[mpich-discuss] machinefile error

[SULLIVAN David (AREVA)]

I verified that yes, each of the nodes appear in the known_hosts file. I
know that I can ssh from any of the nodes into the others. There is no
firewall that I am aware of (I am running Red Hat 5.4). I can freely
ping each of the nodes, wouldn't that fail if they were firewalled? 

Dave

-----Original Message-----
From: mpich-discuss-bounces at mcs.anl.gov
[mailto:mpich-discuss-bounces at mcs.anl.gov] On Behalf Of Pavan Balaji
Sent: Wednesday, July 21, 2010 4:06 PM
To: mpich-discuss at mcs.anl.gov
Subject: Re: [mpich-discuss] machinefile error


On 07/21/2010 02:44 PM, SULLIVAN David (AREVA) wrote:
> I have done that, as well as configured it to log in without a
password.
> I have no idea why it caches the key each time. 

Is the key added to your .ssh/known_hosts file? This needs to work
correctly before any ssh-based process manager works (including Hydra
and MPD).

There also seems to be a second problem that processes on node2 and
node3 are not able to connect back to node1. There are several
possibilities for this problem.

First, node2 and node3 are not able to look up the IP address of node1: 
you can check this by seeing if you can ssh from node2 to node1 (or from
node3 to node1).

Second, is there a firewall setup on these machines? If yes, can you
disable the firewall?

  -- Pavan

--
Pavan Balaji
http://www.mcs.anl.gov/~balaji
_______________________________________________
mpich-discuss mailing list
mpich-discuss at mcs.anl.gov
https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss