At 15:22 last Friday, Google Cloud ran 'maintenance automation intended to shutdown an unused network control component in a single location.' It worked in about 40 locations, leading to various network connectivity issues and failures for 33 Google Cloud Services.
The incident caused significant disruptions, including creation failures of new GKE nodes, loss of network connectivity for VMs, and partial packet loss in specific regions. Google attributed the outage to a bug in the automation tool used for network shutdown, which has been temporarily sidelined until improved.
Collection
[
|
...
]