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 v1.2.3-71-gd317 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 --- Documentation/sysctl/vm.txt | 10 ++++++++ include/linux/compaction.h | 6 +++++ kernel/sysctl.c | 10 ++++++++ mm/compaction.c | 62 +++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 88 insertions(+) (limited to 'include/linux/compaction.h') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 6c7d18c53f84..56dd29b97a91 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -19,6 +19,7 @@ files can be found in mm/swap.c. Currently, these files are in /proc/sys/vm: - block_dump +- compact_memory - dirty_background_bytes - dirty_background_ratio - dirty_bytes @@ -64,6 +65,15 @@ information on block I/O debugging is in Documentation/laptops/laptop-mode.txt. ============================================================== +compact_memory + +Available only when CONFIG_COMPACTION is set. When 1 is written to the file, +all zones are compacted such that free memory is available in contiguous +blocks where possible. This can be important for example in the allocation of +huge pages although processes will also directly compact memory as required. + +============================================================== + dirty_background_bytes Contains the amount of dirty memory at which the pdflush background writeback 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 */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 4c93486b45d1..284f330d6a01 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include @@ -1121,6 +1122,15 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = drop_caches_sysctl_handler, }, +#ifdef CONFIG_COMPACTION + { + .procname = "compact_memory", + .data = &sysctl_compact_memory, + .maxlen = sizeof(int), + .mode = 0200, + .proc_handler = sysctl_compaction_handler, + }, +#endif /* CONFIG_COMPACTION */ { .procname = "min_free_kbytes", .data = &min_free_kbytes, diff --git a/mm/compaction.c b/mm/compaction.c index be1ff3f7552b..77854fbc0f56 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "internal.h" /* @@ -391,3 +392,64 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) return ret; } + +/* Compact all zones within a node */ +static int compact_node(int nid) +{ + int zoneid; + pg_data_t *pgdat; + struct zone *zone; + + if (nid < 0 || nid >= nr_node_ids || !node_online(nid)) + return -EINVAL; + pgdat = NODE_DATA(nid); + + /* Flush pending updates to the LRU lists */ + lru_add_drain_all(); + + for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { + struct compact_control cc = { + .nr_freepages = 0, + .nr_migratepages = 0, + }; + + zone = &pgdat->node_zones[zoneid]; + if (!populated_zone(zone)) + continue; + + cc.zone = zone; + INIT_LIST_HEAD(&cc.freepages); + INIT_LIST_HEAD(&cc.migratepages); + + compact_zone(zone, &cc); + + VM_BUG_ON(!list_empty(&cc.freepages)); + VM_BUG_ON(!list_empty(&cc.migratepages)); + } + + return 0; +} + +/* Compact all nodes in the system */ +static int compact_nodes(void) +{ + int nid; + + for_each_online_node(nid) + compact_node(nid); + + return COMPACT_COMPLETE; +} + +/* The written value is actually unused, all memory is compacted */ +int sysctl_compact_memory; + +/* This is the entry point for compacting all nodes via /proc/sys/vm */ +int sysctl_compaction_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + if (write) + return compact_nodes(); + + return 0; +} -- cgit v1.2.3-71-gd317 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 --- Documentation/ABI/testing/sysfs-devices-node | 7 +++++++ drivers/base/node.c | 3 +++ include/linux/compaction.h | 16 ++++++++++++++++ mm/compaction.c | 23 +++++++++++++++++++++++ 4 files changed, 49 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-devices-node (limited to 'include/linux/compaction.h') diff --git a/Documentation/ABI/testing/sysfs-devices-node b/Documentation/ABI/testing/sysfs-devices-node new file mode 100644 index 000000000000..453a210c3ceb --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-node @@ -0,0 +1,7 @@ +What: /sys/devices/system/node/nodeX/compact +Date: February 2010 +Contact: Mel Gorman +Description: + When this file is written to, all memory within that node + will be compacted. When it completes, memory will be freed + into blocks which have as many contiguous pages as possible diff --git a/drivers/base/node.c b/drivers/base/node.c index 057979a19eea..2bdd8a94ec94 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -246,6 +247,8 @@ int register_node(struct node *node, int num, struct node *parent) scan_unevictable_register_node(node); hugetlb_register_node(node); + + compaction_register_node(node); } return error; } 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 */ diff --git a/mm/compaction.c