Explore the challenges and solutions in managing over 7,000 Kubernetes clusters at scale in this conference talk from KubeCon + CloudNativeCon. Gain insights into architecting resilient systems as Kakao's private Kubernetes as a Service team members share their experiences following a significant data center fire. Learn about the economic and social impacts of the incident, and discover the team's approach to providing highly available Kubernetes clusters efficiently for developers. Delve into design ideas for cluster high-availability, implementation challenges, and concerns encountered while managing a vast infrastructure of 100,000+ nodes. Understand the importance of resilience in cloud-native environments and how to apply these lessons to your own Kubernetes deployments.