From 35cd78156c499ef83f60605e4643d5a98fef14fd Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 21 Sep 2009 17:01:38 -0700 Subject: [PATCH] vmscan: throttle direct reclaim when too many pages are isolated already When way too many processes go into direct reclaim, it is possible for all of the pages to be taken off the LRU. One result of this is that the next process in the page reclaim code thinks there are no reclaimable pages left and triggers an out of memory kill. One solution to this problem is to never let so many processes into the page reclaim path that the entire LRU is emptied. Limiting the system to only having half of each inactive list isolated for reclaim should be safe. Signed-off-by: Rik van Riel Cc: KOSAKI Motohiro Cc: Wu Fengguang Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/mm/vmscan.c b/mm/vmscan.c index 75c2997..f90b760 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1034,6 +1034,31 @@ int isolate_lru_page(struct page *page) } /* + * Are there way too many processes in the direct reclaim path already? + */ +static int too_many_isolated(struct zone *zone, int file, + struct scan_control *sc) +{ + unsigned long inactive, isolated; + + if (current_is_kswapd()) + return 0; + + if (!scanning_global_lru(sc)) + return 0; + + if (file) { + inactive = zone_page_state(zone, NR_INACTIVE_FILE); + isolated = zone_page_state(zone, NR_ISOLATED_FILE); + } else { + inactive = zone_page_state(zone, NR_INACTIVE_ANON); + isolated = zone_page_state(zone, NR_ISOLATED_ANON); + } + + return isolated > inactive; +} + +/* * shrink_inactive_list() is a helper for shrink_zone(). It returns the number * of reclaimed pages */ @@ -1048,6 +1073,14 @@ static unsigned long shrink_inactive_list(unsigned long max_scan, struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc); int lumpy_reclaim = 0; + while (unlikely(too_many_isolated(zone, file, sc))) { + congestion_wait(WRITE, HZ/10); + + /* We are about to die and free our memory. Return now. */ + if (fatal_signal_pending(current)) + return SWAP_CLUSTER_MAX; + } + /* * If we need a large contiguous chunk of memory, or have * trouble getting a small set of contiguous pages, we -- 2.7.4