aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu/intel.c
diff options
context:
space:
mode:
authorYinghai Lu <yinghai@kernel.org>2009-11-21 03:23:37 -0500
committerIngo Molnar <mingo@elte.hu>2009-11-23 04:06:24 -0500
commitd9c2d5ac6af87b4491bff107113aaf16f6c2b2d9 (patch)
tree5cb605d6396a0572dabf2b6152bb26fea425e376 /arch/x86/kernel/cpu/intel.c
parent021428ad1418cf3c386a1a0157140c3ea29b17ef (diff)
x86, numa: Use near(er) online node instead of roundrobin for NUMA
CPU to node mapping is set via the following sequence: 1. numa_init_array(): Set up roundrobin from cpu to online node 2. init_cpu_to_node(): Set that according to apicid_to_node[] according to srat only handle the node that is online, and leave other cpu on node without ram (aka not online) to still roundrobin. 3. later call srat_detect_node for Intel/AMD, will use first_online node or nearby node. Problem is that setup_per_cpu_areas() is not called between 2 and 3, the per_cpu for cpu on node with ram is on different node, and could put that on node with two hops away. So try to optimize this and add find_near_online_node() and call init_cpu_to_node(). Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: David Rientjes <rientjes@google.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <4B07A739.3030104@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch/x86/kernel/cpu/intel.c')
-rw-r--r--arch/x86/kernel/cpu/intel.c6
1 files changed, 5 insertions, 1 deletions
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 40e1835b35e8..c900b73f9224 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -263,8 +263,12 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
263 /* Don't do the funky fallback heuristics the AMD version employs 263 /* Don't do the funky fallback heuristics the AMD version employs
264 for now. */ 264 for now. */
265 node = apicid_to_node[apicid]; 265 node = apicid_to_node[apicid];
266 if (node == NUMA_NO_NODE || !node_online(node)) 266 if (node == NUMA_NO_NODE)
267 node = first_node(node_online_map); 267 node = first_node(node_online_map);
268 else if (!node_online(node)) {
269 /* reuse the value from init_cpu_to_node() */
270 node = cpu_to_node(cpu);
271 }
268 numa_set_node(cpu, node); 272 numa_set_node(cpu, node);
269 273
270 printk(KERN_INFO "CPU %d/0x%x -> Node %d\n", cpu, apicid, node); 274 printk(KERN_INFO "CPU %d/0x%x -> Node %d\n", cpu, apicid, node);