CiliumCon Europe 2025
2025-04-01
London, United Kingdom
[CiliumCon Europe 2023, CiliumCon Europe 2025, CiliumCon Europe 2026]
who it's for
Kubernetes operators, platform engineers, site reliability engineers, network engineers, cloud infrastructure engineers, machine learning infrastructure engineers, security engineers, observability engineers
topics
delegated IPAM native routing; pod-level QoS; multicluster Service API; Gateway API retries and mirroring; EndpointSlice scaling and sync; eBPF host routing and netkit; Cilium identity CRD migration; HA egress operator with kube-vip; Tetragon telemetry to LLM agents (RAG); Hubble rate limiting and metrics; conntrack GC tuning
| title | author | length |
|---|---|---|
| Welcome + Opening Remarks | Hemanth Malla, Bill Mulligan | 09m |
Cilium announces concrete milestones: Cilium 1.17 adds pod-level QoS, multicluster Service API for global services, service-level load‑balancer choice, and… | ||
| Improving Network Efficiency: The Power of Integrating Delegated... | Tamilmani Manoharan, Will Daly | 16m |
Native routing with Delegated IPAM removes VXLAN encapsulation and shows ~20% throughput improvement and lower CPU versus tunnel mode. Implementation uses a… | ||
| Lightning Talk: Mastering Zero Downtime Migrations Between Cilium Identity Alloca... | Anton Ippolitov | 10m |
Datadog migrates Cilium identities from KVStore to CRD by adding double-write mode (landed in Cilium 1.17), running scalability tests, tuning API server… | ||
| Lightning Talk: High Availability for Cilium Egress Gateway | Angelo Conforti | 09m |
Introduces an open source controller that adds HA to Cilium egress by orchestrating cilium-haegress-operator with kube-vip to move a floating egress IP via… | ||
| Closing Remarks | Hemanth Malla, Bill Mulligan | 04m |
Recap of outcomes and next steps: Cilium emphasizes high performance networking and an eBPF foundation with concrete wins in production for high‑scale machine… | ||
| High-Scale Networking for ML Workloads With Cilium | Luigi Zhou | 24m |
Production Cilium on over 10,000 bare‑metal nodes (clusters up to 1,000) runs eBPF dataplane for ML jobs processing 4–5M daily (peaks 11M). A policy map hit… | ||
| Lightning Talk: Agentic Bee: How To Get AI Agents To Talk To Tetragon | Himal Kumar | 11m |
Connects Tetragon runtime telemetry to LLM agents via a simple RAG architecture and FlowPulse sensors over Tetragon’s gRPC API to push dynamic tracing and… | ||
| That’s Just My Cup of Tea: Configuring Cilium for Performance and Scale | Liz Rice, Neha Aggarwal | 25m |
Cilium defaults favor compatibility but can be tuned for big gains: enabling Cilium EndpointSlices (stable since 1.16+) moves agents to watch slices and yields… | ||
| Cilium’s Honeycomb: Cultivating Technical Excellence in a Di... | Donia Chaiehloudj | 07m |
Cilium claims that 95% run multiple Kubernetes clusters, lists 161 public adopters on GitHub, and shows 912 contributors as of yesterday, evidencing wide… | ||
| Simplifying Multi-Cluster Networking With Cilium... | Arthur Outhenin-Chalandre, Marco Iorio | 27m |
Cilium adds beta MCS-API support (Cilium 1.17) and an EndpointSlice sync feature (introduced in Cilium 1.16 behind a flag) so a ServiceExport auto-creates… | ||
| nothing matches | ||