vmscan: have kswapd sleep for a short interval and double check it should be asleep

After kswapd balances all zones in a pgdat, it goes to sleep.  In the
event of no IO congestion, kswapd can go to sleep very shortly after the
high watermark was reached.  If there are a constant stream of allocations
from parallel processes, it can mean that kswapd went to sleep too quickly
and the high watermark is not being maintained for sufficient length time.

This patch makes kswapd go to sleep as a two-stage process.  It first
tries to sleep for HZ/10.  If it is woken up by another process or the
high watermark is no longer met, it's considered a premature sleep and
kswapd continues work.  Otherwise it goes fully to sleep.

This adds more counters to distinguish between fast and slow breaches of
watermarks.  A "fast" premature sleep is one where the low watermark was
hit in a very short time after kswapd going to sleep.  A "slow" premature
sleep indicates that the high watermark was breached after a very short
interval.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Frans Pop <elendil@planet.nl>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 44 insertions, 2 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 61d3a9a0d96f..e176bd3936da 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1904,6 +1904,24 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 }
 #endif
 
+/* is kswapd sleeping prematurely? */
+static int sleeping_prematurely(int order, long remaining)
+{
+	struct zone *zone;
+
+	/* If a direct reclaimer woke kswapd within HZ/10, it's premature */
+	if (remaining)
+		return 1;
+
+	/* If after HZ/10, a zone is below the high mark, it's premature */
+	for_each_populated_zone(zone)
+		if (!zone_watermark_ok(zone, order, high_wmark_pages(zone),
+								0, 0))
+			return 1;
+
+	return 0;
+}
+
 /*
  * For kswapd, balance_pgdat() will work across all this node's zones until
  * they are all at high_wmark_pages(zone).
@@ -2185,8 +2203,30 @@ static int kswapd(void *p)
 			 */
 			order = new_order;
 		} else {
-			if (!freezing(current) && !kthread_should_stop())
-				schedule();
+			if (!freezing(current) && !kthread_should_stop()) {
+				long remaining = 0;
+
+				/* Try to sleep for a short interval */
+				if (!sleeping_prematurely(order, remaining)) {
+					remaining = schedule_timeout(HZ/10);
+					finish_wait(&pgdat->kswapd_wait, &wait);
+					prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
+				}
+
+				/*
+				 * After a short sleep, check if it was a
+				 * premature sleep. If not, then go fully
+				 * to sleep until explicitly woken up
+				 */
+				if (!sleeping_prematurely(order, remaining))
+					schedule();
+				else {
+					if (remaining)
+						count_vm_event(KSWAPD_PREMATURE_FAST);
+					else
+						count_vm_event(KSWAPD_PREMATURE_SLOW);
+				}
+			}
 
 			order = pgdat->kswapd_max_order;
 		}
diff --git a/mm/vmstat.c b/mm/vmstat.c
index dad2327e4580..63ab71455c5b 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -683,6 +683,8 @@ static const char * const vmstat_text[] = {
 	"slabs_scanned",
 	"kswapd_steal",
 	"kswapd_inodesteal",
+	"kswapd_slept_prematurely_fast",
+	"kswapd_slept_prematurely_slow",
 	"pageoutrun",
 	"allocstall",