Hathi, Radon, and Specialized Cluster Maintenance
Update message: After performing necessary repairs, Radon has been returned to service.
-- Previous message: After consulting with vendor support, we have determined that Radon has experienced a failure in its network hardware. Parts and and a vendor engineer will be on-site Tuesday, June 27 to repair. Radon will remain unavailable until that time.
-- Previous message:
The outage is being extended until 11:59am. There have been continued issues bringing Radon back into production due to an issue with its connectivity. At the moment, it cannot be said whether this is due to a networking problem or an issue within the Radon internal server configuration.
As previously stated, all other resources are back online and in production.
Update by 11:59a.
Thank you for your continued patience.
We are extending the outage by two hours due to issues encountered with bringing the Radon cluster back into production.
All other resources are back in online and serving at this time.
Will update by 2:00am with status.
ORIGINAL OUTAGE NOTICE:
The Radon clusters, as well as some restricted access highly-specialized resources will be unavailable beginning at Friday, June 23rd, 2017 at 5:00pm, for scheduled power maintenance. The clusters will return to full production by Tuesday, June 27th, 2017 at 2:00pm.
During this time, power work will be performed in the Math data center.
Any PBS jobs which request a walltime on Radon which would take them past Friday, June 23rd, 2017 at 5:00pm will not start and will remain in the queue until after the maintenance is completed. The other systems affected do not use schedulers which are directly aware of this upcoming maintenance.