From: Jerome Marchand <jmarc...@redhat.com> commit 2ab051e11bfa3cbb7b24177f3d6aaed10a0d743e upstream.
When memory cgoups are enabled, the code that decides to force to scan anonymous pages in get_scan_count() compares global values (free, high_watermark) to a value that is restricted to a memory cgroup (file). It make the code over-eager to force anon scan. For instance, it will force anon scan when scanning a memcg that is mainly populated by anonymous page, even when there is plenty of file pages to get rid of in others memcgs, even when swappiness == 0. It breaks user's expectation about swappiness and hurts performance. This patch makes sure that forced anon scan only happens when there not enough file pages for the all zone, not just in one random memcg. [han...@cmpxchg.org: cleanups] Signed-off-by: Jerome Marchand <jmarc...@redhat.com> Acked-by: Michal Hocko <mho...@suse.cz> Acked-by: Johannes Weiner <han...@cmpxchg.org> Reviewed-by: Rik van Riel <r...@redhat.com> Cc: Mel Gorman <mgor...@suse.de> Signed-off-by: Johannes Weiner <han...@cmpxchg.org> Signed-off-by: Andrew Morton <a...@linux-foundation.org> Signed-off-by: Linus Torvalds <torva...@linux-foundation.org> Signed-off-by: Mel Gorman <mgor...@suse.de> --- mm/vmscan.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 360ef8e..181f0b8 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1847,7 +1847,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, struct zone *zone = lruvec_zone(lruvec); unsigned long anon_prio, file_prio; enum scan_balance scan_balance; - unsigned long anon, file, free; + unsigned long anon, file; bool force_scan = false; unsigned long ap, fp; enum lru_list lru; @@ -1895,11 +1895,6 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, goto out; } - anon = get_lru_size(lruvec, LRU_ACTIVE_ANON) + - get_lru_size(lruvec, LRU_INACTIVE_ANON); - file = get_lru_size(lruvec, LRU_ACTIVE_FILE) + - get_lru_size(lruvec, LRU_INACTIVE_FILE); - /* * If it's foreseeable that reclaiming the file cache won't be * enough to get the zone back into a desirable shape, we have @@ -1907,8 +1902,14 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * thrashing - remaining file pages alone. */ if (global_reclaim(sc)) { - free = zone_page_state(zone, NR_FREE_PAGES); - if (unlikely(file + free <= high_wmark_pages(zone))) { + unsigned long zonefile; + unsigned long zonefree; + + zonefree = zone_page_state(zone, NR_FREE_PAGES); + zonefile = zone_page_state(zone, NR_ACTIVE_FILE) + + zone_page_state(zone, NR_INACTIVE_FILE); + + if (unlikely(zonefile + zonefree <= high_wmark_pages(zone))) { scan_balance = SCAN_ANON; goto out; } @@ -1943,6 +1944,12 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * * anon in [0], file in [1] */ + + anon = get_lru_size(lruvec, LRU_ACTIVE_ANON) + + get_lru_size(lruvec, LRU_INACTIVE_ANON); + file = get_lru_size(lruvec, LRU_ACTIVE_FILE) + + get_lru_size(lruvec, LRU_INACTIVE_FILE); + spin_lock_irq(&zone->lru_lock); if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) { reclaim_stat->recent_scanned[0] /= 2; -- 1.8.4.5 -- To unsubscribe from this list: send the line "unsubscribe stable" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html