[RFC][PATCH 1/7] memcg: check margin to limit for async reclaim

[KAMEZAWA Hiroyuki]

Now, the kernel supports transparent hugepage and it's used at each page fault
if configured. Then, if the THP allocation hits limit of memcg, it needs to
reclaim memory of HPAGE_SIZE. This tends to require much larger scan than
SWAP_CLUSTER_MAX and increases latency. In other allocations, page scanning
at hitting limit causes latency to some extent.

This patch adds a logic to keep usage margin to the limit in asynchronous way.
When the usage over some threshould (determined automatically), asynchronous
memory reclaim runs and shrink memory to limit - MEMCG_ASYNC_STOP_MARGIN.

By this, there will be no difference in total amount of usage of cpu to
scan the LRU but we'll have a chance to make use of wait time of applications
for freeing memory. For example, when an application read a file or socket,
to fill the newly alloated memory, it needs wait. Async reclaim can make use
of that time and give a chance to reduce latency by background works.

This patch only includes required hooks to trigger async reclaim. Core logics
will be in the following patches.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
---
 mm/memcontrol.c |   50 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 50 insertions(+)

Index: mmotm-May6/mm/memcontrol.c
===================================================================
--- mmotm-May6.orig/mm/memcontrol.c
+++ mmotm-May6/mm/memcontrol.c
@@ -115,10 +115,12 @@ enum mem_cgroup_events_index {
 enum mem_cgroup_events_target {
 	MEM_CGROUP_TARGET_THRESH,
 	MEM_CGROUP_TARGET_SOFTLIMIT,
+	MEM_CGROUP_TARGET_ASYNC,
 	MEM_CGROUP_NTARGETS,
 };
 #define THRESHOLDS_EVENTS_TARGET (128)
 #define SOFTLIMIT_EVENTS_TARGET (1024)
+#define ASYNC_EVENTS_TARGET	(512)	/* assume x86-64's hpagesize */
 
 struct mem_cgroup_stat_cpu {
 	long count[MEM_CGROUP_STAT_NSTATS];
@@ -211,6 +213,31 @@ static void mem_cgroup_threshold(struct 
 static void mem_cgroup_oom_notify(struct mem_cgroup *mem);
 
 /*
+ * For example, with transparent hugepages, memory reclaim scan at hitting
+ * limit can very long as to reclaim HPAGE_SIZE of memory. This increases
+ * latency of page fault and may cause fallback. At usual page allocation,
+ * we'll see some (shorter) latency, too. To reduce latency, it's appreciated
+ * to free memory in background to make margin to the limit. This consumes
+ * cpu but we'll have a chance to make use of wait time of applications
+ * (read disk etc..) by asynchronous reclaim.
+ *
+ * This async reclaim tries to reclaim HPAGE_SIZE * 2 of pages when margin
+ * to the limit is smaller than HPAGE_SIZE * 2. This will be enabled
+ * automatically when the limit is set and it's greater than the threshold.
+ */
+#if HPAGE_SIZE != PAGE_SIZE
+#define MEMCG_ASYNC_LIMIT_THRESH      (HPAGE_SIZE * 64)
+#define MEMCG_ASYNC_START_MARGIN      (HPAGE_SIZE * 2)
+#define MEMCG_ASYNC_STOP_MARGIN	      (HPAGE_SIZE * 4)
+#else /* make the margin as 4M bytes */
+#define MEMCG_ASYNC_LIMIT_THRESH      (128 * 1024 * 1024)
+#define MEMCG_ASYNC_START_MARGIN      (4 * 1024 * 1024)
+#define MEMCG_ASYNC_STOP_MARGIN       (8 * 1024 * 1024)
+#endif
+
+static void mem_cgroup_may_async_reclaim(struct mem_cgroup *mem);
+
+/*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
  * statistics based on the statistics developed by Rik Van Riel for clock-pro,
@@ -259,6 +286,7 @@ struct mem_cgroup {
 
 	/* set when res.limit == memsw.limit */
 	bool		memsw_is_minimum;
+	bool		need_async_reclaim;
 
 	/* protect arrays of thresholds */
 	struct mutex thresholds_lock;
@@ -722,6 +750,9 @@ static void __mem_cgroup_target_update(s
 	case MEM_CGROUP_TARGET_SOFTLIMIT:
 		next = val + SOFTLIMIT_EVENTS_TARGET;
 		break;
+	case MEM_CGROUP_TARGET_ASYNC:
+		next = val + ASYNC_EVENTS_TARGET;
+		break;
 	default:
 		return;
 	}
@@ -745,6 +776,11 @@ static void memcg_check_events(struct me
 			__mem_cgroup_target_update(mem,
 				MEM_CGROUP_TARGET_SOFTLIMIT);
 		}
+		if (__memcg_event_check(mem, MEM_CGROUP_TARGET_ASYNC)) {
+			mem_cgroup_may_async_reclaim(mem);
+			__mem_cgroup_target_update(mem,
+				MEM_CGROUP_TARGET_ASYNC);
+		}
 	}
 }
 
@@ -3376,6 +3412,11 @@ static int mem_cgroup_resize_limit(struc
 				memcg->memsw_is_minimum = true;
 			else
 				memcg->memsw_is_minimum = false;
+
+			if (val >= MEMCG_ASYNC_LIMIT_THRESH)
+				memcg->need_async_reclaim = true;
+			else
+				memcg->need_async_reclaim = false;
 		}
 		mutex_unlock(&set_limit_mutex);
 
@@ -3553,6 +3594,15 @@ unsigned long mem_cgroup_soft_limit_recl
 	return nr_reclaimed;
 }
 
+static void mem_cgroup_may_async_reclaim(struct mem_cgroup *mem)
+{
+	if (!mem->need_async_reclaim)
+		return;
+	if (res_counter_margin(&mem->res) <= MEMCG_ASYNC_START_MARGIN) {
+		/* Fill here */
+	}
+}
+
 /*
  * This routine traverse page_cgroup in given list and drop them all.
  * *And* this routine doesn't reclaim page itself, just removes page_cgroup.

--
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/