Lumpy Reclaim V4

When we are out of memory of a suitable size we enter reclaim.  The current
reclaim algorithm targets pages in LRU order, which is great for fairness at
order-0 but highly unsuitable if you desire pages at higher orders.  To get
pages of higher order we must shoot down a very high proportion of memory;
>95% in a lot of cases.

This patch set adds a lumpy reclaim algorithm to the allocator.  It targets
groups of pages at the specified order anchored at the end of the active and
inactive lists.  This encourages groups of pages at the requested orders to
move from active to inactive, and active to free lists.  This behaviour is
only triggered out of direct reclaim when higher order pages have been
requested.

This patch set is particularly effective when utilised with an
anti-fragmentation scheme which groups pages of similar reclaimability
together.

This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms
the foundation.  Credit to Mel Gorman for sanitity checking.

Mel said:

  The patches have an application with hugepage pool resizing.

  When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can
  be resized with greater reliability.  Testing on a desktop machine with 2GB
  of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own
  was very slow as the success rate was quite low.  Without lumpy-reclaim,
  each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages.
  With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical.

[akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup]
[bunk@stusta.de: static declarations for internal functions]
[a.p.zijlstra@chello.nl: initial lumpy V2 implementation]
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

fs/buffer.c

@@ -356,7 +356,7 @@ static void free_more_memory(void)
 	for_each_online_pgdat(pgdat) {
 		zones = pgdat->node_zonelists[gfp_zone(GFP_NOFS)].zones;
 		if (*zones)
-			try_to_free_pages(zones, GFP_NOFS);
+			try_to_free_pages(zones, 0, GFP_NOFS);
 	}
 }
 

include/linux/mmzone.h

@@ -24,6 +24,14 @@
 #endif
 #define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1))
 
+/*
+ * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed
+ * costly to service.  That is between allocation orders which should
+ * coelesce naturally under reasonable reclaim pressure and those which
+ * will not.
+ */
+#define PAGE_ALLOC_COSTLY_ORDER 3
+
 struct free_area {
 	struct list_head	free_list;
 	unsigned long		nr_free;

include/linux/swap.h

@@ -188,7 +188,8 @@ extern int rotate_reclaimable_page(struct page *page);
 extern void swap_setup(void);
 
 /* linux/mm/vmscan.c */
-extern unsigned long try_to_free_pages(struct zone **, gfp_t);
+extern unsigned long try_to_free_pages(struct zone **zones, int order,
+					gfp_t gfp_mask);
 extern unsigned long shrink_all_memory(unsigned long nr_pages);
 extern int vm_swappiness;
 extern int remove_mapping(struct address_space *mapping, struct page *page);

mm/page_alloc.c

@@ -1333,7 +1333,7 @@ nofail_alloc:
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
-	did_some_progress = try_to_free_pages(zonelist->zones, gfp_mask);
+	did_some_progress = try_to_free_pages(zonelist->zones, order, gfp_mask);
 
 	p->reclaim_state = NULL;
 	p->flags &= ~PF_MEMALLOC;
@@ -1370,7 +1370,8 @@ nofail_alloc:
 	 */
 	do_retry = 0;
 	if (!(gfp_mask & __GFP_NORETRY)) {
-		if ((order <= 3) || (gfp_mask & __GFP_REPEAT))
+		if ((order <= PAGE_ALLOC_COSTLY_ORDER) ||
+						(gfp_mask & __GFP_REPEAT))
 			do_retry = 1;
 		if (gfp_mask & __GFP_NOFAIL)
 			do_retry = 1;

mm/vmscan.c

@@ -66,6 +66,8 @@ struct scan_control {
 	int swappiness;
 
 	int all_unreclaimable;
+
+	int order;
 };
 
 /*
@@ -481,7 +483,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 		referenced = page_referenced(page, 1);
 		/* In active use or really unfreeable?  Activate it. */
-		if (referenced && page_mapping_inuse(page))
+		if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
+					referenced && page_mapping_inuse(page))
 			goto activate_locked;
 
