mm, compaction: make full priority ignore pageblock suitability

Several people have reported premature OOMs for order-2 allocations
(stack) due to OOM rework in 4.7.  In the scenario (parallel kernel
build and dd writing to two drives) many pageblocks get marked as
Unmovable and compaction free scanner struggles to isolate free pages.
Joonsoo Kim pointed out that the free scanner skips pageblocks that are
not movable to prevent filling them and forcing non-movable allocations
to fallback to other pageblocks.  Such heuristic makes sense to help
prevent long-term fragmentation, but premature OOMs are relatively more
urgent problem.  As a compromise, this patch disables the heuristic only
for the ultimate compaction priority.

Link: http://lkml.kernel.org/r/20160906135258.18335-5-vbabka@suse.cz
Reported-by: Ralf-Peter Rohbeck <Ralf-Peter.Rohbeck@quantum.com>
Reported-by: Arkadiusz Miskiewicz <a.miskiewicz@gmail.com>
Reported-by: Olaf Hering <olaf@aepfle.de>
Suggested-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/compaction.c b/mm/compaction.c
index 29f6c49dc9c213a8c440b2cdcb33f988e21cc090..86d4d0bbfc7c78c10fb40c16a766374212414b45 100644 (file)
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -997,8 +997,12 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 #ifdef CONFIG_COMPACTION
 
 /* Returns true if the page is within a block suitable for migration to */
-static bool suitable_migration_target(struct page *page)
+static bool suitable_migration_target(struct compact_control *cc,
+                                                       struct page *page)
 {
+       if (cc->ignore_block_suitable)
+               return true;
+
        /* If the page is a large free page, then disallow migration */
        if (PageBuddy(page)) {
                /*
@@ -1083,7 +1087,7 @@ static void isolate_freepages(struct compact_control *cc)
                        continue;
 
                /* Check the block is suitable for migration */
-               if (!suitable_migration_target(page))
+               if (!suitable_migration_target(cc, page))
                        continue;
 
                /* If isolation recently failed, do not retry */
@@ -1656,7 +1660,8 @@ static enum compact_result compact_zone_order(struct zone *zone, int order,
                .classzone_idx = classzone_idx,
                .direct_compaction = true,
                .whole_zone = (prio == MIN_COMPACT_PRIORITY),
-               .ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY)
+               .ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY),
+               .ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY)
        };
        INIT_LIST_HEAD(&cc.freepages);
        INIT_LIST_HEAD(&cc.migratepages);

diff --git a/mm/internal.h b/mm/internal.h
index 5214bf8e3171a142e18d0c707d60adc53458fc6c..537ac9951f5fa6256975152fc599ff44cc24ac95 100644 (file)
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -178,6 +178,7 @@ struct compact_control {
        unsigned long last_migrated_pfn;/* Not yet flushed page being freed */
        enum migrate_mode mode;         /* Async or sync migration mode */
        bool ignore_skip_hint;          /* Scan blocks even if marked skip */
+       bool ignore_block_suitable;     /* Scan blocks considered unsuitable */
        bool direct_compaction;         /* False from kcompactd or /proc/... */
        bool whole_zone;                /* Whole zone should/has been scanned */
        int order;                      /* order a direct compactor needs */