I'm aware - as we discussed on a recent telecon, I put it on my list of
things to resolve. Solution is known - just busy with other things at the
moment.
On 4/8/08 6:06 AM, "Tim Prins" wrote:
> Hi all,
>
> I reported this before, but it seems that the report got lost. I have
> found some situations where mpirun will return a '0' when there is an error.
>
> An easy way to reproduce this is to edit the file
> 'orte/mca/plm/base/plm_base_launch_support.c' and on line 154 put in
> 'return ORTE_ERROR;' (or apply the attached diff).
>
> Then recompile and run mpirun. mpirun will indicate there was an error,
> but will still return 0. The reason this is concerning to me is that MTT
> only looks at return codes, so our tests may be failing and we wouldn't
> know it.
>
> Thanks,
>
> Tim
> Index: orte/mca/plm/base/plm_base_launch_support.c
> ===
> --- orte/mca/plm/base/plm_base_launch_support.c (revision 18092)
> +++ orte/mca/plm/base/plm_base_launch_support.c (working copy)
> @@ -151,7 +151,7 @@
> ORTE_JOBID_PRINT(job), ORTE_ERROR_NAME(rc)));
> return rc;
> }
> -
> + return ORTE_ERROR;
> /* complete wiring up the iof */
> OPAL_OUTPUT_VERBOSE((5, orte_plm_globals.output,
> "%s plm:base:launch wiring up iof",
> ___
> devel mailing list
> de...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/devel