I/O Latency on epyc01 (FC Cluster)

Incident Report for dataflair

Investigating

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.
Posted Jan 29, 2026 - 19:59 CET
This incident affects: firstcolo FRA4 (EPYC KVM Server Cluster).