mm: vmscan: reclaim order-0 and use compaction instead of lumpy reclaim

Lumpy reclaim is disruptive.  It reclaims a large number of pages and
ignores the age of the pages it reclaims.  This can incur significant
stalls and potentially increase the number of major faults.

Compaction has reached the point where it is considered reasonably stable
(meaning it has passed a lot of testing) and is a potential candidate for
displacing lumpy reclaim.  This patch introduces an alternative to lumpy
reclaim whe compaction is available called reclaim/compaction.  The basic
operation is very simple - instead of selecting a contiguous range of
pages to reclaim, a number of order-0 pages are reclaimed and then
compaction is later by either kswapd (compact_zone_order()) or direct
compaction (__alloc_pages_direct_compact()).

[[email protected]: fix build]
[[email protected]: use conventional task_struct naming]
Signed-off-by: Mel Gorman <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: KOSAKI Motohiro <[email protected]>
Cc: Rik van Riel <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Cc: Andy Whitcroft <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/compaction.h

@@ -22,6 +22,9 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask);
+extern unsigned long compaction_suitable(struct zone *zone, int order);
+extern unsigned long compact_zone_order(struct zone *zone, int order,
+						gfp_t gfp_mask);
 
 /* Do not skip compaction more than 64 times */
 #define COMPACT_MAX_DEFER_SHIFT 6
@@ -59,6 +62,17 @@ static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	return COMPACT_CONTINUE;
 }
 
+static inline unsigned long compaction_suitable(struct zone *zone, int order)
+{
+	return COMPACT_SKIPPED;
+}
+
+static inline unsigned long compact_zone_order(struct zone *zone, int order,
+						gfp_t gfp_mask)
+{
+	return 0;
+}
+
 static inline void defer_compaction(struct zone *zone)
 {
 }

include/linux/kernel.h

@@ -600,6 +600,13 @@ struct sysinfo {
 #define NUMA_BUILD 0
 #endif
 
+/* This helps us avoid #ifdef CONFIG_COMPACTION */
+#ifdef CONFIG_COMPACTION
+#define COMPACTION_BUILD 1
+#else
+#define COMPACTION_BUILD 0
+#endif
+
 /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD

mm/compaction.c

@@ -384,10 +384,62 @@ static int compact_finished(struct zone *zone,
 	return COMPACT_CONTINUE;
 }
 
+/*
+ * compaction_suitable: Is this suitable to run compaction on this zone now?
+ * Returns
+ *   COMPACT_SKIPPED  - If there are too few free pages for compaction
+ *   COMPACT_PARTIAL  - If the allocation would succeed without compaction
+ *   COMPACT_CONTINUE - If compaction should run now
+ */
+unsigned long compaction_suitable(struct zone *zone, int order)
+{
+	int fragindex;
+	unsigned long watermark;
+
+	/*
+	 * Watermarks for order-0 must be met for compaction. Note the 2UL.
+	 * This is because during migration, copies of pages need to be
+	 * allocated and for a short time, the footprint is higher
+	 */
+	watermark = low_wmark_pages(zone) + (2UL << order);
+	if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
+		return COMPACT_SKIPPED;
+
+	/*
+	 * fragmentation index determines if allocation failures are due to
+	 * low memory or external fragmentation
+	 *
+	 * index of -1 implies allocations might succeed dependingon watermarks
+	 * index towards 0 implies failure is due to lack of memory
+	 * index towards 1000 implies failure is due to fragmentation
+	 *
+	 * Only compact if a failure would be due to fragmentation.
+	 */
+	fragindex = fragmentation_index(zone, order);
+	if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
+		return COMPACT_SKIPPED;
+
+	if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0))
+		return COMPACT_PARTIAL;
+
+	return COMPACT_CONTINUE;
+}
+
 static int compact_zone(struct zone *zone, struct compact_control *cc)
 {
 	int ret;
 
