Late summer weekend outage affecting 240 servers and services
Hi, everybody! I’m celebrating my return to work after a month off recovering from a broken kneecap (be sure to pay those loan sharks, people!) with an announcement that will cause consternation and worry. I’m just that kinda guy.
You’ve no doubt noticed the construction work happening around the building. You know, that big addition to the south side? Well, a bunch of stuff needed to happen to make that happen, and now we’re in the process of making some things un-happen so we can go back to normal operations. Specifically, we need to bring the on-site cooling equipment back online.
This is not a trivial process. In fact, it’s going to require 3 days to do. And while it’s being done, the entire data center is going to be offline. There are many systems and people affected by this (ALCF, LCRC, TRACC – anything hosted in the building 240 data center). The dates are not finalized, but the proposed dates at the moment are either the weekend of August 17, or September 7.
Most general services from CELS Systems (and all BIS-provided Argonne services) will be unaffected by this, with the exception of the CELS linux workstations and unix home directories and project-specific hardware hosted in building 240.
What I need to hear from you in the next week or so is if there are any show-stopping reasons why either of these dates will not work, so we can communicate this up the chain. I make no promises beyond being a strong advocate against hosing anyone’s work. But this does need to be done (and, between you, me, and the lamp post, I was hoping would be done about 6 months prior to this).
Thanks!