[PATCH] Zone reclaim: Reclaim logic

Some bits for zone reclaim exists in 2.6.15 but they are not usable.  This
patch fixes them up, removes unused code and makes zone reclaim usable.

Zone reclaim allows the reclaiming of pages from a zone if the number of
free pages falls below the watermarks even if other zones still have enough
pages available.  Zone reclaim is of particular importance for NUMA
machines.  It can be more beneficial to reclaim a page than taking the
performance penalties that come with allocating a page on a remote zone.

Zone reclaim is enabled if the maximum distance to another node is higher
than RECLAIM_DISTANCE, which may be defined by an arch.  By default
RECLAIM_DISTANCE is 20.  20 is the distance to another node in the same
component (enclosure or motherboard) on IA64.  The meaning of the NUMA
distance information seems to vary by arch.

If zone reclaim is not successful then no further reclaim attempts will
occur for a certain time period (ZONE_RECLAIM_INTERVAL).

This patch was discussed before. See

http://marc.theaimsgroup.com/?l=linux-kernel&m=113519961504207&w=2
http://marc.theaimsgroup.com/?l=linux-kernel&m=113408418232531&w=2
http://marc.theaimsgroup.com/?l=linux-kernel&m=113389027420032&w=2
http://marc.theaimsgroup.com/?l=linux-kernel&m=113380938612205&w=2

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

5 files changed, 108 insertions, 8 deletions

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 34cbefd2ebd..93a849f742d 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -149,15 +149,17 @@ struct zone {
 	unsigned long		pages_scanned;	   /* since last reclaim */
 	int			all_unreclaimable; /* All pages pinned */
 
-	/*
-	 * Does the allocator try to reclaim pages from the zone as soon
-	 * as it fails a watermark_ok() in __alloc_pages?
-	 */
-	int			reclaim_pages;
 	/* A count of how many reclaimers are scanning this zone */
 	atomic_t		reclaim_in_progress;
 
 	/*
+	 * timestamp (in jiffies) of the last zone reclaim that did not
+	 * result in freeing of pages. This is used to avoid repeated scans
+	 * if all memory in the zone is in use.
+	 */
+	unsigned long		last_unsuccessful_zone_reclaim;
+
+	/*
 	 * prev_priority holds the scanning priority for this zone.  It is
 	 * defined as the scanning priority at which we achieved our reclaim
 	 * target at the previous try_to_free_pages() or balance_pgdat()
diff --git a/include/linux/swap.h b/include/linux/swap.h
index d01f7efb0f2..4a99e4a7fbf 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -176,6 +176,17 @@ extern int try_to_free_pages(struct zone **, gfp_t);
 extern int shrink_all_memory(int);
 extern int vm_swappiness;
 
+#ifdef CONFIG_NUMA
+extern int zone_reclaim_mode;
+extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
+#else
+#define zone_reclaim_mode 0
+static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_MIGRATION
 extern int isolate_lru_page(struct page *p);
 extern int putback_lru_pages(struct list_head *l);
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 315a5163d6a..e8eb0040ce3 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -56,6 +56,14 @@
 #define REMOTE_DISTANCE		20
 #define node_distance(from,to)	((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE)
 #endif
+#ifndef RECLAIM_DISTANCE
+/*
+ * If the distance between nodes in a system is larger than RECLAIM_DISTANCE
+ * (in whatever arch specific measurement units returned by node_distance())
+ * then switch on zone reclaim on boot.
+ */
+#define RECLAIM_DISTANCE 20
+#endif
 #ifndef PENALTY_FOR_NODE_WITH_CPUS
 #define PENALTY_FOR_NODE_WITH_CPUS	(1)
 #endif
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c2e29743a8d..df54e2fc8ee 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -878,7 +878,9 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
 				mark = (*z)->pages_high;
 			if (!zone_watermark_ok(*z, order, mark,
 				    classzone_idx, alloc_flags))
-				continue;
+				if (!zone_reclaim_mode ||
+				    !zone_reclaim(*z, gfp_mask, order))
+					continue;
 		}
 
 		page = buffered_rmqueue(zonelist, *z, order, gfp_mask);
@@ -1595,13 +1597,22 @@ static void __init build_zonelists(pg_data_t *pgdat)
 	prev_node = local_node;
 	nodes_clear(used_mask);
 	while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
+		int distance = node_distance(local_node, node);
+
+		/*
+		 * If another node is sufficiently far away then it is better
+		 * to reclaim pages in a zone before going off node.
+		 */
+		if (distance > RECLAIM_DISTANCE)
+			zone_reclaim_mode = 1;
+
 		/*
 		 * We don't want to pressure a particular node.
 		 * So adding penalty to the first node in same
 		 * distance group to make it round-robin.
 		 */
-		if (node_distance(local_node, node) !=
-				node_distance(local_node, prev_node))
+
+		if (distance != node_distance(local_node, prev_node))
 			node_load[node] += load;
 		prev_node = node;
 		load--;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e5117b6897a..2e34b61a70c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1572,3 +1572,71 @@ static int __init kswapd_init(void)
 }
 
 module_init(kswapd_init)
+
+#ifdef CONFIG_NUMA
+/*
+ * Zone reclaim mode
+ *
+ * If non-zero call zone_reclaim when the number of free pages falls below
+ * the watermarks.
+ *
+ * In the future we may add flags to the mode. However, the page allocator
+ * should only have to check that zone_reclaim_mode != 0 before calling
+ * zone_reclaim().
+ */
+int zone_reclaim_mode __read_mostly;
+
+/*
+ * Mininum time between zone reclaim scans
+ */
+#define ZONE_RECLAIM_INTERVAL HZ/2
+/*
+ * Try to free up some pages from this zone through reclaim.
+ */
+int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+{
+	int nr_pages = 1 << order;
+	struct task_struct *p = current;
+	struct reclaim_state reclaim_state;
+	struct scan_control sc = {
+		.gfp_mask	= gfp_mask,
+		.may_writepage	= 0,
+		.may_swap	= 0,
+		.nr_mapped	= read_page_state(nr_mapped),
+		.nr_scanned	= 0,
+		.nr_reclaimed	= 0,
+		.priority	= 0
+	};
+
+	if (!(gfp_mask & __GFP_WAIT) ||
+		zone->zone_pgdat->node_id != numa_node_id() ||
+		zone->all_unreclaimable ||
+		atomic_read(&zone->reclaim_in_progress) > 0)
+			return 0;
+
+	if (time_before(jiffies,
+		zone->last_unsuccessful_zone_reclaim + ZONE_RECLAIM_INTERVAL))
+			return 0;
+
+	disable_swap_token();
+
+	if (nr_pages > SWAP_CLUSTER_MAX)
+		sc.swap_cluster_max = nr_pages;
+	else
+		sc.swap_cluster_max = SWAP_CLUSTER_MAX;
+
+	cond_resched();
+	p->flags |= PF_MEMALLOC;
+	reclaim_state.reclaimed_slab = 0;
+	p->reclaim_state = &reclaim_state;
+	shrink_zone(zone, &sc);
+	p->reclaim_state = NULL;
+	current->flags &= ~PF_MEMALLOC;
+
+	if (sc.nr_reclaimed == 0)
+		zone->last_unsuccessful_zone_reclaim = jiffies;
+
+	return sc.nr_reclaimed > nr_pages;
+}
+#endif
+