))
@@ -616,7 +593,7 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
if (!c)
continue;
- __kmem_cache_shrink(c);
+ __kmem_cache_shrink(c, true);
arr->entries[idx] = NULL;
}
mutex_unlock(&slab_mutex);
@@ -787,7 +764,7 @@ int kmem_cache_shrink(struct kmem_cache *cachep)
get_online_cpus();
get_online_mems();
kasan_cache_shrink(cachep);
- ret = __kmem_cache_shrink(cachep);
+ ret = __kmem_cache_shrink(cachep, false);
put_online_mems();
put_online_cpus();
return ret;
diff --git a/mm/slob.c b/mm/slob.c
index eac04d4357ec..5ec158054ffe 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -634,7 +634,7 @@ void __kmem_cache_release(struct kmem_cache *c)
{
}
-int __kmem_cache_shrink(struct kmem_cache *d)
+int __kmem_cache_shrink(struct kmem_cache *d, bool deactivate)
{
return 0;
}
diff --git a/mm/slub.c b/mm/slub.c
index 1e5ef312f146..6de08005d9cd 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3891,7 +3891,7 @@ EXPORT_SYMBOL(kfree);
* being allocated from last increasing the chance that the last objects
* are freed in them.
*/
-int __kmem_cache_shrink(struct kmem_cache *s)
+int __kmem_cache_shrink(struct kmem_cache *s, bool deactivate)
{
int node;
int i;
@@ -3903,6 +3903,21 @@ int __kmem_cache_shrink(struct kmem_cache *s)
unsigned long flags;
int ret = 0;
+ if (deactivate) {
+ /*
+ * Disable empty slabs caching. Used to avoid pinning offline
+ * memory cgroups by kmem pages that can be freed.
+ */
+ s->cpu_partial = 0;
+ s->min_partial = 0;
+
+ /*
+ * s->cpu_partial is checked locklessly (see put_cpu_partial),
+ * so we have to make sure the change is visible.
+ */
+ synchronize_sched();
+ }
+
flush_all(s);
for_each_kmem_cache_node(s, node, n) {
INIT_LIST_HEAD(&discard);
@@ -3959,7 +3974,7 @@ static int slab_mem_going_offline_callback(void *arg)
mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list)
- __kmem_cache_shrink(s);
+ __kmem_cache_shrink(s, false);
mutex_unlock(&slab_mutex);
return 0;