Index: linux-2.6.19-rc3/kernel/sched.c
===================================================================
--- linux-2.6.19-rc3.orig/kernel/sched.c	2006-10-27 15:25:08.730814397 -0500
+++ linux-2.6.19-rc3/kernel/sched.c	2006-10-27 15:35:18.318746984 -0500
@@ -2849,17 +2849,17 @@ static void update_load(struct rq *this_
  * Balancing parameters are set up in arch_init_sched_domains.
  */
 
-/* Don't have all balancing operations going off at once: */
-static inline unsigned long cpu_offset(int cpu)
-{
-	return jiffies + cpu * HZ / NR_CPUS;
-}
-
 static void
-rebalance_tick(int this_cpu, struct rq *this_rq, enum idle_type idle)
+rebalance_tick(int this_cpu, struct rq *this_rq)
 {
-	unsigned long interval, j = cpu_offset(this_cpu);
+	unsigned long interval;
 	struct sched_domain *sd;
+	/*
+	 * A task is idle if this is the idle queue
+	 * and we have no runnable task
+	 */
+	enum idle_type idle = (this_rq->idle && !this_rq->nr_running) ?
+				SCHED_IDLE : NOT_IDLE;
 
 	for_each_domain(this_cpu, sd) {
 		if (!(sd->flags & SD_LOAD_BALANCE))
@@ -2874,7 +2874,7 @@ rebalance_tick(int this_cpu, struct rq *
 		if (unlikely(!interval))
 			interval = 1;
 
-		if (j - sd->last_balance >= interval) {
+		if (jiffies - sd->last_balance >= interval) {
 			if (load_balance(this_cpu, this_rq, sd, idle)) {
 				/*
 				 * We've pulled tasks over so either we're no
@@ -3137,20 +3137,18 @@ void scheduler_tick(void)
 	struct task_struct *p = current;
 	int cpu = smp_processor_id();
 	struct rq *rq = cpu_rq(cpu);
-	enum idle_type idle = NOT_IDLE;
 
 	update_cpu_clock(p, rq, now);
 
 	rq->timestamp_last_tick = now;
 
-	if (p == rq->idle) {
+	if (p == rq->idle)
 		/* Task on the idle queue */
-		if (!wake_priority_sleeper(rq))
-			idle = SCHED_IDLE;
-	} else
+		wake_priority_sleeper(rq);
+	else
 		task_running_tick(rq, p);
 	update_load(rq);
-	rebalance_tick(cpu, rq, idle);
+	rebalance_tick(cpu, rq);
 }
 
 #ifdef CONFIG_SCHED_SMT
@@ -6327,6 +6325,16 @@ static void init_sched_groups_power(int 
 }
 
 /*
+ * Calculate jiffies start to use for each cpu. On sched domain
+ * initialization this jiffy value is used to stagger the load balancing
+ * of the cpus so that they do not load balance all at at the same time.
+ */
+static inline unsigned long cpu_offset(int cpu)
+{
+	return jiffies + cpu * HZ / NR_CPUS;
+}
+
+/*
  * Build sched domains for a given set of cpus and attach the sched domains
  * to the individual cpus
  */
@@ -6382,6 +6390,7 @@ static int build_sched_domains(const cpu
 			sd->span = *cpu_map;
 			group = cpu_to_allnodes_group(i, cpu_map);
 			sd->groups = &sched_group_allnodes[group];
+			sd->last_balance = cpu_offset(i);
 			p = sd;
 		} else
 			p = NULL;
@@ -6390,6 +6399,7 @@ static int build_sched_domains(const cpu
 		*sd = SD_NODE_INIT;
 		sd->span = sched_domain_node_span(cpu_to_node(i));
 		sd->parent = p;
+		sd->last_balance = cpu_offset(i);
 		if (p)
 			p->child = sd;
 		cpus_and(sd->span, sd->span, *cpu_map);
@@ -6401,6 +6411,7 @@ static int build_sched_domains(const cpu
 		*sd = SD_CPU_INIT;
 		sd->span = nodemask;
 		sd->parent = p;
+		sd->last_balance = cpu_offset(i);
 		if (p)
 			p->child = sd;
 		sd->groups = &sched_group_phys[group];
@@ -6413,6 +6424,7 @@ static int build_sched_domains(const cpu
 		sd->span = cpu_coregroup_map(i);
 		cpus_and(sd->span, sd->span, *cpu_map);
 		sd->parent = p;
+		sd->last_balance = cpu_offset(i);
 		p->child = sd;
 		sd->groups = &sched_group_core[group];
 #endif
@@ -6425,6 +6437,7 @@ static int build_sched_domains(const cpu
 		sd->span = cpu_sibling_map[i];
 		cpus_and(sd->span, sd->span, *cpu_map);
 		sd->parent = p;
+		sd->last_balance = cpu_offset(i);
 		p->child = sd;
 		sd->groups = &sched_group_cpus[group];
 #endif