summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
authorChris Down <chris@chrisdown.name>2019-05-31 22:30:22 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-06-01 15:51:31 -0700
commit9852ae3fe5293264f01c49f2571ef7688f7823ce (patch)
tree6e9847c13762ce77ab3eb1e7a604be7b9cf6c09a /include
parentbc81426f5beef7da863d3365bc9d45e820448745 (diff)
downloadlinux-9852ae3fe5293264f01c49f2571ef7688f7823ce.tar.bz2
mm, memcg: consider subtrees in memory.events
memory.stat and other files already consider subtrees in their output, and we should too in order to not present an inconsistent interface. The current situation is fairly confusing, because people interacting with cgroups expect hierarchical behaviour in the vein of memory.stat, cgroup.events, and other files. For example, this causes confusion when debugging reclaim events under low, as currently these always read "0" at non-leaf memcg nodes, which frequently causes people to misdiagnose breach behaviour. The same confusion applies to other counters in this file when debugging issues. Aggregation is done at write time instead of at read-time since these counters aren't hot (unlike memory.stat which is per-page, so it does it at read time), and it makes sense to bundle this with the file notifications. After this patch, events are propagated up the hierarchy: [root@ktst ~]# cat /sys/fs/cgroup/system.slice/memory.events low 0 high 0 max 0 oom 0 oom_kill 0 [root@ktst ~]# systemd-run -p MemoryMax=1 true Running as unit: run-r251162a189fb4562b9dabfdc9b0422f5.service [root@ktst ~]# cat /sys/fs/cgroup/system.slice/memory.events low 0 high 0 max 7 oom 1 oom_kill 1 As this is a change in behaviour, this can be reverted to the old behaviour by mounting with the `memory_localevents' flag set. However, we use the new behaviour by default as there's a lack of evidence that there are any current users of memory.events that would find this change undesirable. akpm: this is a behaviour change, so Cc:stable. THis is so that forthcoming distros which use cgroup v2 are more likely to pick up the revised behaviour. Link: http://lkml.kernel.org/r/20190208224419.GA24772@chrisdown.name Signed-off-by: Chris Down <chris@chrisdown.name> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Shakeel Butt <shakeelb@google.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: Roman Gushchin <guro@fb.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include')
-rw-r--r--include/linux/cgroup-defs.h5
-rw-r--r--include/linux/memcontrol.h10
2 files changed, 13 insertions, 2 deletions
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 77258d276f93..11e215d7937e 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -89,6 +89,11 @@ enum {
* Enable cpuset controller in v1 cgroup to use v2 behavior.
*/
CGRP_ROOT_CPUSET_V2_MODE = (1 << 4),
+
+ /*
+ * Enable legacy local memory.events.
+ */
+ CGRP_ROOT_MEMORY_LOCAL_EVENTS = (1 << 5),
};
/* cftype->flags */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 73fe0a700911..edf9e8f32d70 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -737,8 +737,14 @@ static inline void count_memcg_event_mm(struct mm_struct *mm,
static inline void memcg_memory_event(struct mem_cgroup *memcg,
enum memcg_memory_event event)
{
- atomic_long_inc(&memcg->memory_events[event]);
- cgroup_file_notify(&memcg->events_file);
+ do {
+ atomic_long_inc(&memcg->memory_events[event]);
+ cgroup_file_notify(&memcg->events_file);
+
+ if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS)
+ break;
+ } while ((memcg = parent_mem_cgroup(memcg)) &&
+ !mem_cgroup_is_root(memcg));
}
static inline void memcg_memory_event_mm(struct mm_struct *mm,