memcg: fix numa scan information update to be triggered by memory event

commit 889976dbcb12 ("memcg: reclaim memory from nodes in round-robin
order") adds an numa node round-robin for memcg.  But the information is
updated once per 10sec.

This patch changes the update trigger from jiffies to memcg's event count.
 After this patch, numa scan information will be updated when we see 1024
events of pagein/pageout under a memcg.

[akpm@linux-foundation.org: attempt to repair code layout]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 27 insertions, 6 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a7a5cb1bf2c7..e013b8e57d25 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -108,10 +108,12 @@ enum mem_cgroup_events_index {
 enum mem_cgroup_events_target {
 	MEM_CGROUP_TARGET_THRESH,
 	MEM_CGROUP_TARGET_SOFTLIMIT,
+	MEM_CGROUP_TARGET_NUMAINFO,
 	MEM_CGROUP_NTARGETS,
 };
 #define THRESHOLDS_EVENTS_TARGET (128)
 #define SOFTLIMIT_EVENTS_TARGET (1024)
+#define NUMAINFO_EVENTS_TARGET	(1024)
 
 struct mem_cgroup_stat_cpu {
 	long count[MEM_CGROUP_STAT_NSTATS];
@@ -237,7 +239,8 @@ struct mem_cgroup {
 	int last_scanned_node;
 #if MAX_NUMNODES > 1
 	nodemask_t	scan_nodes;
-	unsigned long   next_scan_node_update;
+	atomic_t	numainfo_events;
+	atomic_t	numainfo_updating;
 #endif
 	/*
 	 * Should the accounting and control be hierarchical, per subtree?
@@ -680,6 +683,9 @@ static void __mem_cgroup_target_update(struct mem_cgroup *mem, int target)
 	case MEM_CGROUP_TARGET_SOFTLIMIT:
 		next = val + SOFTLIMIT_EVENTS_TARGET;
 		break;
+	case MEM_CGROUP_TARGET_NUMAINFO:
+		next = val + NUMAINFO_EVENTS_TARGET;
+		break;
 	default:
 		return;
 	}
@@ -698,11 +704,19 @@ static void memcg_check_events(struct mem_cgroup *mem, struct page *page)
 		mem_cgroup_threshold(mem);
 		__mem_cgroup_target_update(mem, MEM_CGROUP_TARGET_THRESH);
 		if (unlikely(__memcg_event_check(mem,
-			MEM_CGROUP_TARGET_SOFTLIMIT))){
+			     MEM_CGROUP_TARGET_SOFTLIMIT))) {
 			mem_cgroup_update_tree(mem, page);
 			__mem_cgroup_target_update(mem,
-				MEM_CGROUP_TARGET_SOFTLIMIT);
+						   MEM_CGROUP_TARGET_SOFTLIMIT);
+		}
+#if MAX_NUMNODES > 1
+		if (unlikely(__memcg_event_check(mem,
+			MEM_CGROUP_TARGET_NUMAINFO))) {
+			atomic_inc(&mem->numainfo_events);
+			__mem_cgroup_target_update(mem,
+				MEM_CGROUP_TARGET_NUMAINFO);
 		}
+#endif
 	}
 }
 
@@ -1582,11 +1596,15 @@ static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *mem,
 static void mem_cgroup_may_update_nodemask(struct mem_cgroup *mem)
 {
 	int nid;
-
-	if (time_after(mem->next_scan_node_update, jiffies))
+	/*
+	 * numainfo_events > 0 means there was at least NUMAINFO_EVENTS_TARGET
+	 * pagein/pageout changes since the last update.
+	 */
+	if (!atomic_read(&mem->numainfo_events))
+		return;
+	if (atomic_inc_return(&mem->numainfo_updating) > 1)
 		return;
 
-	mem->next_scan_node_update = jiffies + 10*HZ;
 	/* make a nodemask where this memcg uses memory from */
 	mem->scan_nodes = node_states[N_HIGH_MEMORY];
 
@@ -1595,6 +1613,9 @@ static void mem_cgroup_may_update_nodemask(struct mem_cgroup *mem)
 		if (!test_mem_cgroup_node_reclaimable(mem, nid, false))
 			node_clear(nid, mem->scan_nodes);
 	}
+
+	atomic_set(&mem->numainfo_events, 0);
+	atomic_set(&mem->numainfo_updating, 0);
 }
 
 /*