vmscan: only defer compaction for failed order and higher

Currently a failed order-9 (transparent hugepage) compaction can lead to
memory compaction being temporarily disabled for a memory zone.  Even if
we only need compaction for an order 2 allocation, eg.  for jumbo frames
networking.

The fix is relatively straightforward: keep track of the highest order at
which compaction is succeeding, and only defer compaction for orders at
which compaction is failing.

Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Hillf Danton <dhillf@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 7a9323aef4a34a4165a18cbdd082825f4a3f0d54..51a90b7f2d606a3dcb9bb582cd209add0c429351 100644 (file)
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -34,20 +34,26 @@ extern unsigned long compaction_suitable(struct zone *zone, int order);
  * 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)
+static inline void defer_compaction(struct zone *zone, int order)
 {
        zone->compact_considered = 0;
        zone->compact_defer_shift++;
 
+       if (order < zone->compact_order_failed)
+               zone->compact_order_failed = order;
+
        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)
+static inline bool compaction_deferred(struct zone *zone, int order)
 {
        unsigned long defer_limit = 1UL << zone->compact_defer_shift;
 
+       if (order < zone->compact_order_failed)
+               return false;
+
        /* Avoid possible overflow */
        if (++zone->compact_considered > defer_limit)
                zone->compact_considered = defer_limit;
@@ -73,11 +79,11 @@ static inline unsigned long compaction_suitable(struct zone *zone, int order)
        return COMPACT_SKIPPED;
 }
 
-static inline void defer_compaction(struct zone *zone)
+static inline void defer_compaction(struct zone *zone, int order)
 {
 }
 
-static inline bool compaction_deferred(struct zone *zone)
+static inline bool compaction_deferred(struct zone *zone, int order)
 {
        return 1;
 }

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 650ba2fb3301af5975fa1b027ebdb008cf573e61..dff711509661c8e5eb74fce083eef26e526a783e 100644 (file)
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -365,6 +365,7 @@ struct zone {
         */
        unsigned int            compact_considered;
        unsigned int            compact_defer_shift;
+       int                     compact_order_failed;
 #endif
 
        ZONE_PADDING(_pad1_)

diff --git a/mm/compaction.c b/mm/compaction.c
index 36f0f61f4a240e9de667ff0b4ec68368698352b4..c4b344a95032a0f09cba718daf486a4b0e448e5f 100644 (file)
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -695,9 +695,19 @@ static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
                INIT_LIST_HEAD(&cc->freepages);
                INIT_LIST_HEAD(&cc->migratepages);
 
-               if (cc->order < 0 || !compaction_deferred(zone))
+               if (cc->order < 0 || !compaction_deferred(zone, cc->order))
                        compact_zone(zone, cc);
 
+               if (cc->order > 0) {
+                       int ok = zone_watermark_ok(zone, cc->order,
+                                               low_wmark_pages(zone), 0, 0);
+                       if (ok && cc->order > zone->compact_order_failed)
+                               zone->compact_order_failed = cc->order + 1;
+                       /* Currently async compaction is never deferred. */
+                       else if (!ok && cc->sync)
+                               defer_compaction(zone, cc->order);
+               }
+
                VM_BUG_ON(!list_empty(&cc->freepages));
                VM_BUG_ON(!list_empty(&cc->migratepages));
        }

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a13ded1938f0bacd90a438d983e3d301a649bfe9..572b93ea475c8c57fbf0d1d6be5dd68914352058 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1990,7 +1990,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
        if (!order)
                return NULL;
 
-       if (compaction_deferred(preferred_zone)) {
+       if (compaction_deferred(preferred_zone, order)) {
                *deferred_compaction = true;
                return NULL;
        }
@@ -2012,6 +2012,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
                if (page) {
                        preferred_zone->compact_considered = 0;
                        preferred_zone->compact_defer_shift = 0;
+                       if (order >= preferred_zone->compact_order_failed)
+                               preferred_zone->compact_order_failed = order + 1;
                        count_vm_event(COMPACTSUCCESS);
                        return page;
                }
@@ -2028,7 +2030,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
                 * defer if the failure was a sync compaction failure.
                 */
                if (sync_migration)
-                       defer_compaction(preferred_zone);
+                       defer_compaction(preferred_zone, order);
 
                cond_resched();
        }

diff --git a/mm/vmscan.c b/mm/vmscan.c
index b2b4c4a0ada24491f2dbb6b2c84a54b71a633aa8..87e4d6a6dc11f50e1d96a5aeea8400305c4408fb 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2198,7 +2198,7 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
         * If compaction is deferred, reclaim up to a point where
         * compaction will have a chance of success when re-enabled
         */
-       if (compaction_deferred(zone))
+       if (compaction_deferred(zone, sc->order))
                return watermark_ok;
 
        /* If compaction is not ready to start, keep reclaiming */