I am trying to run Fluent 19.1.0 (without gui or graphics) on our new HPC cluster which runs Rocky Linux 8.6. Fluent however fails to spawn processes; this already happens when running on a single node with a single process:
@k28i14:vof_wice$ fluent 3ddp -ptrace -t1 -g -cnf=k28i14 -i simulation.jou
/ANSYS/19.1/ansys_inc/v191/fluent/fluent19.1.0/bin/fluent -r19.1.0 3ddp -ptrace -t1 -g -cnf=k28i14 -i simulation.jou
/ANSYS/19.1/ansys_inc/v191/fluent/fluent19.1.0/cortex/lnamd64/cortex.19.1.0 -f fluent -g -i simulation.jou (fluent "3ddp -pmpi-auto-selected -host -r19.1.0 -t1 -mpi=ibmmpi -cnf=k28i14 -path/ANSYS/19.1/ansys_inc/v191/fluent -ptrace -ssh")
/ANSYS/19.1/ansys_inc/v191/fluent/fluent19.1.0/bin/fluent -r19.1.0 3ddp -pmpi-auto-selected -host -t1 -mpi=ibmmpi -cnf=k28i14 -path/ANSYS/19.1/ansys_inc/v191/fluent -ptrace -ssh -cx k28i14.:34149:46055
Starting /ANSYS/19.1/ansys_inc/v191/fluent/fluent19.1.0/lnamd64/3ddp_host/fluent.19.1.0 host -cx k28i14.:34149:46055 "(list (rpsetvar (QUOTE parallel/function) "fluent 3ddp -flux -node -r19.1.0 -t1 -pmpi-auto-selected -mpi=ibmmpi -cnf=k28i14 -ssh") (rpsetvar (QUOTE parallel/rhost) "") (rpsetvar (QUOTE parallel/ruser) "") (rpsetvar (QUOTE parallel/nprocs_string) "1") (rpsetvar (QUOTE parallel/auto-spawn?) #t) (rpsetvar (QUOTE parallel/trace-level) 1) (rpsetvar (QUOTE parallel/remote-shell) 1) (rpsetvar (QUOTE parallel/path) "/ANSYS/19.1/ansys_inc/v191/fluent") (rpsetvar (QUOTE parallel/hostsfile) "k28i14") )"
Welcome to ANSYS Fluent Release 19.1
Copyright 1987-2018 ANSYS, Inc. All Rights Reserved.
Unauthorized use, distribution or duplication is prohibited.
This product is subject to U.S. laws governing export and re-export.
For full Legal Notice, see documentation.
Build Time: Apr 09 2018 13:46:05 EDT Build Id: 10123
*********************************************
Info: Your license enables 4-way parallel execution.
For faster simulations, please start the application with the appropriate parallel options.
*********************************************
--------------------------------------------------------------
This is an academic version of ANSYS FLUENT. Usage of this product
license is limited to the terms and conditions specified in your ANSYS
license form, additional terms section.
--------------------------------------------------------------
Host spawning Node 0 on machine "k28i14" (unix).
Process is being spawned with command:
/ANSYS/19.1/ansys_inc/v191/fluent/bin/fluent 3ddp -flux -node -r19.1.0 -t1 -pmpi-auto-selected -mpi=ibmmpi -cnf=k28i14 -ssh -mportv ::45139:0
/ANSYS/19.1/ansys_inc/v191/fluent/fluent19.1.0/bin/fluent -r19.1.0 3ddp -flux -node -t1 -pmpi-auto-selected -mpi=ibmmpi -cnf=k28i14 -ssh -mportv ::45139:0
Failed to connect to k28i14
I have tried different values (default, intel, openmpi) for the -mpi option, but this all gives the same result. Leaving out the -cnf option, fluent does start. But unless I am mistaking, it will not be possible to run on multiple nodes.
I expect people will comment on this thread that there is something wrong with the ssh setup, but I can definitely tell that a simple ssh connection works without any password (it could still be there is a problem with launching a remote command over ssh, but I can't figure out which command fluent executes over ssh). As a further confirmation of this, with the newer Fluent version 2021R2, everything is working fine (i.e. I can do multi-node Fluent runs with that version).
On a side note, version 19.1.0 is working fine on another cluster that is running CentOS 7.
Do you have advice on what I could further try to get this working?
You are navigating away from the AIS Discovery experience