Reported Outages

There is an upcoming data center outage in the room hosting the CHI@UC resources set for Friday, September 6, 2019 at 4PM CST through Monday, September 9, inclusive. This work requires that the cooling for the data center will be offline during this time while the building management brings another cooling system online, thus CHI@UC will be unavailable for this entire time. We don't currently have an estimate on the exact time CHI@UC will be available again, but we will post an all clear message once we are back online.

Networking at TACC has experienced an outage since 8:15am CST, but usage has been restored.  CHI@UC was not affected.

Networking outage for CHI@TACC.

Networking at TACC outage

Update (06/15 4:30pm CT): The storage node has been successfully restored and things are now back online. There may be some flaky behavior over the next bit as the system converges back to a steady state. Thanks again for your patience; please reach out if you are still experiencing issues over the rest of the weekend.

Update (06/17 2:00pm): we completed the maintenance successfully at 10:10am, but were affected by an unrelated power maintenance elsewhere in the data center. Those issues have also been resolved now and this maintenance can be considered complete. Hoping for smoother sailing through the rest of June.

We are testing a failure case on some of our networking hardware on Friday morning at 9am Central Time. The Bare Metal site and Jupyter environments will be down for about 15 minutes as a result. We expect the disruption to be minimal.

Update: the maintenance completed successfully. Happy Friday.

We are experiencing a network outage at the UC site. This affects all experiments running on the bare metal site and also the Jupyter Notebook environment. We are working on identifying the root cause.

Update: this was resolved at 13:00 CT. Apologies for the disturbance!

We are experiencing an issue with snapshotting baremetal instances at both the TACC and UC site since yesterday morning. We are looking in to resolving the issue right now and hope to have updates soon.

UPDATE: Instance networking has been restored. 

CHI@TACC is experiencing networking issues preventing access to instances. We are working to correct the problem, and will update when service has been restored.

Thanks,

The Chameleon Team