From 86a294a81f93d6f36d00ec3ff779d36d218f852d Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 20 May 2016 16:57:12 -0700 Subject: [PATCH] mm, oom, compaction: prevent from should_compact_retry looping for ever for costly orders "mm: consider compaction feedback also for costly allocation" has removed the upper bound for the reclaim/compaction retries based on the number of reclaimed pages for costly orders. While this is desirable the patch did miss a mis interaction between reclaim, compaction and the retry logic. The direct reclaim tries to get zones over min watermark while compaction backs off and returns COMPACT_SKIPPED when all zones are below low watermark + 1< Acked-by: Hillf Danton Acked-by: Vlastimil Babka Cc: David Rientjes Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Mel Gorman Cc: Tetsuo Handa Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 4 ++++ include/linux/mmzone.h | 3 +++ mm/compaction.c | 42 +++++++++++++++++++++++++++++++++++++++--- mm/page_alloc.c | 23 +++++++++++++---------- 4 files changed, 59 insertions(+), 13 deletions(-) diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 8d8c916..a58c852 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -142,6 +142,10 @@ static inline bool compaction_withdrawn(enum compact_result result) return false; } + +bool compaction_zonelist_suitable(struct alloc_context *ac, int order, + int alloc_flags); + extern int kcompactd_run(int nid); extern void kcompactd_stop(int nid); extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c60db20..8dd0333 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -739,6 +739,9 @@ static inline bool is_dev_zone(const struct zone *zone) extern struct mutex zonelists_mutex; void build_all_zonelists(pg_data_t *pgdat, struct zone *zone); void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); +bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, + int classzone_idx, unsigned int alloc_flags, + long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx, unsigned int alloc_flags); diff --git a/mm/compaction.c b/mm/compaction.c index 4af1577..d8a20fc 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1318,7 +1318,8 @@ static enum compact_result compact_finished(struct zone *zone, */ static enum compact_result __compaction_suitable(struct zone *zone, int order, unsigned int alloc_flags, - int classzone_idx) + int classzone_idx, + unsigned long wmark_target) { int fragindex; unsigned long watermark; @@ -1341,7 +1342,8 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order, * allocated and for a short time, the footprint is higher */ watermark += (2UL << order); - if (!zone_watermark_ok(zone, 0, watermark, classzone_idx, alloc_flags)) + if (!__zone_watermark_ok(zone, 0, watermark, classzone_idx, + alloc_flags, wmark_target)) return COMPACT_SKIPPED; /* @@ -1368,7 +1370,8 @@ enum compact_result compaction_suitable(struct zone *zone, int order, { enum compact_result ret; - ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx); + ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx, + zone_page_state(zone, NR_FREE_PAGES)); trace_mm_compaction_suitable(zone, order, ret); if (ret == COMPACT_NOT_SUITABLE_ZONE) ret = COMPACT_SKIPPED; @@ -1376,6 +1379,39 @@ enum compact_result compaction_suitable(struct zone *zone, int order, return ret; } +bool compaction_zonelist_suitable(struct alloc_context *ac, int order, + int alloc_flags) +{ + struct zone *zone; + struct zoneref *z; + + /* + * Make sure at least one zone would pass __compaction_suitable if we continue + * retrying the reclaim. + */ + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, + ac->nodemask) { + unsigned long available; + enum compact_result compact_result; + + /* + * Do not consider all the reclaimable memory because we do not + * want to trash just for a single high order allocation which + * is even not guaranteed to appear even if __compaction_suitable + * is happy about the watermark check. + */ + available = zone_reclaimable_pages(zone) / order; + available += zone_page_state_snapshot(zone, NR_FREE_PAGES); + compact_result = __compaction_suitable(zone, order, alloc_flags, + ac_classzone_idx(ac), available); + if (compact_result != COMPACT_SKIPPED && + compact_result != COMPACT_NOT_SUITABLE_ZONE) + return true; + } + + return false; +} + static enum compact_result compact_zone(struct zone *zone, struct compact_control *cc) { enum compact_result ret; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index dea406a..089f760 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2750,10 +2750,9 @@ static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) * one free page of a suitable size. Checking now avoids taking the zone lock * to check in the allocation paths if no pages are free. */ -static bool __zone_watermark_ok(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx, - unsigned int alloc_flags, - long free_pages) +bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, + int classzone_idx, unsigned int alloc_flags, + long free_pages) { long min = mark; int o; @@ -3256,8 +3255,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, } static inline bool -should_compact_retry(unsigned int order, enum compact_result compact_result, - enum migrate_mode *migrate_mode, +should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, + enum compact_result compact_result, enum migrate_mode *migrate_mode, int compaction_retries) { int max_retries = MAX_COMPACT_RETRIES; @@ -3281,9 +3280,11 @@ should_compact_retry(unsigned int order, enum compact_result compact_result, /* * make sure the compaction wasn't deferred or didn't bail out early * due to locks contention before we declare that we should give up. + * But do not retry if the given zonelist is not suitable for + * compaction. */ if (compaction_withdrawn(compact_result)) - return true; + return compaction_zonelist_suitable(ac, order, alloc_flags); /* * !costly requests are much more important than __GFP_REPEAT @@ -3311,7 +3312,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, } static inline bool -should_compact_retry(unsigned int order, enum compact_result compact_result, +should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags, + enum compact_result compact_result, enum migrate_mode *migrate_mode, int compaction_retries) { @@ -3706,8 +3708,9 @@ retry: * of free memory (see __compaction_suitable) */ if (did_some_progress > 0 && - should_compact_retry(order, compact_result, - &migration_mode, compaction_retries)) + should_compact_retry(ac, order, alloc_flags, + compact_result, &migration_mode, + compaction_retries)) goto retry; /* Reclaim has failed us, start killing things */ -- 2.7.4