From c55e8d035b28b2867e68b0e2d0eee2c0f1016b43 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 24 Feb 2017 14:56:23 -0800 Subject: [PATCH] mm: vmscan: move dirty pages out of the way until they're flushed We noticed a performance regression when moving hadoop workloads from 3.10 kernels to 4.0 and 4.6. This is accompanied by increased pageout activity initiated by kswapd as well as frequent bursts of allocation stalls and direct reclaim scans. Even lowering the dirty ratios to the equivalent of less than 1% of memory would not eliminate the issue, suggesting that dirty pages concentrate where the scanner is looking. This can be traced back to recent efforts of thrash avoidance. Where 3.10 would not detect refaulting pages and continuously supply clean cache to the inactive list, a thrashing workload on 4.0+ will detect and activate refaulting pages right away, distilling used-once pages on the inactive list much more effectively. This is by design, and it makes sense for clean cache. But for the most part our workload's cache faults are refaults and its use-once cache is from streaming writes. We end up with most of the inactive list dirty, and we don't go after the active cache as long as we have use-once pages around. But waiting for writes to avoid reclaiming clean cache that *might* refault is a bad trade-off. Even if the refaults happen, reads are faster than writes. Before getting bogged down on writeback, reclaim should first look at *all* cache in the system, even active cache. To accomplish this, activate pages that are dirty or under writeback when they reach the end of the inactive LRU. The pages are marked for immediate reclaim, meaning they'll get moved back to the inactive LRU tail as soon as they're written back and become reclaimable. But in the meantime, by reducing the inactive list to only immediately reclaimable pages, we allow the scanner to deactivate and refill the inactive list with clean cache from the active list tail to guarantee forward progress. [hannes@cmpxchg.org: update comment] Link: http://lkml.kernel.org/r/20170202191957.22872-8-hannes@cmpxchg.org Link: http://lkml.kernel.org/r/20170123181641.23938-6-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Minchan Kim Acked-by: Michal Hocko Acked-by: Hillf Danton Cc: Mel Gorman Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 7 +++++++ mm/swap.c | 9 +++++---- mm/vmscan.c | 15 ++++++++++++--- 3 files changed, 24 insertions(+), 7 deletions(-) diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 41d376e7116d..e030a68ead7e 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -50,6 +50,13 @@ static __always_inline void add_page_to_lru_list(struct page *page, list_add(&page->lru, &lruvec->lists[lru]); } +static __always_inline void add_page_to_lru_list_tail(struct page *page, + struct lruvec *lruvec, enum lru_list lru) +{ + update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page)); + list_add_tail(&page->lru, &lruvec->lists[lru]); +} + static __always_inline void del_page_from_lru_list(struct page *page, struct lruvec *lruvec, enum lru_list lru) { diff --git a/mm/swap.c b/mm/swap.c index aabf2e90fe32..c4910f14f957 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -209,9 +209,10 @@ static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec, { int *pgmoved = arg; - if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { - enum lru_list lru = page_lru_base_type(page); - list_move_tail(&page->lru, &lruvec->lists[lru]); + if (PageLRU(page) && !PageUnevictable(page)) { + del_page_from_lru_list(page, lruvec, page_lru(page)); + ClearPageActive(page); + add_page_to_lru_list_tail(page, lruvec, page_lru(page)); (*pgmoved)++; } } @@ -235,7 +236,7 @@ static void pagevec_move_tail(struct pagevec *pvec) */ void rotate_reclaimable_page(struct page *page) { - if (!PageLocked(page) && !PageDirty(page) && !PageActive(page) && + if (!PageLocked(page) && !PageDirty(page) && !PageUnevictable(page) && PageLRU(page)) { struct pagevec *pvec; unsigned long flags; diff --git a/mm/vmscan.c b/mm/vmscan.c index 92e56cadceae..ae3d982216b5 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1056,6 +1056,15 @@ static unsigned long shrink_page_list(struct list_head *page_list, * throttling so we could easily OOM just because too many * pages are in writeback and there is nothing else to * reclaim. Wait for the writeback to complete. + * + * In cases 1) and 2) we activate the pages to get them out of + * the way while we continue scanning for clean pages on the + * inactive list and refilling from the active list. The + * observation here is that waiting for disk writes is more + * expensive than potentially causing reloads down the line. + * Since they're marked for immediate reclaim, they won't put + * memory pressure on the cache working set any longer than it + * takes to write them to disk. */ if (PageWriteback(page)) { /* Case 1 above */ @@ -1063,7 +1072,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, PageReclaim(page) && test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { nr_immediate++; - goto keep_locked; + goto activate_locked; /* Case 2 above */ } else if (sane_reclaim(sc) || @@ -1081,7 +1090,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, */ SetPageReclaim(page); nr_writeback++; - goto keep_locked; + goto activate_locked; /* Case 3 above */ } else { @@ -1174,7 +1183,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, inc_node_page_state(page, NR_VMSCAN_IMMEDIATE); SetPageReclaim(page); - goto keep_locked; + goto activate_locked; } if (references == PAGEREF_RECLAIM_CLEAN)