mm: vmscan: decide whether to compact the pgdat based on reclaim progress

In the past, kswapd makes a decision on whether to compact memory after
the pgdat was considered balanced.  This more or less worked but it is
late to make such a decision and does not fit well now that kswapd makes a
decision whether to exit the zone scanning loop depending on reclaim
progress.

This patch will compact a pgdat if at least the requested number of pages
were reclaimed from unbalanced zones for a given priority.  If any zone is
currently balanced, kswapd will not call compaction as it is expected the
necessary pages are already available.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Tested-by: Zlatko Calusic <zcalusic@bitsync.net>
Cc: dormando <dormando@rydia.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1c10ee51221537b003d281d2e73b311136c43b61..cd0980393bac765218b0828b315c6ea50bfc5b64 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2661,7 +2661,8 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
  */
 static bool kswapd_shrink_zone(struct zone *zone,
                               struct scan_control *sc,
-                              unsigned long lru_pages)
+                              unsigned long lru_pages,
+                              unsigned long *nr_attempted)
 {
        unsigned long nr_slab;
        struct reclaim_state *reclaim_state = current->reclaim_state;
@@ -2677,6 +2678,9 @@ static bool kswapd_shrink_zone(struct zone *zone,
        nr_slab = shrink_slab(&shrink, sc->nr_scanned, lru_pages);
        sc->nr_reclaimed += reclaim_state->reclaimed_slab;
 
+       /* Account for the number of pages attempted to reclaim */
+       *nr_attempted += sc->nr_to_reclaim;
+
        if (nr_slab == 0 && !zone_reclaimable(zone))
                zone->all_unreclaimable = 1;
 
@@ -2724,7 +2728,9 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 
        do {
                unsigned long lru_pages = 0;
+               unsigned long nr_attempted = 0;
                bool raise_priority = true;
+               bool pgdat_needs_compaction = (order > 0);
 
                sc.nr_reclaimed = 0;
 
@@ -2774,7 +2780,21 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
                for (i = 0; i <= end_zone; i++) {
                        struct zone *zone = pgdat->node_zones + i;
 
+                       if (!populated_zone(zone))
+                               continue;
+
                        lru_pages += zone_reclaimable_pages(zone);
+
+                       /*
+                        * If any zone is currently balanced then kswapd will
+                        * not call compaction as it is expected that the
+                        * necessary pages are already available.
+                        */
+                       if (pgdat_needs_compaction &&
+                                       zone_watermark_ok(zone, order,
+                                               low_wmark_pages(zone),
+                                               *classzone_idx, 0))
+                               pgdat_needs_compaction = false;
                }
 
                /*
@@ -2843,7 +2863,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
                                 * already being scanned that high
                                 * watermark would be met at 100% efficiency.
                                 */
-                               if (kswapd_shrink_zone(zone, &sc, lru_pages))
+                               if (kswapd_shrink_zone(zone, &sc, lru_pages,
+                                                      &nr_attempted))
                                        raise_priority = false;
                        }
 
@@ -2895,6 +2916,13 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
                if (try_to_freeze() || kthread_should_stop())
                        break;
 
+               /*
+                * Compact if necessary and kswapd is reclaiming at least the
+                * high watermark number of pages as requsted
+                */
+               if (pgdat_needs_compaction && sc.nr_reclaimed > nr_attempted)
+                       compact_pgdat(pgdat, order);
+
                /*
                 * Raise priority if scanning rate is too low or there was no
                 * progress in reclaiming pages
@@ -2904,33 +2932,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
        } while (sc.priority >= 0 &&
                 !pgdat_balanced(pgdat, order, *classzone_idx));
 
-       /*
-        * If kswapd was reclaiming at a higher order, it has the option of
-        * sleeping without all zones being balanced. Before it does, it must
-        * ensure that the watermarks for order-0 on *all* zones are met and
-        * that the congestion flags are cleared. The congestion flag must
-        * be cleared as kswapd is the only mechanism that clears the flag
-        * and it is potentially going to sleep here.
-        */
-       if (order) {
-               int zones_need_compaction = 1;
-
-               for (i = 0; i <= end_zone; i++) {
-                       struct zone *zone = pgdat->node_zones + i;
-
-                       if (!populated_zone(zone))
-                               continue;
-
-                       /* Check if the memory needs to be defragmented. */
-                       if (zone_watermark_ok(zone, order,
-                                   low_wmark_pages(zone), *classzone_idx, 0))
-                               zones_need_compaction = 0;
-               }
-
-               if (zones_need_compaction)
-                       compact_pgdat(pgdat, order);
-       }
-
 out:
        /*
         * Return the order we were reclaiming at so prepare_kswapd_sleep()