The Hopper cluster will undergo biannual maintenance this July. Hopper will be unavailable between 6:00AM on Monday, 07/13/2026 and the end of Wednesday, 07/15/2026 for scheduled maintenance. We plan to upgrade the compute, network, and storage infrastructure of the cluster during this maintenance window.
Maintenance Schedule:
– Start Time: Monday July 13th, 6:00AM
– End Time: Wednesday July 15th, End of Day
Affected services:
1. Login/Head and Compute Nodes: All login/head and compute nodes will be inaccessible. Users will not be able to log in or submit jobs during this time.
2. Open On-Demand (OOD): The Open On-Demand (OOD) interface will be inaccessible. Users are advised to plan their activities accordingly and save any unsaved work.
3. Storage and Related Services: Most storage services, including Samba and Globus, will have limited intermittent availability.
4. Virtual Machines: Most virtual machines will have intermittent availability. Users with virtual machines should be prepared for potential interruptions in service.
Job Scheduling:
All SLURM partitions will be drained when the maintenance window starts. Any jobs started between now, and the maintenance period must be timed to end before the maintenance window begins. When submitting a job in the week leading to the maintenance window, make sure to set the Slurm time limit in SLURM to less than 7 days and reduce it as the maintenance window gets closer.:
We have provided a script named ‘time-to-maintenance-window.py ‘to give guidance on acceptable job wall times. Or you can calculate backwards from the start of maintenance and adjust your job length:
#SBATCH — time= 4-00:00:00 ## Days-Hours:Mins:Secs
Please note that any jobs that are configured to run past the planned maintenance dates will not start.
The clusters should be back online by the end of 07/15/2026.
If you have any questions or concerns, please email us at [email protected].