From 9861a62c335cd34a2b6b25aaaf5898e8370299ec Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 7 Oct 2016 16:57:53 -0700 Subject: [PATCH] mm, compaction: create compact_gap wrapper Compaction uses a watermark gap of (2UL << order) pages at various places and it's not immediately obvious why. Abstract it through a compact_gap() wrapper to create a single place with a thorough explanation. [vbabka@suse.cz: clarify the comment of compact_gap()] Link: http://lkml.kernel.org/r/7b6aed1f-fdf8-2063-9ff4-bbe4de712d37@suse.cz Link: http://lkml.kernel.org/r/20160810091226.6709-9-vbabka@suse.cz Signed-off-by: Vlastimil Babka Tested-by: Lorenzo Stoakes Acked-by: Michal Hocko Cc: Mel Gorman Cc: Joonsoo Kim Cc: David Rientjes Cc: Rik van Riel Signed-off-by: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 23 +++++++++++++++++++++++ mm/compaction.c | 7 +++---- mm/vmscan.c | 6 +++--- 3 files changed, 29 insertions(+), 7 deletions(-) diff --git a/include/linux/compaction.h b/include/linux/compaction.h index a1fba9994728..585d55cb0dc0 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -58,6 +58,29 @@ enum compact_result { struct alloc_context; /* in mm/internal.h */ +/* + * Number of free order-0 pages that should be available above given watermark + * to make sure compaction has reasonable chance of not running out of free + * pages that it needs to isolate as migration target during its work. + */ +static inline unsigned long compact_gap(unsigned int order) +{ + /* + * Although all the isolations for migration are temporary, compaction + * free scanner may have up to 1 << order pages on its list and then + * try to split an (order - 1) free page. At that point, a gap of + * 1 << order might not be enough, so it's safer to require twice that + * amount. Note that the number of pages on the list is also + * effectively limited by COMPACT_CLUSTER_MAX, as that's the maximum + * that the migrate scanner can have isolated on migrate list, and free + * scanner is only invoked when the number of isolated free pages is + * lower than that. But it's not worth to complicate the formula here + * as a bigger gap for higher orders than strictly necessary can also + * improve chances of compaction success. + */ + return 2UL << order; +} + #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, diff --git a/mm/compaction.c b/mm/compaction.c index e2618ac062a6..bbf41ee99142 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1391,11 +1391,10 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order, return COMPACT_SUCCESS; /* - * 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 + * Watermarks for order-0 must be met for compaction to be able to + * isolate free pages for migration targets. */ - watermark = low_wmark_pages(zone) + (2UL << order); + watermark = low_wmark_pages(zone) + compact_gap(order); if (!__zone_watermark_ok(zone, 0, watermark, classzone_idx, alloc_flags, wmark_target)) return COMPACT_SKIPPED; diff --git a/mm/vmscan.c b/mm/vmscan.c index 981fc84e7434..2a6978a07d56 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2480,7 +2480,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, * If we have not reclaimed enough pages for compaction and the * inactive lists are large enough, continue reclaiming */ - pages_for_compaction = (2UL << sc->order); + pages_for_compaction = compact_gap(sc->order); inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); if (get_nr_swap_pages() > 0) inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); @@ -2612,7 +2612,7 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) * there is a buffer of free pages available to give compaction * a reasonable chance of completing and allocating the page */ - watermark = high_wmark_pages(zone) + (2UL << sc->order); + watermark = high_wmark_pages(zone) + compact_gap(sc->order); watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); /* @@ -3169,7 +3169,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat, * excessive reclaim. Assume that a process requested a high-order * can direct reclaim/compact. */ - if (sc->order && sc->nr_reclaimed >= 2UL << sc->order) + if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order)) sc->order = 0; return sc->nr_scanned >= sc->nr_to_reclaim;