UPDATE - Friday Aug 16 - 9:20am: Good news! The repairs have been completed. As it turns out, we did not have to interrupt any running jobs in any racks, including D30 and D31. No HPC jobs were affected.
The problem was that one of the electrical wires feeding our power supply was poorly connected to a breaker, creating a dangerous situation in the Sliger Data Center. The problem is 100% resolved now. Please let us know if you have any questions or concerns (firstname.lastname@example.org).
UPDATE - Friday Aug 16 - 9am: The electricians have rrived to perform the maintenance, and we are going to shut down the nodes now. Once again, all jobs running on compute nodes in the D30 and D31 racks (and possibly others) will be stopped.
We will let you know as soon as the situation is resolved.
A hazardous condition was discovered in some of the electrical wiring that feeds part of the HPC. We are coordinating with the electrician and will send out another notice when they arrive. This will affect compute nodes in the D30 and D31 racks, but possibly includes others.
This will affect running compute jobs. We expect this maintenance to take no more than a few hours. We apologize for any disruption to research this may cause, and will work hard to get the issue resolved quickly.
We will let you know as soon as the maintenance begins.