+	ret = compaction_suitable(zone, cc->order);
+	switch (ret) {
+	case COMPACT_PARTIAL:
+	case COMPACT_SKIPPED:
+		/* Compaction is likely to fail */
+		return ret;
+	case COMPACT_CONTINUE:
+		/* Fall through to compaction */
+		;
+	}
+
 	/* Setup to move all movable pages to the end of the zone */
 	cc->migrate_pfn = zone->zone_start_pfn;
 	cc->free_pfn = cc->migrate_pfn + zone->spanned_pages;
@@ -429,7 +481,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	return ret;
 }
 
-static unsigned long compact_zone_order(struct zone *zone,
+unsigned long compact_zone_order(struct zone *zone,
 						int order, gfp_t gfp_mask)
 {
 	struct compact_control cc = {
@@ -462,7 +514,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
 	int may_perform_io = gfp_mask & __GFP_IO;
-	unsigned long watermark;
 	struct zoneref *z;
 	struct zone *zone;
 	int rc = COMPACT_SKIPPED;
@@ -480,43 +531,13 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	/* Compact each zone in the list */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
 								nodemask) {
-		int fragindex;
 		int status;
 
-		/*
-		 * Watermarks for order-0 must be met for compaction. Note
-		 * the 2UL. This is because during migration, copies of
-		 * pages need to be allocated and for a short time, the
-		 * footprint is higher
-		 */
-		watermark = low_wmark_pages(zone) + (2UL << order);
-		if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
-			continue;
-
-		/*
-		 * fragmentation index determines if allocation failures are
-		 * due to low memory or external fragmentation
-		 *
-		 * index of -1 implies allocations might succeed depending
-		 * 	on watermarks
-		 * index towards 0 implies failure is due to lack of memory
-		 * index towards 1000 implies failure is due to fragmentation
-		 *
-		 * Only compact if a failure would be due to fragmentation.
-		 */
-		fragindex = fragmentation_index(zone, order);
-		if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
-			continue;
-
-		if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0)) {
-			rc = COMPACT_PARTIAL;
-			break;
-		}
-
 		status = compact_zone_order(zone, order, gfp_mask);
 		rc = max(status, rc);
 
-		if (zone_watermark_ok(zone, order, watermark, 0, 0))
+		/* If a normal allocation would succeed, stop compacting */
+		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
 			break;
 	}
 

mm/migrate.c

@@ -639,6 +639,23 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	if (!trylock_page(page)) {
 		if (!force)
 			goto move_newpage;
+
+		/*
+		 * It's not safe for direct compaction to call lock_page.
+		 * For example, during page readahead pages are added locked
+		 * to the LRU. Later, when the IO completes the pages are
+		 * marked uptodate and unlocked. However, the queueing
+		 * could be merging multiple pages for one bio (e.g.
+		 * mpage_readpages). If an allocation happens for the
+		 * second or third page, the process can end up locking
+		 * the same page twice and deadlocking. Rather than
+		 * trying to be clever about what pages can be locked,
+		 * avoid the use of lock_page for direct compaction
+		 * altogether.
+		 */
+		if (current->flags & PF_MEMALLOC)
+			goto move_newpage;
+
 		lock_page(page);
 	}
 

mm/page_alloc.c

@@ -1815,12 +1815,15 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	int migratetype, unsigned long *did_some_progress)
 {
 	struct page *page;
+	struct task_struct *tsk = current;
 
 	if (!order || compaction_deferred(preferred_zone))
 		return NULL;
 
+	tsk->flags |= PF_MEMALLOC;
 	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
 								nodemask);
+	tsk->flags &= ~PF_MEMALLOC;
 	if (*did_some_progress != COMPACT_SKIPPED) {
 
 		/* Page migration frees to the PCP lists but we want merging */
@@ -2121,6 +2124,19 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 		/* Wait for some write requests to complete then retry */
 		wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
 		goto rebalance;
+	} else {
+		/*
+		 * High-order allocations do not necessarily loop after
+		 * direct reclaim and reclaim/compaction depends on compaction
+		 * being called after reclaim so call directly if necessary
+		 */
+		page = __alloc_pages_direct_compact(gfp_mask, order,
+					zonelist, high_zoneidx,
+					nodemask,
+					alloc_flags, preferred_zone,
+					migratetype, &did_some_progress);
+		if (page)
+			goto got_pg;
 	}
 
 nopage: