Simplifying the Networking and Secur...
summary
Cilium now claims production scale up to 65,000 nodes with control-plane tweaks to handle pod churn spikes around 500 lifecycle events/sec, and a high-scale profile that disables nonessential features. Latest release adds QoS, Gateway API 1.2, multicluster services and tighter network policy performance; teams replace kube-proxy/iptables with eBPF host routing to lower latency and use a single flag to enable transparent encryption for pod-to-pod/node-to-node TLS. Tetragon exposes per-BPF CPU and memory metrics and initial eBPF-on-Windows support targets the June 1.5 release.
AI-written summary · about
chapters (5)
- 0:00Cilium project overview
- 4:54User case study: DB Schenker
- 12:51Scalability at GKE
- 17:52Tetragon updates
- 26:09Community and next steps
related talks
31mUnleashing the Tides of Kubernetes Networking by Removing kube-proxy
24mThe Cilium Story - Why We Created Cilium
28mLessons from Building Scalable Network Policy Enforcement with eBPF
20mTackling Container Networking at Scale
09mWelcome + Opening Remarks
05mLightning Talk: Unveiling 5 Essential Insights from Cilium Implementation in a...
26mSupercharge Kubernetes Networking with Cilium and IPv6
29mThe Swiss Army Knife of Cloud Native Networking