From: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx> Subject: mm/page_alloc: limit the number of pages on PCP lists when reclaim is active When kswapd is active then direct reclaim is potentially active. In either case, it is possible that a zone would be balanced if pages were not trapped on PCP lists. Instead of draining remote pages, simply limit the size of the PCP lists while kswapd is active. Link: https://lkml.kernel.org/r/20210525080119.5455-6-mgorman@xxxxxxxxxxxxxxxxxxx Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx> Acked-by: Vlastimil Babka <vbabka@xxxxxxx> Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx> Cc: Hillf Danton <hdanton@xxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/mmzone.h | 1 + mm/page_alloc.c | 19 ++++++++++++++++++- mm/vmscan.c | 35 +++++++++++++++++++++++++++++++++++ 3 files changed, 54 insertions(+), 1 deletion(-) --- a/include/linux/mmzone.h~mm-page_alloc-limit-the-number-of-pages-on-pcp-lists-when-reclaim-is-active +++ a/include/linux/mmzone.h @@ -647,6 +647,7 @@ enum zone_flags { ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. * Cleared when kswapd is woken. */ + ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */ }; static inline unsigned long zone_managed_pages(struct zone *zone) --- a/mm/page_alloc.c~mm-page_alloc-limit-the-number-of-pages-on-pcp-lists-when-reclaim-is-active +++ a/mm/page_alloc.c @@ -3302,6 +3302,23 @@ static int nr_pcp_free(struct per_cpu_pa return batch; } +static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone) +{ + int high = READ_ONCE(pcp->high); + + if (unlikely(!high)) + return 0; + + if (!test_bit(ZONE_RECLAIM_ACTIVE, &zone->flags)) + return high; + + /* + * If reclaim is active, limit the number of pages that can be + * stored on pcp lists + */ + return min(READ_ONCE(pcp->batch) << 2, high); +} + static void free_unref_page_commit(struct page *page, unsigned long pfn, int migratetype) { @@ -3313,7 +3330,7 @@ static void free_unref_page_commit(struc pcp = this_cpu_ptr(zone->per_cpu_pageset); list_add(&page->lru, &pcp->lists[migratetype]); pcp->count++; - high = READ_ONCE(pcp->high); + high = nr_pcp_high(pcp, zone); if (pcp->count >= high) { int batch = READ_ONCE(pcp->batch); --- a/mm/vmscan.c~mm-page_alloc-limit-the-number-of-pages-on-pcp-lists-when-reclaim-is-active +++ a/mm/vmscan.c @@ -3722,6 +3722,38 @@ static bool kswapd_shrink_node(pg_data_t return sc->nr_scanned >= sc->nr_to_reclaim; } +/* Page allocator PCP high watermark is lowered if reclaim is active. */ +static inline void +update_reclaim_active(pg_data_t *pgdat, int highest_zoneidx, bool active) +{ + int i; + struct zone *zone; + + for (i = 0; i <= highest_zoneidx; i++) { + zone = pgdat->node_zones + i; + + if (!managed_zone(zone)) + continue; + + if (active) + set_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); + else + clear_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); + } +} + +static inline void +set_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) +{ + update_reclaim_active(pgdat, highest_zoneidx, true); +} + +static inline void +clear_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) +{ + update_reclaim_active(pgdat, highest_zoneidx, false); +} + /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is @@ -3774,6 +3806,7 @@ static int balance_pgdat(pg_data_t *pgda boosted = nr_boost_reclaim; restart: + set_reclaim_active(pgdat, highest_zoneidx); sc.priority = DEF_PRIORITY; do { unsigned long nr_reclaimed = sc.nr_reclaimed; @@ -3907,6 +3940,8 @@ restart: pgdat->kswapd_failures++; out: + clear_reclaim_active(pgdat, highest_zoneidx); + /* If reclaim was boosted, account for the reclaim done in this pass */ if (boosted) { unsigned long flags; _