Jeremy Fitzhardinge wrote:
> The softlockup watchdog is currently a nuisance in a virtual machine,
> since the whole system could have the CPU stolen from it for a long
> period of time. While it would be unlikely for a guest domain to be
> denied timer interrupts for over 10s, it could happen and any softlockup
> message would be completely spurious.
>
> Earlier I proposed that sched_clock() return time in unstolen
> nanoseconds, which is how Xen and VMI currently implement it. If the
> softlockup watchdog uses sched_clock() to measure time, it would
> automatically ignore stolen time, and therefore only report when the
> guest itself locked up. When running native, sched_clock() returns
> real-time nanoseconds, so the behaviour would be unchanged.
>
> Does this seem sound?
>
> Also, softlockup.c's use of jiffies seems archaic now. Should it be
> converted to use timers? Mightn't it report lockups just because there
> was no timer event?
>
> Signed-off-by: Jeremy Fitzhardinge <[EMAIL PROTECTED]>
Less desperately broken version.
diff -r b41fb9e70d72 kernel/softlockup.c
--- a/kernel/softlockup.c Thu Mar 22 16:25:15 2007 -0700
+++ b/kernel/softlockup.c Thu Mar 22 17:03:03 2007 -0700
@@ -17,8 +17,8 @@
static DEFINE_SPINLOCK(print_lock);
-static DEFINE_PER_CPU(unsigned long, touch_timestamp);
-static DEFINE_PER_CPU(unsigned long, print_timestamp);
+static DEFINE_PER_CPU(unsigned long long, touch_timestamp);
+static DEFINE_PER_CPU(unsigned long long, print_timestamp);
static DEFINE_PER_CPU(struct task_struct *, watchdog_task);
static int did_panic = 0;
@@ -37,7 +37,7 @@ static struct notifier_block panic_block
void touch_softlockup_watchdog(void)
{
- __raw_get_cpu_var(touch_timestamp) = jiffies;
+ __raw_get_cpu_var(touch_timestamp) = sched_clock();
}
EXPORT_SYMBOL(touch_softlockup_watchdog);
@@ -48,10 +48,15 @@ void softlockup_tick(void)
void softlockup_tick(void)
{
int this_cpu = smp_processor_id();
- unsigned long touch_timestamp = per_cpu(touch_timestamp, this_cpu);
+ unsigned long long touch_timestamp = per_cpu(touch_timestamp, this_cpu);
+ unsigned long long now;
- /* prevent double reports: */
- if (per_cpu(print_timestamp, this_cpu) == touch_timestamp ||
+ /* watchdog task hasn't updated timestamp yet */
+ if (touch_timestamp == 0)
+ return;
+
+ /* report at most once a second */
+ if (per_cpu(print_timestamp, this_cpu) < (touch_timestamp +
NSEC_PER_SEC) ||
did_panic ||
!per_cpu(watchdog_task, this_cpu))
return;
@@ -62,12 +67,14 @@ void softlockup_tick(void)
return;
}
+ now = sched_clock();
+
/* Wake up the high-prio watchdog task every second: */
- if (time_after(jiffies, touch_timestamp + HZ))
+ if (now > (touch_timestamp + NSEC_PER_SEC))
wake_up_process(per_cpu(watchdog_task, this_cpu));
/* Warn about unreasonable 10+ seconds delays: */
- if (time_after(jiffies, touch_timestamp + 10*HZ)) {
+ if (now > (touch_timestamp + 10ull*NSEC_PER_SEC)) {
per_cpu(print_timestamp, this_cpu) = touch_timestamp;
spin_lock(&print_lock);
@@ -87,6 +94,9 @@ static int watchdog(void * __bind_cpu)
sched_setscheduler(current, SCHED_FIFO, ¶m);
current->flags |= PF_NOFREEZE;
+
+ /* initialize timestamp */
+ touch_softlockup_watchdog();
/*
* Run briefly once per second to reset the softlockup timestamp.
@@ -120,7 +130,7 @@ cpu_callback(struct notifier_block *nfb,
printk("watchdog for %i failed\n", hotcpu);
return NOTIFY_BAD;
}
- per_cpu(touch_timestamp, hotcpu) = jiffies;
+ per_cpu(touch_timestamp, hotcpu) = 0;
per_cpu(watchdog_task, hotcpu) = p;
kthread_bind(p, hotcpu);
break;
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
