Re: 2.6.21-rc2-git3 soft lockup detected on CPU#0 (crash dumpkernel)

From: Thomas Gleixner
Date: Sun Mar 04 2007 - 10:32:36 EST


On Sun, 2007-03-04 at 15:36 +0100, Michal Piotrowski wrote:
> > > BUG: soft lockup detected on CPU#0!
> > > [<c1604556>] show_trace_log_lvl+0x1a/0x2f
> > > [<c1604c2c>] show_trace+0x12/0x14
> > > [<c1604cde>] dump_stack+0x16/0x18
> > > [<c16426e7>] softlockup_tick+0x97/0xa7
> > > [<c161de38>] run_local_timers+0x12/0x14
> > > [<c161e1ce>] update_process_times+0x3e/0x63
> > > [<c162c44b>] tick_sched_timer+0x5d/0xa1
> > > [<c1629715>] hrtimer_interrupt+0x11e/0x1b2
> > > [<c160684e>] timer_interrupt+0xe/0x15
> > > [<c164299e>] handle_IRQ_event+0x1a/0x46
> > > [<c1643cfe>] handle_level_irq+0x81/0xcb
> > > [<c1605dd8>] do_IRQ+0xb4/0xe0
> > >
> > > This time it's a crash dump kernel without SMP.
> >
> > Is the box stuck, or do you just get those softlockup messages from time
> > to time ?
>
> The box stuck on it.
>
> I can reproduce this on 2.6.21-rc2-git3 and 2.6.20.1.

Ahh. That's something different, i.e. unrelated to highres/dynticks.
2.6.20.1 does not have them.

Can you please add "initcall_debug" and "ignore_loglevel" to the kernel
command line ?

tglx


-
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/