b/mm/compaction.c index 77854fbc0f56..f61f77983ff4 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "internal.h" /* @@ -453,3 +454,25 @@ int sysctl_compaction_handler(struct ctl_table *table, int write, return 0; } + +#if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) +ssize_t sysfs_compact_node(struct sys_device *dev, + struct sysdev_attribute *attr, + const char *buf, size_t count) +{ + compact_node(dev->id); + + return count; +} +static SYSDEV_ATTR(compact, S_IWUSR, NULL, sysfs_compact_node); + +int compaction_register_node(struct node *node) +{ + return sysdev_create_file(&node->sysdev, &attr_compact); +} + +void compaction_unregister_node(struct node *node) +{ + return sysdev_remove_file(&node->sysdev, &attr_compact); +} +#endif /* CONFIG_SYSFS && CONFIG_NUMA */ -- cgit v1.2.3-71-gd317 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 ++++++++-- include/linux/vmstat.h | 1 + mm/compaction.c | 117 +++++++++++++++++++++++++++++++++++++++++++++ mm/page_alloc.c | 63 ++++++++++++++++++++++++ mm/vmstat.c | 16 ++++++- 5 files changed, 215 insertions(+), 6 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) diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index b421d1b22b62..7f43ccdc1d38 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -45,6 +45,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PAGEOUTRUN, ALLOCSTALL, PGROTATED, #ifdef CONFIG_COMPACTION COMPACTBLOCKS, COMPACTPAGES, COMPACTPAGEFAILED, + COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS, #endif #ifdef CONFIG_HUGETLB_PAGE HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL, diff --git a/mm/compaction.c b/mm/compaction.c index f61f77983ff4..9583e193dc47 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -35,6 +35,8 @@ struct compact_control { unsigned long nr_anon; unsigned long nr_file; + unsigned int order; /* order a direct compactor needs */ + int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; }; @@ -341,6 +343,9 @@ static void update_nr_listpages(struct compact_control *cc) static int compact_finished(struct zone *zone, struct compact_control *cc) { + unsigned int order; + unsigned long watermark = low_wmark_pages(zone) + (1 << cc->order); + if (fatal_signal_pending(current)) return COMPACT_PARTIAL; @@ -348,6 +353,24 @@ static int compact_finished(struct zone *zone, if (cc->free_pfn <= cc->migrate_pfn) return COMPACT_COMPLETE; + /* Compaction run is not finished if the watermark is not met */ + if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0)) + return COMPACT_CONTINUE; + + if (cc->order == -1) + return COMPACT_CONTINUE; + + /* Direct compactor: Is a suitable page free? */ + for (order = cc->order; order < MAX_ORDER; order++) { + /* Job done if page is free of the right migratetype */ + if (!list_empty(&zone->free_area[order].free_list[cc->migratetype])) + return COMPACT_PARTIAL; + + /* Job done if allocation would set block type */ + if (order >= pageblock_order && zone->free_area[order].nr_free) + return COMPACT_PARTIAL; + } + return COMPACT_CONTINUE; } @@ -394,6 +417,99 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) return ret; } +static unsigned long compact_zone_order(struct zone *zone, + int order, gfp_t gfp_mask) +{ + struct compact_control cc = { + .nr_freepages = 0, + .nr_migratepages = 0, + .order = order, + .migratetype = allocflags_to_migratetype(gfp_mask), + .zone = zone, + }; + INIT_LIST_HEAD(&cc.freepages); + INIT_LIST_HEAD(&cc.migratepages); + + return compact_zone(zone, &cc); +} + +/** + * try_to_compact_pages - Direct compact to satisfy a high-order allocation + * @zonelist: The zonelist used for the current allocation + * @order: The order of the current allocation + * @gfp_mask: The GFP mask of the current allocation + * @nodemask: The allowed nodes to allocate from + * + * This is the main entry point for direct page compaction. + */ +unsigned long try_to_compact_pages(struct zonelist *zonelist, + int order, gfp_t gfp_mask, nodemask_t *nodemask) +{ + enum zone_type high_zoneidx = gfp_zone(gfp_mask); + int may_enter_fs = gfp_mask & __GFP_FS; + int may_perform_io = gfp_mask & __GFP_IO; + unsigned long watermark; + struct zoneref *z; + struct zone *zone; + int rc = COMPACT_SKIPPED; + + /* + * Check whether it is worth even starting compaction. The order check is + * made because an assumption is made that the page allocator can satisfy + * the "cheaper" orders without taking special steps + */ + if (order <= PAGE_ALLOC_COSTLY_ORDER || !may_enter_fs || !may_perform_io) + return rc; + + count_vm_event(COMPACTSTALL); + + /* Compact each zone in the list */ + for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx, + nodemask) { + int fragindex; + int status; + + /* + * Watermarks for order-0 must be met for compaction. Note + * the 2UL. This is because during migration, copies of + * pages need to be allocated and for a short time, the + * footprint is higher + */ + watermark = low_wmark_pages(zone) + (2UL << order); + if (!zone_watermark_ok(zone, 0, watermark, 0, 0)) + continue; + + /* + * fragmentation index determines if allocation failures are + * due to low memory or external fragmentation + * + * index of -1 implies allocations might succeed depending + * on watermarks + * index towards 0 implies failure is due to lack of memory + * index towards 1000 implies failure is due to fragmentation + * + * Only compact if a failure would be due to fragmentation. + */ + fragindex = fragmentation_index(zone, order); + if (fragindex >= 0 && fragindex <= 500) + continue; + + if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0)) { + rc = COMPACT_PARTIAL; + break; + } + + status = compact_zone_order(zone, order, gfp_mask); + rc = max(status, rc); + + if (zone_watermark_ok(zone, order, watermark, 0, 0)) + break; + } + + return rc; +} + + /* Compact all zones within a node */ static int compact_node(int nid) { @@ -412,6 +528,7 @@ static int compact_node(int nid) struct compact_control cc = { .nr_freepages = 0, .nr_migratepages = 0, + .order = -1, }; zone = &pgdat->node_zones[zoneid]; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c54376a09f30..cd88a860f088 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include @@ -1758,6 +1759,59 @@ out: return page; } +#ifdef CONFIG_COMPACTION +/* Try memory compaction for high-order allocations before reclaim */ +static struct page * +__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, enum zone_type high_zoneidx, + nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, + int migratetype, unsigned long *did_some_progress) +{ + struct page *page; + + if (!order) + return NULL; + + *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, + nodemask); + if (*did_some_progress != COMPACT_SKIPPED) { + + /* Page migration frees to the PCP lists but we want merging */ + drain_pages(get_cpu()); + put_cpu(); + + page = get_page_from_freelist(gfp_mask, nodemask, + order, zonelist, high_zoneidx, + alloc_flags, preferred_zone, + migratetype); + if (page) { + count_vm_event(COMPACTSUCCESS); + return page; + } + + /* + * It's bad if compaction run occurs and fails. + * The most likely reason is that pages exist, + * but not enough to satisfy watermarks. + */ + count_vm_event(COMPACTFAIL); + + cond_resched(); + } + + return NULL; +} +#else +static inline struct page * +__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, enum zone_type high_zoneidx, + nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, + int migratetype, unsigned long *did_some_progress) +{ + return NULL; +} +#endif /* CONFIG_COMPACTION */ + /* The really slow allocator path where we enter direct reclaim */ static inline struct page * __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, @@ -1944,6 +1998,15 @@ rebalance: if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL)) goto nopage; + /* Try direct compaction */ + page = __alloc_pages_direct_compact(gfp_mask, order, + zonelist, high_zoneidx, + nodemask, + alloc_flags, preferred_zone, + migratetype, &did_some_progress); + if (page) + goto got_pg; + /* Try direct reclaim and then allocating */ page = __alloc_pages_direct_reclaim(gfp_mask, order, zonelist, high_zoneidx, diff --git a/mm/vmstat.c b/mm/vmstat.c index c6aacf51b554..7759941d4e77 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -429,7 +429,7 @@ static void fill_contig_page_info(struct zone *zone, * The value can be used to determine if page reclaim or compaction * should be used */ -int fragmentation_index(unsigned int order, struct contig_page_info *info) +static int __fragmentation_index(unsigned int order, struct contig_page_info *info) { unsigned long requested = 1UL << order; @@ -448,6 +448,15 @@ int fragmentation_index(unsigned int order, struct contig_page_info *info) */ return 1000 - div_u64( (1000+(div_u64(info->free_pages * 1000ULL, requested))), info->free_blocks_total); } + +/* Same as __fragmentation index but allocs contig_page_info on stack */ +int fragmentation_index(struct zone *zone, unsigned int order) +{ + struct contig_page_info info; + + fill_contig_page_info(zone, order, &info); + return __fragmentation_index(order, &info); +} #endif #if defined(CONFIG_PROC_FS) || defined(CONFIG_COMPACTION) @@ -771,6 +780,9 @@ static const char * const vmstat_text[] = { "compact_blocks_moved", "compact_pages_moved", "compact_pagemigrate_failed", + "compact_stall", + "compact_fail", + "compact_success", #endif #ifdef CONFIG_HUGETLB_PAGE @@ -1136,7 +1148,7 @@ static void extfrag_show_print(struct seq_file *m, zone->name); for (order = 0; order < MAX_ORDER; ++order) { fill_contig_page_info(zone, order, &info); - index = fragmentation_index(order, &info); + index = __fragmentation_index(order, &info); seq_printf(m, "%d.