Users may have been experiencing job failures on Owens cluster since April 16, 2018
We have been experiencing an issue with the Ethernet switches in the Owens cluster.
Rolling reboots of all three clusters, starting from Tuesday, September 4, 2018
We will have rolling reboots of Owens and Ruby clusters starting from 8 AM Monday, August 6, 2018.
We've been having intermittent issues with connecting to the batch server hosts on Owens.
Rolling reboots of all clusters, starting from 8 AM Tuesday, June 19, 2018
User may have been getting the following error message when trying to submit a PBS job using job arrays
We will have a rolling reboot of login and compute nodes of Owens cluster starting from Monday, April 16, 2018.
We will have rolling reboots of Oakley, Ruby and Owens clusters starting from Monday Feb 5, 2018.
Updated at 9:07PM on Dec 20, 2017 :
Owens batch was restored by updating Torque resource manager at 6:37pm Dec 19, 2017.
Original Post at 4:45PM on Dec 19, 2017:
Owens batch has been down since approximately 4pm Dec 19, 2017 with returning the following message: