Power outage impacting multiple clusters
Link to update at April 4, 2025 10:41am EDT UPDATE:
Majority of the nodes have recovered by 10:30am and cluster scheduling remains enabled. Users are requested to resubmit the jobs that crashed due to the power outage.
Link to original posting ORIGINAL:
Due to a campus-wide power outage, the Anvil, Negishi, Rowdy, and Scholar clusters experienced an unscheduled reboot at Friday, April 4th, 2025 at 8:30am EDT. Engineers are currently diagnosing the impacted nodes and bringing services back online.
If you have any questions or need assistance, please reach out to rcac-help@purdue.edu.