mm, memcg: introduce memory.events.local

The memory controller in cgroup v2 exposes memory.events file for each
memcg which shows the number of times events like low, high, max, oom
and oom_kill have happened for the whole tree rooted at that memcg.
Users can also poll or register notification to monitor the changes in
that file.  Any event at any level of the tree rooted at memcg will
notify all the listeners along the path till root_mem_cgroup.  There are
existing users which depend on this behavior.

However there are users which are only interested in the events
happening at a specific level of the memcg tree and not in the events in
the underlying tree rooted at that memcg.  One such use-case is a
centralized resource monitor which can dynamically adjust the limits of
the jobs running on a system.  The jobs can create their sub-hierarchy
for their own sub-tasks.  The centralized monitor is only interested in
the events at the top level memcgs of the jobs as it can then act and
adjust the limits of the jobs.  Using the current memory.events for such
centralized monitor is very inconvenient.  The monitor will keep
receiving events which it is not interested and to find if the received
event is interesting, it has to read memory.event files of the next
level and compare it with the top level one.  So, let's introduce
memory.events.local to the memcg which shows and notify for the events
at the memcg level.

Now, does memory.stat and memory.pressure need their local versions.  IMHO
no due to the no internal process contraint of the cgroup v2.  The
memory.stat file of the top level memcg of a job shows the stats and
vmevents of the whole tree.  The local stats or vmevents of the top level
memcg will only change if there is a process running in that memcg but v2
does not allow that.  Similarly for memory.pressure there will not be any
process in the internal nodes and thus no chance of local pressure.

Link: http://lkml.kernel.org/r/20190527174643.209172-1-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Chris Down <chris@chrisdown.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index a5c845338d6d70f5c0eec37b8572cd11bd0d0a9c..a9548de56ac997c1e41f0a484b9da60fa24bab5c 100644 (file)
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1146,6 +1146,11 @@ PAGE_SIZE multiple when read back.
        otherwise, a value change in this file generates a file
        modified event.
 
+       Note that all fields in this file are hierarchical and the
+       file modified event can be generated due to an event down the
+       hierarchy. For for the local events at the cgroup level see
+       memory.events.local.
+
          low
                The number of times the cgroup is reclaimed due to
                high memory pressure even though its usage is under
@@ -1185,6 +1190,11 @@ PAGE_SIZE multiple when read back.
                The number of processes belonging to this cgroup
                killed by any kind of OOM killer.
 
+  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
+       generated on this file reflects only the local events.
+
   memory.stat
        A read-only flat-keyed file which exists on non-root cgroups.
 

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1dcb763bb610a85295893645fe285f2659532f1a..22141ebc5e1541e2f17d3d825e6add6814b12c9c 100644 (file)
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -233,8 +233,9 @@ struct mem_cgroup {
        /* OOM-Killer disable */
        int             oom_kill_disable;
 
-       /* memory.events */
+       /* memory.events and memory.events.local */
        struct cgroup_file events_file;
+       struct cgroup_file events_local_file;
 
        /* handle for "memory.swap.events" */
        struct cgroup_file swap_events_file;
@@ -281,6 +282,7 @@ struct mem_cgroup {
 
        /* memory.events */
        atomic_long_t           memory_events[MEMCG_NR_MEMORY_EVENTS];
+       atomic_long_t           memory_events_local[MEMCG_NR_MEMORY_EVENTS];
 
        unsigned long           socket_pressure;
 
@@ -747,6 +749,9 @@ 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_local[event]);
+       cgroup_file_notify(&memcg->events_local_file);
+
        do {
                atomic_long_inc(&memcg->memory_events[event]);
                cgroup_file_notify(&memcg->events_file);

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 2ad94d0ce22fb0e303498f1293d269fa2f33b521..0a9bd604aa155d4736aa9782d41b7d77890142c9 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5624,21 +5624,29 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
        return nbytes;
 }
 
+static void __memory_events_show(struct seq_file *m, atomic_long_t *events)
+{
+       seq_printf(m, "low %lu\n", atomic_long_read(&events[MEMCG_LOW]));
+       seq_printf(m, "high %lu\n", atomic_long_read(&events[MEMCG_HIGH]));
+       seq_printf(m, "max %lu\n", atomic_long_read(&events[MEMCG_MAX]));
+       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]));
+}
+
 static int memory_events_show(struct seq_file *m, void *v)
 {
        struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
-       seq_printf(m, "low %lu\n",
-                  atomic_long_read(&memcg->memory_events[MEMCG_LOW]));
-       seq_printf(m, "high %lu\n",
-                  atomic_long_read(&memcg->memory_events[MEMCG_HIGH]));
-       seq_printf(m, "max %lu\n",
-                  atomic_long_read(&memcg->memory_events[MEMCG_MAX]));
-       seq_printf(m, "oom %lu\n",
-                  atomic_long_read(&memcg->memory_events[MEMCG_OOM]));
-       seq_printf(m, "oom_kill %lu\n",
-                  atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL]));
+       __memory_events_show(m, memcg->memory_events);
+       return 0;
+}
+
+static int memory_events_local_show(struct seq_file *m, void *v)
+{
+       struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
+       __memory_events_show(m, memcg->memory_events_local);
        return 0;
 }
 
@@ -5800,6 +5808,12 @@ static struct cftype memory_files[] = {
                .file_offset = offsetof(struct mem_cgroup, events_file),
                .seq_show = memory_events_show,
        },
+       {
+               .name = "events.local",
+               .flags = CFTYPE_NOT_ON_ROOT,
+               .file_offset = offsetof(struct mem_cgroup, events_local_file),
+               .seq_show = memory_events_local_show,
+       },
        {
                .name = "stat",
                .flags = CFTYPE_NOT_ON_ROOT,