[torqueusers] Odd Communication Problem

Patrick McGuigan mcguigan at uta.edu
Thu Jul 10 02:39:33 MDT 2008


I have built both 2.3.0 and 2.3.1 on a Rocks 4.3 with SLC 4.6 (on 
x86_64) and I am seeing an odd problem with communication to the PBS 
server.  I am using 2.3.0/Rocks 4.3/SLC 4.6 (32bit) on another cluster 
without any problems.

I can start pbs_server without complaint and create the basic queue via 
the setup script.  I then usually restart the server and try some 
additional interactive qmgr commands.  These additional commands will 
sometimes work and sometimes not.  When the they fail, the qmgr command 
will exit. and the server log will contain:

PBS_Server;Req;dis_request_read;req header bad, dis error 7 (Premature 
end of message), type=Connect

PBS_Server;Req;req_reject;Reject reply code=15056(Bad DIS based Request 
Protocol MSG=cannot decode message), aux=0, type=Connect, from @


I have seen where premature end of message problems have been associated 
with firewall issues in the past, and I am seeing such issues with a 
test mom installation.  I have tried turning off all firewalls but I am 
still seeing the problem above.

Any advice is greatly appreciated,

Patrick



More information about the torqueusers mailing list