From c603844bdcb5238980de8d58b393f52d7729d651 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 19 May 2016 17:13:38 -0700 Subject: mm, page_alloc: convert alloc_flags to unsigned alloc_flags is a bitmask of flags but it is signed which does not necessarily generate the best code depending on the compiler. Even without an impact, it makes more sense that this be unsigned. Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Jesper Dangaard Brouer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/compaction.h') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index d7c8de583a23..242b660f64e6 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -39,12 +39,12 @@ extern int sysctl_compact_unevictable_allowed; extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order, - int alloc_flags, const struct alloc_context *ac, - enum migrate_mode mode, int *contended); + unsigned int alloc_flags, const struct alloc_context *ac, + enum migrate_mode mode, int *contended); extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order, - int alloc_flags, int classzone_idx); + unsigned int alloc_flags, int classzone_idx); extern void defer_compaction(struct zone *zone, int order); extern bool compaction_deferred(struct zone *zone, int order); -- cgit v1.2.3 From ea7ab982b6bdb7ce218fd3a7850bb2e2b414fdd0 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 20 May 2016 16:56:38 -0700 Subject: mm, compaction: change COMPACT_ constants into enum Compaction code is doing weird dances between COMPACT_FOO -> int -> unsigned long But there doesn't seem to be any reason for that. All functions which return/use one of those constants are not expecting any other value so it really makes sense to define an enum for them and make it clear that no other values are expected. This is a pure cleanup and shouldn't introduce any functional changes. Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Acked-by: Hillf Danton 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 | 45 +++++++++++++++++++++++++++------------------ 1 file changed, 27 insertions(+), 18 deletions(-) (limited to 'include/linux/compaction.h') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 242b660f64e6..706cbf00e919 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -2,21 +2,29 @@ #define _LINUX_COMPACTION_H /* Return values for compact_zone() and try_to_compact_pages() */ -/* compaction didn't start as it was deferred due to past failures */ -#define COMPACT_DEFERRED 0 -/* compaction didn't start as it was not possible or direct reclaim was more suitable */ -#define COMPACT_SKIPPED 1 -/* compaction should continue to another pageblock */ -#define COMPACT_CONTINUE 2 -/* direct compaction partially compacted a zone and there are suitable pages */ -#define COMPACT_PARTIAL 3 -/* The full zone was compacted */ -#define COMPACT_COMPLETE 4 -/* For more detailed tracepoint output */ -#define COMPACT_NO_SUITABLE_PAGE 5 -#define COMPACT_NOT_SUITABLE_ZONE 6 -#define COMPACT_CONTENDED 7 /* 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 should continue to another pageblock */ + COMPACT_CONTINUE, + /* + * direct compaction partially compacted a zone and there are suitable + * pages + */ + COMPACT_PARTIAL, + /* The full zone was compacted */ + COMPACT_COMPLETE, + /* For more detailed tracepoint output */ + COMPACT_NO_SUITABLE_PAGE, + COMPACT_NOT_SUITABLE_ZONE, + COMPACT_CONTENDED, +}; /* Used to signal whether compaction detected need_sched() or lock contention */ /* No contention detected */ @@ -38,12 +46,13 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, extern int sysctl_compact_unevictable_allowed; extern int fragmentation_index(struct zone *zone, unsigned int order); -extern unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order, +extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, + unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum migrate_mode mode, int *contended); extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); -extern unsigned long compaction_suitable(struct zone *zone, int order, +extern enum compact_result compaction_suitable(struct zone *zone, int order, unsigned int alloc_flags, int classzone_idx); extern void defer_compaction(struct zone *zone, int order); @@ -57,7 +66,7 @@ extern void kcompactd_stop(int nid); extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx); #else -static inline unsigned long try_to_compact_pages(gfp_t gfp_mask, +static inline enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, int alloc_flags, const struct alloc_context *ac, enum migrate_mode mode, int *contended) @@ -73,7 +82,7 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat) { } -static inline unsigned long compaction_suitable(struct zone *zone, int order, +static inline enum