From b6bf9abb0aa44e53ffe9c1e6e1d32568f5b25e4a Mon Sep 17 00:00:00 2001 From: Dan Schatzberg Date: Fri, 14 Jan 2022 14:05:35 -0800 Subject: [PATCH] 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@gmail.com: changes from Johannes and Chris] Link: https://lkml.kernel.org/r/20211213162511.2492267-1-schatzberg.dan@gmail.com Link: https://lkml.kernel.org/r/20211203162426.3375036-1-schatzberg.dan@gmail.com Signed-off-by: Dan Schatzberg Reviewed-by: Roman Gushchin Acked-by: Johannes Weiner Acked-by: Chris Down Reviewed-by: Shakeel Butt Acked-by: Michal Hocko Cc: Tejun Heo Cc: Zefan Li Cc: Jonathan Corbet Cc: Vladimir Davydov Cc: Matthew Wilcox (Oracle) Cc: Muchun Song Cc: Alex Shi Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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(+) diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 2aeb7ae8b393..8269bfa240f4 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/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 diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0c5c403f4be6..951f24f42147 100644 --- a/include/linux/memcontrol.h +++ b/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, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bfe9bdec192b..2d39d58baccf 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6318,6 +6318,8 @@ static void __memory_events_show(struct seq_file *m, atomic_long_t *events) 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) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 1ddabefcfb5a..e52ce0b1465d 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -994,6 +994,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) * 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); -- 2.11.0