[torqueusers] possible protocol problem.

Garrick Staples garrick at usc.edu
Tue Nov 16 13:29:14 MST 2004


On Tue, Nov 16, 2004 at 12:55:13PM -0500, Chris Johnson alleged:
> On Tue, 16 Nov 2004, Garrick Staples wrote:
> 
> > Yah, this is a fun one.  pbs_server sits around piling up TCP connections to
> > your hanging node too.
> 
>      Wonderful.  Any solutions to this?  It's a real problem in my
> environment.

So far, just reset the failing node, kill -9 pbs_server, and start it again.

I'll try and look at the code later on today.

-- 
Garrick Staples, Linux/HPCC Administrator
University of Southern California
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: not available
Url : http://www.supercluster.org/pipermail/torqueusers/attachments/20041116/9fe1b15b/attachment.bin


More information about the torqueusers mailing list