Go to complete cluster step only after remote installation of all the nodes
and after rebooting the all the clients from their local hardisk. This error
comes only when u run complete cluster setup before any of the nodes is not
running from the local hardisk.
----- Original Message -----
Sent: Wednesday, June 30, 2004 11:27 AM
Subject: [Oscar-users] Problem with eth0
> I have formed a cluster consisting of 4 nodes 1 server and 3 clients
> oscarnode1,oscarnode2 ,oscarnode3.Installation went on smoothly
> The problem I hae noticed that only the NIC(eth0 ) of oscarnode1(first
> has the Ip address assigned to it..
> But oscarnode2 and oscarnode3 does not show ip address assigned to their
> interface when I issue "ifconfig -a" .
> I checked the /etc/sysconfig/network-scripts/ifcfg-eth0 file on both
> Entries in this file are correct .
> I need to manually issue the command "service network restart" for the IP
> address to be assigned to eth0 on both these clients.
> But when I reboot the these clients(oscarnode2 and oscarnode3 ) again the
> It is strange because the installatiom on these three clients was done
> Please let me know why this disparity in these three systems regarding
> When I execute the last step which is Test Cluster I get this error
> /home mounts 2 nodes failed [FAILED]
> PVM(via PBS) [FAILED]
> PBS Shell test [FAILED]
> MPICH(via PBS) [FAILED]
> LAM/MPI(via PBS) [FAILED]
> PBS HDF5 Test [FAILED]
> 11,51 All
> This SF.Net email sponsored by Black Hat Briefings & Training.
> Attend Black Hat Briefings & Training, Las Vegas July 24-29 -
> digital self defense, top technical experts, no vendor pitches,
> unmatched networking opportunities. Visit http://www.blackhat.com
> Oscar-users mailing list