Before kswapd goes to sleep, it uses sleeping_prematurely() to check if
there was a race pushing a zone below its watermark. If the race
happened, it stays awake. However, balance_pgdat() can decide to reclaim
at a lower order if it decides that high-order reclaim is not working as
expected. This information is not passed back to sleeping_prematurely().
The impact is that kswapd remains awake reclaiming pages long after it
should have gone to sleep. This patch passes the adjusted order to
sleeping_prematurely and uses the same logic as balance_pgdat to decide
if it's ok to go to sleep.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
---
 mm/vmscan.c |   30 ++++++++++++++++++++++++------
 1 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 67e4283..9891efd 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2118,15 +2118,17 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 #endif
 
 /* is kswapd sleeping prematurely? */
-static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining)
+static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining)
 {
 	int i;
+	bool all_zones_ok = true;
+	bool any_zone_ok = false;
 
 	/* 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 */
+	/* Check the watermark levels */
 	for (i = 0; i < pgdat->nr_zones; i++) {
 		struct zone *zone = pgdat->node_zones + i;
 
@@ -2138,10 +2140,20 @@ static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining)
 
 		if (!zone_watermark_ok(zone, order, high_wmark_pages(zone),
 								0, 0))
-			return 1;
+			all_zones_ok = false;
+		else
+			any_zone_ok = true;
 	}
 
-	return 0;
+	/*
+	 * For high-order requests, any zone meeting the watermark is enough
+	 *   to allow kswapd go back to sleep
+	 * For order-0, all zones must be balanced
+	 */
+	if (order)
+		return !any_zone_ok;
+	else
+		return !all_zones_ok;
 }
 
 /*
@@ -2382,7 +2394,13 @@ out:
 		zone_clear_flag(zone, ZONE_CONGESTED);
 	}
 
-	return sc.nr_reclaimed;
+	/*
+	 * Return the order we were reclaiming at so sleeping_prematurely()
+	 * makes a decision on the order we were last reclaiming at. However,
+	 * if another caller entered the allocator slow path while kswapd
+	 * was awake, order will remain at the higher level
+	 */
+	return order;
 }
 
 /*
@@ -2492,7 +2510,7 @@ static int kswapd(void *p)
 		 */
 		if (!ret) {
 			trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
-			balance_pgdat(pgdat, order, zone_highidx);
+			order = balance_pgdat(pgdat, order, zone_highidx);
 		}
 	}
 	return 0;
-- 
1.7.1

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