Re: soft lockup - CPU#1 stuck for 15s! [swapper:0]

[Thomas Gleixner]

On Mon, 17 Dec 2007, Thomas Gleixner wrote:
> I try to come up with some more debug patches tomorrow.

Sorry took a bit longer than a day :(

Can you apply the patch below + the debug patch which prints the timer
stats on softlockup and provide the output of this.

Thanks,

	tglx

diff --git a/include/linux/tick.h b/include/linux/tick.h
index f4a1395..22d921f 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -39,6 +39,8 @@ enum tick_nohz_mode {
  * @idle_calls:		Total number of idle calls
  * @idle_sleeps:	Number of idle calls, where the sched tick was stopped
  * @idle_entrytime:	Time when the idle call was entered
+ * @idle_waketime:	Time when the idle was interrupted
+ * @idle_exittime:	Time when the idle state was left
  * @idle_sleeptime:	Sum of the time slept in idle with sched tick stopped
  * @sleep_length:	Duration of the current idle sleep
  */
@@ -52,6 +54,8 @@ struct tick_sched {
 	unsigned long			idle_calls;
 	unsigned long			idle_sleeps;
 	ktime_t				idle_entrytime;
+	ktime_t				idle_waketime;
+	ktime_t				idle_exittime;
 	ktime_t				idle_sleeptime;
 	ktime_t				sleep_length;
 	unsigned long			last_jiffies;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index cb89fa8..206a436 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -133,14 +133,15 @@ void tick_nohz_update_jiffies(void)
 	if (!ts->tick_stopped)
 		return;
 
-	touch_softlockup_watchdog();
-
 	cpu_clear(cpu, nohz_cpu_mask);
 	now = ktime_get();
 
 	local_irq_save(flags);
 	tick_do_update_jiffies64(now);
 	local_irq_restore(flags);
+
+	ts->idle_waketime = now;
+	touch_softlockup_watchdog();
 }
 
 /**
@@ -369,6 +370,7 @@ void tick_nohz_restart_sched_tick(void)
 	 * Cancel the scheduled timer and restore the tick
 	 */
 	ts->tick_stopped  = 0;
+	ts->idle_exittime = now;
 	hrtimer_cancel(&ts->sched_timer);
 	ts->sched_timer.expires = ts->idle_tick;
 
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 12c5f4c..d3d94c1 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -166,6 +166,8 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 		P(idle_calls);
 		P(idle_sleeps);
 		P_ns(idle_entrytime);
+		P_ns(idle_waketime);
+		P_ns(idle_exittime);
 		P_ns(idle_sleeptime);
 		P(last_jiffies);
 		P(next_jiffies);


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/