[PATCH] scheduler: NUMA aware placement of sched_group_allnodes

When the per cpu sched domains are build then they also need to be placed
on the node where the cpu resides otherwise we will have frequent off node
accesses which will slow down the system.

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/kernel/sched.c b/kernel/sched.c
index fec97e4e196d039e3055572844bdfb4394ee6514..53608a59d6e3c0fd3d0b18dbf919beb9b0125397 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6349,9 +6349,10 @@ static int build_sched_domains(const cpumask_t *cpu_map)
                                > SD_NODES_PER_DOMAIN*cpus_weight(nodemask)) {
                        if (!sched_group_allnodes) {
                                sched_group_allnodes
-                                       = kmalloc(sizeof(struct sched_group)
-                                                       * MAX_NUMNODES,
-                                                 GFP_KERNEL);
+                                       = kmalloc_node(sizeof(struct sched_group)
+                                                       * MAX_NUMNODES,
+                                                 GFP_KERNEL,
+                                                 cpu_to_node(i));
                                if (!sched_group_allnodes) {
                                        printk(KERN_WARNING
                                        "Can not alloc allnodes sched group\n");