From f87904029252ae7765aede622c89e8998ff085c0 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 28 Sep 2012 10:19:49 +1000 Subject: [PATCH] mm: compaction: clear PG_migrate_skip based on compaction and reclaim activity Compaction caches if a pageblock was scanned and no pages were isolated so that the pageblocks can be skipped in the future to reduce scanning. This information is not cleared by the page allocator based on activity due to the impact it would have to the page allocator fast paths. Hence there is a requirement that something clear the cache or pageblocks will be skipped forever. Currently the cache is cleared if there were a number of recent allocation failures and it has not been cleared within the last 5 seconds. Time-based decisions like this are terrible as they have no relationship to VM activity and is basically a big hammer. Unfortunately, accurate heuristics would add cost to some hot paths so this patch implements a rough heuristic. There are two cases where the cache is cleared. 1. If a !kswapd process completes a compaction cycle (migrate and free scanner meet), the zone is marked compact_blockskip_flush. When kswapd goes to sleep, it will clear the cache. This is expected to be the common case where the cache is cleared. It does not really matter if kswapd happens to be asleep or going to sleep when the flag is set as it will be woken on the next allocation request. 2. If there have been multiple failures recently and compaction just finished being deferred then a process will clear the cache and start a full scan. This situation happens if there are multiple high-order allocation requests under heavy memory pressure. The clearing of the PG_migrate_skip bits and other scans is inherently racy but the race is harmless. For allocations that can fail such as THP, they will simply fail. For requests that cannot fail, they will retry the allocation. Tests indicated that scanning rates were roughly similar to when the time-based heuristic was used and the allocation success rates were similar. Signed-off-by: Mel Gorman Cc: Rik van Riel Cc: Richard Davies Cc: Shaohua Li Cc: Avi Kivity Cc: Rafael Aquini Signed-off-by: Andrew Morton --- include/linux/compaction.h | 15 ++++++++++++ include/linux/mmzone.h | 3 ++- mm/compaction.c | 50 ++++++++++++++++++++++++++------------ mm/page_alloc.c | 1 + mm/vmscan.c | 8 ++++++ 5 files changed, 60 insertions(+), 17 deletions(-) diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 0e38a1deeb23..6ecb6dc2f303 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -24,6 +24,7 @@ extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask, bool sync, bool *contended, struct page **page); extern int 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); /* Do not skip compaction more than 64 times */ @@ -61,6 +62,16 @@ static inline bool compaction_deferred(struct zone *zone, int order) return zone->compact_considered < defer_limit; } +/* Returns true if restarting compaction after many failures */ +static inline bool compaction_restarting(struct zone *zone, int order) +{ + if (order < zone->compact_order_failed) + return false; + + return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT && + 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, @@ -74,6 +85,10 @@ static inline int compact_pgdat(pg_data_t *pgdat, int order) return COMPACT_CONTINUE; } +static inline void reset_isolation_suitable(pg_data_t *pgdat) +{ +} + static inline unsigned long compaction_suitable(struct zone *zone, int order) { return COMPACT_SKIPPED; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index a0da80c133fd..a36baa99ac0b 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -359,7 +359,8 @@ struct zone { spinlock_t lock; int all_unreclaimable; /* All pages pinned */ #if defined CONFIG_COMPACTION || defined CONFIG_CMA - unsigned long compact_blockskip_expire; + /* Set to true when the PG_migrate_skip bits should be cleared */ + bool compact_blockskip_flush; /* pfns where compaction scanners should start */ unsigned long compact_cached_free_pfn; diff --git a/mm/compaction.c b/mm/compaction.c index 8b2d42088e0d..76d8a5e76a4c 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -66,24 +66,15 @@ static inline bool isolation_suitable(struct compact_control *cc, * should be skipped for page isolation when the migrate and free page scanner * meet. */ -static void reset_isolation_suitable(struct zone *zone) +static void __reset_isolation_suitable(struct zone *zone) { unsigned long start_pfn = zone->zone_start_pfn; unsigned long end_pfn = zone->zone_start_pfn + zone->spanned_pages; unsigned long pfn; - /* - * Do not reset more than once every five seconds. If allocations are - * failing sufficiently quickly to allow this to happen then continually - * scanning for compaction is not going to help. The choice of five - * seconds is arbitrary but will mitigate excessive scanning. - */ - if (time_before(jiffies, zone->compact_blockskip_expire)) - return; - zone->compact_cached_migrate_pfn = start_pfn; zone->compact_cached_free_pfn = end_pfn; - zone->compact_blockskip_expire = jiffies + (HZ * 5); + zone->compact_blockskip_flush = false; /* Walk the zone and mark every pageblock as suitable for isolation */ for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { @@ -102,9 +93,24 @@ static void reset_isolation_suitable(struct zone *zone) } } +void reset_isolation_suitable(pg_data_t *pgdat) +{ + int zoneid; + + for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { + struct zone *zone = &pgdat->node_zones[zoneid]; + if (!populated_zone(zone)) + continue; + + /* Only flush if a full compaction finished recently */ + if (zone->compact_blockskip_flush) + __reset_isolation_suitable(zone); + } +} + /* * If no pages were isolated then mark this pageblock to be skipped in the - * future. The information is later cleared by reset_isolation_suitable(). + * future. The information is later cleared by __reset_isolation_suitable(). */ static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long nr_isolated, @@ -827,7 +833,15 @@ static int compact_finished(struct zone *zone, /* Compaction run completes if the migrate and free scanner meet */ if (cc->free_pfn <= cc->migrate_pfn) { - reset_isolation_suitable(cc->zone); + /* + * Mark that the PG_migrate_skip information should be cleared + * by kswapd when it goes to sleep. kswapd does not set the + * flag itself as the decision to be clear should be directly + * based on an allocation request. + */ + if (!current_is_kswapd()) + zone->compact_blockskip_flush = true; + return COMPACT_COMPLETE; } @@ -950,9 +964,13 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) zone->compact_cached_migrate_pfn = cc->migrate_pfn; } - /* Clear pageblock skip if there are numerous alloc failures */ - if (zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT) - reset_isolation_suitable(zone); + /* + * Clear pageblock skip if there were failures recently and compaction + * is about to be retried after being deferred. kswapd does not do + * this reset as it'll reset the cached information when going to sleep. + */ + if (compaction_restarting(zone, cc->order) && !current_is_kswapd()) + __reset_isolation_suitable(zone); migrate_prep_local(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e238fa34cdf9..deadd1c93041 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2171,6 +2171,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, preferred_zone, migratetype); if (page) { got_page: + preferred_zone->compact_blockskip_flush = false; preferred_zone->compact_considered = 0; preferred_zone->compact_defer_shift = 0; if (order >= preferred_zone->compact_order_failed) diff --git a/mm/vmscan.c b/mm/vmscan.c index 1ee4b69a28a5..b010efc43891 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2895,6 +2895,14 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); + /* + * Compaction records what page blocks it recently failed to + * isolate pages from and skips them in the future scanning. + * When kswapd is going to sleep, it is reasonable to assume + * that pages and compaction may succeed so reset the cache. + */ + reset_isolation_suitable(pgdat); + if (!kthread_should_stop()) schedule(); -- 2.39.5