Gautschi Scheduling Paused - Emergency maintenance on Gautschi, Tuesday, November 3
Link to update at November 5, 2026 10:21am EST UPDATE:
Gautschi has returned to service and job scheduling has resumed. The scratch filesystem is available again.
Batch jobs that were running Tuesday morning were requeued and will start as normal.
Interactive jobs (OnDemand sessions, desktops, Jupyter) and jobs with requeueing disabled were cancelled and will need to be resubmitted.
Please spot-check important files in your scratch space. If anything is missing or looks wrong, contact rcac-help@purdue.edu.
Link to update at November 4, 2026 9:18pm EST UPDATE:
Our engineers are still working through issues with the restoration of Gautschi’s scratch filesystem. Gautschi will remain out of service overnight.
Job scheduling remains paused, and scratch remains offline.
We will post our next update at or before 11:00 AM ET on Thursday, November 5. Contact rcac-help@purdue.edu. We apologize for the continued disruption.
Link to update at November 4, 2026 3:42pm EST UPDATE:
Work to restore Gautschi’s scratch filesystem is continuing. Gautschi will remain out of service past 5:00 PM Eastern today, Wednesday, November 4.
- Job scheduling remains paused, and scratch remains offline.
- Jobs already in the queue will stay queued and will not start until Gautschi returns to service.
- This affects Gautschi only. Other RCAC clusters and their filesystems are not affected.
We will post our next update at or before 9:00 PM ET.
Link to update at November 4, 2026 10:00am EST UPDATE:
Work is continuing to restore Gauthschi's scratch file system. Scheduling is still paused. The next update will be at or before 5:00pm EDT.
Link to update at November 3, 2026 7:56pm EST UPDATE:
The emergency maintenance on Gautschi’s Lustre scratch filesystem is taking longer than planned. We now expect Gautschi to remain out of service until at least 10:00 AM Eastern on Wednesday, November 4.
Link to original posting ORIGINAL:
Gautschi is under emergency maintenance to repair and upgrade its Lustre scratch filesystem. The cluster’s job scheduler has been paused and the repair work will begin Tuesday morning.
What’s happening: Our engineers identified a problem with the Gautschi scratch filesystem that requires an emergency upgrade and repair. The procedure must be done with the filesystem offline and is expected to take 8-10 hours or more. To avoid any risk of further damage, we have stopped new jobs from starting on Gautschi as of Monday afternoon, November 2.
Timeline
Now: No new jobs will start.
Tuesday, November 3, 8:00 AM: Remaining non-interactive batch jobs will be requeued, and interactive jobs (including OnDemand sessions) will be ended. Scratch will be unmounted and work will begin.
Estimated completion: Late Tuesday, though it may run longer.