Savio is tentatively scheduled to be offline for one day on Monday, October 26, 2026. During the outage we will fix a Lustre issue that has been causing intermittent inactive OSTs on login and compute nodes, and we will also do general node maintenance and repairs.
Slurm reservation: A reservation is already in place for October 26. If a job’s requested time limit would run into the maintenance window, the job will stay in the queue until the cluster is back online. This mostly affects jobs with long time limits, and it applies more widely as October 26 gets closer. To keep jobs running before the outage, set time limits that let them finish before the reservation begins.
Posted Oct 16, 2026 - 15:01 PDT
This scheduled maintenance affects: Home Directory Storage, Scratch Storage, Login Nodes, Compute Nodes, Data Transfer Nodes (DTNs), Job Scheduler, and Open OnDemand (OOD).