diff -urNp linux-2.5.55-ms-ilb-nba/kernel/sched.c linux-2.5.55-ms-ilb-nbav/kernel/sched.c
--- linux-2.5.55-ms-ilb-nba/kernel/sched.c	2003-01-12 18:15:34.000000000 +0100
+++ linux-2.5.55-ms-ilb-nbav/kernel/sched.c	2003-01-12 23:16:25.000000000 +0100
@@ -629,6 +629,9 @@ static inline void double_rq_unlock(runq
 
 #if CONFIG_NUMA
 static atomic_t node_nr_running[MAX_NUMNODES] ____cacheline_maxaligned_in_smp = {[0 ...MAX_NUMNODES-1] = ATOMIC_INIT(0)};
+#define MAX_INTERNODE_LB 40
+#define MIN_INTERNODE_LB 4
+static int internode_lb[MAX_NUMNODES] ____cacheline_maxaligned_in_smp = {[0 ...MAX_NUMNODES-1] = MAX_INTERNODE_LB};
 
 __init void node_nr_running_init(void)
 {
@@ -715,21 +718,31 @@ void sched_balance_exec(void)
 static int find_busiest_node(int this_node)
 {
 	int i, node = this_node, load, this_load, maxload;
+	int avg_load;
 	
 	this_load = maxload = (this_rq()->prev_node_load[this_node] >> 1)
 		+ atomic_read(&node_nr_running[this_node]);
 	this_rq()->prev_node_load[this_node] = this_load;
+	avg_load = this_load;
 	for (i = 0; i < numnodes; i++) {
 		if (i == this_node)
 			continue;
 		load = (this_rq()->prev_node_load[i] >> 1)
 			+ atomic_read(&node_nr_running[i]);
+		avg_load += load;
 		this_rq()->prev_node_load[i] = load;
 		if (load > maxload && (4*load > ((5*4*this_load)/4))) {
 			maxload = load;
 			node = i;
 		}
 	}
+	avg_load = avg_load / (numnodes ? numnodes : 1);
+	if (this_load < (avg_load / 2)) {
+		if (internode_lb[this_node] == MAX_INTERNODE_LB)
+			internode_lb[this_node] = MIN_INTERNODE_LB;
+	} else
+		if (internode_lb[this_node] == MIN_INTERNODE_LB)
+			internode_lb[this_node] = MAX_INTERNODE_LB;
 	return node;
 }
 #endif /* CONFIG_NUMA */
@@ -846,11 +859,10 @@ static inline runqueue_t *find_busiest_q
 {
 	unsigned long cpumask = __node_to_cpu_mask(__cpu_to_node(this_cpu));
 #if CONFIG_NUMA
-	int node;
-#       define INTERNODE_LB 10
+	int node, this_node = __cpu_to_node(this_cpu);
 
-	/* rebalance across nodes only every INTERNODE_LB call */
-	if (!(++(this_rq->lb_cntr) % INTERNODE_LB)) {
+	/* rarely rebalance across nodes */
+	if (!(++(this_rq->lb_cntr) % internode_lb[this_node])) {
 		node = find_busiest_node(__cpu_to_node(this_cpu));
 		cpumask |= __node_to_cpu_mask(node);
 	}