X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fvmscan.c;h=cb69f717799f65e4deb33ccca56d78ba89c53f6f;hb=1cb1729b1385884648170d9d1d3aa0c66780d64b;hp=61d3a9a0d96f87ec0ff29fdb68908ca13a810e7b;hpb=6aceb53be44ed55a2374c20a62e3aef9d3919e8d;p=safe%2Fjmp%2Flinux-2.6

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 61d3a9a..cb69f71 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1904,6 +1904,30 @@ 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)
+{
+	int i;
+
+	/* 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 (i = 0; i < pgdat->nr_zones; i++) {
+		struct zone *zone = pgdat->node_zones + i;
+
+		if (!populated_zone(zone))
+			continue;
+
+		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).
@@ -1961,6 +1985,7 @@ 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)
@@ -2067,6 +2092,15 @@ 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 */
@@ -2074,8 +2108,12 @@ 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
@@ -2185,8 +2223,30 @@ 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(pgdat, 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(pgdat, order, remaining))
+					schedule();
+				else {
+					if (remaining)
+						count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
+					else
+						count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY);
+				}
+			}
 
 			order = pgdat->kswapd_max_order;
 		}