numa: mempolicy: dynamic interleave map for system init

[net-next-2.6.git] / mm / mempolicy.c

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d76e8eb342d0df2e0468f014076a720866ae2277..a67c8f1828aceeccdda03a7f6a54dd3a20729e15 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1597,6 +1597,10 @@ void mpol_free_shared_policy(struct shared_policy *p)
 /* assumes fs == KERNEL_DS */
 void __init numa_policy_init(void)
 {
+       nodemask_t interleave_nodes;
+       unsigned long largest = 0;
+       int nid, prefer = 0;
+
        policy_cache = kmem_cache_create("numa_policy",
                                         sizeof(struct mempolicy),
                                         0, SLAB_PANIC, NULL, NULL);
@@ -1605,10 +1609,31 @@ void __init numa_policy_init(void)
                                     sizeof(struct sp_node),
                                     0, SLAB_PANIC, NULL, NULL);
 
-       /* Set interleaving policy for system init. This way not all
-          the data structures allocated at system boot end up in node zero. */
+       /*
+        * Set interleaving policy for system init. Interleaving is only
+        * enabled across suitably sized nodes (default is >= 16MB), or
+        * fall back to the largest node if they're all smaller.
+        */
+       nodes_clear(interleave_nodes);
+       for_each_online_node(nid) {
+               unsigned long total_pages = node_present_pages(nid);
+
+               /* Preserve the largest node */
+               if (largest < total_pages) {
+                       largest = total_pages;
+                       prefer = nid;
+               }
+
+               /* Interleave this node? */
+               if ((total_pages << PAGE_SHIFT) >= (16 << 20))
+                       node_set(nid, interleave_nodes);
+       }
+
+       /* All too small, use the largest */
+       if (unlikely(nodes_empty(interleave_nodes)))
+               node_set(prefer, interleave_nodes);
 
-       if (do_set_mempolicy(MPOL_INTERLEAVE, &node_online_map))
+       if (do_set_mempolicy(MPOL_INTERLEAVE, &interleave_nodes))
                printk("numa_policy_init: interleaving failed\n");
 }