Ada Volumes Restored
Hi everyone,
Yesterday (October 8th 2025) at around 14:30ET, we experienced an unexpected system downtime. While investigating, we found that the failure stemmed from a failure on the file server associated with the ada GPU cluster (ada-rstor). In order to make the chip hardware available to users, we temporarily disabled all network connections between the chip cluster and ada-rstor file server. Please note that if you had a slurm job running that was using a file from ada-rstor it will likely have failed. All other slurm jobs should have been unaffected.
We have resolved the issue and volumes associated with ada-rstor (paths starting with “/umbc/ada”), should be back to normal use. We appreciate the patience of all users who were affected by the outage of both the hardware and file system.
As always if you notice any issues with chip’s performance, file-systems, or otherwise, please report them via RT (https://rtforms.umbc.edu/rt_authenticated/doit/DoIT-support.php?auto=Research%20Computing) with as much information as possible.
Max Breitmeyer
HPC Specialist
Tags:
Posted: October 9, 2025, 11:46 AM