[PATCH] memcg: reduce size of per-cpu-stat to be appropriate size.

[KAMEZAWA Hiroyuki]

How about this one ?
tested on x86-64 + mmotm-Nov10, works well. 
(test on other arch is welcome.)

-Kame
==
As  Jan Blunck <jblunck@xxxxxxx> pointed out, allocating
per-cpu stat for memcg to the size of NR_CPUS is not good.

This patch changes mem_cgroup's cpustat allocation not based
on NR_CPUS but based on nr_cpu_ids.

From: Jan Blunck <jblunck@xxxxxxx>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>

---
 mm/memcontrol.c |   34 ++++++++++++++++++----------------
 1 file changed, 18 insertions(+), 16 deletions(-)

Index: mmotm-2.6.28-Nov10/mm/memcontrol.c
===================================================================
--- mmotm-2.6.28-Nov10.orig/mm/memcontrol.c
+++ mmotm-2.6.28-Nov10/mm/memcontrol.c
@@ -60,7 +60,7 @@ struct mem_cgroup_stat_cpu {
 } ____cacheline_aligned_in_smp;
 
 struct mem_cgroup_stat {
-	struct mem_cgroup_stat_cpu cpustat[NR_CPUS];
+	struct mem_cgroup_stat_cpu cpustat[0];
 };
 
 /*
@@ -129,11 +129,10 @@ struct mem_cgroup {
 
 	int	prev_priority;	/* for recording reclaim priority */
 	/*
-	 * statistics.
+	 * statistics. This must be placed at the end of memcg.
 	 */
 	struct mem_cgroup_stat stat;
 };
-static struct mem_cgroup init_mem_cgroup;
 
 enum charge_type {
 	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
@@ -1292,42 +1291,45 @@ static void free_mem_cgroup_per_zone_inf
 	kfree(mem->info.nodeinfo[node]);
 }
 
+static int mem_cgroup_size(void)
+{
+	int cpustat_size = nr_cpu_ids * sizeof(struct mem_cgroup_stat_cpu);
+	return sizeof(struct mem_cgroup) + cpustat_size;
+}
+
+
 static struct mem_cgroup *mem_cgroup_alloc(void)
 {
 	struct mem_cgroup *mem;
+	int size = mem_cgroup_size();
 
-	if (sizeof(*mem) < PAGE_SIZE)
-		mem = kmalloc(sizeof(*mem), GFP_KERNEL);
+	if (size < PAGE_SIZE)
+		mem = kmalloc(size, GFP_KERNEL);
 	else
-		mem = vmalloc(sizeof(*mem));
+		mem = vmalloc(size);
 
 	if (mem)
-		memset(mem, 0, sizeof(*mem));
+		memset(mem, 0, size);
 	return mem;
 }
 
 static void mem_cgroup_free(struct mem_cgroup *mem)
 {
-	if (sizeof(*mem) < PAGE_SIZE)
+	if (mem_cgroup_size() < PAGE_SIZE)
 		kfree(mem);
 	else
 		vfree(mem);
 }
 
-
 static struct cgroup_subsys_state *
 mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 {
 	struct mem_cgroup *mem;
 	int node;
 
-	if (unlikely((cont->parent) == NULL)) {
-		mem = &init_mem_cgroup;
-	} else {
-		mem = mem_cgroup_alloc();
-		if (!mem)
-			return ERR_PTR(-ENOMEM);
-	}
+	mem = mem_cgroup_alloc();
+	if (!mem)
+		return ERR_PTR(-ENOMEM);
 
 	res_counter_init(&mem->res);
 

--
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/