All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: vdavydov.dev@gmail.com, cl@linux.com, penberg@kernel.org,
	rientjes@google.com, iamjoonsoo.kim@lge.com,
	akpm@linux-foundation.org
Cc: jsvana@fb.com, hannes@cmpxchg.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, cgroups@vger.kernel.org, kernel-team@fb.com,
	Tejun Heo <tj@kernel.org>
Subject: [PATCH 10/10] slab: use memcg_kmem_cache_wq for slab destruction operations
Date: Tue, 17 Jan 2017 15:54:11 -0800	[thread overview]
Message-ID: <20170117235411.9408-11-tj@kernel.org> (raw)
In-Reply-To: <20170117235411.9408-1-tj@kernel.org>

If there's contention on slab_mutex, queueing the per-cache
destruction work item on the system_wq can unnecessarily create and
tie up a lot of kworkers.

Rename memcg_kmem_cache_create_wq to memcg_kmem_cache_wq and make it
global and use that workqueue for the destruction work items too.
While at it, convert the workqueue from an unbound workqueue to a
per-cpu one with concurrency limited to 1.  It's generally preferable
to use per-cpu workqueues and concurrency limit of 1 is safe enough.

This is suggested by Joonsoo Kim.

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>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/memcontrol.h |  1 +
 mm/memcontrol.c            | 16 ++++++++--------
 mm/slab_common.c           |  2 +-
 3 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 4de925c..67f3303 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -810,6 +810,7 @@ void memcg_kmem_uncharge(struct page *page, int order);
 
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 extern struct static_key_false memcg_kmem_enabled_key;
+extern struct workqueue_struct *memcg_kmem_cache_wq;
 
 extern int memcg_nr_cache_ids;
 void memcg_get_cache_ids(void);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a2b20f7f..8757403 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -317,6 +317,8 @@ void memcg_put_cache_ids(void)
 DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key);
 EXPORT_SYMBOL(memcg_kmem_enabled_key);
 
+struct workqueue_struct *memcg_kmem_cache_wq;
+
 #endif /* !CONFIG_SLOB */
 
 /**
@@ -2145,8 +2147,6 @@ struct memcg_kmem_cache_create_work {
 	struct work_struct work;
 };
 
-static struct workqueue_struct *memcg_kmem_cache_create_wq;
-
 static void memcg_kmem_cache_create_func(struct work_struct *w)
 {
 	struct memcg_kmem_cache_create_work *cw =
@@ -2178,7 +2178,7 @@ static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
 	cw->cachep = cachep;
 	INIT_WORK(&cw->work, memcg_kmem_cache_create_func);
 
-	queue_work(memcg_kmem_cache_create_wq, &cw->work);
+	queue_work(memcg_kmem_cache_wq, &cw->work);
 }
 
 static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
@@ -5780,12 +5780,12 @@ static int __init mem_cgroup_init(void)
 #ifndef CONFIG_SLOB
 	/*
 	 * Kmem cache creation is mostly done with the slab_mutex held,
-	 * so use a special workqueue to avoid stalling all worker
-	 * threads in case lots of cgroups are created simultaneously.
+	 * so use a workqueue with limited concurrency to avoid stalling
+	 * all worker threads in case lots of cgroups are created and
+	 * destroyed simultaneously.
 	 */
-	memcg_kmem_cache_create_wq =
-		alloc_ordered_workqueue("memcg_kmem_cache_create", 0);
-	BUG_ON(!memcg_kmem_cache_create_wq);
+	memcg_kmem_cache_wq = alloc_workqueue("memcg_kmem_cache", 0, 1);
+	BUG_ON(!memcg_kmem_cache_wq);
 #endif
 
 	cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL,
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 32610d1..5e6a98c 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -656,7 +656,7 @@ static void kmemcg_deactivate_rcufn(struct rcu_head *head)
 	 * initialized eariler.
 	 */
 	INIT_WORK(&s->memcg_params.deact_work, kmemcg_deactivate_workfn);
-	schedule_work(&s->memcg_params.deact_work);
+	queue_work(memcg_kmem_cache_wq, &s->memcg_params.deact_work);
 }
 
 /**
-- 
2.9.3

WARNING: multiple messages have this Message-ID (diff)
From: Tejun Heo <tj@kernel.org>
To: vdavydov.dev@gmail.com, cl@linux.com, penberg@kernel.org,
	rientjes@google.com, iamjoonsoo.kim@lge.com,
	akpm@linux-foundation.org
Cc: jsvana@fb.com, hannes@cmpxchg.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, cgroups@vger.kernel.org, kernel-team@fb.com,
	Tejun Heo <tj@kernel.org>
Subject: [PATCH 10/10] slab: use memcg_kmem_cache_wq for slab destruction operations
Date: Tue, 17 Jan 2017 15:54:11 -0800	[thread overview]
Message-ID: <20170117235411.9408-11-tj@kernel.org> (raw)
In-Reply-To: <20170117235411.9408-1-tj@kernel.org>

If there's contention on slab_mutex, queueing the per-cache
destruction work item on the system_wq can unnecessarily create and
tie up a lot of kworkers.

Rename memcg_kmem_cache_create_wq to memcg_kmem_cache_wq and make it
global and use that workqueue for the destruction work items too.
While at it, convert the workqueue from an unbound workqueue to a
per-cpu one with concurrency limited to 1.  It's generally preferable
to use per-cpu workqueues and concurrency limit of 1 is safe enough.

This is suggested by Joonsoo Kim.

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>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/memcontrol.h |  1 +
 mm/memcontrol.c            | 16 ++++++++--------
 mm/slab_common.c           |  2 +-
 3 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 4de925c..67f3303 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -810,6 +810,7 @@ void memcg_kmem_uncharge(struct page *page, int order);
 
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 extern struct static_key_false memcg_kmem_enabled_key;
+extern struct workqueue_struct *memcg_kmem_cache_wq;
 
 extern int memcg_nr_cache_ids;
 void memcg_get_cache_ids(void);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a2b20f7f..8757403 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -317,6 +317,8 @@ void memcg_put_cache_ids(void)
 DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key);
 EXPORT_SYMBOL(memcg_kmem_enabled_key);
 
+struct workqueue_struct *memcg_kmem_cache_wq;
+
 #endif /* !CONFIG_SLOB */
 
 /**
@@ -2145,8 +2147,6 @@ struct memcg_kmem_cache_create_work {
 	struct work_struct work;
 };
 
-static struct workqueue_struct *memcg_kmem_cache_create_wq;
-
 static void memcg_kmem_cache_create_func(struct work_struct *w)
 {
 	struct memcg_kmem_cache_create_work *cw =
@@ -2178,7 +2178,7 @@ static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
 	cw->cachep = cachep;
 	INIT_WORK(&cw->work, memcg_kmem_cache_create_func);
 
-	queue_work(memcg_kmem_cache_create_wq, &cw->work);
+	queue_work(memcg_kmem_cache_wq, &cw->work);
 }
 
 static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
@@ -5780,12 +5780,12 @@ static int __init mem_cgroup_init(void)
 #ifndef CONFIG_SLOB
 	/*
 	 * Kmem cache creation is mostly done with the slab_mutex held,
-	 * so use a special workqueue to avoid stalling all worker
-	 * threads in case lots of cgroups are created simultaneously.
+	 * so use a workqueue with limited concurrency to avoid stalling
+	 * all worker threads in case lots of cgroups are created and
+	 * destroyed simultaneously.
 	 */
-	memcg_kmem_cache_create_wq =
-		alloc_ordered_workqueue("memcg_kmem_cache_create", 0);
-	BUG_ON(!memcg_kmem_cache_create_wq);
+	memcg_kmem_cache_wq = alloc_workqueue("memcg_kmem_cache", 0, 1);
+	BUG_ON(!memcg_kmem_cache_wq);
 #endif
 
