Building an Edge Computing Platform for Network Services Using Cloud Native Technology [I]
summary
A small-platform prototype runs containerized CNFs on Kubernetes, using BPF via BCC for pluggable data paths and a Kubernetes sidecar event handler model to let microservices emit events and call gRPC-based SDKs. Operators define service graphs (chains) of microservices; demo deploys a proxy, policy manager and content inspector to tens–hundreds of edge servers, then hot-inserts an antivirus microservice and rolls pods; push failures cited at 5–30% motivate local validation and rollback, and traces show dynamic routing and successful updates.
AI-written summary · about
chapters (13)
- 0:00Introduction
- 0:23What is Network Function Virtualization
- 1:28Edge Network Use Cases
- 3:02Why Cloud Native
- 6:48Architecture
- 8:10EPF
- 9:52Demo
- 18:52Call floats
- 19:31Data collection
- 21:06Usability
- 22:26Legacy VNF
- 24:07Cloud Native Ecosystem
- 25:36Information
related talks
32mEdge-Native: The New Paradigm For Operating And Developing Edge Apps
36mEdge Computing in Kubernetes: Best Practices for the Future
34mKubeEdge: Kubernetes Native Edge Computing Framework
26mIntro to KubeEdge: Kubernetes Native Edge Computing Framework
34mManaging Edge Nodes With “KubeEdge”
36mEdge Computing and Kubernetes BOF
39mIoT Application Running on KubeEdge + ARM Platform
31mIntro to KubeEdge: Kubernetes Native Edge Computing Framework