[torqueusers] server/client builds

[nathaniel.x.woody at gsk.com]

Well, Thanks for feedback, sounds  like my config ought to be fine.  I'll 
probably attempt it this week or next, so I'll let everybody know what 
happens (sorry, no means to test 64 bit nodes with 32 bit server).

Nate





"scoggins" <jscoggins at lbl.gov> 
Sent by: torqueusers-bounces at supercluster.org
02-Apr-2007 12:15
 
To
"Garrick Staples" <garrick at usc.edu>
cc
torqueusers at supercluster.org
Subject
Re: [torqueusers] server/client builds






Well I got the following errors last week when I was trying to get a 
32-bit built system running over a 64 bit node:

  PBS_Server: stream_eof, connection to n0000 is bad, remote service 
may be down, message may be corrupt, or connection may have been 
dropped remotely (Premature end of message).  setting node state to down

Looked at the source code and thought that maybe the stream_io was 
having problems because they were different architectures.  Once I 
installed a 64-bit server on the same net I was able to get it to 
work without any problems.  I read that the network might be the 
cause but once I built the 64-bit system and it worked I assumed it 
was not the network but the architecture.  If you have a working one 
please tell me what did you do to get it working?

Thanks

Jackie


On Apr 2, 2007, at 9:10 AM, Garrick Staples wrote:

> On Mon, Apr 02, 2007 at 08:49:47AM -0700, scoggins alleged:
>> I did the opposite 32-bit server with 64-bit nodes and that did not
>> work.  I kept getting a communication error from the pbs_server
>> trying to check in with the pbs_mom on the client side.  So I built a
>
> It has always worked fine for me in testing.
>
>
> -- 
> Garrick Staples, GNU/Linux HPCC SysAdmin
> University of Southern California
> _______________________________________________
> torqueusers mailing list
> torqueusers at supercluster.org
> http://www.supercluster.org/mailman/listinfo/torqueusers
_______________________________________________
torqueusers mailing list
torqueusers at supercluster.org
http://www.supercluster.org/mailman/listinfo/torqueusers


-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.supercluster.org/pipermail/torqueusers/attachments/20070402/44d4cd47/attachment.html