From: Dan Schatzberg <schatzberg.dan@xxxxxxxxx> Subject: mm/memcg: add oom_group_kill memory event Our container agent wants to know when a container exits if it was OOM killed or not to report to the user. We use memory.oom.group = 1 to ensure that OOM kills within the container's cgroup kill everything. Existing memory.events are insufficient for knowing if this triggered: 1) Our current approach reads memory.events oom_kill and reports the container was killed if the value is non-zero. This is erroneous in some cases where containers create their children cgroups with memory.oom.group=1 as such OOM kills will get counted against the container cgroup's oom_kill counter despite not actually OOM killing the entire container. 2) Reading memory.events.local will fail to identify OOM kills in leaf cgroups (that don't set memory.oom.group) within the container cgroup. This patch adds a new oom_group_kill event when memory.oom.group triggers to allow userspace to cleanly identify when an entire cgroup is oom killed. [schatzberg.dan@xxxxxxxxx: changes from Johannes and Chris] Link: https://lkml.kernel.org/r/20211213162511.2492267-1-schatzberg.dan@xxxxxxxxx Link: https://lkml.kernel.org/r/20211203162426.3375036-1-schatzberg.dan@xxxxxxxxx Signed-off-by: Dan Schatzberg <schatzberg.dan@xxxxxxxxx> Reviewed-by: Roman Gushchin <guro@xxxxxx> Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx> Acked-by: Chris Down <chris@xxxxxxxxxxxxxx> Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx> Acked-by: Michal Hocko <mhocko@xxxxxxxx> Cc: Tejun Heo <tj@xxxxxxxxxx> Cc: Zefan Li <lizefan.x@xxxxxxxxxxxxx> Cc: Jonathan Corbet <corbet@xxxxxxx> Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx> Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx> Cc: Muchun Song <songmuchun@xxxxxxxxxxxxx> Cc: Alex Shi <alexs@xxxxxxxxxx> Cc: Wei Yang <richard.weiyang@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- Documentation/admin-guide/cgroup-v2.rst | 3 +++ include/linux/memcontrol.h | 1 + mm/memcontrol.c | 2 ++ mm/oom_kill.c | 1 + 4 files changed, 7 insertions(+) --- a/Documentation/admin-guide/cgroup-v2.rst~mm-add-group_oom_kill-memory-event +++ a/Documentation/admin-guide/cgroup-v2.rst @@ -1268,6 +1268,9 @@ PAGE_SIZE multiple when read back. The number of processes belonging to this cgroup killed by any kind of OOM killer. + oom_group_kill + The number of times a group OOM has occurred. + memory.events.local Similar to memory.events but the fields in the file are local to the cgroup i.e. not hierarchical. The file modified event --- a/include/linux/memcontrol.h~mm-add-group_oom_kill-memory-event +++ a/include/linux/memcontrol.h @@ -42,6 +42,7 @@ enum memcg_memory_event { MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, + MEMCG_OOM_GROUP_KILL, MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, --- a/mm/memcontrol.c~mm-add-group_oom_kill-memory-event +++ a/mm/memcontrol.c @@ -6318,6 +6318,8 @@ static void __memory_events_show(struct seq_printf(m, "oom %lu\n", atomic_long_read(&events[MEMCG_OOM])); seq_printf(m, "oom_kill %lu\n", atomic_long_read(&events[MEMCG_OOM_KILL])); + seq_printf(m, "oom_group_kill %lu\n", + atomic_long_read(&events[MEMCG_OOM_GROUP_KILL])); } static int memory_events_show(struct seq_file *m, void *v) --- a/mm/oom_kill.c~mm-add-group_oom_kill-memory-event +++ a/mm/oom_kill.c @@ -994,6 +994,7 @@ static void oom_kill_process(struct oom_ * If necessary, kill all tasks in the selected memory cgroup. */ if (oom_group) { + memcg_memory_event(oom_group, MEMCG_OOM_GROUP_KILL); mem_cgroup_print_oom_group(oom_group); mem_cgroup_scan_tasks(oom_group, oom_kill_memcg_member, (void *)message); _
