Subject: [merged] mm-vmscan-stall-page-reclaim-after-a-list-of-pages-have-been-processed-v3.patch removed from -mm tree To: mgorman@xxxxxxx,Valdis.Kletnieks@xxxxxx,dormando@xxxxxxxxx,hannes@xxxxxxxxxxx,jslaby@xxxxxxx,kamezawa.hiroyu@xxxxxxxxxxxxxx,mhocko@xxxxxxx,riel@xxxxxxxxxx,trond.myklebust@xxxxxxxxxx,zcalusic@xxxxxxxxxxx,mm-commits@xxxxxxxxxxxxxxx From: akpm@xxxxxxxxxxxxxxxxxxxx Date: Mon, 08 Jul 2013 12:24:54 -0700 The patch titled Subject: mm: vmscan: stall page reclaim after a list of pages have been processed has been removed from the -mm tree. Its filename was mm-vmscan-stall-page-reclaim-after-a-list-of-pages-have-been-processed-v3.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Mel Gorman <mgorman@xxxxxxx> Subject: mm: vmscan: stall page reclaim after a list of pages have been processed Commit "mm: vmscan: Block kswapd if it is encountering pages under writeback" blocks page reclaim if it encounters pages under writeback marked for immediate reclaim. It blocks while pages are still isolated from the LRU which is unnecessary. This patch defers the blocking until after the isolated pages have been processed and tidies up some of the comments. Signed-off-by: Mel Gorman <mgorman@xxxxxxx> Cc: Johannes Weiner <hannes@xxxxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxx> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Cc: Jiri Slaby <jslaby@xxxxxxx> Cc: Valdis Kletnieks <Valdis.Kletnieks@xxxxxx> Cc: Zlatko Calusic <zcalusic@xxxxxxxxxxx> Cc: dormando <dormando@xxxxxxxxx> Cc: Trond Myklebust <trond.myklebust@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/vmscan.c | 49 +++++++++++++++++++++++++++++++++---------------- 1 file changed, 33 insertions(+), 16 deletions(-) diff -puN mm/vmscan.c~mm-vmscan-stall-page-reclaim-after-a-list-of-pages-have-been-processed-v3 mm/vmscan.c --- a/mm/vmscan.c~mm-vmscan-stall-page-reclaim-after-a-list-of-pages-have-been-processed-v3 +++ a/mm/vmscan.c @@ -697,6 +697,7 @@ static unsigned long shrink_page_list(st enum ttu_flags ttu_flags, unsigned long *ret_nr_unqueued_dirty, unsigned long *ret_nr_writeback, + unsigned long *ret_nr_immediate, bool force_reclaim) { LIST_HEAD(ret_pages); @@ -707,6 +708,7 @@ static unsigned long shrink_page_list(st unsigned long nr_congested = 0; unsigned long nr_reclaimed = 0; unsigned long nr_writeback = 0; + unsigned long nr_immediate = 0; cond_resched(); @@ -773,8 +775,8 @@ static unsigned long shrink_page_list(st * IO can complete. Waiting on the page itself risks an * indefinite stall if it is impossible to writeback the * page due to IO error or disconnected storage so instead - * block for HZ/10 or until some IO completes then clear the - * ZONE_WRITEBACK flag to recheck if the condition exists. + * note that the LRU is being scanned too quickly and the + * caller can stall after page list has been processed. * * 2) Global reclaim encounters a page, memcg encounters a * page that is not marked for immediate reclaim or @@ -804,10 +806,8 @@ static unsigned long shrink_page_list(st if (current_is_kswapd() && PageReclaim(page) && zone_is_reclaim_writeback(zone)) { - unlock_page(page); - congestion_wait(BLK_RW_ASYNC, HZ/10); - zone_clear_flag(zone, ZONE_WRITEBACK); - goto keep; + nr_immediate++; + goto keep_locked; /* Case 2 above */ } else if (global_reclaim(sc) || @@ -1033,6 +1033,7 @@ keep: mem_cgroup_uncharge_end(); *ret_nr_unqueued_dirty += nr_unqueued_dirty; *ret_nr_writeback += nr_writeback; + *ret_nr_immediate += nr_immediate; return nr_reclaimed; } @@ -1044,7 +1045,7 @@ unsigned long reclaim_clean_pages_from_l .priority = DEF_PRIORITY, .may_unmap = 1, }; - unsigned long ret, dummy1, dummy2; + unsigned long ret, dummy1, dummy2, dummy3; struct page *page, *next; LIST_HEAD(clean_pages); @@ -1057,7 +1058,7 @@ unsigned long reclaim_clean_pages_from_l ret = shrink_page_list(&clean_pages, zone, &sc, TTU_UNMAP|TTU_IGNORE_ACCESS, - &dummy1, &dummy2, true); + &dummy1, &dummy2, &dummy3, true); list_splice(&clean_pages, page_list); __mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret); return ret; @@ -1353,6 +1354,7 @@ shrink_inactive_list(unsigned long nr_to unsigned long nr_taken; unsigned long nr_unqueued_dirty = 0; unsigned long nr_writeback = 0; + unsigned long nr_immediate = 0; isolate_mode_t isolate_mode = 0; int file = is_file_lru(lru); struct zone *zone = lruvec_zone(lruvec); @@ -1394,7 +1396,8 @@ shrink_inactive_list(unsigned long nr_to return 0; nr_reclaimed = shrink_page_list(&page_list, zone, sc, TTU_UNMAP, - &nr_unqueued_dirty, &nr_writeback, false); + &nr_unqueued_dirty, &nr_writeback, &nr_immediate, + false); spin_lock_irq(&zone->lru_lock); @@ -1447,14 +1450,28 @@ shrink_inactive_list(unsigned long nr_to } /* - * Similarly, if many dirty pages are encountered that are not - * currently being written then flag that kswapd should start - * writing back pages and stall to give a chance for flushers - * to catch up. + * memcg will stall in page writeback so only consider forcibly + * stalling for global reclaim */ - if (global_reclaim(sc) && nr_unqueued_dirty == nr_taken) { - congestion_wait(BLK_RW_ASYNC, HZ/10); - zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY); + if (global_reclaim(sc)) { + /* + * If dirty pages are scanned that are not queued for IO, it + * implies that flushers are not keeping up. In this case, flag + * the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing + * pages from reclaim context. It will forcibly stall in the + * next check. + */ + if (nr_unqueued_dirty == nr_taken) + zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY); + + /* + * In addition, if kswapd scans pages marked marked for + * immediate reclaim and under writeback (nr_immediate), it + * implies that pages are cycling through the LRU faster than + * they are written so also forcibly stall. + */ + if (nr_unqueued_dirty == nr_taken || nr_immediate) + congestion_wait(BLK_RW_ASYNC, HZ/10); } trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id, _ 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