WHAT HAPPENED?

Several GTISC systems were shut down in the CoC HPCF (High Performance Computing Facility).

WHEN DID IT HAPPEN?

Beginning at approximately 1:50 AM, Tuesday, November 10, 2009.

WHY DID IT HAPPEN?

A campus chiller went down, causing the temperature in the HPCF to rise to 84 degrees. Several of the systems had reached critical internal temperatures and had to be shut down.

WHO WAS AFFECTED?

GTISC researchers.

WHAT DO YOU NEED TO DO?

Michael Lee, a GTISC systems administrator, will contact the affected researchers.

HAS THE PROBLEM BEEN RESOLVED?

Yes. Campus facilities brought up another chiller and pushed one of the alternate chillers that was running at reduced load up to 100% capacity. Temperatures in the HPCF began coming back into the normal range by 03:00 AM. At approximately 3:20 AM, the GTISC systems that were previously shut down were restarted. TSO remained on-site to continue monitoring the temperature in the HPCF, which returned to normal by 4:00 AM, November 10.

WHO SHOULD YOU CONTACT FOR QUESTIONS?

TSO Help Desk (CCB 148, 404.894.7065, helpdesk@cc.gatech.edu)

Owner of Alert
TSO