Ok, thanks - that's good to know.
-Andrew
--
* Andrew Benson: http://users.obs.carnegiescience.edu/abenson/contact.html
* Galacticus: http://sites.google.com/site/galacticusmodel
On Sat, Oct 6, 2018, 10:02 AM Ralph H Castain wrote:
> Just FYI: on master (and perhaps 4.0), child jobs do not
Just FYI: on master (and perhaps 4.0), child jobs do not inherit their parent's
mapping policy by default. You have to add “-mca rmaps_base_inherit 1” to your
mpirun cmd line.
> On Oct 6, 2018, at 10:00 AM, Andrew Benson
> wrote:
>
> Thanks, I'll try this right away.
>
> Thanks,
> Andrew
>
Sorry for delay - this should be fixed by
https://github.com/open-mpi/ompi/pull/5854
> On Sep 19, 2018, at 8:00 AM, Andrew Benson wrote:
>
> On further investigation removing the "preconnect_all" option does change the
> problem at least. Without "preconnect_all" I no longer see:
>
>
On further investigation removing the "preconnect_all" option does change the
problem at least. Without "preconnect_all" I no longer see:
--
At least one pair of MPI processes are unable to reach each other for
MPI communicat
On further investigation removing the "preconnect_all" option does change the
problem at least. Without "preconnect_all" I no longer see:
--
At least one pair of MPI processes are unable to reach each other for
MPI communicat
Removing the preconnect_all option didn't resolve the problem unfortunately.
I tried changing a few of the other options that I pass to mpirun. What does
seem to make a difference is the "--map-by node" option. If I remove that
option that my test code runs successfully - the output is in the
Thanks - I'll try removing that option.
On Sunday, September 16, 2018 7:03:15 AM PDT Ralph H Castain wrote:
> I see you are using “preconnect_all” - that is the source of the trouble. I
> don’t believe we have tested that option in years and the code is almost
> certainly dead. I’d suggest removin
I see you are using “preconnect_all” - that is the source of the trouble. I
don’t believe we have tested that option in years and the code is almost
certainly dead. I’d suggest removing that option and things should work.
> On Sep 15, 2018, at 1:46 PM, Andrew Benson wrote:
>
> I'm running int
I'm running into problems trying to spawn MPI processes across multiple nodes
on a cluster using recent versions of OpenMPI. Specifically, using the attached
Fortan code, compiled using OpenMPI 3.1.2 with:
mpif90 test.F90 -o test.exe
and run via a PBS scheduler using the attached test1.pbs, it