 #ifdef CONFIG_SWAP
@@ -514,7 +517,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		}
 
 		if (PageDirty(page)) {
-			if (referenced)
+			if (sc->order <= PAGE_ALLOC_COSTLY_ORDER && referenced)
 				goto keep_locked;
 			if (!may_enter_fs)
 				goto keep_locked;
@@ -598,6 +601,51 @@ keep:
 	return nr_reclaimed;
 }
 
+/* LRU Isolation modes. */
+#define ISOLATE_INACTIVE 0	/* Isolate inactive pages. */
+#define ISOLATE_ACTIVE 1	/* Isolate active pages. */
+#define ISOLATE_BOTH 2		/* Isolate both active and inactive pages. */
+
+/*
+ * Attempt to remove the specified page from its LRU.  Only take this page
+ * if it is of the appropriate PageActive status.  Pages which are being
+ * freed elsewhere are also ignored.
+ *
+ * page:	page to consider
+ * mode:	one of the LRU isolation modes defined above
+ *
+ * returns 0 on success, -ve errno on failure.
+ */
+static int __isolate_lru_page(struct page *page, int mode)
+{
+	int ret = -EINVAL;
+
+	/* Only take pages on the LRU. */
+	if (!PageLRU(page))
+		return ret;
+
+	/*
+	 * When checking the active state, we need to be sure we are
+	 * dealing with comparible boolean values.  Take the logical not
+	 * of each.
+	 */
+	if (mode != ISOLATE_BOTH && (!PageActive(page) != !mode))
+		return ret;
+
+	ret = -EBUSY;
+	if (likely(get_page_unless_zero(page))) {
+		/*
+		 * Be careful not to clear PageLRU until after we're
+		 * sure the page is not being freed elsewhere -- the
+		 * page release code relies on it.
+		 */
+		ClearPageLRU(page);
+		ret = 0;
+	}
+
+	return ret;
+}
+
 /*
  * zone->lru_lock is heavily contended.  Some of the functions that
  * shrink the lists perform better by taking out a batch of pages
@@ -612,44 +660,114 @@ keep:
  * @src:	The LRU list to pull pages off.
  * @dst:	The temp list to put pages on to.
  * @scanned:	The number of pages that were scanned.
+ * @order:	The caller's attempted allocation order
+ * @mode:	One of the LRU isolation modes
  *
  * returns how many pages were moved onto *@dst.
  */
 static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		struct list_head *src, struct list_head *dst,
-		unsigned long *scanned)
+		unsigned long *scanned, int order, int mode)
 {
 	unsigned long nr_taken = 0;
-	struct page *page;
 	unsigned long scan;
 
 	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
-		struct list_head *target;
+		struct page *page;
+		unsigned long pfn;
+		unsigned long end_pfn;
+		unsigned long page_pfn;
+		int zone_id;
+
 		page = lru_to_page(src);
 		prefetchw_prev_lru_page(page, src, flags);
 
 		VM_BUG_ON(!PageLRU(page));
 
-		list_del(&page->lru);
-		target = src;
-		if (likely(get_page_unless_zero(page))) {
-			/*
-			 * Be careful not to clear PageLRU until after we're
-			 * sure the page is not being freed elsewhere -- the
-			 * page release code relies on it.
-			 */
-			ClearPageLRU(page);
-			target = dst;
+		switch (__isolate_lru_page(page, mode)) {
+		case 0:
+			list_move(&page->lru, dst);
 			nr_taken++;
-		} /* else it is being freed elsewhere */
+			break;
 
