diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 7d73882e2c27..187ce4f599a2 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -63,6 +63,7 @@ Currently, these files are in /proc/sys/vm: - swappiness - user_reserve_kbytes - vfs_cache_pressure +- watermark_boost_factor - watermark_scale_factor - zone_reclaim_mode @@ -856,6 +857,26 @@ ten times more freeable objects than there are. ============================================================= +watermark_boost_factor: + +This factor controls the level of reclaim when memory is being fragmented. +It defines the percentage of the high watermark of a zone that will be +reclaimed if pages of different mobility are being mixed within pageblocks. +The intent is that compaction has less work to do in the future and to +increase the success rate of future high-order allocations such as SLUB +allocations, THP and hugetlbfs pages. + +To make it sensible with respect to the watermark_scale_factor parameter, +the unit is in fractions of 10,000. The default value of 15,000 means +that up to 150% of the high watermark will be reclaimed in the event of +a pageblock being mixed due to fragmentation. The level of reclaim is +determined by the number of fragmentation events that occurred in the +recent past. If this value is smaller than a pageblock then a pageblocks +worth of pages will be reclaimed (e.g. 2MB on 64-bit x86). A boost factor +of 0 will disable the feature. + +============================================================= + watermark_scale_factor: This factor controls the aggressiveness of kswapd. It defines the diff --git a/include/linux/mm.h b/include/linux/mm.h index 1d2be4c2d34a..031b2ce983f9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2256,6 +2256,7 @@ extern void zone_pcp_reset(struct zone *zone); /* page_alloc.c */ extern int min_free_kbytes; +extern int watermark_boost_factor; extern int watermark_scale_factor; /* nommu.c */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index dcf1b66a96ab..5b4bfb90fb94 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -269,10 +269,10 @@ enum zone_watermarks { NR_WMARK }; -#define min_wmark_pages(z) (z->_watermark[WMARK_MIN]) -#define low_wmark_pages(z) (z->_watermark[WMARK_LOW]) -#define high_wmark_pages(z) (z->_watermark[WMARK_HIGH]) -#define wmark_pages(z, i) (z->_watermark[i]) +#define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost) +#define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) +#define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) +#define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost) struct per_cpu_pages { int count; /* number of pages in the list */ @@ -364,6 +364,7 @@ struct zone { /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long _watermark[NR_WMARK]; + unsigned long watermark_boost; unsigned long nr_reserved_highatomic; @@ -890,6 +891,8 @@ static inline int is_highmem(struct zone *zone) struct ctl_table; int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); +int watermark_boost_factor_sysctl_handler(struct ctl_table *, int, + void __user *, size_t *, loff_t *); int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 5fc724e4e454..1825f712e73b 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1462,6 +1462,14 @@ static struct ctl_table vm_table[] = { .proc_handler = min_free_kbytes_sysctl_handler, .extra1 = &zero, }, + { + .procname = "watermark_boost_factor", + .data = &watermark_boost_factor, + .maxlen = sizeof(watermark_boost_factor), + .mode = 0644, + .proc_handler = watermark_boost_factor_sysctl_handler, + .extra1 = &zero, + }, { .procname = "watermark_scale_factor", .data = &watermark_scale_factor, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 32b3e121a388..80373eca453d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -262,6 +262,7 @@ compound_page_dtor * const compound_page_dtors[] = { int min_free_kbytes = 1024; int user_min_free_kbytes = -1; +int watermark_boost_factor __read_mostly = 15000; int watermark_scale_factor = 10; static unsigned long nr_kernel_pages __meminitdata; @@ -2129,6 +2130,21 @@ static bool can_steal_fallback(unsigned int order, int start_mt) return false; } +static inline void boost_watermark(struct zone *zone) +{ + unsigned long max_boost; + + if (!watermark_boost_factor) + return; + + max_boost = mult_frac(zone->_watermark[WMARK_HIGH], + watermark_boost_factor, 10000); + max_boost = max(pageblock_nr_pages, max_boost); + + zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages, + max_boost); +} + /* * This function implements actual steal behaviour. If order is large enough, * we can steal whole pageblock. If not, we first move freepages in this @@ -2138,7 +2154,7 @@ static bool can_steal_fallback(unsigned int order, int start_mt) * itself, so pages freed in the future will be put on the correct free list. */ static void steal_suitable_fallback(struct zone *zone, struct page *page, - int start_type, bool whole_block) + unsigned int alloc_flags, int start_type, bool whole_block) { unsigned int current_order = page_order(page); struct free_area *area; @@ -2160,6 +2176,15 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page, goto single_page; } + /* + * Boost watermarks to increase reclaim pressure to reduce the + * likelihood of future fallbacks. Wake kswapd now as the node + * may be balanced overall and kswapd will not wake naturally. + */ + boost_watermark(zone); + if (alloc_flags & ALLOC_KSWAPD) + wakeup_kswapd(zone, 0, 0, zone_idx(zone)); + /* We are not allowed to try stealing from the whole block */ if (!whole_block) goto single_page; @@ -2443,7 +2468,8 @@ do_steal: page = list_first_entry(&area->free_list[fallback_mt], struct page, lru); - steal_suitable_fallback(zone, page, start_migratetype, can_steal); + steal_suitable_fallback(zone, page, alloc_flags, start_migratetype, + can_steal); trace_mm_page_alloc_extfrag(page, order, current_order, start_migratetype, fallback_mt); @@ -7454,6 +7480,7 @@ static void __setup_per_zone_wmarks(void) zone->_watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp; zone->_watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2; + zone->watermark_boost = 0; spin_unlock_irqrestore(&zone->lock, flags); } @@ -7554,6 +7581,18 @@ int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write, return 0; } +int watermark_boost_factor_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + int rc; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + + return 0; +} + int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { diff --git a/mm/vmscan.c b/mm/vmscan.c index 24ab1f7394ab..bd8971a29204 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -88,6 +88,9 @@ struct scan_control { /* Can pages be swapped as part of reclaim? */ unsigned int may_swap:1; + /* e.g. boosted watermark reclaim leaves slabs alone */ + unsigned int may_shrinkslab:1; + /* * Cgroups are not reclaimed below their configured memory.low, * unless we threaten to OOM. If any cgroups are skipped due to @@ -2756,8 +2759,10 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) shrink_node_memcg(pgdat, memcg, sc, &lru_pages); node_lru_pages += lru_pages; - shrink_slab(sc->gfp_mask, pgdat->node_id, + if (sc->may_shrinkslab) { + shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); + } /* Record the group's reclaim efficiency */ vmpressure(sc->gfp_mask, memcg, false, @@ -3239,6 +3244,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = 1, + .may_shrinkslab = 1, }; /* @@ -3283,6 +3289,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, .may_unmap = 1, .reclaim_idx = MAX_NR_ZONES - 1, .may_swap = !noswap, + .may_shrinkslab = 1, }; unsigned long lru_pages; @@ -3329,6 +3336,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = may_swap, + .may_shrinkslab = 1, }; /* @@ -3379,6 +3387,30 @@ static void age_active_anon(struct pglist_data *pgdat, } while (memcg); } +static bool pgdat_watermark_boosted(pg_data_t *pgdat, int classzone_idx) +{ + int i; + struct zone *zone; + + /* + * Check for watermark boosts top-down as the higher zones + * are more likely to be boosted. Both watermarks and boosts + * should not be checked at the time time as reclaim would + * start prematurely when there is no boosting and a lower + * zone is balanced. + */ + for (i = classzone_idx; i >= 0; i--) { + zone = pgdat->node_zones + i; + if (!managed_zone(zone)) + continue; + + if (zone->watermark_boost) + return true; + } + + return false; +} + /* * Returns true if there is an eligible zone balanced for the request order * and classzone_idx @@ -3389,6 +3421,10 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) unsigned long mark = -1; struct zone *zone; + /* + * Check watermarks bottom-up as lower zones are more likely to + * meet watermarks. + */ for (i = 0; i <= classzone_idx; i++) { zone = pgdat->node_zones + i; @@ -3517,14 +3553,14 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; unsigned