[intrepid-notify] Network issues on intrepid

ALCF Support support at alcf.anl.gov
Tue Apr 29 12:09:20 CDT 2008


FYI-

At around 10:30 AM today, we began to encounter widespread network  
issues on intrepid. The network problems are affecting home directory  
access on the frontend nodes, as well BG/P jobs on some parts of the  
machine.   To prevent job failures, we have temporarily disabled all  
Cobalt queueing on intrepid (though we have not killed any running  
jobs).  Some of the running jobs may be OK, but we don't know the  
full scope of the problem yet since the scope has broadened since we  
first noticed the issue.  Once we have everything back online and  
things have stabilized, we should be able to assess which jobs have  
been affected by the problem.

We will send out another note as soon as everything is working  
properly again.

Thanks,
ALCF Support Team




More information about the intrepid-notify mailing list