From 748446bb6b5a9390b546af38ec899c868a9dbcf0 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:27 -0700 Subject: mm: compaction: memory compaction core This patch is the core of a mechanism which compacts memory in a zone by relocating movable pages towards the end of the zone. A single compaction run involves a migration scanner and a free scanner. Both scanners operate on pageblock-sized areas in the zone. The migration scanner starts at the bottom of the zone and searches for all movable pages within each area, isolating them onto a private list called migratelist. The free scanner starts at the top of the zone and searches for suitable areas and consumes the free pages within making them available for the migration scanner. The pages isolated for migration are then migrated to the newly isolated free pages. [aarcange@redhat.com: Fix unsafe optimisation] [mel@csn.ul.ie: do not schedule work on other CPUs for compaction] Signed-off-by: Mel Gorman Acked-by: Rik van Riel Reviewed-by: Minchan Kim Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 include/linux/compaction.h (limited to 'include/linux/compaction.h') diff --git a/include/linux/compaction.h b/include/linux/compaction.h new file mode 100644 index 000000000000..465ca88615ed --- /dev/null +++ b/include/linux/compaction.h @@ -0,0 +1,9 @@ +#ifndef _LINUX_COMPACTION_H +#define _LINUX_COMPACTION_H + +/* Return values for compact_zone() */ +#define COMPACT_CONTINUE 0 +#define COMPACT_PARTIAL 1 +#define COMPACT_COMPLETE 2 + +#endif /* _LINUX_COMPACTION_H */ -- cgit v1.2.3 From 76ab0f530e4a01d4dc20cdc1d5e87753c579dc18 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:28 -0700 Subject: mm: compaction: add /proc trigger for memory compaction Add a proc file /proc/sys/vm/compact_memory. When an arbitrary value is written to the file, all zones are compacted. The expected user of such a trigger is a job scheduler that prepares the system before the target application runs. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Reviewed-by: KAMEZAWA Hiroyuki Reviewed-by: Minchan Kim Reviewed-by: KOSAKI Motohiro Reviewed-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/compaction.h') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 465ca88615ed..572388880ba8 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -6,4 +6,10 @@ #define COMPACT_PARTIAL 1 #define COMPACT_COMPLETE 2 +#ifdef CONFIG_COMPACTION +extern int sysctl_compact_memory; +extern int sysctl_compaction_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos); +#endif /* CONFIG_COMPACTION */ + #endif /* _LINUX_COMPACTION_H */ -- cgit v1.2.3 From ed4a6d7f0676db50b5023cc01f6cda82a2f2a307 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:29 -0700 Subject: mm: compaction: add /sys trigger for per-node memory compaction Add a per-node sysfs file called compact. When the file is written to, each zone in that node is compacted. The intention that this would be used by something like a job scheduler in a batch system before a job starts so that the job can allocate the maximum number of hugepages without significant start-up cost. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Reviewed-by: KOSAKI Motohiro Reviewed-by: Christoph Lameter Reviewed-by: Minchan Kim Reviewed-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux/compaction.h') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 572388880ba8..ba98cfe0ae15 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -12,4 +12,20 @@ extern int sysctl_compaction_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); #endif /* CONFIG_COMPACTION */ +#if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) +extern int compaction_register_node(struct node *node); +extern void compaction_unregister_node(struct node *node); + +#else + +static inline int compaction_register_node(struct node *node) +{ + return 0; +} + +static inline void compaction_unregister_node(struct node *node) +{ +} +#endif /* CONFIG_COMPACTION && CONFIG_SYSFS && CONFIG_NUMA */ + #endif /* _LINUX_COMPACTION_H */ -- cgit v1.2.3 From 56de7263fcf3eb10c8dcdf8d59a9cec831795f3f Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:30 -0700 Subject: mm: compaction: direct compact when a high-order allocation fails Ordinarily when a high-order allocation fails, direct reclaim is entered to free pages to satisfy the allocation. With this patch, it is determined if an allocation failed due to external fragmentation instead of low memory and if so, the calling process will compact until a suitable page is freed. Compaction by moving pages in memory is considerably cheaper than paging out to disk and works where there are locked pages or no swap. If compaction fails to free a page of a suitable size, then reclaim will still occur. Direct compaction returns as soon as possible. As each block is compacted, it is checked if a suitable page has been freed and if so, it returns. [akpm@linux-foundation.org: Fix build errors] [aarcange@redhat.com: fix count_vm_event preempt in memory compaction direct reclaim] Signed-off-by: Mel Gorman Acked-by: Rik van Riel Reviewed-by: Minchan Kim Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) (limited to 