[RFC][PATCH 5/5] memcg softlimit hooks to kswapd

[KAMEZAWA Hiroyuki]

This patch needs MORE investigation...

==
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>

This patch adds hooks for memcg's softlimit to kswapd().

Softlimit handler is called...
  - before generic shrink_zone() is called.
  - # of pages to be scanned depends on priority.
  - If not enough progress, selected memcg will be moved to UNUSED queue.
  - at each call for balance_pgdat(), softlimit queue is rebalanced.

Changelog: v3 -> v4
 - move "sc" as local variable

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
---
 mm/vmscan.c |   52 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

Index: mmotm-2.6.29-Mar10/mm/vmscan.c
===================================================================
--- mmotm-2.6.29-Mar10.orig/mm/vmscan.c
+++ mmotm-2.6.29-Mar10/mm/vmscan.c
@@ -1733,6 +1733,49 @@ unsigned long try_to_free_mem_cgroup_pag
 }
 #endif
 
+static void shrink_zone_softlimit(struct zone *zone, int order, int priority,
+			   int target, int end_zone)
+{
+	int scan = SWAP_CLUSTER_MAX;
+	int nid = zone->zone_pgdat->node_id;
+	int zid = zone_idx(zone);
+	struct mem_cgroup *mem;
+	struct scan_control sc =  {
+		.gfp_mask = GFP_KERNEL,
+		.may_writepage = !laptop_mode,
+		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.may_unmap = 1,
+		.swappiness = vm_swappiness,
+		.order = order,
+		.mem_cgroup = NULL,
+		.isolate_pages = mem_cgroup_isolate_pages,
+	};
+
+	scan = target * 2;
+
+	sc.nr_scanned = 0;
+	sc.nr_reclaimed = 0;
+	while (scan > 0) {
+		if (zone_watermark_ok(zone, order, target, end_zone, 0))
+			break;
+		mem = mem_cgroup_schedule(nid, zid);
+		if (!mem)
+			return;
+		sc.mem_cgroup = mem;
+
+		sc.nr_reclaimed = 0;
+		shrink_zone(priority, zone, &sc);
+
+		if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX/2)
+			mem_cgroup_schedule_end(nid, zid, mem, true);
+		else
+			mem_cgroup_schedule_end(nid, zid, mem, false);
+
+		scan -= sc.nr_scanned;
+	}
+
+	return;
+}
 /*
  * For kswapd, balance_pgdat() will work across all this node's zones until
  * they are all at pages_high.
@@ -1776,6 +1819,8 @@ static unsigned long balance_pgdat(pg_da
 	 */
 	int temp_priority[MAX_NR_ZONES];
 
+	/* Refill softlimit queue */
+	mem_cgroup_reschedule_all(pgdat->node_id);
 loop_again:
 	total_scanned = 0;
 	sc.nr_reclaimed = 0;
@@ -1856,6 +1901,13 @@ loop_again:
 					       end_zone, 0))
 				all_zones_ok = 0;
 			temp_priority[i] = priority;
+
+			/*
+			 * Try soft limit at first.  This reclaims page
+			 * with regard to user's hint.
+			 */
+			shrink_zone_softlimit(zone, order, priority,
+					       8 * zone->pages_high, end_zone);
 			sc.nr_scanned = 0;
 			note_zone_scanning_priority(zone, priority);
 			/*

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/