[PATCH] zoned vm counters: zone_reclaim: remove /proc/sys/vm/zone_reclaim_interval

The zone_reclaim_interval was necessary because we were not able to determine
how many unmapped pages exist in a zone.  Therefore we had to scan in
intervals to figure out if any pages were unmapped.

With the zoned counters and NR_ANON_PAGES we now know the number of pagecache
pages and the number of mapped pages in a zone.  So we can simply skip the
reclaim if there is an insufficient number of unmapped pages.  We use
SWAP_CLUSTER_MAX as the boundary.

Drop all support for /proc/sys/vm/zone_reclaim_interval.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

Documentation/sysctl/vm.txt

@@ -28,7 +28,6 @@ Currently, these files are in /proc/sys/vm:
 - block_dump
 - drop-caches
 - zone_reclaim_mode
-- zone_reclaim_interval
 - panic_on_oom
 
 ==============================================================
@@ -167,18 +166,6 @@ use of files and builds up large slab caches. However, the slab
 shrink operation is global, may take a long time and free slabs
 in all nodes of the system.
 
-================================================================
-
-zone_reclaim_interval:
-
-The time allowed for off node allocations after zone reclaim
-has failed to reclaim enough pages to allow a local allocation.
-
-Time is set in seconds and set by default to 30 seconds.
-
-Reduce the interval if undesired off node allocations occur. However, too
-frequent scans will have a negative impact onoff node allocation performance.
-
 =============================================================
 
 panic_on_oom

include/linux/mmzone.h

@@ -178,12 +178,6 @@ struct zone {
 
 	/* Zone statistics */
 	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
-	/*
-	 * 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

include/linux/swap.h

@@ -189,7 +189,6 @@ extern long vm_total_pages;
 
 #ifdef CONFIG_NUMA
 extern int zone_reclaim_mode;
-extern int zone_reclaim_interval;
 extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
 #else
 #define zone_reclaim_mode 0

kernel/sysctl.c

@@ -933,15 +933,6 @@ static ctl_table vm_table[] = {
 		.strategy	= &sysctl_intvec,
 		.extra1		= &zero,
 	},
-	{
-		.ctl_name	= VM_ZONE_RECLAIM_INTERVAL,
-		.procname	= "zone_reclaim_interval",
-		.data		= &zone_reclaim_interval,
-		.maxlen		= sizeof(zone_reclaim_interval),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_jiffies,
-		.strategy	= &sysctl_jiffies,
-	},
 #endif
 #ifdef CONFIG_X86_32
 	{

mm/vmscan.c

@@ -1517,11 +1517,6 @@ int zone_reclaim_mode __read_mostly;
 #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 */
 
-/*
- * Mininum time between zone reclaim scans
- */
-int zone_reclaim_interval __read_mostly = 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
@@ -1587,16 +1582,6 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 
 	p->reclaim_state = NULL;
 	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
-
-	if (nr_reclaimed == 0) {
-		/*
-		 * We were unable to reclaim enough pages to stay on node.  We
-		 * now allow off node accesses for a certain time period before
-		 * trying again to reclaim pages from the local zone.
-		 */
-		zone->last_unsuccessful_zone_reclaim = jiffies;
-	}
-
 	return nr_reclaimed >= nr_pages;
 }
 
@@ -1606,13 +1591,17 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	int node_id;
 
 	/*
-	 * Do not reclaim if there was a recent unsuccessful attempt at zone
-	 * reclaim.  In that case we let allocations go off node for the
-	 * zone_reclaim_interval.  Otherwise we would scan for each off-node
-	 * page allocation.
+	 * Do not reclaim if there are not enough reclaimable pages in this
+	 * zone that would satify this allocations.
+	 *
+	 * All unmapped pagecache pages are reclaimable.
+	 *
+	 * Both counters may be temporarily off a bit so we use
+	 * SWAP_CLUSTER_MAX as the boundary. It may also be good to
+	 * leave a few frequently used unmapped pagecache pages around.
 	 */
-	if (time_before(jiffies,
-		zone->last_unsuccessful_zone_reclaim + zone_reclaim_interval))
+	if (zone_page_state(zone, NR_FILE_PAGES) -
+		zone_page_state(zone, NR_FILE_MAPPED) < SWAP_CLUSTER_MAX)
 			return 0;
 
 	/*