[torqueusers] stream_eof error message

[Yang Wang]

Hello all,

 

I just added a new nodes (of 8 cpu) to our existing cluster. After restart the pbs_server/pbs_mom/maui, the job submitted to this new nodes will be execute.

When the "pbsnodes -a", the node seems OK.

 

#pbsnodes -a 

.

bio206.agencourt.com

     state = free

     np = 7

     ntype = cluster

     status = opsys=linux,uname=Linux bio206.agencourt.com 2.6.9-67.ELsmp #1 SMP Wed Nov 7 13:56:44 EST 2007 x86_64,sessions=419,nsessions=1,nusers=1,idletime=4830,totmem=34921672kb,availmem=34531120kb,physmem=32890064kb,ncpus=8,loadave=0.00,netload=159574755634,state=free,jobs=,varattr=,rectime=1217882344

 

Here is the related part of the server log file:

 

08/04/2008 15:31:50;0040;PBS_Server;Req;ping_nodes;successful ping to node bio206.agencourt.com (stream 6)

 

08/04/2008 15:31:54;0001;PBS_Server;Svr;PBS_Server;stream_eof, connection to bio206.agencourt.com is bad, remo

te service may be down, message may be corrupt, or connection may have been dropped remotely (Premature end of

 message).  setting node state to down

 

 

 

What else I need to do to bring this nodes to a useable stage.

 

 

Thanks for the help.

 

 

Yang

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.supercluster.org/pipermail/torqueusers/attachments/20080804/53fff47f/attachment.html