I/O Latency on epyc01 (FC Cluster)

Unfortunately, we have not yet been able to identify the exact root cause of the issue. However, we suspect that the problem may be related to general performance limitations of the older hardware installed in this node.

As a result, this node will be prioritized for decommissioning, and the affected customers will be migrated to the new Xeon systems to ensure a more stable and performant infrastructure.

Further details will be provided as the migration progresses.

A few hours after closing the previous incident, continuous monitoring and customer feedback indicated that the read/write performance of the RAID subsystem on epyc01 (FC cluster) is below expected levels.

We are currently conducting a more detailed analysis to identify and permanently resolve the underlying cause of the I/O latency.

Further updates will be provided as soon as new information becomes available.