 	cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL,
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 32610d1..5e6a98c 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -656,7 +656,7 @@ static void kmemcg_deactivate_rcufn(struct rcu_head *head)
 	 * initialized eariler.
 	 */
 	INIT_WORK(&s->memcg_params.deact_work, kmemcg_deactivate_workfn);
-	schedule_work(&s->memcg_params.deact_work);
+	queue_work(memcg_kmem_cache_wq, &s->memcg_params.deact_work);
 }
 
 /**
-- 
2.9.3

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2017-01-17 23:57 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-01-17 23:54 [PATCHSET v3] slab: make memcg slab destruction scalable Tejun Heo
2017-01-17 23:54 ` Tejun Heo
2017-01-17 23:54 ` [PATCH 01/10] Revert "slub: move synchronize_sched out of slab_mutex on shrink" Tejun Heo
2017-01-17 23:54   ` Tejun Heo
2017-01-17 23:54 ` [PATCH 02/10] slub: separate out sysfs_slab_release() from sysfs_slab_remove() Tejun Heo
2017-01-17 23:54   ` Tejun Heo
2017-01-23 22:54   ` [PATCH v2 " Tejun Heo
2017-01-23 22:54     ` Tejun Heo
2017-01-23 22:54     ` Tejun Heo
2017-01-27 18:00     ` Vladimir Davydov
2017-01-27 18:00       ` Vladimir Davydov
2017-01-17 23:54 ` [PATCH 03/10] slab: remove synchronous rcu_barrier() call in memcg cache release path Tejun Heo
2017-01-17 23:54   ` Tejun Heo
2017-01-27 18:03   ` Vladimir Davydov
2017-01-27 18:03     ` Vladimir Davydov
2017-01-17 23:54 ` [PATCH 04/10] slab: reorganize memcg_cache_params Tejun Heo
2017-01-17 23:54   ` Tejun Heo
2017-01-17 23:54 ` [PATCH 05/10] slab: link memcg kmem_caches on their associated memory cgroup Tejun Heo
2017-01-17 23:54   ` Tejun Heo
2017-01-17 23:54 ` [PATCH 06/10] slab: implement slab_root_caches list Tejun Heo
2017-01-17 23:54   ` Tejun Heo
2017-01-27 18:06   ` Vladimir Davydov
2017-01-27 18:06     ` Vladimir Davydov
2017-01-17 23:54 ` [PATCH 07/10] slab: introduce __kmemcg_cache_deactivate() Tejun Heo
2017-01-17 23:54   ` Tejun Heo
2017-01-17 23:54 ` [PATCH 08/10] slab: remove synchronous synchronize_sched() from memcg cache deactivation path Tejun Heo
2017-01-17 23:54   ` Tejun Heo
2017-01-17 23:54 ` [PATCH 09/10] slab: remove slub sysfs interface files early for empty memcg caches Tejun Heo
2017-01-17 23:54   ` Tejun Heo
2017-01-17 23:54 ` Tejun Heo [this message]
2017-01-17 23:54   ` [PATCH 10/10] slab: use memcg_kmem_cache_wq for slab destruction operations Tejun Heo
2017-01-29 16:04   ` Vladimir Davydov
2017-01-29 16:04     ` Vladimir Davydov
2017-02-03 17:43 ` [PATCHSET v3] slab: make memcg slab destruction scalable Tejun Heo
2017-02-03 17:43   ` Tejun Heo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170117235411.9408-11-tj@kernel.org \
    --to=tj@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=cgroups@vger.kernel.org \
    --cc=cl@linux.com \
    --cc=hannes@cmpxchg.org \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=jsvana@fb.com \
    --cc=kernel-team@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=penberg@kernel.org \
    --cc=rientjes@google.com \
    --cc=vdavydov.dev@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.