[PATCH] VM: early zone reclaim

This is the core of the (much simplified) early reclaim.  The goal of this
patch is to reclaim some easily-freed pages from a zone before falling back
onto another zone.

One of the major uses of this is NUMA machines.  With the default allocator
behavior the allocator would look for memory in another zone, which might be
off-node, before trying to reclaim from the current zone.

This adds a zone tuneable to enable early zone reclaim.  It is selected on a
per-zone basis and is turned on/off via syscall.

Adding some extra throttling on the reclaim was also required (patch
4/4).  Without the machine would grind to a crawl when doing a "make -j"
kernel build.  Even with this patch the System Time is higher on
average, but it seems tolerable.  Here are some numbers for kernbench
runs on a 2-node, 4cpu, 8Gig RAM Altix in the "make -j" run:

			wall  user   sys   %cpu  ctx sw.  sleeps
			----  ----   ---   ----   ------  ------
No patch		1009  1384   847   258   298170   504402
w/patch, no reclaim     880   1376   667   288   254064   396745
w/patch & reclaim       1079  1385   926   252   291625   548873

These numbers are the average of 2 runs of 3 "make -j" runs done right
after system boot.  Run-to-run variability for "make -j" is huge, so
these numbers aren't terribly useful except to seee that with reclaim
the benchmark still finishes in a reasonable amount of time.

I also looked at the NUMA hit/miss stats for the "make -j" runs and the
reclaim doesn't make any difference when the machine is thrashing away.

Doing a "make -j8" on a single node that is filled with page cache pages
takes 700 seconds with reclaim turned on and 735 seconds without reclaim
(due to remote memory accesses).

The simple zone_reclaim syscall program is at
http://www.bork.org/~mort/sgi/zone_reclaim.cSigned-off-by: Martin Hicks <mort@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/i386/kernel/syscall_table.S

@@ -251,7 +251,7 @@ ENTRY(sys_call_table)
 	.long sys_io_submit
 	.long sys_io_cancel
 	.long sys_fadvise64	/* 250 */
-	.long sys_ni_syscall
+	.long sys_set_zone_reclaim
 	.long sys_exit_group
 	.long sys_lookup_dcookie
 	.long sys_epoll_create

arch/ia64/kernel/entry.S

@@ -1579,7 +1579,7 @@ sys_call_table:
 	data8 sys_keyctl
 	data8 sys_ni_syscall
 	data8 sys_ni_syscall			// 1275
-	data8 sys_ni_syscall
+	data8 sys_set_zone_reclaim
 	data8 sys_ni_syscall
 	data8 sys_ni_syscall
 	data8 sys_ni_syscall

include/asm-i386/unistd.h

@@ -256,7 +256,7 @@
 #define __NR_io_submit		248
 #define __NR_io_cancel		249
 #define __NR_fadvise64		250
-
+#define __NR_set_zone_reclaim	251
 #define __NR_exit_group		252
 #define __NR_lookup_dcookie	253
 #define __NR_epoll_create	254

include/asm-ia64/unistd.h

@@ -263,6 +263,7 @@
 #define __NR_add_key			1271
 #define __NR_request_key		1272
 #define __NR_keyctl			1273
+#define __NR_set_zone_reclaim		1276
 
 #ifdef __KERNEL__
 

include/linux/mmzone.h

@@ -144,6 +144,12 @@ 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;
+
 	/*
 	 * prev_priority holds the scanning priority for this zone.  It is
 	 * defined as the scanning priority at which we achieved our reclaim

include/linux/swap.h

@@ -173,6 +173,7 @@ extern void swap_setup(void);
 
 /* linux/mm/vmscan.c */
 extern int try_to_free_pages(struct zone **, unsigned int, unsigned int);
+extern int zone_reclaim(struct zone *, unsigned int, unsigned int);
 extern int shrink_all_memory(int);
 extern int vm_swappiness;
 

kernel/sys_ni.c

@@ -77,6 +77,7 @@ cond_syscall(sys_request_key);
 cond_syscall(sys_keyctl);
 cond_syscall(compat_sys_keyctl);
 cond_syscall(compat_sys_socketcall);
+cond_syscall(sys_set_zone_reclaim);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);

mm/page_alloc.c

@@ -724,6 +724,14 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 	return 1;
 }
 
