memcg: replace ss->id_lock with a rwlock
While back-porting Johannes Weiner's patch "mm: memcg-aware global
reclaim" for an internal effort, we noticed a significant performance
regression during page-reclaim heavy workloads due to high contention of
the ss->id_lock. This lock protects idr map, and serializes calls to
idr_get_next() in css_get_next() (which is used during the memcg hierarchy
walk).
Since idr_get_next() is just doing a look up, we need only serialize it
with respect to idr_remove()/idr_get_new(). By making the ss->id_lock a
rwlock, contention is greatly reduced and performance improves.
Tested: cat a 256m file from a ramdisk in a 128m container 50 times on
each core (one file + container per core) in parallel on a NUMA machine.
Result is the time for the test to complete in 1 of the containers.
Both kernels included Johannes' memcg-aware global reclaim patches.
Before rwlock patch: 1710.778s
After rwlock patch: 152.227s
Signed-off-by: Andrew Bresticker <abrestic@google.com>
Cc: Paul Menage <menage@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Ying Han <yinghan@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index da7e4bc..1b7f9d5 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -516,7 +516,7 @@
struct list_head sibling;
/* used when use_id == true */
struct idr idr;
- spinlock_t id_lock;
+ rwlock_t id_lock;
/* should be defined only by modular subsystems */
struct module *module;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8386b21..d9d5648 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4883,9 +4883,9 @@
rcu_assign_pointer(id->css, NULL);
rcu_assign_pointer(css->id, NULL);
- spin_lock(&ss->id_lock);
+ write_lock(&ss->id_lock);
idr_remove(&ss->idr, id->id);
- spin_unlock(&ss->id_lock);
+ write_unlock(&ss->id_lock);
kfree_rcu(id, rcu_head);
}
EXPORT_SYMBOL_GPL(free_css_id);
@@ -4911,10 +4911,10 @@
error = -ENOMEM;
goto err_out;
}
- spin_lock(&ss->id_lock);
+ write_lock(&ss->id_lock);
/* Don't use 0. allocates an ID of 1-65535 */
error = idr_get_new_above(&ss->idr, newid, 1, &myid);
- spin_unlock(&ss->id_lock);
+ write_unlock(&ss->id_lock);
/* Returns error when there are no free spaces for new ID.*/
if (error) {
@@ -4929,9 +4929,9 @@
return newid;
remove_idr:
error = -ENOSPC;
- spin_lock(&ss->id_lock);
+ write_lock(&ss->id_lock);
idr_remove(&ss->idr, myid);
- spin_unlock(&ss->id_lock);
+ write_unlock(&ss->id_lock);
err_out:
kfree(newid);
return ERR_PTR(error);
@@ -4943,7 +4943,7 @@
{
struct css_id *newid;
- spin_lock_init(&ss->id_lock);
+ rwlock_init(&ss->id_lock);
idr_init(&ss->idr);
newid = get_new_cssid(ss, 0);
@@ -5038,9 +5038,9 @@
* scan next entry from bitmap(tree), tmpid is updated after
* idr_get_next().
*/
- spin_lock(&ss->id_lock);
+ read_lock(&ss->id_lock);
tmp = idr_get_next(&ss->idr, &tmpid);
- spin_unlock(&ss->id_lock);
+ read_unlock(&ss->id_lock);
if (!tmp)
break;