Subject: [merged] mm-vmscan-have-kswapd-writeback-pages-based-on-dirty-pages-encountered-not-priority.patch removed from -mm tree To: mgorman@xxxxxxx,Valdis.Kletnieks@xxxxxx,dormando@xxxxxxxxx,hannes@xxxxxxxxxxx,jslaby@xxxxxxx,kamezawa.hiroyu@xxxxxxxxxxxxxx,mhocko@xxxxxxx,riel@xxxxxxxxxx,zcalusic@xxxxxxxxxxx,mm-commits@xxxxxxxxxxxxxxx From: akpm@xxxxxxxxxxxxxxxxxxxx Date: Mon, 08 Jul 2013 12:24:43 -0700 The patch titled Subject: mm: vmscan: have kswapd writeback pages based on dirty pages encountered, not priority has been removed from the -mm tree. Its filename was mm-vmscan-have-kswapd-writeback-pages-based-on-dirty-pages-encountered-not-priority.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Mel Gorman <mgorman@xxxxxxx> Subject: 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 <mgorman@xxxxxxx> Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx> Reviewed-by: Michal Hocko <mhocko@xxxxxxx> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxx> Cc: Jiri Slaby <jslaby@xxxxxxx> Cc: Valdis Kletnieks <Valdis.Kletnieks@xxxxxx> Tested-by: Zlatko Calusic <zcalusic@xxxxxxxxxxx> Cc: dormando <dormando@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/mmzone.h | 9 +++++++++ mm/vmscan.c | 31 +++++++++++++++++++++++++------ 2 files changed, 34 insertions(+), 6 deletions(-) diff -puN include/linux/mmzone.h~mm-vmscan-have-kswapd-writeback-pages-based-on-dirty-pages-encountered-not-priority include/linux/mmzone.h --- a/include/linux/mmzone.h~mm-vmscan-have-kswapd-writeback-pages-based-on-dirty-pages-encountered-not-priority +++ a/include/linux/mmzone.h @@ -495,6 +495,10 @@ 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) @@ -517,6 +521,11 @@ static inline int zone_is_reclaim_conges 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 -puN mm/vmscan.c~mm-vmscan-have-kswapd-writeback-pages-based-on-dirty-pages-encountered-not-priority mm/vmscan.c --- a/mm/vmscan.c~mm-vmscan-have-kswapd-writeback-pages-based-on-dirty-pages-encountered-not-priority +++ a/mm/vmscan.c @@ -676,13 +676,14 @@ static unsigned long shrink_page_list(st 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; @@ -808,14 +809,17 @@ static unsigned long shrink_page_list(st 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() @@ -960,7 +964,7 @@ 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; } @@ -1373,6 +1377,15 @@ shrink_inactive_list(unsigned long nr_to (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, @@ -2769,8 +2782,12 @@ static unsigned long balance_pgdat(pg_da 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); } } @@ -2888,8 +2905,10 @@ static unsigned long balance_pgdat(pg_da * 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); } /* _ Patches currently in -mm which might be from mgorman@xxxxxxx are origin.patch linux-next.patch fs-bump-inode-and-dentry-counters-to-long.patch super-fix-calculation-of-shrinkable-objects-for-small-numbers.patch dcache-convert-dentry_statnr_unused-to-per-cpu-counters.patch dentry-move-to-per-sb-lru-locks.patch dcache-remove-dentries-from-lru-before-putting-on-dispose-list.patch mm-new-shrinker-api.patch shrinker-convert-superblock-shrinkers-to-new-api.patch list-add-a-new-lru-list-type.patch inode-convert-inode-lru-list-to-generic-lru-list-code.patch dcache-convert-to-use-new-lru-list-infrastructure.patch list_lru-per-node-list-infrastructure.patch list_lru-per-node-api.patch shrinker-add-node-awareness.patch vmscan-per-node-deferred-work.patch fs-convert-inode-and-dentry-shrinking-to-be-node-aware.patch xfs-convert-buftarg-lru-to-generic-code.patch xfs-rework-buffer-dispose-list-tracking.patch xfs-convert-dquot-cache-lru-to-list_lru.patch fs-convert-fs-shrinkers-to-new-scan-count-api.patch drivers-convert-shrinkers-to-new-count-scan-api.patch i915-bail-out-earlier-when-shrinker-cannot-acquire-mutex.patch shrinker-convert-remaining-shrinkers-to-count-scan-api.patch hugepage-convert-huge-zero-page-shrinker-to-new-shrinker-api.patch shrinker-kill-old-shrink-api.patch list_lru-dynamically-adjust-node-arrays.patch zbud-add-to-mm.patch zswap-add-to-mm.patch zswap-add-documentation.patch mm-vmscan-do-not-continue-scanning-if-reclaim-was-aborted-for-compaction.patch mm-vmscan-do-not-scale-writeback-pages-when-deciding-whether-to-set-zone_writeback.patch mm-memmap_init_zone-performance-improvement.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html