long pflags; + unsigned long nr_boost_reclaim; + unsigned long zone_boosts[MAX_NR_ZONES] = { 0, }; + bool boosted; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .order = order, - .priority = DEF_PRIORITY, - .may_writepage = !laptop_mode, .may_unmap = 1, - .may_swap = 1, }; psi_memstall_enter(&pflags); @@ -3532,9 +3568,28 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) count_vm_event(PAGEOUTRUN); + /* + * Account for the reclaim boost. Note that the zone boost is left in + * place so that parallel allocations that are near the watermark will + * stall or direct reclaim until kswapd is finished. + */ + nr_boost_reclaim = 0; + for (i = 0; i <= classzone_idx; i++) { + zone = pgdat->node_zones + i; + if (!managed_zone(zone)) + continue; + + nr_boost_reclaim += zone->watermark_boost; + zone_boosts[i] = zone->watermark_boost; + } + boosted = nr_boost_reclaim; + +restart: + sc.priority = DEF_PRIORITY; do { unsigned long nr_reclaimed = sc.nr_reclaimed; bool raise_priority = true; + bool balanced; bool ret; sc.reclaim_idx = classzone_idx; @@ -3561,13 +3616,40 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) } /* - * Only reclaim if there are no eligible zones. Note that - * sc.reclaim_idx is not used as buffer_heads_over_limit may - * have adjusted it. + * If the pgdat is imbalanced then ignore boosting and preserve + * the watermarks for a later time and restart. Note that the + * zone watermarks will be still reset at the end of balancing + * on the grounds that the normal reclaim should be enough to + * re-evaluate if boosting is required when kswapd next wakes. */ - if (pgdat_balanced(pgdat, sc.order, classzone_idx)) + balanced = pgdat_balanced(pgdat, sc.order, classzone_idx); + if (!balanced && nr_boost_reclaim) { + nr_boost_reclaim = 0; + goto restart; + } + + /* + * If boosting is not active then only reclaim if there are no + * eligible zones. Note that sc.reclaim_idx is not used as + * buffer_heads_over_limit may have adjusted it. + */ + if (!nr_boost_reclaim && balanced) goto out; + /* Limit the priority of boosting to avoid reclaim writeback */ + if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2) + raise_priority = false; + + /* + * Do not writeback or swap pages for boosted reclaim. The + * intent is to relieve pressure not issue sub-optimal IO + * from reclaim context. If no pages are reclaimed, the + * reclaim will be aborted. + */ + sc.may_writepage = !laptop_mode && !nr_boost_reclaim; + sc.may_swap = !nr_boost_reclaim; + sc.may_shrinkslab = !nr_boost_reclaim; + /* * Do some background aging of the anon list, to give * pages a chance to be referenced before reclaiming. All @@ -3619,6 +3701,16 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) * progress in reclaiming pages */ nr_reclaimed = sc.nr_reclaimed - nr_reclaimed; + nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed); + + /* + * If reclaim made no progress for a boost, stop reclaim as + * IO cannot be queued and it could be an infinite loop in + * extreme circumstances. + */ + if (nr_boost_reclaim && !nr_reclaimed) + break; + if (raise_priority || !nr_reclaimed) sc.priority--; } while (sc.priority >= 1); @@ -3627,6 +3719,28 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) pgdat->kswapd_failures++; out: + /* If reclaim was boosted, account for the reclaim done in this pass */ + if (boosted) { + unsigned long flags; + + for (i = 0; i <= classzone_idx; i++) { + if (!zone_boosts[i]) + continue; + + /* Increments are under the zone lock */ + zone = pgdat->node_zones + i; + spin_lock_irqsave(&zone->lock, flags); + zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]); + spin_unlock_irqrestore(&zone->lock, flags); + } + + /* + * As there is now likely space, wakeup kcompact to defragment + * pageblocks. + */ + wakeup_kcompactd(pgdat, pageblock_order, classzone_idx); + } + snapshot_refaults(NULL, pgdat); __fs_reclaim_release(); psi_memstall_leave(&pflags); @@ -3855,7 +3969,8 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, /* Hopeless node, leave it to direct reclaim if possible */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || - pgdat_balanced(pgdat, order, classzone_idx)) { + (pgdat_balanced(pgdat, order, classzone_idx) && + !pgdat_watermark_boosted(pgdat, classzone_idx))) { /* * There may be plenty of free memory available, but it's too * fragmented for high-order allocations. Wake up kcompactd