[PATCH 1/3] vm: kswapd incmin

[Nick Piggin <nickpiggin@yahoo.com.au>]

[-- Attachment #1: Type: text/plain, Size: 33 bytes --]

1/3

-- 
SUSE Labs, Novell Inc.


[-- Attachment #2: vm-kswapd-incmin.patch --]
[-- Type: text/plain, Size: 4705 bytes --]

Explicitly teach kswapd about the incremental min logic instead of just scanning
all zones under the first low zone. This should keep more even pressure applied
on the zones.

Signed-off-by: Nick Piggin <npiggin@suse.de>


Index: linux-2.6/mm/vmscan.c
===================================================================
--- linux-2.6.orig/mm/vmscan.c	2005-11-01 13:42:33.000000000 +1100
+++ linux-2.6/mm/vmscan.c	2005-11-01 14:27:16.000000000 +1100
@@ -1051,97 +1051,63 @@ loop_again:
 	}
 
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
-		int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
 		unsigned long lru_pages = 0;
+		int first_low_zone = 0;
 
 		all_zones_ok = 1;
+		sc.nr_scanned = 0;
+		sc.nr_reclaimed = 0;
+		sc.priority = priority;
+		sc.swap_cluster_max = nr_pages ? nr_pages : SWAP_CLUSTER_MAX;
 
-		if (nr_pages == 0) {
-			/*
-			 * Scan in the highmem->dma direction for the highest
-			 * zone which needs scanning
-			 */
-			for (i = pgdat->nr_zones - 1; i >= 0; i--) {
-				struct zone *zone = pgdat->node_zones + i;
+		/* Scan in the highmem->dma direction */
+		for (i = pgdat->nr_zones - 1; i >= 0; i--) {
+			struct zone *zone = pgdat->node_zones + i;
 
-				if (zone->present_pages == 0)
-					continue;
+			if (zone->present_pages == 0)
+				continue;
 
-				if (zone->all_unreclaimable &&
-						priority != DEF_PRIORITY)
+			if (nr_pages == 0) {	/* Not software suspend */
+				if (zone_watermark_ok(zone, order,
+					zone->pages_high, first_low_zone, 0, 0))
 					continue;
 
-				if (!zone_watermark_ok(zone, order,
-						zone->pages_high, 0, 0, 0)) {
-					end_zone = i;
-					goto scan;
-				}
+				all_zones_ok = 0;
+				if (first_low_zone < i)
+					first_low_zone = i;
 			}
-			goto out;
-		} else {
-			end_zone = pgdat->nr_zones - 1;
-		}
-scan:
-		for (i = 0; i <= end_zone; i++) {
-			struct zone *zone = pgdat->node_zones + i;
-
-			lru_pages += zone->nr_active + zone->nr_inactive;
-		}
-
-		/*
-		 * Now scan the zone in the dma->highmem direction, stopping
-		 * at the last zone which needs scanning.
-		 *
-		 * We do this because the page allocator works in the opposite
-		 * direction.  This prevents the page allocator from allocating
-		 * pages behind kswapd's direction of progress, which would
-		 * cause too much scanning of the lower zones.
-		 */
-		for (i = 0; i <= end_zone; i++) {
-			struct zone *zone = pgdat->node_zones + i;
-			int nr_slab;
-
-			if (zone->present_pages == 0)
-				continue;
 
 			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;
 
-			if (nr_pages == 0) {	/* Not software suspend */
-				if (!zone_watermark_ok(zone, order,
-						zone->pages_high, end_zone, 0, 0))
-					all_zones_ok = 0;
-			}
 			zone->temp_priority = priority;
 			if (zone->prev_priority > priority)
 				zone->prev_priority = priority;
-			sc.nr_scanned = 0;
-			sc.nr_reclaimed = 0;
-			sc.priority = priority;
-			sc.swap_cluster_max = nr_pages? nr_pages : SWAP_CLUSTER_MAX;
+			lru_pages += zone->nr_active + zone->nr_inactive;
+
 			atomic_inc(&zone->reclaim_in_progress);
 			shrink_zone(zone, &sc);
 			atomic_dec(&zone->reclaim_in_progress);
-			reclaim_state->reclaimed_slab = 0;
-			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
-						lru_pages);
-			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
-			total_reclaimed += sc.nr_reclaimed;
-			total_scanned += sc.nr_scanned;
-			if (zone->all_unreclaimable)
-				continue;
-			if (nr_slab == 0 && zone->pages_scanned >=
+
+			if (zone->pages_scanned >=
 				    (zone->nr_active + zone->nr_inactive) * 4)
 				zone->all_unreclaimable = 1;
-			/*
-			 * If we've done a decent amount of scanning and
-			 * the reclaim ratio is low, start doing writepage
-			 * even in laptop mode
-			 */
-			if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
-			    total_scanned > total_reclaimed+total_reclaimed/2)
-				sc.may_writepage = 1;
 		}
+		reclaim_state->reclaimed_slab = 0;
+		shrink_slab(sc.nr_scanned, GFP_KERNEL, lru_pages);
+		sc.nr_reclaimed += reclaim_state->reclaimed_slab;
+		total_reclaimed += sc.nr_reclaimed;
+		total_scanned += sc.nr_scanned;
+
+		/*
+		 * If we've done a decent amount of scanning and
+		 * the reclaim ratio is low, start doing writepage
+		 * even in laptop mode
+		 */
+		if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
+		    total_scanned > total_reclaimed+total_reclaimed/2)
+			sc.may_writepage = 1;
+
 		if (nr_pages && to_free > total_reclaimed)
 			continue;	/* swsusp: need to do more work */
 		if (all_zones_ok)
@@ -1162,7 +1128,6 @@ scan:
 		if ((total_reclaimed >= SWAP_CLUSTER_MAX) && (!nr_pages))
 			break;
 	}
-out:
 	for (i = 0; i < pgdat->nr_zones; i++) {
 		struct zone *zone = pgdat->node_zones + i;