I'm trying to make MPI run on a small cluster on Centos 7 OS. The firewall is preventing it from running. This is the error I get:
$ mpirun -np 30 -hostfile hosts.txt mpi_sample_program/mpitest
------------------------------------------------------------
A process or daemon was unable to complete a TCP connection
to another process:
Local host: marcher5
Remote host: ***.***.***.***.***
This is usually caused by a firewall on the remote host. Please
check that any firewall (e.g., iptables) has been disabled and
try again.
------------------------------------------------------------
--------------------------------------------------------------------------
ORTE was unable to reliably start one or more daemons.
This usually is caused by:
* not finding the required libraries and/or binaries on
one or more nodes. Please check your PATH and LD_LIBRARY_PATH
settings, or configure OMPI with --enable-orterun-prefix-by-default
* lack of authority to execute on one or more specified nodes.
Please verify your allocation and authorities.
* the inability to write startup files into /tmp (--tmpdir/orte_tmpdir_base).
Please check with your sys admin to determine the correct location to use.
* compilation of the orted with dynamic libraries when static are required
(e.g., on Cray). Please check your configure cmd line and consider using
one of the contrib/platform definitions for your system type.
* an inability to create a connection back to mpirun due to a
lack of common network interfaces and/or no route found between
them. Please check network connectivity (including firewalls
and network routing requirements).
--------------------------------------------------------------------------
When I disable firewall using : sudo systemctl disable firewalld, MPI works just fine. I've been trying for a long week to add a rule that allows MPI to run without turning off the firewalld butit didn't work yet. I was able to do it with sudo iptables -A INPUT -s -j ACCEPT and it worked. But now I have to use firewall-cmd because of Centos 7. What do you suggest I do without compromising the security of the cluster. Should I add a rule to allow all traffic between my nodes?
My current firewall-cmd configuration is:
$ firewall-cmd --list-all
work (default, active)
interfaces: eno1
sources:
services: dhcpv6-client ipp-client ssh
ports:
masquerade: no
forward-ports:
icmp-blocks:
rich rules:
I tried to add source using this:
sudo firewall-cmd --permanent --zone=work --add-source=[host_IP]
But still couldn't make the MPI application run correctly. Then decided that the only way to enable MPI on this cluster is to make a rule to accept all traffic between the nodes. I ran those 2 commands.
sudo firewall-cmd --permanent --direct --add-rule ipv4 filter INPUT 0 -s [server+IP] -j ACCEPT
firewall-cmd --reload
and it worked like a charm.Not sure if this is the best solution security wise though.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With