From: Michal Hocko <mhocko@xxxxxxxx>
Subject: mm, compaction: distinguish COMPACT_DEFERRED from COMPACT_SKIPPED
try_to_compact_pages() can currently return COMPACT_SKIPPED even when the
compaction is defered for some zone just because zone DMA is skipped in
99% of cases due to watermark checks. This makes COMPACT_DEFERRED
basically unusable for the page allocator as a feedback mechanism.
Make sure we distinguish those two states properly and switch their
ordering in the enum. This would mean that the COMPACT_SKIPPED will be
returned only when all eligible zones are skipped.
As a result COMPACT_DEFERRED handling for THP in __alloc_pages_slowpath
will be more precise and we would bail out rather than reclaim.
Signed-off-by: Michal Hocko <mhocko@xxxxxxxx>
Acked-by: Vlastimil Babka <vbabka@xxxxxxx>
Acked-by: Hillf Danton <hillf.zj@xxxxxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Joonsoo Kim <js1304@xxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx>
Cc: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/compaction.h | 7 +++++--
include/trace/events/compaction.h | 2 +-
mm/compaction.c | 8 +++++---
3 files changed, 11 insertions(+), 6 deletions(-)
diff -puN include/linux/compaction.h~mm-compaction-distinguish-compact_deferred-from-compact_skipped include/linux/compaction.h
--- a/include/linux/compaction.h~mm-compaction-distinguish-compact_deferred-from-compact_skipped
+++ a/include/linux/compaction.h
@@ -4,13 +4,16 @@
/* Return values for compact_zone() and try_to_compact_pages() */
/* When adding new states, please adjust include/trace/events/compaction.h */
enum compact_result {
- /* compaction didn't start as it was deferred due to past failures */
- COMPACT_DEFERRED,
/*
* compaction didn't start as it was not possible or direct reclaim
* was more suitable
*/
COMPACT_SKIPPED,
+ /* compaction didn't start as it was deferred due to past failures */
+ COMPACT_DEFERRED,
+ /* compaction not active last round */
+ COMPACT_INACTIVE = COMPACT_DEFERRED,
+
/* compaction should continue to another pageblock */
COMPACT_CONTINUE,
/*
diff -puN include/trace/events/compaction.h~mm-compaction-distinguish-compact_deferred-from-compact_skipped include/trace/events/compaction.h
--- a/include/trace/events/compaction.h~mm-compaction-distinguish-compact_deferred-from-compact_skipped
+++ a/include/trace/events/compaction.h
@@ -10,8 +10,8 @@
#include <trace/events/mmflags.h>
#define COMPACTION_STATUS \
- EM( COMPACT_DEFERRED, "deferred") \
EM( COMPACT_SKIPPED, "skipped") \
+ EM( COMPACT_DEFERRED, "deferred") \
EM( COMPACT_CONTINUE, "continue") \
EM( COMPACT_PARTIAL, "partial") \
EM( COMPACT_COMPLETE, "complete") \
diff -puN mm/compaction.c~mm-compaction-distinguish-compact_deferred-from-compact_skipped mm/compaction.c
--- a/mm/compaction.c~mm-compaction-distinguish-compact_deferred-from-compact_skipped
+++ a/mm/compaction.c
@@ -1578,7 +1578,7 @@ enum compact_result try_to_compact_pages
int may_perform_io = gfp_mask & __GFP_IO;
struct zoneref *z;
struct zone *zone;
- enum compact_result rc = COMPACT_DEFERRED;
+ enum compact_result rc = COMPACT_SKIPPED;
int all_zones_contended = COMPACT_CONTENDED_LOCK; /* init for &= op */
*contended = COMPACT_CONTENDED_NONE;
@@ -1595,8 +1595,10 @@ enum compact_result try_to_compact_pages
enum compact_result status;
int zone_contended;
- if (compaction_deferred(zone, order))
+ if (compaction_deferred(zone, order)) {
+ rc = max_t(enum compact_result, COMPACT_DEFERRED, rc);
continue;
+ }
status = compact_zone_order(zone, order, gfp_mask, mode,
&zone_contended, alloc_flags,
@@ -1667,7 +1669,7 @@ break_loop:
* If at least one zone wasn't deferred or skipped, we report if all
* zones that were tried were lock contended.
*/
- if (rc > COMPACT_SKIPPED && all_zones_contended)
+ if (rc > COMPACT_INACTIVE && all_zones_contended)
*contended = COMPACT_CONTENDED_LOCK;
return rc;
_
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