%03d ", index / 1000, index % 1000); } -- cgit v1.2.3-71-gd317 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 --- Documentation/sysctl/vm.txt | 15 +++++++++++++++ include/linux/compaction.h | 3 +++ kernel/sysctl.c | 15 +++++++++++++++ mm/compaction.c | 12 +++++++++++- 4 files changed, 44 insertions(+), 1 deletion(-) (limited to 'include/linux/compaction.h') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 56dd29b97a91..5fdbb612aeb8 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -27,6 +27,7 @@ Currently, these files are in /proc/sys/vm: - dirty_ratio - dirty_writeback_centisecs - drop_caches +- extfrag_threshold - hugepages_treat_as_movable - hugetlb_shm_group - laptop_mode @@ -149,6 +150,20 @@ user should run `sync' first. ============================================================== +extfrag_threshold + +This parameter affects whether the kernel will compact memory or direct +reclaim to satisfy a high-order allocation. /proc/extfrag_index shows what +the fragmentation index for each order is in each zone in the system. Values +tending towards 0 imply allocations would fail due to lack of memory, +values towards 1000 imply failures are due to fragmentation and -1 implies +that the allocation will succeed as long as watermarks are met. + +The kernel will not compact memory in a zone if the +fragmentation index is <= extfrag_threshold. The default value is 500. + +============================================================== + hugepages_treat_as_movable This parameter is only useful when kernelcore= is specified at boot time to 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, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 284f330d6a01..84ff5e75c084 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -263,6 +263,11 @@ static int min_sched_shares_ratelimit = 100000; /* 100 usec */ static int max_sched_shares_ratelimit = NSEC_PER_SEC; /* 1 second */ #endif +#ifdef CONFIG_COMPACTION +static int min_extfrag_threshold; +static int max_extfrag_threshold = 1000; +#endif + static struct ctl_table kern_table[] = { { .procname = "sched_child_runs_first", @@ -1130,6 +1135,16 @@ static struct ctl_table vm_table[] = { .mode = 0200, .proc_handler = sysctl_compaction_handler, }, + { + .procname = "extfrag_threshold", + .data = &sysctl_extfrag_threshold, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sysctl_extfrag_handler, + .extra1 = &min_extfrag_threshold, + .extra2 = &max_extfrag_threshold, + }, + #endif /* CONFIG_COMPACTION */ { .procname = "min_free_kbytes", diff --git a/mm/compaction.c b/mm/compaction.c index 9583e193dc47..94cce51b0b35 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -433,6 +433,8 @@ static unsigned long compact_zone_order(struct zone *zone, return compact_zone(zone, &cc); } +int sysctl_extfrag_threshold = 500; + /** * try_to_compact_pages - Direct compact to satisfy a high-order allocation * @zonelist: The zonelist used for the current allocation @@ -491,7 +493,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, * Only compact if a failure would be due to fragmentation. */ fragindex = fragmentation_index(zone, order); - if (fragindex >= 0 && fragindex <= 500) + if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) continue; if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0)) { @@ -572,6 +574,14 @@ int sysctl_compaction_handler(struct ctl_table *table, int write, return 0; } +int sysctl_extfrag_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + proc_dointvec_minmax(table, write, buffer, length, ppos); + + return 0; +} + #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) ssize_t sysfs_compact_node(struct sys_device *dev, struct sysdev_attribute *attr, -- cgit v1.2.3-71-gd317 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 +++++++++++++++++++++++++++++++++++++++ include/linux/mmzone.h | 9 +++++++++ mm/page_alloc.c | 5 ++++- 3 files changed, 52 insertions(+), 1 deletion(-) (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) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index cf9e458e96b0..fd55f725a09e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -321,6 +321,15 @@ struct zone { unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ +#ifdef CONFIG_COMPACTION + /* + * On compaction failure, 1<compact_considered = 0; + preferred_zone->compact_defer_shift = 0; count_vm_event(COMPACTSUCCESS); return page; } @@ -1795,6 +1797,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, * but not enough to satisfy watermarks. */ count_vm_event(COMPACTFAIL); + defer_compaction(preferred_zone); cond_resched(); } -- cgit v1.2.3-71-gd317