Problem: Starting a job is canceled giving the error message
Connecting client 139.27.166.22:44784 (rank 6) failed : Network is unreachable PSIlogger: Child with rank 12 exited with status 1.
This typically happens, if the frontend or head node is included as compute node and also acts as gateway for the compute nodes. The "external" address of the frontend is not known to the compute nodes.
Use the PSP_NETWORK
environment variable to
re-direct all traffic to the cluster-internal network. See
ps_environment(5) and the section called “Controlling ParaStation MPI communication paths” for details.