GPFS brief outage

Incident Report for CU Boulder RC

Resolved

A brief outage of GPFS (Summit scratch) occurred due to a restart of opafm service on the standby fabric manager. The standby fabric manager attempted to seize the master role causing a dual-head situation. opafm service was stopped as soon as the situation was noticed. It appears the outage had minimal impact and was caught quickly enough to prevent more serious issues. We will continue to monitor the service and work with the network vendor to determine root cause.

Posted Sep 15, 2021 - 09:49 MDT