Unscheduled Depot Outage on Compute Clusters

January 3, 2018 11:30am - 1:30pm
Outages and Maintenance
Snyder, Rice, Halstead, HalsteadGPU, Scholar, Brown, Conte, Radon

UPDATE: January 3, 2018  1:35pm

As of 1:35pm, all nodes and other systems affected by this incident have had their service restored.


ORIGINAL: January 3, 2018 11:30am - 1:30pm

The servers providing access to Data Depot from Snyder, Rice, Halstead, HalsteadGPU, Scholar, Brown, Conte, and Radon suffered a partial failure.

Many nodes in these clusters temporarily lost access to Depot. Jobs accessing files on Depot may have paused or terminated depending on the severity of the issue on each node and the nature of the job being run.

The issue is already being corrected and access restored, but some job failures or delays may be seen.

Originally posted: January 3, 2018 12:33pm