path: root/mm
diff options
authorKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>2009-04-02 16:57:38 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2009-04-02 19:04:55 -0700
commit0b7f569e45bb6be142d87017030669a6a7d327a1 (patch)
tree8df7877b95c093ebf4cb4e1006cea16f75fc79b7 /mm
parentmemcg: fix shrinking memory to return -EBUSY by fixing retry algorithm (diff)
memcg: fix OOM killer under memcg
This patch tries to fix OOM Killer problems caused by hierarchy. Now, memcg itself has OOM KILL function (in oom_kill.c) and tries to kill a task in memcg. But, when hierarchy is used, it's broken and correct task cannot be killed. For example, in following cgroup /groupA/ hierarchy=1, limit=1G, 01 nolimit 02 nolimit All tasks' memory usage under /groupA, /groupA/01, groupA/02 is limited to groupA's 1Gbytes but OOM Killer just kills tasks in groupA. This patch provides makes the bad process be selected from all tasks under hierarchy. BTW, currently, oom_jiffies is updated against groupA in above case. oom_jiffies of tree should be updated. To see how oom_jiffies is used, please check mem_cgroup_oom_called() callers. [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: const fix] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Paul Menage <menage@google.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
1 files changed, 28 insertions, 2 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6f6a575e77ad..025f8abfae2d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -295,6 +295,9 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
struct mem_cgroup *mem = NULL;
+ if (!mm)
+ return NULL;
* Because we have no locks, mm->owner's may be being moved to other
* cgroup. We use css_tryget() here even if this looks
@@ -486,10 +489,20 @@ void mem_cgroup_move_lists(struct page *page,
int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
int ret;
+ struct mem_cgroup *curr = NULL;
- ret = task->mm && mm_match_cgroup(task->mm, mem);
+ rcu_read_lock();
+ curr = try_get_mem_cgroup_from_mm(task->mm);
+ rcu_read_unlock();
+ if (!curr)
+ return 0;
+ if (curr->use_hierarchy)
+ ret = css_is_ancestor(&curr->css, &mem->css);
+ else
+ ret = (curr == mem);
+ css_put(&curr->css);
return ret;
@@ -820,6 +833,19 @@ bool mem_cgroup_oom_called(struct task_struct *task)
return ret;
+static int record_last_oom_cb(struct mem_cgroup *mem, void *data)
+ mem->last_oom_jiffies = jiffies;
+ return 0;
+static void record_last_oom(struct mem_cgroup *mem)
+ mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb);
* Unlike exported interface, "oom" parameter is added. if oom==true,
* oom-killer can be invoked.
@@ -902,7 +928,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
mem_cgroup_out_of_memory(mem_over_limit, gfp_mask);
- mem_over_limit->last_oom_jiffies = jiffies;
+ record_last_oom(mem_over_limit);
goto nomem;