Tales from On-Call: Operating Etcd at Scale

Tales from On-Call: Operating Etcd at Scale

Dive into the challenges and solutions of operating etcd at scale in this 31-minute conference talk by Amazon engineers Geeta Gharpure and Chao Chen. Explore the critical role of etcd as the backbone of Kubernetes clusters and learn how large-scale workloads push it to its limits. Gain valuable insights into handling etcd out-of-memory conditions, managing size quotas, detecting and recovering from revision divergence, and other operational issues. Whether you're an on-call engineer looking to compare notes or seeking to deepen your understanding of etcd operations, this CNCF presentation offers practical knowledge for maintaining robust Kubernetes infrastructures.