If reclaim fails to make sufficient progress, the priority is raised.

Once the priority is higher, kswapd starts waiting on congestion. 
However, if the zone is below the min watermark then kswapd needs to
continue working without delay as there is a danger of an increased rate
of GFP_ATOMIC allocation failure.

This patch changes the conditions under which kswapd waits on congestion
by only going to sleep if the min watermarks are being met.

[mel@csn.ul.ie: Add stats to track how relevant the logic is]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/vmstat.h

@@ -41,6 +41,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #endif
 		PGINODESTEAL, SLABS_SCANNED, KSWAPD_STEAL, KSWAPD_INODESTEAL,
 		KSWAPD_PREMATURE_FAST, KSWAPD_PREMATURE_SLOW,
+		KSWAPD_SKIP_CONGESTION_WAIT,
 		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
 #ifdef CONFIG_HUGETLB_PAGE
 		HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL,

mm/vmscan.c

@@ -1983,6 +1983,7 @@ loop_again:
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
 		int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
 		unsigned long lru_pages = 0;
+		int has_under_min_watermark_zone = 0;
 
 		/* The swap token gets in the way of swapout... */
 		if (!priority)
@@ -2089,6 +2090,15 @@ loop_again:
 			if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
 			    total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
 				sc.may_writepage = 1;
+
+			/*
+			 * We are still under min water mark. it mean we have
+			 * GFP_ATOMIC allocation failure risk. Hurry up!
+			 */
+			if (!zone_watermark_ok(zone, order, min_wmark_pages(zone),
+					      end_zone, 0))
+				has_under_min_watermark_zone = 1;
+
 		}
 		if (all_zones_ok)
 			break;		/* kswapd: all done */
@@ -2096,8 +2106,12 @@ loop_again:
 		 * OK, kswapd is getting into trouble.  Take a nap, then take
 		 * another pass across the zones.
 		 */
-		if (total_scanned && priority < DEF_PRIORITY - 2)
-			congestion_wait(BLK_RW_ASYNC, HZ/10);
+		if (total_scanned && (priority < DEF_PRIORITY - 2)) {
+			if (has_under_min_watermark_zone)
+				count_vm_event(KSWAPD_SKIP_CONGESTION_WAIT);
+			else
+				congestion_wait(BLK_RW_ASYNC, HZ/10);
+		}
 
 		/*
 		 * We do this so kswapd doesn't build up large priorities for

mm/vmstat.c

@@ -685,6 +685,7 @@ static const char * const vmstat_text[] = {
 	"kswapd_inodesteal",
 	"kswapd_slept_prematurely_fast",
 	"kswapd_slept_prematurely_slow",
+	"kswapd_skip_congestion_wait",
 	"pageoutrun",
 	"allocstall",