From 6f04f48dc9c0433e2bb687f5f7f7af1aba97b04d Mon Sep 17 00:00:00 2001 From: Suleiman Souhlal Date: Wed, 4 Jun 2014 16:06:44 -0700 Subject: mm: only force scan in reclaim when none of the LRUs are big enough. Prior to this change, we would decide whether to force scan a LRU during reclaim if that LRU itself was too small for the current priority. However, this can lead to the file LRU getting force scanned even if there are a lot of anonymous pages we can reclaim, leading to hot file pages getting needlessly reclaimed. To address this, we instead only force scan when none of the reclaimable LRUs are big enough. Gives huge improvements with zswap. For example, when doing -j20 kernel build in a 500MB container with zswap enabled, runtime (in seconds) is greatly reduced: x without this change + with this change N Min Max Median Avg Stddev x 5 700.997 790.076 763.928 754.05 39.59493 + 5 141.634 197.899 155.706 161.9 21.270224 Difference at 95.0% confidence -592.15 +/- 46.3521 -78.5293% +/- 6.14709% (Student's t, pooled s = 31.7819) Should also give some improvements in regular (non-zswap) swap cases. Yes, hughd found significant speedup using regular swap, with several memcgs under pressure; and it should also be effective in the non-memcg case, whenever one or another zone LRU is forced too small. Signed-off-by: Suleiman Souhlal Signed-off-by: Hugh Dickins Cc: Suleiman Souhlal Cc: Mel Gorman Acked-by: Rik van Riel Acked-by: Rafael Aquini Cc: Michal Hocko Cc: Yuanhan Liu Cc: Seth Jennings Cc: Bob Liu Cc: Minchan Kim Cc: Luigi Semenzato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 66 ++++++++++++++++++++++++++++++++++++------------------------- 1 file changed, 39 insertions(+), 27 deletions(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index 32c661d66a45..7901cb749e17 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1866,6 +1866,8 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, bool force_scan = false; unsigned long ap, fp; enum lru_list lru; + bool some_scanned; + int pass; /* * If the zone or memcg is small, nr[l] can be 0. This @@ -1989,39 +1991,49 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, fraction[1] = fp; denominator = ap + fp + 1; out: - for_each_evictable_lru(lru) { - int file = is_file_lru(lru); - unsigned long size; - unsigned long scan; + some_scanned = false; + /* Only use force_scan on second pass. */ + for (pass = 0; !some_scanned && pass < 2; pass++) { + for_each_evictable_lru(lru) { + int file = is_file_lru(lru); + unsigned long size; + unsigned long scan; - size = get_lru_size(lruvec, lru); - scan = size >> sc->priority; + size = get_lru_size(lruvec, lru); + scan = size >> sc->priority; - if (!scan && force_scan) - scan = min(size, SWAP_CLUSTER_MAX); + if (!scan && pass && force_scan) + scan = min(size, SWAP_CLUSTER_MAX); - switch (scan_balance) { - case SCAN_EQUAL: - /* Scan lists relative to size */ - break; - case SCAN_FRACT: + switch (scan_balance) { + case SCAN_EQUAL: + /* Scan lists relative to size */ + break; + case SCAN_FRACT: + /* + * Scan types proportional to swappiness and + * their relative recent reclaim efficiency. + */ + scan = div64_u64(scan * fraction[file], + denominator); + break; + case SCAN_FILE: + case SCAN_ANON: + /* Scan one type exclusively */ + if ((scan_balance == SCAN_FILE) != file) + scan = 0; + break; + default: + /* Look ma, no brain */ + BUG(); + } + nr[lru] = scan; /* - * Scan types proportional to swappiness and - * their relative recent reclaim efficiency. + * Skip the second pass and don't force_scan, + * if we found something to scan. */ - scan = div64_u64(scan * fraction[file], denominator); - break; - case SCAN_FILE: - case SCAN_ANON: - /* Scan one type exclusively */ - if ((scan_balance == SCAN_FILE) != file) - scan = 0; - break; - default: - /* Look ma, no brain */ - BUG(); + some_scanned |= !!scan; } - nr[lru] = scan; } } -- cgit v1.2.1