memcg: fix vmscan count in small memcgs

commit 4508378b9523e22a2a0175d8bf64d932fb10a67d upstream.

Commit 246e87a93934 ("memcg: fix get_scan_count() for small targets")
fixes the memcg/kswapd behavior against small targets and prevent vmscan
priority too high.

But the implementation is too naive and adds another problem to small
memcg.  It always force scan to 32 pages of file/anon and doesn't handle
swappiness and other rotate_info.  It makes vmscan to scan anon LRU
regardless of swappiness and make reclaim bad.  This patch fixes it by
adjusting scanning count with regard to swappiness at el.

At a test "cat 1G file under 300M limit." (swappiness=20)
 before patch
        scanned_pages_by_limit 360919
        scanned_anon_pages_by_limit 180469
        scanned_file_pages_by_limit 180450
        rotated_pages_by_limit 31
        rotated_anon_pages_by_limit 25
        rotated_file_pages_by_limit 6
        freed_pages_by_limit 180458
        freed_anon_pages_by_limit 19
        freed_file_pages_by_limit 180439
        elapsed_ns_by_limit 429758872
 after patch
        scanned_pages_by_limit 180674
        scanned_anon_pages_by_limit 24
        scanned_file_pages_by_limit 180650
        rotated_pages_by_limit 35
        rotated_anon_pages_by_limit 24
        rotated_file_pages_by_limit 11
        freed_pages_by_limit 180634
        freed_anon_pages_by_limit 0
        freed_file_pages_by_limit 180634
        elapsed_ns_by_limit 367119089
        scanned_pages_by_system 0

the numbers of scanning anon are decreased(as expected), and elapsed time
reduced. By this patch, small memcgs will work better.
(*) Because the amount of file-cache is much bigger than anon,
    recalaim_stat's rotate-scan counter make scanning files more.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/mm/vmscan.c b/mm/vmscan.c
index d036e59..6072d74 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1748,6 +1748,7 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
        enum lru_list l;
        int noswap = 0;
        int force_scan = 0;
+       unsigned long nr_force_scan[2];
 
 
        anon  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
@@ -1770,6 +1771,8 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
                fraction[0] = 0;
                fraction[1] = 1;
                denominator = 1;
+               nr_force_scan[0] = 0;
+               nr_force_scan[1] = SWAP_CLUSTER_MAX;
                goto out;
        }
 
@@ -1781,6 +1784,8 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
                        fraction[0] = 1;
                        fraction[1] = 0;
                        denominator = 1;
+                       nr_force_scan[0] = SWAP_CLUSTER_MAX;
+                       nr_force_scan[1] = 0;
                        goto out;
                }
        }
@@ -1829,6 +1834,11 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
        fraction[0] = ap;
        fraction[1] = fp;
        denominator = ap + fp + 1;
+       if (force_scan) {
+               unsigned long scan = SWAP_CLUSTER_MAX;
+               nr_force_scan[0] = div64_u64(scan * ap, denominator);
+               nr_force_scan[1] = div64_u64(scan * fp, denominator);
+       }
 out:
        for_each_evictable_lru(l) {
                int file = is_file_lru(l);
@@ -1849,12 +1859,8 @@ out:
                 * memcg, priority drop can cause big latency. So, it's better
                 * to scan small amount. See may_noscan above.
                 */
-               if (!scan && force_scan) {
-                       if (file)
-                               scan = SWAP_CLUSTER_MAX;
-                       else if (!noswap)
-                               scan = SWAP_CLUSTER_MAX;
-               }
+               if (!scan && force_scan)
+                       scan = nr_force_scan[file];
                nr[l] = scan;
        }
 }