Friday, May 19th, 2017
In order to perform the annual scheduled maintenance at the MGHPCC, there will be a full power outage at the site starting at 9:00am on Monday, May 22 and ending at 9:00am on Wednesday, May 24. This outage impacts the Shared Computing Cluster (SCC) and ATLAS, as well as the Linux Virtual Lab (scc-lite.bu.edu) and class.bu.edu which use filesystems located at the MGHPCC. All SCC login and compute nodes, home directories, and Project Disk Space will be unavailable during the outage. The planned outage is scheduled to last until Wednesday at 9:00am; we will let you know if the work is completed early and the systems are available for use sooner at http://www.bu.edu/tech/research/sccupdates/.
You may continue to submit jobs until the downtime. However, on Friday, April 21 we will start a process of draining the batch queues on the SCC to prevent long running jobs from starting. Any jobs that would not complete prior to the shutdown will remain pending until the computer systems are returned to normal operations. This process will continue until Monday, May 22, 9:00am, at which time and we shut down all SCC computer systems including all of the login nodes.
If you would like to run and complete jobs on the batch system over the next four weeks before the downtime, you should adjust your hard run time limits accordingly. For more details see: http://www.bu.edu/tech/support/research/system-usage/running-jobs/submitting-jobs/#job-resources.
We anticipate having all systems returned to production status by 9:00am on Wednesday, May 24 at which time pending jobs will begin to be processed.
We will post updates before, during, and after the downtime on the SCC status page at http://www.bu.edu/tech/research/sccupdates/. Please email firstname.lastname@example.org if you have any additional questions or concerns.