Re: [uml-devel] BUG: soft lockup for a user mode linux image

[Fengguang Wu]

On Fri, Oct 11, 2013 at 04:57:01PM +0800, Fengguang Wu wrote:
> On Fri, Oct 11, 2013 at 10:42:19AM +0200, Toralf FÃrster wrote:
> > yeah, now the picture becomes more clear
> > ...
> > net.core.warnings = 0                                                                         [ ok ]
> > ick: pause : -717
> >                  ick : min_pause : -177
> >                                    ick : max_pause : -717
> >                                                      ick: pages_dirtied : 14
> >                                                                             ick: task_ratelimit: 0
> 
> Great and thanks! So it's the max pause calculation went wrong.

However I still suspect this is not the main reason for the soft
lockup. Because schedule_timeout() will directly return on negative
timeout. So yes, we have encountered some negative pauses, however
we still need to fix the huge dirtied pages problem which should be
more fundamental. 

Thanks,
Fengguang
--
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/