Thirty Seconds of Silence - A Kubernetes Cluster Horror Story

Explore a gripping conference talk that delves into a mysterious 30-second incident that brought a Kubernetes cluster to a complete standstill. Follow along as the speaker unravels the events of a seemingly normal day in cluster-dev-us-east-1 that turned into a technical nightmare when deployments froze, container images failed to pull, and pod creation ceased entirely. Through detailed technical analysis and storytelling, discover what triggered this brief but impactful outage that set off PagerDuty alarms and disrupted normal cluster operations. Learn valuable insights about Kubernetes cluster management, troubleshooting, and the unexpected challenges that can arise in cloud-native environments.