zone_reclaim: partial scans instead of full scan.

Instead of scanning all the pages in a zone, imitate real swap and
scan only a portion of the pages and gradually scan more if we do not
free up enough pages. This avoids a zone suddenly loosing all unused
pagecache pages but still frees up large chunks if a zone only contains
unused pagecache pages.

Signed-off-by: Christoph Lameter <clameter@sgi.com>

Index: linux-2.6.16-rc1-mm3/mm/vmscan.c
===================================================================
--- linux-2.6.16-rc1-mm3.orig/mm/vmscan.c	2006-01-25 10:02:09.000000000 -0800
+++ linux-2.6.16-rc1-mm3/mm/vmscan.c	2006-01-25 10:05:05.000000000 -0800
@@ -1835,6 +1835,14 @@ int zone_reclaim_mode __read_mostly;
  * Mininum time between zone reclaim scans
  */
 #define ZONE_RECLAIM_INTERVAL 30*HZ
+
+/*
+ * Priority for ZONE_RECLAIM. This determines the fraction of pages
+ * of a node considered for each zone_reclaim. 4 scans 1/16th of
+ * a zone.
+ */
+#define ZONE_RECLAIM_PRIORITY 4
+
 /*
  * Try to free up some pages from this zone through reclaim.
  */
@@ -1865,7 +1873,7 @@ int zone_reclaim(struct zone *zone, gfp_
 	sc.may_swap = 0;
 	sc.nr_scanned = 0;
 	sc.nr_reclaimed = 0;
-	sc.priority = 0;
+	sc.priority = ZONE_RECLAIM_PRIORITY + 1;
 	sc.nr_mapped = read_page_state(nr_mapped);
 	sc.gfp_mask = gfp_mask;
 
@@ -1882,7 +1890,15 @@ int zone_reclaim(struct zone *zone, gfp_
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
-	shrink_zone(zone, &sc);
+	/*
+	 * Free memory by calling shrink zone with increasing priorities
+	 * until we have enough memory freed.
+	 */
+	do {
+		sc.priority--;
+		shrink_zone(zone, &sc);
+
+	} while (sc.nr_reclaimed < nr_pages && sc.priority > 0);
 
 	p->reclaim_state = NULL;
 	current->flags &= ~PF_MEMALLOC;