Problem when running mpirun on an Ubuntu computer cluster error (ORTE does not know how to route a message to the specified daemon located on the indicated node:)

[jonny261]

I have a master with IP (192.168.1.10) and 4 nodes with IPs (.20, .30, .40, .50). I configured passwordless SSH, and from the master, I can access each node without using a password. I installed pssh, and I can run commands in parallel on each node from the master. I installed NFS, created a directory, mounted it on each node, and it works. I installed OpenMPI, and when I try to run 'mpirun -hostfile hosts ./hello_world

It hangs, and I have to do Ctrl + Z to cancel it, and it shows me this message

^Z mpirun Forwarding signal 20 to job

ORTE does not know how to route a message to the specified daemon
located on the indicated node:

my node: master-H510M-H
target node: 192.168.1.20

This is usually an internal programming error that should be
reported to the developers. In the meantime, a workaround may
be to set the MCA param routed=direct on the command line or
in your environment. We apologize for the problem.

[master-H510M-H] 3 more processes have sent help message help-errmgr-base.txt / no-path
[master-H510M-H] Set MCA parameter "orte_base_help_aggregate" to 0 to see all help / error messages

Could you help me solve this error and be able to execute in parallel?

[jsquyres]

Please provide all the information that was requested in the github "ask a question" template: https://github.com/open-mpi/ompi/blob/main/.github/ISSUE_TEMPLATE/ask-a-question.md

[jonny261]

ok