Uploaded August 2026 | Updated September 2026, 3 weeks ago
Don't miss out! Join us at our next KubeCon + CloudNativeCon events in Shanghai, China (8-9 September, 2026) and Salt Lake City, United States (Nov 9–12, 2026). Connect with our current graduated, incubating, and sandbox projects as the community gathers to further the education and advancement of cloud native computing. Learn more at kubecon.io
The Road To Cilium: Migrating 150+ Kubernetes Clusters at Airbnb - Yifei Sun, Airbnb
Airbnb migrated from AWS VPC CNI to Cilium across 150+ Kubernetes clusters to unlock eBPF-based capabilities like kube-proxy replacement and cluster-wide network policy. This talk shares lessons from that journey. While grounded in Airbnb’s experience, the patterns and lessons apply broadly to teams operating Kubernetes at scale.
We cover pod lifecycle performance testing at scale, using AWS VPC CNI as a reference. We’ll dive into how differences in IPAM configuration, EC2 API interactions, and workload identity allocation introduce scalability bottlenecks, particularly under high-churn data and batch workloads (e.g., Spark).
We also discuss rollout strategies across cluster, node, and pod levels, exploring the trade-offs of each. Finally, we’ll walk through practical solutions for challenges like dual-stack environments and circular dependencies during bootstrap. Attendees will leave with a safe, incremental rollout approach for large-scale Cilium adoption.
Don't miss out! Join us at our next KubeCon + CloudNativeCon events in Shanghai, China (8-9 September, 2026) and Salt Lake City, United States (Nov 9–12, 2026). Connect with our current graduated, incubating, and sandbox projects as the community gathers to further the education and advancement of cloud native computing. Learn more at kubecon.io
The Road To Cilium: Migrating 150+ Kubernetes Clusters at Airbnb - Yifei Sun, Airbnb
Airbnb migrated from AWS VPC CNI to Cilium across 150+ Kubernetes clusters to unlock eBPF-based capabilities like kube-proxy replacement and cluster-wide network policy. This talk shares lessons from that journey. While grounded in Airbnb’s experience, the patterns and lessons apply broadly to teams operating Kubernetes at scale.
We cover pod lifecycle performance testing at scale, using AWS VPC CNI as a reference. We’ll dive into how differences in IPAM configuration, EC2 API interactions, and workload identity allocation introduce scalability bottlenecks, particularly under high-churn data and batch workloads (e.g., Spark).
We also discuss rollout strategies across cluster, node, and pod levels, exploring the trade-offs of each. Finally, we’ll walk through practical solutions for challenges like dual-stack environments and circular dependencies during bootstrap. Attendees will leave with a safe, incremental rollout approach for large-scale Cilium adoption.
