Re: [OMPI users] [EXTERNAL] Re: MPI_Comm_Spawn failure: All nodes already filled

2019-08-07 Thread Mccall, Kurt E. (MSFC-EV41) via users
Ralph, I downloaded and compiled the August 7 tarball with Torque/Maui support and ran my test program – resulting in the same error when MPI_Comm_spawn was called. Can you suggest anything the might be wrong with my environment or our Torque configuration that might be causing this? Thanks,

[OMPI users] MPI_Comm_Spawn failure: All nodes already filled

2019-08-07 Thread Mccall, Kurt E. (MSFC-EV41) via users
Ralph, I got MPI_Comm_spawn to work by making sure that the hostfiles on the head (where mpiexec is called) and the remote node are identical. I had assumed that only the one on the head node was read by OpenMPI. Is this correct? Thanks, Kurt From: Ralph Castain Subject: [EXTERNAL] Re: [O

Re: [OMPI users] MPI_Comm_Spawn failure: All nodes already filled

2019-08-07 Thread Ralph Castain via users
Yeah, we do currently require that to be true. Process mapping is distributed across the daemons - i.e., the daemon on each node independently computes the map. We have talked about picking up the hostfile on the head node and sending out the contents, but haven't implemented that yet. On Aug