Re: 24 lost ticks with 2.6.20.10 kernel

[Andi Kleen]

Michel Lespinasse <walken@xxxxxxx> writes:
> 
> running with report_lost_ticks, I see the following:
> 
> May  1 12:58:57 server kernel: time.c: Lost 24 timer tick(s)! rip _spin_unlock_irqrestore+0x8/0x9)
> May  1 12:58:59 server kernel: time.c: Lost 24 timer tick(s)! rip _spin_unlock_irqrestore+0x8/0x9)
> May  1 12:59:01 server kernel: time.c: Lost 25 timer tick(s)! rip _spin_unlock_irqrestore+0x8/0x9)
> May  1 12:59:03 server kernel: time.c: Lost 24 timer tick(s)! rip _spin_unlock_irqrestore+0x8/0x9)

This means some code disabled interrupts using a spinlock for far too long.
Can you add a dump_stack() in arch/x86_64/kernel/time.c:handle_lost_ticks()? That should 
tell the culprit

-Andi
-
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/