===== include/linux/gfp.h 1.18 vs edited =====
--- 1.18/include/linux/gfp.h	2004-05-22 14:56:25 -07:00
+++ edited/include/linux/gfp.h	2004-08-12 16:27:01 -07:00
@@ -86,6 +86,8 @@
 		NODE_DATA(nid)->node_zonelists + (gfp_mask & GFP_ZONEMASK));
 }
 
+extern struct page *alloc_page_round_robin(unsigned int gfp_mask);
+
 #ifdef CONFIG_NUMA
 extern struct page *alloc_pages_current(unsigned gfp_mask, unsigned order);
 
===== include/linux/pagemap.h 1.43 vs edited =====
--- 1.43/include/linux/pagemap.h	2004-06-24 01:55:57 -07:00
+++ edited/include/linux/pagemap.h	2004-08-12 14:37:36 -07:00
@@ -52,12 +52,12 @@
 
 static inline struct page *page_cache_alloc(struct address_space *x)
 {
-	return alloc_pages(mapping_gfp_mask(x), 0);
+	return alloc_page_round_robin(mapping_gfp_mask(x));
 }
 
 static inline struct page *page_cache_alloc_cold(struct address_space *x)
 {
-	return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0);
+	return alloc_page_round_robin(mapping_gfp_mask(x)|__GFP_COLD);
 }
 
 typedef int filler_t(void *, struct page *);
===== mm/page_alloc.c 1.224 vs edited =====
--- 1.224/mm/page_alloc.c	2004-08-07 23:43:41 -07:00
+++ edited/mm/page_alloc.c	2004-08-12 16:27:43 -07:00
@@ -31,6 +31,7 @@
 #include <linux/topology.h>
 #include <linux/sysctl.h>
 #include <linux/cpu.h>
+#include <linux/percpu.h>
 
 #include <asm/tlbflush.h>
 
@@ -41,6 +42,7 @@
 long nr_swap_pages;
 int numnodes = 1;
 int sysctl_lower_zone_protection = 0;
+static DEFINE_PER_CPU(int, next_rr_node);
 
 EXPORT_SYMBOL(totalram_pages);
 EXPORT_SYMBOL(nr_swap_pages);
@@ -577,6 +579,23 @@
 	}
 	return page;
 }
+
+/**
+ * alloc_page_round_robin - distribute pages across nodes
+ * @gfp_mask: GFP_* flags
+ *
+ * alloc_page_round_robin() will simply allocate from a different node
+ * than was allocated from in the last call using the next_rr_node variable.
+ * We use __get_cpu_var since we don't care about disabling preemption (we're
+ * using a mod function so nid will always be less than numnodes).  A per-cpu
+ * variable will make round robin allocations scale a bit better.
+ */
+struct page *alloc_page_round_robin(unsigned int gfp_mask)
+{
+	return alloc_pages_node(__get_cpu_var(next_rr_node)++ % numnodes,
+				gfp_mask, 0);
+}
+
 
 /*
  * This is the 'heart' of the zoned buddy allocator.