summaryrefslogtreecommitdiff
path: root/mm/vmscan.c
diff options
context:
space:
mode:
authorMel Gorman <mgorman@techsingularity.net>2016-07-29 01:45:59 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2016-07-29 02:07:41 +0300
commit86c79f6b5426ce118d32c73fa9e328f0a86ab590 (patch)
tree8cc32bcea6199c34326976a043b49c4df82a5851 /mm/vmscan.c
parent6256c6b499a1689d62ddfcb38d8048f9cd177070 (diff)
downloadlinux-86c79f6b5426ce118d32c73fa9e328f0a86ab590.tar.xz
mm: vmscan: do not reclaim from kswapd if there is any eligible zone
kswapd scans from highest to lowest for a zone that requires balancing. This was necessary when reclaim was per-zone to fairly age pages on lower zones. Now that we are reclaiming on a per-node basis, any eligible zone can be used and pages will still be aged fairly. This patch avoids reclaiming excessively unless buffer_heads are over the limit and it's necessary to reclaim from a higher zone than requested by the waker of kswapd to relieve low memory pressure. [hillf.zj@alibaba-inc.com: Force kswapd reclaim no more than needed] Link: http://lkml.kernel.org/r/1466518566-30034-12-git-send-email-mgorman@techsingularity.net Link: http://lkml.kernel.org/r/1467970510-21195-13-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Signed-off-by: Hillf Danton <hillf.zj@alibaba-inc.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@surriel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/vmscan.c')
-rw-r--r--mm/vmscan.c59
1 files changed, 27 insertions, 32 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8b39b903bd14..b7a276f4b1b0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3144,31 +3144,39 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
sc.nr_reclaimed = 0;
- /* Scan from the highest requested zone to dma */
- for (i = classzone_idx; i >= 0; i--) {
- zone = pgdat->node_zones + i;
- if (!populated_zone(zone))
- continue;
-
- /*
- * If the number of buffer_heads in the machine
- * exceeds the maximum allowed level and this node
- * has a highmem zone, force kswapd to reclaim from
- * it to relieve lowmem pressure.
- */
- if (buffer_heads_over_limit && is_highmem_idx(i)) {
- classzone_idx = i;
- break;
- }
+ /*
+ * If the number of buffer_heads in the machine exceeds the
+ * maximum allowed level then reclaim from all zones. This is
+ * not specific to highmem as highmem may not exist but it is
+ * it is expected that buffer_heads are stripped in writeback.
+ */
+ if (buffer_heads_over_limit) {
+ for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
+ zone = pgdat->node_zones + i;
+ if (!populated_zone(zone))
+ continue;
- if (!zone_balanced(zone, order, 0)) {
classzone_idx = i;
break;
}
}
- if (i < 0)
- goto out;
+ /*
+ * Only reclaim if there are no eligible zones. Check from
+ * high to low zone as allocations prefer higher zones.
+ * Scanning from low to high zone would allow congestion to be
+ * cleared during a very small window when a small low
+ * zone was balanced even under extreme pressure when the
+ * overall node may be congested.
+ */
+ for (i = classzone_idx; i >= 0; i--) {
+ zone = pgdat->node_zones + i;
+ if (!populated_zone(zone))
+ continue;
+
+ if (zone_balanced(zone, sc.order, classzone_idx))
+ goto out;
+ }
/*
* Do some background aging of the anon list, to give
@@ -3214,19 +3222,6 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
break;
/*
- * Stop reclaiming if any eligible zone is balanced and clear
- * node writeback or congested.
- */
- for (i = 0; i <= classzone_idx; i++) {
- zone = pgdat->node_zones + i;
- if (!populated_zone(zone))
- continue;
-
- if (zone_balanced(zone, sc.order, classzone_idx))
- goto out;
- }
-
- /*
* Raise priority if scanning rate is too low or there was no
* progress in reclaiming pages
*/