Memoryless nodes: Allow profiling data to fall back to other nodes
Christoph Lameter [Tue, 16 Oct 2007 08:25:34 +0000 (01:25 -0700)]
Processors on memoryless nodes must be able to fall back to remote nodes in
order to get a profiling buffer.  This may lead to excessive NUMA traffic but
I think we should allow this rather than failing.

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Acked-by: Nishanth Aravamudan <nacc@us.ibm.com>
Acked-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Bob Picco <bob.picco@hp.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@skynet.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

kernel/profile.c

index cb1e37d..6f69bf7 100644 (file)
@@ -346,7 +346,7 @@ static int __devinit profile_cpu_callback(struct notifier_block *info,
                per_cpu(cpu_profile_flip, cpu) = 0;
                if (!per_cpu(cpu_profile_hits, cpu)[1]) {
                        page = alloc_pages_node(node,
-                                       GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+                                       GFP_KERNEL | __GFP_ZERO,
                                        0);
                        if (!page)
                                return NOTIFY_BAD;
@@ -354,7 +354,7 @@ static int __devinit profile_cpu_callback(struct notifier_block *info,
                }
                if (!per_cpu(cpu_profile_hits, cpu)[0]) {
                        page = alloc_pages_node(node,
-                                       GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+                                       GFP_KERNEL | __GFP_ZERO,
                                        0);
                        if (!page)
                                goto out_free;