Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

From: Mostyn Lewis (Mostyn.Lewis_at_[hidden])
Date: 2007-04-23 21:22:25


I tried this on a humble PC and it works there.
I see in the --mca mpi_show_mca_params 1 print out that there is a
[bb17:06646] paffinity=
entry, so I expect that sets the value entry back to 0?

I'll get to the SLES10 cluster when I can (other people doing
benchmarks) and see what I can. I see there's no stdbool.h there,
so maybe this is an artifact of defining the bool type on an
operton. I'll get back to you when I can.

The test of boundness was a perl program invoked via system() in a
C MPI program. The /proc/<pid>/stat result shows the CPU you are
bound to (3rd number from the end) and a taskset call gets back the
mask to show if you are bound or not.

Regards,
Mostyn

On Mon, 23 Apr 2007, Jeff Squyres wrote:

> On Apr 22, 2007, at 8:46 PM, Mostyn Lewis wrote:
>
>> More information.
>>
>> --mca mpi_paffinity_alone 0
>
> Can you describe how you're verifying that the process is actually
> bound?
>
>> May I ask I question about the code, which I scanned.
>>
>> I see in ompi/runtime/ompi_mpi_params.c you do a:
>>
>> mca_base_param_reg_int_name("mpi", "paffinity_alone",
>> "If nonzero, assume that this job
>> is the only (set of) process(es) r
>> unning on each node and bind processes to processors, starting with
>> processor ID 0",
>> false, false,
>> (int) ompi_mpi_paffinity_alone,
>> &value);
>> ompi_mpi_paffinity_alone = OPAL_INT_TO_BOOL(value);
>
> You're right that we're not checking the return value here, which is
> bad. However, this is a pretty stable portion of the code -- I would
> be surprised if it is failing.
>
> Have you stepped through this with a debugger to verify if it is
> actually failing or not?
>
> --
> Jeff Squyres
> Cisco Systems
>
> _______________________________________________
> users mailing list
> users_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/users
>