[gmx-users] Gromacs and ssh problem

[Mark Abraham]

Bernhard Knapp wrote:
> Hi
> 
> I installed Gromacs successfully on Fedora 8 nodes. Afterwards I ran a 
> successful small simulation. Thereafter I moved the node to our 
> server-room did the following:
> - set ip adress, subnetmask and gateway
> - changed the ssh port in /etc/ssh/sshd_config since we use port 
> forwarding on our router and /usr/sbin/semanage port -a -t 
> inetd_child_port_t -p tcp 5101
> - changed the firewall settings to additionally allow the new port
> - changed the hostname via hostname command
> 
> Then I started exactly the same simulation (same command, same data) as 
> before (before the network configuration) and Gromacs comes up with:
> 
> ssh: quoVadis01: Name or service not known
> --------------------------------------------------------------------------
> A daemon (pid 5039) died unexpectedly with status 255 while attempting
> to launch so we are aborting.
> 
> There may be more information reported by the environment (see above).
> 
> This may be because the daemon was unable to find all the needed shared
> libraries on the remote node. You may set your LD_LIBRARY_PATH to have the
> location of the shared libraries on the remote nodes and this will
> automatically be forwarded to the remote nodes.
> --------------------------------------------------------------------------
> --------------------------------------------------------------------------
> mpirun noticed that the job aborted, but has no info as to the process
> that caused that situation.
> --------------------------------------------------------------------------
> mpirun: clean termination accomplished

Strictly this is not a GROMACS problem at all. You seem to have your MPI 
configured to require interaction with ssh to get at local cores. This 
seems likely to be erroneous. The above messages are coming from mpirun, 
not the GROMACS child process.

> How is possible that some network configurations screw up Gromacs? The 
> simulation is running in parallel on the 4 local cores of the maschine 
> no network interaction is necessary at all. Can anybody tell me where 
> the problem is. The error message above is obviously incorrect since it 
> was already working and the library paths are ok ...

Guessing wildly, quoVadis01 was in your MPI config before, and it is no 
longer a valid hostname.

Mark