From ba3a73862fe957ae943e5dffc0a52c971004cf19 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 3 Jul 2013 15:01:50 -0700 Subject: [PATCH] mm: vmscan: have kswapd writeback pages based on dirty pages encountered, not priority Currently kswapd queues dirty pages for writeback if scanning at an elevated priority but the priority kswapd scans at is not related to the number of unqueued dirty encountered. Since commit "mm: vmscan: Flatten kswapd priority loop", the priority is related to the size of the LRU and the zone watermark which is no indication as to whether kswapd should write pages or not. This patch tracks if an excessive number of unqueued dirty pages are being encountered at the end of the LRU. If so, it indicates that dirty pages are being recycled before flusher threads can clean them and flags the zone so that kswapd will start writing pages until the zone is balanced. Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Reviewed-by: Michal Hocko Cc: KAMEZAWA Hiroyuki Cc: Rik van Riel Cc: Jiri Slaby Cc: Valdis Kletnieks Tested-by: Zlatko Calusic Cc: dormando Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Git-commit: d43006d503ac921c7df4f94d13c17db6f13c9d26 Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git Change-Id: I565caf3aef9f3e5f59cda1adc70207412719a2ed Signed-off-by: Vinayak Menon --- include/linux/mmzone.h | 9 +++++++++ mm/vmscan.c | 31 +++++++++++++++++++++++++------ 2 files changed, 34 insertions(+), 6 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7dd8a1af6c02..e3184dbfa975 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -523,6 +523,10 @@ typedef enum { ZONE_CONGESTED, /* zone has many dirty pages backed by * a congested BDI */ + ZONE_TAIL_LRU_DIRTY, /* reclaim scanning has recently found + * many dirty file pages at the tail + * of the LRU. + */ } zone_flags_t; static inline void zone_set_flag(struct zone *zone, zone_flags_t flag) @@ -545,6 +549,11 @@ static inline int zone_is_reclaim_congested(const struct zone *zone) return test_bit(ZONE_CONGESTED, &zone->flags); } +static inline int zone_is_reclaim_dirty(const struct zone *zone) +{ + return test_bit(ZONE_TAIL_LRU_DIRTY, &zone->flags); +} + static inline int zone_is_reclaim_locked(const struct zone *zone) { return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags); diff --git a/mm/vmscan.c b/mm/vmscan.c index f88563fe40bf..9922518712e2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -764,13 +764,14 @@ static unsigned long shrink_page_list(struct list_head *page_list, struct zone *zone, struct scan_control *sc, enum ttu_flags ttu_flags, - unsigned long *ret_nr_dirty, + unsigned long *ret_nr_unqueued_dirty, unsigned long *ret_nr_writeback, bool force_reclaim) { LIST_HEAD(ret_pages); LIST_HEAD(free_pages); int pgactivate = 0; + unsigned long nr_unqueued_dirty = 0; unsigned long nr_dirty = 0; unsigned long nr_congested = 0; unsigned long nr_reclaimed = 0; @@ -896,14 +897,17 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (PageDirty(page)) { nr_dirty++; + if (!PageWriteback(page)) + nr_unqueued_dirty++; + /* * Only kswapd can writeback filesystem pages to - * avoid risk of stack overflow but do not writeback - * unless under significant pressure. + * avoid risk of stack overflow but only writeback + * if many dirty pages have been encountered. */ if (page_is_file_cache(page) && (!current_is_kswapd() || - sc->priority >= DEF_PRIORITY - 2)) { + !zone_is_reclaim_dirty(zone))) { /* * Immediately reclaim when written back. * Similar in principal to deactivate_page() @@ -1048,7 +1052,7 @@ keep: list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); mem_cgroup_uncharge_end(); - *ret_nr_dirty += nr_dirty; + *ret_nr_unqueued_dirty += nr_unqueued_dirty; *ret_nr_writeback += nr_writeback; return nr_reclaimed; } @@ -1462,6 +1466,15 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, (nr_taken >> (DEF_PRIORITY - sc->priority))) wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10); + /* + * Similarly, if many dirty pages are encountered that are not + * currently being written then flag that kswapd should start + * writing back pages. + */ + if (global_reclaim(sc) && nr_dirty && + nr_dirty >= (nr_taken >> (DEF_PRIORITY - sc->priority))) + zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY); + trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id, zone_idx(zone), nr_scanned, nr_reclaimed, @@ -2882,8 +2895,12 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, end_zone = i; break; } else { - /* If balanced, clear the congested flag */ + /* + * If balanced, clear the dirty and congested + * flags + */ zone_clear_flag(zone, ZONE_CONGESTED); + zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY); } } @@ -3001,8 +3018,10 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, * possible there are dirty pages backed by * congested BDIs but as pressure is relieved, * speculatively avoid congestion waits + * or writing pages from kswapd context. */ zone_clear_flag(zone, ZONE_CONGESTED); + zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY); } /*