2 files changed, 22 insertions, 3 deletions

diff --git a/include/linux/swap.h b/include/linux/swap.h
index c335055c4253..ed6ebe690f4a 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -155,6 +155,15 @@ enum {
 #define SWAP_CLUSTER_MAX 32
 #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
 
+/*
+ * Ratio between the present memory in the zone and the "gap" that
+ * we're allowing kswapd to shrink in addition to the per-zone high
+ * wmark, even for zones that already have the high wmark satisfied,
+ * in order to provide better per-zone lru behavior. We are ok to
+ * spend not more than 1% of the memory for this zone balancing "gap".
+ */
+#define KSWAPD_ZONE_BALANCE_GAP_RATIO 100
+
 #define SWAP_MAP_MAX    0x3e    /* Max duplication count, in first swap_map */
 #define SWAP_MAP_BAD    0x3f    /* Note pageblock is bad, in first swap_map */
 #define SWAP_HAS_CACHE  0x40    /* Flag page is cached, in first swap_map */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 665b090b6c72..060e4c191403 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2399,6 +2399,7 @@ loop_again:
                 for (i = 0; i <= end_zone; i++) {
                         struct zone *zone = pgdat->node_zones + i;
                         int nr_slab;
+                        unsigned long balance_gap;
 
                         if (!populated_zone(zone))
                                 continue;
@@ -2415,11 +2416,20 @@ loop_again:
                         mem_cgroup_soft_limit_reclaim(zone, order, sc.gfp_mask);
 
                         /*
-                         * We put equal pressure on every zone, unless one
-                         * zone has way too many pages free already.
+                         * We put equal pressure on every zone, unless
+                         * one zone has way too many pages free
+                         * already. The "too many pages" is defined
+                         * as the high wmark plus a "gap" where the
+                         * gap is either the low watermark or 1%
+                         * of the zone, whichever is smaller.
                          */
+                        balance_gap = min(low_wmark_pages(zone),
+                                (zone->present_pages +
+                                        KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
+                                KSWAPD_ZONE_BALANCE_GAP_RATIO);
                         if (!zone_watermark_ok_safe(zone, order,
-                                        8*high_wmark_pages(zone), end_zone, 0))
+                                        high_wmark_pages(zone) + balance_gap,
+                                        end_zone, 0))
                                 shrink_zone(priority, zone, &sc);
                         reclaim_state->reclaimed_slab = 0;
                         nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,