-		list_add(&page->lru, target);
+		case -EBUSY:
+			/* else it is being freed elsewhere */
+			list_move(&page->lru, src);
+			continue;
+
+		default:
+			BUG();
+		}
+
+		if (!order)
+			continue;
+
+		/*
+		 * Attempt to take all pages in the order aligned region
+		 * surrounding the tag page.  Only take those pages of
+		 * the same active state as that tag page.  We may safely
+		 * round the target page pfn down to the requested order
+		 * as the mem_map is guarenteed valid out to MAX_ORDER,
+		 * where that page is in a different zone we will detect
+		 * it from its zone id and abort this block scan.
+		 */
+		zone_id = page_zone_id(page);
+		page_pfn = page_to_pfn(page);
+		pfn = page_pfn & ~((1 << order) - 1);
+		end_pfn = pfn + (1 << order);
+		for (; pfn < end_pfn; pfn++) {
+			struct page *cursor_page;
+
+			/* The target page is in the block, ignore it. */
+			if (unlikely(pfn == page_pfn))
+				continue;
+
+			/* Avoid holes within the zone. */
+			if (unlikely(!pfn_valid_within(pfn)))
+				break;
+
+			cursor_page = pfn_to_page(pfn);
+			/* Check that we have not crossed a zone boundary. */
+			if (unlikely(page_zone_id(cursor_page) != zone_id))
+				continue;
+			switch (__isolate_lru_page(cursor_page, mode)) {
+			case 0:
+				list_move(&cursor_page->lru, dst);
+				nr_taken++;
+				scan++;
+				break;
+
+			case -EBUSY:
+				/* else it is being freed elsewhere */
+				list_move(&cursor_page->lru, src);
+			default:
+				break;
+			}
+		}
 	}
 
 	*scanned = scan;
 	return nr_taken;
 }
 
+/*
+ * clear_active_flags() is a helper for shrink_active_list(), clearing
+ * any active bits from the pages in the list.
+ */
+static unsigned long clear_active_flags(struct list_head *page_list)
+{
+	int nr_active = 0;
+	struct page *page;
+
+	list_for_each_entry(page, page_list, lru)
+		if (PageActive(page)) {
+			ClearPageActive(page);
+			nr_active++;
+		}
+
+	return nr_active;
+}
+
 /*
  * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
  * of reclaimed pages
@@ -671,11 +789,18 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		unsigned long nr_taken;
 		unsigned long nr_scan;
 		unsigned long nr_freed;
+		unsigned long nr_active;
 
 		nr_taken = isolate_lru_pages(sc->swap_cluster_max,
-					     &zone->inactive_list,
-					     &page_list, &nr_scan);
-		__mod_zone_page_state(zone, NR_INACTIVE, -nr_taken);
+			     &zone->inactive_list,
+			     &page_list, &nr_scan, sc->order,
+			     (sc->order > PAGE_ALLOC_COSTLY_ORDER)?
+					     ISOLATE_BOTH : ISOLATE_INACTIVE);
+		nr_active = clear_active_flags(&page_list);
+
+		__mod_zone_page_state(zone, NR_ACTIVE, -nr_active);
+		__mod_zone_page_state(zone, NR_INACTIVE,
+						-(nr_taken - nr_active));
 		zone->pages_scanned += nr_scan;
 		spin_unlock_irq(&zone->lru_lock);
 
@@ -820,7 +945,7 @@ force_reclaim_mapped:
 	lru_add_drain();
 	spin_lock_irq(&zone->lru_lock);
 	pgmoved = isolate_lru_pages(nr_pages, &zone->active_list,
-				    &l_hold, &pgscanned);
+			    &l_hold, &pgscanned, sc->order, ISOLATE_ACTIVE);
 	zone->pages_scanned += pgscanned;
 	__mod_zone_page_state(zone, NR_ACTIVE, -pgmoved);
 	spin_unlock_irq(&zone->lru_lock);
@@ -1011,7 +1136,7 @@ static unsigned long shrink_zones(int priority, struct zone **zones,
  * holds filesystem locks which prevent writeout this might not work, and the
  * allocation attempt will fail.
  */
-unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
+unsigned long try_to_free_pages(struct zone **zones, int order, gfp_t gfp_mask)
 {
 	int priority;
 	int ret = 0;
@@ -1026,6 +1151,7 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.may_swap = 1,
 		.swappiness = vm_swappiness,
+		.order = order,
 	};
 
 	count_vm_event(ALLOCSTALL);
@@ -1131,6 +1257,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 		.may_swap = 1,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.swappiness = vm_swappiness,
+		.order = order,
 	};
 	/*
 	 * temp_priority is used to remember the scanning priority at which