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 7a9323a..51a90b7 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -34,20 +34,26 @@
* 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 @@
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 650ba2f..dff7115 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -365,6 +365,7 @@
*/
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 36f0f61..c4b344a 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -695,9 +695,19 @@
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 a13ded1..572b93e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1990,7 +1990,7 @@
if (!order)
return NULL;
- if (compaction_deferred(preferred_zone)) {
+ if (compaction_deferred(preferred_zone, order)) {
*deferred_compaction = true;
return NULL;
}
@@ -2012,6 +2012,8 @@
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 @@
* 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 b2b4c4a..87e4d6a 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2198,7 +2198,7 @@
* 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 */