[PATCH] zone_reclaim: dynamic slab reclaim

Currently one can enable slab reclaim by setting an explicit option in
/proc/sys/vm/zone_reclaim_mode.  Slab reclaim is then used as a final
option if the freeing of unmapped file backed pages is not enough to free
enough pages to allow a local allocation.

However, that means that the slab can grow excessively and that most memory
of a node may be used by slabs.  We have had a case where a machine with
46GB of memory was using 40-42GB for slab.  Zone reclaim was effective in
dealing with pagecache pages.  However, slab reclaim was only done during
global reclaim (which is a bit rare on NUMA systems).

This patch implements slab reclaim during zone reclaim.  Zone reclaim
occurs if there is a danger of an off node allocation.  At that point we

1. Shrink the per node page cache if the number of pagecache
   pages is more than min_unmapped_ratio percent of pages in a zone.

2. Shrink the slab cache if the number of the nodes reclaimable slab pages
   (patch depends on earlier one that implements that counter)
   are more than min_slab_ratio (a new /proc/sys/vm tunable).

The shrinking of the slab cache is a bit problematic since it is not node
specific.  So we simply calculate what point in the slab we want to reach
(current per node slab use minus the number of pages that neeed to be
allocated) and then repeately run the global reclaim until that is
unsuccessful or we have reached the limit.  I hope we will have zone based
slab reclaim at some point which will make that easier.

The default for the min_slab_ratio is 5%

Also remove the slab option from /proc/sys/vm/zone_reclaim_mode.

[akpm@osdl.org: cleanups]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 54 insertions, 21 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 47e9842..cf913bd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2005,6 +2005,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat,
 #ifdef CONFIG_NUMA
 		zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio)
 						/ 100;
+		zone->min_slab_pages = (realsize * sysctl_min_slab_ratio) / 100;
 #endif
 		zone->name = zone_names[j];
 		spin_lock_init(&zone->lock);
@@ -2318,6 +2319,22 @@ int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write,
 				sysctl_min_unmapped_ratio) / 100;
 	return 0;
 }
+
+int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
+	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+{
+	struct zone *zone;
+	int rc;
+
+	rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+	if (rc)
+		return rc;
+
+	for_each_zone(zone)
+		zone->min_slab_pages = (zone->present_pages *
+				sysctl_min_slab_ratio) / 100;
+	return 0;
+}
 #endif
 
 /*
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 349797b..089e943c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1527,7 +1527,6 @@ int zone_reclaim_mode __read_mostly;
 #define RECLAIM_ZONE (1<<0)	/* Run shrink_cache on the zone */
 #define RECLAIM_WRITE (1<<1)	/* Writeout pages during reclaim */
 #define RECLAIM_SWAP (1<<2)	/* Swap pages out during reclaim */
-#define RECLAIM_SLAB (1<<3)	/* Do a global slab shrink if the zone is out of memory */
 
 /*
  * Priority for ZONE_RECLAIM. This determines the fraction of pages
@@ -1543,6 +1542,12 @@ int zone_reclaim_mode __read_mostly;
 int sysctl_min_unmapped_ratio = 1;
 
 /*
+ * If the number of slab pages in a zone grows beyond this percentage then
+ * slab reclaim needs to occur.
+ */
+int sysctl_min_slab_ratio = 5;
+
+/*
  * Try to free up some pages from this zone through reclaim.
  */
 static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
@@ -1573,29 +1578,37 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
-	/*
-	 * Free memory by calling shrink zone with increasing priorities
-	 * until we have enough memory freed.
-	 */
-	priority = ZONE_RECLAIM_PRIORITY;
-	do {
-		nr_reclaimed += shrink_zone(priority, zone, &sc);
-		priority--;
-	} while (priority >= 0 && nr_reclaimed < nr_pages);
+	if (zone_page_state(zone, NR_FILE_PAGES) -
+		zone_page_state(zone, NR_FILE_MAPPED) >
+		zone->min_unmapped_pages) {
+		/*
+		 * Free memory by calling shrink zone with increasing
+		 * priorities until we have enough memory freed.
+		 */
+		priority = ZONE_RECLAIM_PRIORITY;
+		do {
+			nr_reclaimed += shrink_zone(priority, zone, &sc);
+			priority--;
+		} while (priority >= 0 && nr_reclaimed < nr_pages);
+	}
 
-	if (nr_reclaimed < nr_pages && (zone_reclaim_mode & RECLAIM_SLAB)) {
+	if (zone_page_state(zone, NR_SLAB_RECLAIMABLE) > zone->min_slab_pages) {
 		/*
 		 * shrink_slab() does not currently allow us to determine how
-		 * many pages were freed in this zone. So we just shake the slab
-		 * a bit and then go off node for this particular allocation
-		 * despite possibly having freed enough memory to allocate in
-		 * this zone.  If we freed local memory then the next
-		 * allocations will be local again.
+		 * many pages were freed in this zone. So we take the current
+		 * number of slab pages and shake the slab until it is reduced
+		 * by the same nr_pages that we used for reclaiming unmapped
+		 * pages.
 		 *
-		 * shrink_slab will free memory on all zones and may take
-		 * a long time.
+		 * Note that shrink_slab will free memory on all zones and may
+		 * take a long time.
 		 */
-		shrink_slab(sc.nr_scanned, gfp_mask, order);
+		unsigned long limit = zone_page_state(zone,
+				NR_SLAB_RECLAIMABLE) - nr_pages;
+
+		while (shrink_slab(sc.nr_scanned, gfp_mask, order) &&
+			zone_page_state(zone, NR_SLAB_RECLAIMABLE) > limit)
+			;
 	}
 
 	p->reclaim_state = NULL;
@@ -1609,7 +1622,8 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	int node_id;
 
 	/*
-	 * Zone reclaim reclaims unmapped file backed pages.
+	 * Zone reclaim reclaims unmapped file backed pages and
+	 * slab pages if we are over the defined limits.
 	 *
 	 * A small portion of unmapped file backed pages is needed for
 	 * file I/O otherwise pages read by file I/O will be immediately
@@ -1618,7 +1632,9 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	 * unmapped file backed pages.
 	 */
 	if (zone_page_state(zone, NR_FILE_PAGES) -
-	    zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_pages)
+	    zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_pages
+	    && zone_page_state(zone, NR_SLAB_RECLAIMABLE)
+			<= zone->min_slab_pages)
 		return 0;
 
 	/*