--- linux-2.4.1-pre10/kernel/sched.c	Tue Jan 23 19:28:16 2001
+++ linux-akpm/kernel/sched.c	Tue Jan 23 23:18:21 2001
@@ -33,6 +33,13 @@
 extern void tqueue_bh(void);
 extern void immediate_bh(void);
 
+#include <asm/msr.h>
+static struct {
+	unsigned long acc_time;
+	unsigned long n_times;
+	unsigned long long in;
+} ____cacheline_aligned schedule_stats[NR_CPUS + 1];
+
 /*
  * scheduler variables
  */
@@ -505,7 +512,7 @@
  * tasks can run. It can not be killed, and it cannot sleep. The 'state'
  * information in task[0] is never used.
  */
-asmlinkage void schedule(void)
+static void __schedule(void)
 {
 	struct schedule_data * sched_data;
 	struct task_struct *prev, *next, *p;
@@ -688,6 +695,88 @@
 	BUG();
 	return;
 }
+
+//////////////////////
+
+static unsigned long long dummy;
+static unsigned long long calib;
+static int done_calib;
+
+static void do_one(void)
+{
+	rdtscll(dummy);
+}
+
+static void calibrate(void)
+{
+	unsigned long long in, out;
+	unsigned long flags;
+	int i;
+
+	local_irq_save(flags);
+	rdtscll(in);
+	for (i = 0; i < 0x10000; i++) {
+		do_one();
+	}
+	rdtscll(out);
+	local_irq_restore(flags);
+	calib = (out - in) >> 16;
+	done_calib = 1;
+}
+
+asmlinkage void schedule(void)
+{
+	int cpu = smp_processor_id();
+	unsigned long long out;
+
+	if (!done_calib)
+		calibrate();
+
+	rdtscll(schedule_stats[cpu].in);
+	__schedule();
+	rdtscll(out);
+
+	schedule_stats[cpu].acc_time += out - schedule_stats[cpu].in - calib;
+	schedule_stats[cpu].n_times++;
+}
+
+static atomic_t cpu_count;
+
+static void ss_dumper(void *dummy)
+{
+	int cpu = smp_processor_id();
+	while (atomic_read(&cpu_count) != cpu)
+		;
+	printk("CPU %d: %lu / %lu = %lu cycles/switch\n",
+		cpu, schedule_stats[cpu].acc_time, schedule_stats[cpu].n_times,
+		schedule_stats[cpu].acc_time / schedule_stats[cpu].n_times);
+	
+	schedule_stats[NR_CPUS].acc_time += schedule_stats[cpu].acc_time;
+	schedule_stats[NR_CPUS].n_times += schedule_stats[cpu].n_times;
+
+	schedule_stats[cpu].acc_time = 0;
+	schedule_stats[cpu].n_times = 0;
+	atomic_inc(&cpu_count);
+	if (atomic_read(&cpu_count) == smp_num_cpus) {
+		printk("total: %lu / %lu = %lu cycles/switch\n",
+			schedule_stats[NR_CPUS].acc_time, schedule_stats[NR_CPUS].n_times,
+			schedule_stats[NR_CPUS].acc_time / schedule_stats[NR_CPUS].n_times);
+	}		
+}
+
+void dump_schedule_stats(void)
+{
+	schedule_stats[NR_CPUS].acc_time = 0;
+	schedule_stats[NR_CPUS].n_times = 0;
+	atomic_set(&cpu_count, 0);
+	printk("\n");
+	smp_call_function(ss_dumper, 0, 0, 0);
+	ss_dumper(0);
+}
+
+
+//////////////////////////
+
 
 static inline void __wake_up_common (wait_queue_head_t *q, unsigned int mode,
 			 	     int nr_exclusive, const int sync)
--- linux-2.4.1-pre10/drivers/char/sysrq.c	Tue Dec 12 19:24:17 2000
+++ linux-akpm/drivers/char/sysrq.c	Tue Jan 23 22:35:34 2001
@@ -95,6 +95,9 @@
 			sysrq_power_off();
 		}
 		break;
+	case 'q':
+		dump_schedule_stats();
+		break;
 	case 's':					    /* S -- emergency sync */
 		printk("Emergency Sync\n");
 		emergency_sync_scheduled = EMERG_SYNC;