compact_result compaction_suitable(struct zone *zone, int order, int alloc_flags, int classzone_idx) { return COMPACT_SKIPPED; -- cgit v1.2.3 From 1d4746d395975e0ff5103e20ab169d1a95b4ef9e Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 20 May 2016 16:56:44 -0700 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 Acked-by: Vlastimil Babka Acked-by: Hillf Danton 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 | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux/compaction.h') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 706cbf00e919..11f228712ed5 100644 --- a/include/linux/compaction.h +++ b/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, /* -- cgit v1.2.3 From c8f7de0bfae36e8532e5e25a39d15407f02aca78 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 20 May 2016 16:56:47 -0700 Subject: mm, compaction: distinguish between full and partial COMPACT_COMPLETE COMPACT_COMPLETE now means that compaction and free scanner met. This is not very useful information if somebody just wants to use this feedback and make any decisions based on that. The current caller might be a poor guy who just happened to scan tiny portion of the zone and that could be the reason no suitable pages were compacted. Make sure we distinguish the full and partial zone walks. Consumers should treat COMPACT_PARTIAL_SKIPPED as a potential success and be optimistic in retrying. The existing users of COMPACT_COMPLETE are conservatively changed to use COMPACT_PARTIAL_SKIPPED as well but some of them should be probably reconsidered and only defer the compaction only for COMPACT_COMPLETE with the new semantic. This patch shouldn't introduce any functional changes. Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Acked-by: Hillf Danton 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 | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux/compaction.h') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 11f228712ed5..9b37f9d3f7a8 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -21,7 +21,15 @@ enum compact_result { * pages */ COMPACT_PARTIAL, - /* The full zone was compacted */ + /* + * direct compaction has scanned part of the zone but wasn't successfull + * to compact suitable pages. + */ + COMPACT_PARTIAL_SKIPPED, + /* + * The full zone was compacted scanned but wasn't successfull to compact + * suitable pages. + */ COMPACT_COMPLETE, /* For more detailed tracepoint output */ COMPACT_NO_SUITABLE_PAGE, -- cgit v1.2.3 From 4f9a358c36fcdad3ea1db263ec4d484a70ad543e Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 20 May 2016 16:56:50 -0700 Subject: mm, compaction: update compaction_result ordering compaction_result will be used as the primary feedback channel for compaction users. At the same time try_to_compact_pages (and potentially others) assume a certain ordering where a more specific feedback takes precendence. This gets a bit awkward when we have conflicting feedback from different zones. E.g one returing COMPACT_COMPLETE meaning the full zone has been scanned without any outcome while other returns with COMPACT_PARTIAL aka made some progress. The caller should get COMPACT_PARTIAL because that means that the compaction still can make some progress. The same applies for COMPACT_PARTIAL vs COMPACT_PARTIAL_SKIPPED. Reorder PARTIAL to be the largest one so the larger the value is the more progress we have done. Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Acked-by: Hillf Danton 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 | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'include/linux/compaction.h') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 9b37f9d3f7a8..ff39fa0a1ede 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -4,6 +4,8 @@ /* Return values for compact_zone() and try_to_compact_pages() */ /* When adding new states, please adjust include/trace/events/compaction.h */ enum compact_result { + /* For more detailed tracepoint output - internal to compaction */ + COMPACT_NOT_SUITABLE_ZONE, /* * compaction didn't start as it was not possible or direct reclaim * was more suitable @@ -11,30 +13,34 @@ enum compact_result { 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, + /* For more detailed tracepoint output - internal to compaction */ + COMPACT_NO_SUITABLE_PAGE, /* compaction should continue to another pageblock */ COMPACT_CONTINUE, + /* - * direct compaction partially compacted a zone and there are suitable - * pages + * The full zone was compacted scanned but wasn't successfull to compact + * suitable pages. */ - COMPACT_PARTIAL, + COMPACT_COMPLETE, /* * direct compaction has scanned part of the zone but wasn't successfull * to compact suitable pages. */ COMPACT_PARTIAL_SKIPPED, + + /* compaction terminated prematurely due to