When datacenters lose power, generators should kick in. That didn’t happen for Google in London
The europe-west-2-b availability zone outage resulted from a failure in an external underground cable from the power supplier coinciding with primary feeder B being offline for corrective repairs. Google's 2N redundant power architecture with dual-path design and central high-voltage generator bank was misconfigured, preventing automatic generator activation. A standby utility connection exists for manual campus-wide transfer during maintenance or emergencies, but the combination of failed infrastructure and disabled redundancy exposed the system.
Key points
- Root cause: misconfigured emergency generators failed to start during power cable failure
- Outage affected major UK financial and postal services
- Feeder B circuit breaker was physically open for quarterly repairs when feeder A cable failed
- Facility uses redundant 2N power architecture with backup generators
Summary and key points written by AI from the headline and a short excerpt, so they can be incomplete or wrong. The Register did the reporting; read the original for the full story.
Read the full story at The Register
