Re: mm3 hang

Martin J. Bligh (mbligh@aracnet.com)
Wed, 04 Jun 2003 14:43:07 -0700


--On Wednesday, June 04, 2003 14:47:36 -0700 Andrew Morton <akpm@digeo.com> wrote:

> "Martin J. Bligh" wrote:
>>
>> SDET hangs it every few runs.
>
> You have a large number of `ps' instances which appear to be
> stuck on /proc's i_sem and lots of processes stuck in
> sched_balance_exec->set_cpus_allowed->wait_for_completion.

OK, thanks. I'm getting several different hangs, so getting confused ;-)

> The latter is a NUMA-special. You might want to examine the
> sched_best_cpu() fixes carefully.

Mmm. those looked like they were only for nodes with no cpus ... matt?

> Also see whether 2.5.70+bk does the same thing.

Good point - will try that.

Thanks,

M.

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