lock contentions */ + COMPACT_CONTENDED, + /* - * The full zone was compacted scanned but wasn't successfull to compact - * suitable pages. + * direct compaction partially compacted a zone and there might be + * suitable pages */ - COMPACT_COMPLETE, - /* For more detailed tracepoint output */ - COMPACT_NO_SUITABLE_PAGE, - COMPACT_NOT_SUITABLE_ZONE, - COMPACT_CONTENDED, + COMPACT_PARTIAL, }; /* Used to signal whether compaction detected need_sched() or lock contention */ -- cgit v1.2.3 From cab1802b5f0dddea30547a7451fda8c7e4c593f0 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 20 May 2016 16:56:56 -0700 Subject: mm, compaction: abstract compaction feedback to helpers Compaction can provide a wild variation of feedback to the caller. Many of them are implementation specific and the caller of the compaction (especially the page allocator) shouldn't be bound to specifics of the current implementation. This patch abstracts the feedback into three basic types: - compaction_made_progress - compaction was active and made some progress. - compaction_failed - compaction failed and further attempts to invoke it would most probably fail and therefore it is not worth retrying - compaction_withdrawn - compaction wasn't invoked for an implementation specific reasons. In the current implementation it means that the compaction was deferred, contended or the page scanners met too early without any progress. Retrying is still worthwhile. [vbabka@suse.cz: do not change thp back off behavior] [akpm@linux-foundation.org: fix typo in comment, per Hillf] Signed-off-by: Michal Hocko 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 | 79 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 79 insertions(+) (limited to 'include/linux/compaction.h') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index ff39fa0a1ede..8d8c916fe67a 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -78,6 +78,70 @@ extern void compaction_defer_reset(struct zone *zone, int order, bool alloc_success); extern bool compaction_restarting(struct zone *zone, int order); +/* Compaction has made some progress and retrying makes sense */ +static inline bool compaction_made_progress(enum compact_result result) +{ + /* + * Even though this might sound confusing this in fact tells us + * that the compaction successfully isolated and migrated some + * pageblocks. + */ + if (result == COMPACT_PARTIAL) + return true; + + return false; +} + +/* Compaction has failed and it doesn't make much sense to keep retrying. */ +static inline bool compaction_failed(enum compact_result result) +{ + /* All zones were scanned completely and still not result. */ + if (result == COMPACT_COMPLETE) + return true; + + return false; +} + +/* + * Compaction has backed off for some reason. It might be throttling or + * lock contention. Retrying is still worthwhile. + */ +static inline bool compaction_withdrawn(enum compact_result result) +{ + /* + * Compaction backed off due to watermark checks for order-0 + * so the regular reclaim has to try harder and reclaim something. + */ + if (result == COMPACT_SKIPPED) + return true; + + /* + * If compaction is deferred for high-order allocations, it is + * because sync compaction recently failed. If this is the case + * and the caller requested a THP allocation, we do not want + * to heavily disrupt the system, so we fail the allocation + * instead of entering direct reclaim. + */ + if (result == COMPACT_DEFERRED) + return true; + + /* + * If compaction in async mode encounters contention or blocks higher + * priority task we back off early rather than cause stalls. + */ + if (result == COMPACT_CONTENDED) + return true; + + /* + * Page scanners have met but we haven't scanned full zones so this + * is a back off in fact. + */ + if (result == COMPACT_PARTIAL_SKIPPED) + return true; + + return false; +} + 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); @@ -114,6 +178,21 @@ static inline bool compaction_deferred(struct zone *zone, int order) return true; } +static inline bool compaction_made_progress(enum compact_result result) +{ + return false; +} + +static inline bool compaction_failed(enum compact_result result) +{ + return false; +} + +static inline bool compaction_withdrawn(enum compact_result result) +{ + return true; +} + static inline int kcompactd_run(int nid) { return 0; -- cgit v1.2.3 From 86a294a81f93d6f36d00ec3ff779d36d218f852d Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 20 May 2016 16:57:12 -0700 Subject: 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 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/compaction.h') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 8d8c916fe67a..a58c852a268f 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); -- cgit v1.2.3