[torqueusers] Re: pbsnodes -a do not see the state of all nodes

Hannu Väisänen hvaisane at joyx.joensuu.fi
Thu Feb 24 01:14:56 MST 2005

On Wed, Feb 23, 2005 at 08:34:42AM -0800, Garrick Staples wrote:
> So mom is rejecting messages from server (momctl doesn't work) and server is
> rejecting messages from mom (message above).
> Port filtering or firewalling?

Yes. I put

pbs             15001/tcp
pbs_sched       15004/tcp
pbs_resmon      15003/tcp
pbs_resmon      15003/udp
pbs_mom         15002/tcp

into /etc/services on both machines and enabled ports 1500[1-4]
in firewall and restarted everything that starts with pbs_

Now momctl works but psnodes -a still says

     state = state-unknown,down
     np = 1
     ntype = cluster

momctl -d 4 -h <node-name> says

Host: xxxx   Server: xxxx   Version: torque_1.2.0p1
HomeDirectory:          /usr/spool/PBS/mom_priv
MOM active:             1800 seconds
WARNING:  no messages received from server
Server Update Interval: 20 seconds
Server Update Interval: 20 seconds
WARNING:  no hello/cluster-addrs messages received from server
Init Msgs Sent:         59 hellos
LOGLEVEL:               0 (use SIGUSR1/SIGUSR2 to adjust)
Communication Model:    RPP
TCP Timeout:            20 seconds
Prolog Alarm Time:      300 seconds
Alarm Time:             0 of 10 seconds
Trusted Client List:    xxxx
JobList:                NONE

diagnostics complete

More information about the torqueusers mailing list