+static inline int
+should_reclaim_zone(struct zone *z, unsigned int gfp_mask)
+{
+	if (!z->reclaim_pages)
+		return 0;
+	return 1;
+}
+
 /*
  * This is the 'heart' of the zoned buddy allocator.
  */
@@ -760,16 +768,31 @@ __alloc_pages(unsigned int __nocast gfp_mask, unsigned int order,
 
 	classzone_idx = zone_idx(zones[0]);
 
- restart:
+restart:
 	/* Go through the zonelist once, looking for a zone with enough free */
 	for (i = 0; (z = zones[i]) != NULL; i++) {
+		int do_reclaim = should_reclaim_zone(z, gfp_mask);
 
-		if (!zone_watermark_ok(z, order, z->pages_low,
-				       classzone_idx, 0, 0))
+		if (!cpuset_zone_allowed(z))
 			continue;
 
-		if (!cpuset_zone_allowed(z))
+		/*
+		 * If the zone is to attempt early page reclaim then this loop
+		 * will try to reclaim pages and check the watermark a second
+		 * time before giving up and falling back to the next zone.
+		 */
+zone_reclaim_retry:
+		if (!zone_watermark_ok(z, order, z->pages_low,
+				       classzone_idx, 0, 0)) {
+			if (!do_reclaim)
 				continue;
+			else {
+				zone_reclaim(z, gfp_mask, order);
+				/* Only try reclaim once */
+				do_reclaim = 0;
+				goto zone_reclaim_retry;
+			}
+		}
 
 		page = buffered_rmqueue(z, order, gfp_mask);
 		if (page)

mm/vmscan.c

@@ -1323,3 +1323,67 @@ static int __init kswapd_init(void)
 }
 
 module_init(kswapd_init)
+
+
+/*
+ * Try to free up some pages from this zone through reclaim.
+ */
+int zone_reclaim(struct zone *zone, unsigned int gfp_mask, unsigned int order)
+{
+	struct scan_control sc;
+	int nr_pages = 1 << order;
+	int total_reclaimed = 0;
+
+	/* The reclaim may sleep, so don't do it if sleep isn't allowed */
+	if (!(gfp_mask & __GFP_WAIT))
+		return 0;
+	if (zone->all_unreclaimable)
+		return 0;
+
+	sc.gfp_mask = gfp_mask;
+	sc.may_writepage = 0;
+	sc.may_swap = 0;
+	sc.nr_mapped = read_page_state(nr_mapped);
+	sc.nr_scanned = 0;
+	sc.nr_reclaimed = 0;
+	/* scan at the highest priority */
+	sc.priority = 0;
+
+	if (nr_pages > SWAP_CLUSTER_MAX)
+		sc.swap_cluster_max = nr_pages;
+	else
+		sc.swap_cluster_max = SWAP_CLUSTER_MAX;
+
+	shrink_zone(zone, &sc);
+	total_reclaimed = sc.nr_reclaimed;
+
+	return total_reclaimed;
+}
+
+asmlinkage long sys_set_zone_reclaim(unsigned int node, unsigned int zone,
+				     unsigned int state)
+{
+	struct zone *z;
+	int i;
+
+	if (node >= MAX_NUMNODES || !node_online(node))
+		return -EINVAL;
+
+	/* This will break if we ever add more zones */
+	if (!(zone & (1<<ZONE_DMA|1<<ZONE_NORMAL|1<<ZONE_HIGHMEM)))
+		return -EINVAL;
+
+	for (i = 0; i < MAX_NR_ZONES; i++) {
+		if (!(zone & 1<<i))
+			continue;
+
+		z = &NODE_DATA(node)->node_zones[i];
+
+		if (state)
+			z->reclaim_pages = 1;
+		else
+			z->reclaim_pages = 0;
+	}
+
+	return 0;
+}