From 726d061fbd3658e4bfeffa1b8e82da97de2ca4dd Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 24 Feb 2017 14:56:14 -0800 Subject: [PATCH] mm: vmscan: kick flushers when we encounter dirty pages on the LRU Memory pressure can put dirty pages at the end of the LRU without anybody running into dirty limits. Don't start writing individual pages from kswapd while the flushers might be asleep. Unlike the old direct reclaim flusher wakeup (removed in the next patch) that flushes the number of pages just scanned, this patch wakes the flushers for all outstanding dirty pages. That seemed to perform better in a synthetic test that pushes dirty pages to the end of the LRU and into reclaim, because we know LRU aging outstrips writeback already, and this way we give younger dirty pages a headstart rather than wait until reclaim runs into them as well. It also means less plugging and risk of exhausting the struct request pool from reclaim. There is a concern that this will cause temporary files that used to get dirtied and truncated before writeback to now get written to disk under memory pressure. If this turns out to be a real problem, we'll have to revisit this and tame the reclaim flusher wakeups. [hannes@cmpxchg.org: mention dirty expiration as a condition] Link: http://lkml.kernel.org/r/20170126174739.GA30636@cmpxchg.org Link: http://lkml.kernel.org/r/20170123181641.23938-3-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Minchan Kim Acked-by: Michal Hocko Acked-by: Mel Gorman Acked-by: Hillf Danton Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/writeback.h | 2 +- include/trace/events/writeback.h | 2 +- mm/vmscan.c | 18 +++++++++++++----- 3 files changed, 15 insertions(+), 7 deletions(-) diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 5527d910ba3d..a3c0cbd7c888 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -46,7 +46,7 @@ enum writeback_sync_modes { */ enum wb_reason { WB_REASON_BACKGROUND, - WB_REASON_TRY_TO_FREE_PAGES, + WB_REASON_VMSCAN, WB_REASON_SYNC, WB_REASON_PERIODIC, WB_REASON_LAPTOP_TIMER, diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 2ccd9ccbf9ef..7bd8783a590f 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -31,7 +31,7 @@ #define WB_WORK_REASON \ EM( WB_REASON_BACKGROUND, "background") \ - EM( WB_REASON_TRY_TO_FREE_PAGES, "try_to_free_pages") \ + EM( WB_REASON_VMSCAN, "vmscan") \ EM( WB_REASON_SYNC, "sync") \ EM( WB_REASON_PERIODIC, "periodic") \ EM( WB_REASON_LAPTOP_TIMER, "laptop_timer") \ diff --git a/mm/vmscan.c b/mm/vmscan.c index 0d05f7f3b532..83c92b866afe 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1798,12 +1798,20 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, /* * If dirty pages are scanned that are not queued for IO, it - * implies that flushers are not keeping up. In this case, flag - * the pgdat PGDAT_DIRTY and kswapd will start writing pages from - * reclaim context. + * implies that flushers are not doing their job. This can + * happen when memory pressure pushes dirty pages to the end of + * the LRU before the dirty limits are breached and the dirty + * data has expired. It can also happen when the proportion of + * dirty pages grows not through writes but through memory + * pressure reclaiming all the clean cache. And in some cases, + * the flushers simply cannot keep up with the allocation + * rate. Nudge the flusher threads in case they are asleep, but + * also allow kswapd to start writing pages during reclaim. */ - if (stat.nr_unqueued_dirty == nr_taken) + if (stat.nr_unqueued_dirty == nr_taken) { + wakeup_flusher_threads(0, WB_REASON_VMSCAN); set_bit(PGDAT_DIRTY, &pgdat->flags); + } /* * If kswapd scans pages marked marked for immediate @@ -2787,7 +2795,7 @@ retry: writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2; if (total_scanned > writeback_threshold) { wakeup_flusher_threads(laptop_mode ? 0 : total_scanned, - WB_REASON_TRY_TO_FREE_PAGES); + WB_REASON_VMSCAN); sc->may_writepage = 1; } } while (--sc->priority >= 0); -- 2.20.1