[PATCH 20/31] mm, vmscan: only wakeup kswapd once per node for the requested classzone

[Mel Gorman]

kswapd is woken when zones are below the low watermark but the wakeup
decision is not taking the classzone into account.  Now that reclaim is
node-based, it is only required to wake kswapd once per node and only if
all zones are unbalanced for the requested classzone.

Note that one node might be checked multiple times if the zonelist is
ordered by node because there is no cheap way of tracking what nodes have
already been visited.  For zone-ordering, each node should be checked only
once.

Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Acked-by: Vlastimil Babka <vbabka@xxxxxxx>
---
 mm/page_alloc.c |  8 ++++++--
 mm/vmscan.c     | 13 +++++++++++--
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 441f482bf9a2..2fe2fbb4f2ad 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3410,10 +3410,14 @@ static void wake_all_kswapds(unsigned int order, const struct alloc_context *ac)
 {
 	struct zoneref *z;
 	struct zone *zone;
+	pg_data_t *last_pgdat = NULL;
 
 	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
-						ac->high_zoneidx, ac->nodemask)
-		wakeup_kswapd(zone, order, ac_classzone_idx(ac));
+					ac->high_zoneidx, ac->nodemask) {
+		if (last_pgdat != zone->zone_pgdat)
+			wakeup_kswapd(zone, order, ac_classzone_idx(ac));
+		last_pgdat = zone->zone_pgdat;
+	}
 }
 
 static inline unsigned int
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c1c8b77d8cb4..e02091be0e12 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3420,6 +3420,7 @@ static int kswapd(void *p)
 void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 {
 	pg_data_t *pgdat;
+	int z;
 
 	if (!populated_zone(zone))
 		return;
@@ -3433,8 +3434,16 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	pgdat->kswapd_order = max(pgdat->kswapd_order, order);
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
-	if (zone_balanced(zone, order, 0))
-		return;
+
+	/* Only wake kswapd if all zones are unbalanced */
+	for (z = 0; z <= classzone_idx; z++) {
+		zone = pgdat->node_zones + z;
+		if (!populated_zone(zone))
+			continue;
+
+		if (zone_balanced(zone, order, classzone_idx))
+			return;
+	}
 
 	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
 	wake_up_interruptible(&pgdat->kswapd_wait);
-- 
2.6.4