Google Cloud attributed a multi-hour outage on October 20 to a "power event" in its europe-west2-b zone in London. The earlier Register report said there was no recovery time in sight and no workarounds; a later update said recovery was tentatively expected by 1300 UTC and that most customers were back online by 14:03 UTC. Both reports agree on the scope: a single availability zone failure took down a wide range of Google Cloud services and customer-facing sites.
Affected Google services included Google Kubernetes Engine, Cloud Run, App Engine, Cloud Filestore, BigQuery Data Transfer Service, Cloud NetApp Volumes, and Managed Service for Apache Kafka. Downstream, Lloyds Bank, HSBC, Royal Mail, Rightmove, DPD, BT, Screwfix, and Revolut all reported disruption. Google said the power event was mitigated and that it was prioritizing recovery of existing workloads, but customers could not yet create new workloads at the time.
The Register's earlier report noted no workarounds and no recovery estimate; the later update said Google had no further updates and would publish an incident analysis after completing its internal investigation. Keele University's Dr Amro Al-Said Ahmad estimated 38 services were affected and said the incident shows that cloud resilience requires designing for regional failures through multi-region deployments, workload portability, and tested disaster recovery procedures.