mm: compaction: defer compaction using an exponential backoff when compaction fails

The fragmentation index may indicate that a failure is due to external
fragmentation but after a compaction run completes, it is still possible
for an allocation to fail.  There are two obvious reasons as to why

  o Page migration cannot move all pages so fragmentation remains
  o A suitable page may exist but watermarks are not met

In the event of compaction followed by an allocation failure, this patch
defers further compaction in the zone (1 << compact_defer_shift) times.
If the next compaction attempt also fails, compact_defer_shift is
increased up to a maximum of 6.  If compaction succeeds, the defer
counters are reset again.

The zone that is deferred is the first zone in the zonelist - i.e.  the
preferred zone.  To defer compaction in the other zones, the information
would need to be stored in the zonelist or implemented similar to the
zonelist_cache.  This would impact the fast-paths and is not justified at
this time.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 48 insertions, 0 deletions

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 3719325c609..5ac51552d90 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -22,6 +22,36 @@ 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);
+
+/* Do not skip compaction more than 64 times */
+#define COMPACT_MAX_DEFER_SHIFT 6
+
+/*
+ * Compaction is deferred when compaction fails to result in a page
+ * allocation success. 1 << compact_defer_limit compactions are skipped up
+ * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
+ */
+static inline void defer_compaction(struct zone *zone)
+{
+	zone->compact_considered = 0;
+	zone->compact_defer_shift++;
+
+	if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT)
+		zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT;
+}
+
+/* Returns true if compaction should be skipped this time */
+static inline bool compaction_deferred(struct zone *zone)
+{
+	unsigned long defer_limit = 1UL << zone->compact_defer_shift;
+
+	/* Avoid possible overflow */
+	if (++zone->compact_considered > defer_limit)
+		zone->compact_considered = defer_limit;
+
+	return zone->compact_considered < (1UL << zone->compact_defer_shift);
+}
+
 #else
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask)
@@ -29,6 +59,15 @@ static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	return COMPACT_CONTINUE;
 }
 
+static inline void defer_compaction(struct zone *zone)
+{
+}
+
+static inline bool compaction_deferred(struct zone *zone)
+{
+	return 1;
+}
+
 #endif /* CONFIG_COMPACTION */
 
 #if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index cf9e458e96b..fd55f725a09 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -321,6 +321,15 @@ struct zone {
 	unsigned long		*pageblock_flags;
 #endif /* CONFIG_SPARSEMEM */
 
+#ifdef CONFIG_COMPACTION
+	/*
+	 * On compaction failure, 1<<compact_defer_shift compactions
+	 * are skipped before trying again. The number attempted since
+	 * last failure is tracked with compact_considered.
+	 */
+	unsigned int		compact_considered;
+	unsigned int		compact_defer_shift;
+#endif
 
 	ZONE_PADDING(_pad1_)