From 9f28735b1bb7727e7495cf76e88e63ad8953ba65 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 7 Jun 2014 19:11:23 -0700 Subject: Revert "revert "mm: vmscan: do not swap anon pages just because free+file is low"" This reverts commit 623762517e2370be3b3f95f4fe08d6c063a49b06. Ben rightly points out that commit 0bf1457f0cfc, which is what this original commit was reverting, never ended up in 3.14-stable, but was only for 3.15. So revert this patch as we now have the same check twice in a row, which is pretty pointless. Although the comments were "prettier"... Cc: Ben Hutchings Cc: Johannes Weiner Cc: Christian Borntraeger Cc: Christian Borntraeger Cc: Rafael Aquini Cc: Rik van Riel Cc: Andrew Morton Cc: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/vmscan.c | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index 30a4b096ff6e..a9c74b409681 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1915,24 +1915,6 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, } } - /* - * Prevent the reclaimer from falling into the cache trap: as - * cache pages start out inactive, every cache fault will tip - * the scan balance towards the file LRU. And as the file LRU - * shrinks, so does the window for rotation from references. - * This means we have a runaway feedback loop where a tiny - * thrashing file LRU becomes infinitely more attractive than - * anon pages. Try to detect this based on file LRU size. - */ - if (global_reclaim(sc)) { - unsigned long free = zone_page_state(zone, NR_FREE_PAGES); - - if (unlikely(file + free <= high_wmark_pages(zone))) { - scan_balance = SCAN_ANON; - goto out; - } - } - /* * There is enough inactive page cache, do not reclaim * anything from the anonymous working set right now. -- cgit v1.2.3