12/21/2017 4:00 p.m.
The work on kingspeak, lonepeak, ash, and tangent to fix the issues is now complete. Reservations have been released and jobs in the queue have
This downtime is needed to put a fix in place for issues that have been observed since the September 28 downtime when we upgraded the OS of the clusters. This is the same fix that was put in place on ember on December 14th which solved the observed issues.
The clusters will be down all day.
Reservations are in place to drain the batch queues of all running jobs on the remaining clusters by 8am on December 21. Any jobs submitted to the batch queue with a wall time that will not allow for completion before these times will not start until after the downtime.
If you have questions or concerns regarding this downtime, please email email@example.com.