|Tuesday, February 06, 2024 6 a.m.
|Thursday, February 08, 2024 3:21 p.m.
Update: 3pm Feb 8: Outage is resolved, all skylake and rtx_6000 nodes now have 2 10G network interfaces (up from one each)
Update: 7PM Feb 6th: The site is online, and all P3 nodes (everything except compute_skylake and gpu_rtx_6000) are accessible.
Re-cabling the switches for the P2 nodes has taken longer than anticipated, but we plan to finish that work tomorrow (the 7th), giving all P2 nodes a second 10g interface, and increasing the amount of inter-rack bandwidth available to them.
On Feb 6th, 2024, we'll be taking the CHI@UC site down for maintenance, in order to replace some failing network hardware, and in the process, provide all P2 nodes with a second 10g network interface.
This will be a full day outage, and instances at CHI@UC will not be accessible during this time. Instances will otherwise be unaffected, and will be accessable again after the outage ends.
Of note, the last remaining Corsa switch, and thus Openflow support will be deprecated as part of this maintenance until it can be relocated for the upcoming "reservable switch" feature.
Please get in touch with us if this presents a large issue, and we can assist in finding alternatives at the other Chameleon sites.