'include/linux/compaction.h') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index ba98cfe0ae15..eed40ec4280b 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -1,15 +1,31 @@ #ifndef _LINUX_COMPACTION_H #define _LINUX_COMPACTION_H -/* Return values for compact_zone() */ -#define COMPACT_CONTINUE 0 -#define COMPACT_PARTIAL 1 -#define COMPACT_COMPLETE 2 +/* Return values for compact_zone() and try_to_compact_pages() */ +/* compaction didn't start as it was not possible or direct reclaim was more suitable */ +#define COMPACT_SKIPPED 0 +/* compaction should continue to another pageblock */ +#define COMPACT_CONTINUE 1 +/* direct compaction partially compacted a zone and there are suitable pages */ +#define COMPACT_PARTIAL 2 +/* The full zone was compacted */ +#define COMPACT_COMPLETE 3 #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); + +extern int fragmentation_index(struct zone *zone, unsigned int order); +extern unsigned long try_to_compact_pages(struct zonelist *zonelist, + int order, gfp_t gfp_mask, nodemask_t *mask); +#else +static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, + int order, gfp_t gfp_mask, nodemask_t *nodemask) +{ + return COMPACT_CONTINUE; +} + #endif /* CONFIG_COMPACTION */ #if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) -- cgit v1.2.3 From 5e7719058079a1423ccce56148b0aaa56b2df821 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:31 -0700 Subject: mm: compaction: add a tunable that decides when memory should be compacted and when it should be reclaimed The kernel applies some heuristics when deciding if memory should be compacted or reclaimed to satisfy a high-order allocation. One of these is based on the fragmentation. If the index is below 500, memory will not be compacted. This choice is arbitrary and not based on data. To help optimise the system and set a sensible default for this value, this patch adds a sysctl extfrag_threshold. The kernel will only compact memory if the fragmentation index is above the extfrag_threshold. [randy.dunlap@oracle.com: Fix build errors when proc fs is not configured] Signed-off-by: Mel Gorman Signed-off-by: Randy Dunlap Cc: Rik van Riel Cc: Minchan Kim Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/compaction.h') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index eed40ec4280b..3719325c6091 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -15,6 +15,9 @@ extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); +extern int sysctl_extfrag_threshold; +extern int sysctl_extfrag_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos); extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, -- cgit v1.2.3 From 4f92e2586b43a2402e116055d4edda704f911b5b Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:32 -0700 Subject: mm: compaction: defer compaction using an exponential backoff when compaction fails The fragmentation index may indicate that a failure is due to external fragmentation but after a compaction run completes, it is still possible for an allocation to fail. There are two obvious reasons as to why o Page migration cannot move all pages so fragmentation remains o A suitable page may exist but watermarks are not met In the event of compaction followed by an allocation failure, this patch defers further compaction in the zone (1 << compact_defer_shift) times. If the next compaction attempt also fails, compact_defer_shift is increased up to a maximum of 6. If compaction succeeds, the defer counters are reset again. The zone that is deferred is the first zone in the zonelist - i.e. the preferred zone. To defer compaction in the other zones, the information would need to be stored in the zonelist or implemented similar to the zonelist_cache. This would impact the fast-paths and is not justified at this time. Signed-off-by: Mel Gorman Cc: Rik van Riel Cc: Minchan Kim Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include/linux/compaction.h') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 3719325c6091..5ac51552d908 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -22,6 +22,36 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); + +/* Do not skip compaction more than 64 times */ +#define COMPACT_MAX_DEFER_SHIFT 6 + +/* + * Compaction is deferred when compaction fails to result in a page + * 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) +{ + zone->compact_considered = 0; + zone->compact_defer_shift++; + + 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) +{ + unsigned long defer_limit = 1UL << zone->compact_defer_shift; + + /* Avoid possible overflow */ + if (++zone->compact_considered > defer_limit) + zone->compact_considered = defer_limit; + + return zone->compact_considered < (1UL << zone->compact_defer_shift); +} + #else static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask) @@ -29,6 +59,15 @@ static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, return COMPACT_CONTINUE; } +static inline void defer_compaction(struct zone *zone) +{ +} + +static inline bool compaction_deferred(struct zone *zone) +{ + return 1; +} + #endif /* CONFIG_COMPACTION */ #if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) -- cgit v1.2.3