Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1376677

[PATCH 26/28] mm: page_alloc: Cache the last node whose dirty limit is reached

Show all headers | View raw

If a page is about to be dirtied then the page allocator attempts to limit
the total number of dirty pages that exists in any given zone. The call
to node_dirty_ok is expensive so this patch records if the last pgdat
examined hit the dirty limits. In some cases, this reduces the number
of calls to node_dirty_ok().

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 mm/page_alloc.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b54f45876130..490a3cd34b7d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2699,6 +2699,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 {
 	struct zoneref *z = ac->preferred_zoneref;
 	struct zone *zone;
+	struct pglist_data *last_pgdat_dirty_limit = NULL;
+
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
 	 * See also __cpuset_node_allowed() comment in kernel/cpuset.c.
@@ -2731,8 +2733,15 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 		 * will require awareness of nodes in the
 		 * dirty-throttling and the flusher threads.
 		 */
-		if (ac->spread_dirty_pages && !node_dirty_ok(zone->zone_pgdat))
-			continue;
+		if (ac->spread_dirty_pages) {
+			if (last_pgdat_dirty_limit == zone->zone_pgdat)
+				continue;
+
+			if (!node_dirty_ok(zone->zone_pgdat)) {
+				last_pgdat_dirty_limit = zone->zone_pgdat;
+				continue;
+			}
+		}
 
 		mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
 		if (!zone_watermark_fast(zone, order, mark,
-- 
2.6.4

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH 00/28] Move LRU page reclaim from zones to nodes v4 Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:30 +0200
  [PATCH 03/28] mm, vmscan: Move lru_lock to the node Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:30 +0200
  [PATCH 09/28] mm, vmscan: Simplify the logic deciding whether kswapd sleeps Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:30 +0200
  [PATCH 11/28] mm, vmscan: Clear congestion, dirty and need for compaction on a per-node basis Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:30 +0200
  [PATCH 27/28] mm: vmstat: Replace __count_zone_vm_events with a zone id equivalent Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200
  [PATCH 21/28] mm, vmscan: Update classzone_idx if buffer_heads_over_limit Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200
  [PATCH 24/28] mm, vmscan: Add classzone information to tracepoints Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200
  [PATCH 28/28] mm: vmstat: Account per-zone stalls and pages skipped during reclaim Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200
  [PATCH 17/28] mm: Move page mapped accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200
  [PATCH 26/28] mm: page_alloc: Cache the last node whose dirty limit is reached Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200
  [PATCH 25/28] mm, page_alloc: Remove fair zone allocation policy Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200
  [PATCH 14/28] mm, memcg: Move memcg limit enforcement from zones to nodes Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200
    [PATCH 15/28] mm, workingset: Make working set detection node-aware Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200
    [PATCH 23/28] mm: Convert zone_reclaim to node_reclaim Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200
    [PATCH 20/28] mm: Move vmscan writes and file write accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200
    [PATCH 16/28] mm, page_alloc: Consider dirtyable memory in terms of nodes Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200
    [PATCH 18/28] mm: Rename NR_ANON_PAGES to NR_ANON_MAPPED Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200
    [PATCH 22/28] mm, vmscan: Only wakeup kswapd once per node for the requested classzone Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200
    [PATCH 19/28] mm: Move most file-based accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-04-12 12:50 +0200

csiph-web