Happy end of June everyone,
I'm writing to give everyone an update regarding the UMBC HPCF and other Research Computing projects currently undertaken by DoIT during the month of June.
Summary
-
ada Volumes Being Sunset by End of Summer
-
Continued Work to Improve Ceph Performance in Edge Cases
-
chip Maintenance Period Scheduled for July 28th https://my3.my.umbc.edu/groups/hpcf/posts/160868
ada Volumes Being Sunset by end of Summer
As mentioned in the previous newsletter, the ada file storage server is aging and we are starting the process to migrate the 170TB spread across 42 volumes to RRStor in coordination with volume owners. We’ve sent out emails to all of the volume owners that will be affected with a deadline of June 30th (today!) to respond.
Huge thanks to everyone who has responded to get their migrations scheduled! We’ve already migrated ~20% of the volumes and are in a good position to finish before our goal of July 31st.
Continued Work to Improve Ceph Performance in Edge Cases
Our team is continuing to collaborate closely with the users experiencing performance anomalies on the RRStor Ceph storage cluster. While we’ve made some headway with understanding where the bottlenecks are, we are still actively diagnosing the underlying causes and evaluating potential approaches to see what will be most effective. We deeply appreciate the patience and collaboration of those affected as we work toward ensuring a consistent, high-speed storage experience for all workloads.
If you experience unexpected slowness or suboptimal performance with the new RRStor storage cluster, please submit an RT Ticket so we can investigate!
chip Maintenance Period Scheduled for July 28th
As we mentioned yesterday, the chip cluster will undergo a scheduled maintenance window on July 28th from 0800-1800ET to implement essential infrastructure and software upgrades. You can refer to https://my3.my.umbc.edu/groups/hpcf/posts/160868 for more information on the downtime.
Please plan your workloads and batch jobs accordingly, as cluster services will be temporarily unavailable during this window. We appreciate your patience as we complete these updates to ensure a more robust and high-performing computing environment.
Publications
If you have any publications, presentations, theses, or other works that made use of the campus cluster, please submit an RT Ticket with bibliographic information so that we can accurately reflect this work in our records and on the HPCF Website.
Need Help?
As always, please communicate any issues/questions to the Research Computing RT Queue (hpcf.umbc.edu > User Support > Request Help).
Gregory Ballantine,
HPC System Administrator