[PATCH] memcg, vmscan: count how many times low limit has been breached

[Michal Hocko]

The counter is displayed in memory.stat file.

Signed-off-by: Michal Hocko <mhocko@xxxxxxx>
---
 Documentation/cgroups/memory.txt | 6 +++++-
 include/linux/memcontrol.h       | 5 +++++
 mm/memcontrol.c                  | 7 +++++++
 mm/vmscan.c                      | 8 ++++++--
 4 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 7f3a7414bdf2..ad0f31402d84 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -58,6 +58,9 @@ Brief summary of control files.
 				 (See 5.5 for details)
  memory.limit_in_bytes		 # set/show limit of memory usage
  memory.low_limit_in_bytes	 # set/show low limit for memory reclaim
+ memory.low_limit_breached	 # number of times low_limit has been
+				 # ignored and the cgroup reclaimed even
+				 # when it was above the limit
  memory.memsw.limit_in_bytes	 # set/show limit of memory+Swap usage
  memory.failcnt			 # show the number of memory usage hits limits
  memory.memsw.failcnt		 # show the number of memory+Swap hits limits
@@ -251,7 +254,8 @@ doesn't include groups (and their subgroups - see 6. Hierarchy support)
 which are below the low limit if there is other eligible cgroup in the
 reclaimed hierarchy. If all groups which participate reclaim are under
 their low limits then all of them are reclaimed and the low limit is
-ignored.
+ignored. low_limit_breached counter in memory.stat file can be checked
+to see how many times such an event occurred.
 
 Note2: When panic_on_oom is set to "2", the whole system will panic.
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 077a777bd9ff..5e2ca2163b12 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -94,6 +94,8 @@ bool task_in_mem_cgroup(struct task_struct *task,
 
 extern bool mem_cgroup_within_guarantee(struct mem_cgroup *memcg,
 		struct mem_cgroup *root);
+
+extern void mem_cgroup_guarantee_breached(struct mem_cgroup *memcg);
 extern bool mem_cgroup_all_within_guarantee(struct mem_cgroup *root);
 
 extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
@@ -297,6 +299,9 @@ static inline bool mem_cgroup_within_guarantee(struct mem_cgroup *memcg,
 {
 	return false;
 }
+static inline  void mem_cgroup_guarantee_breached(struct mem_cgroup *memcg)
+{
+}
 static inline bool mem_cgroup_all_within_guarantee(struct mem_cgroup *root)
 {
 	return false;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4fd4784d1548..4af05d5f59bc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -102,6 +102,7 @@ enum mem_cgroup_events_index {
 	MEM_CGROUP_EVENTS_PGPGOUT,	/* # of pages paged out */
 	MEM_CGROUP_EVENTS_PGFAULT,	/* # of page-faults */
 	MEM_CGROUP_EVENTS_PGMAJFAULT,	/* # of major page-faults */
+	MEM_CGROUP_EVENTS_LOW_LIMIT_FALLBACK, /* # of times low limit was breached */
 	MEM_CGROUP_EVENTS_NSTATS,
 };
 
@@ -110,6 +111,7 @@ static const char * const mem_cgroup_events_names[] = {
 	"pgpgout",
 	"pgfault",
 	"pgmajfault",
+	"low_limit_breached",
 };
 
 static const char * const mem_cgroup_lru_names[] = {
@@ -2833,6 +2835,11 @@ bool mem_cgroup_within_guarantee(struct mem_cgroup *memcg,
 	return false;
 }
 
+void mem_cgroup_guarantee_breached(struct mem_cgroup *memcg)
+{
+	this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_LOW_LIMIT_FALLBACK]);
+}
+
 bool mem_cgroup_all_within_guarantee(struct mem_cgroup *root)
 {
 	struct mem_cgroup *iter;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2686e47f04cc..8041b0667673 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2245,10 +2245,11 @@ static unsigned __shrink_zone(struct zone *zone, struct scan_control *sc,
 		memcg = mem_cgroup_iter(root, NULL, &reclaim);
 		do {
 			struct lruvec *lruvec;
+			bool within_guarantee;
 
 			/* Memcg might be protected from the reclaim */
-			if (honor_memcg_guarantee &&
-					mem_cgroup_within_guarantee(memcg, root)) {
+			within_guarantee = mem_cgroup_within_guarantee(memcg, root);
+			if (honor_memcg_guarantee && within_guarantee) {
 				/*
 				 * It would be more optimal to skip the memcg
 				 * subtree now but we do not have a memcg iter
@@ -2258,6 +2259,9 @@ static unsigned __shrink_zone(struct zone *zone, struct scan_control *sc,
 				continue;
 			}
 
+			if (within_guarantee)
+				mem_cgroup_guarantee_breached(memcg);
+
 			lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 			nr_scanned_groups++;
 
-- 
2.0.0.rc4

-- 
Michal Hocko
SUSE Labs
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/