Monitoring Kubernetes Traffic with eBPF
summary
Explains what eBPF is and its main use cases, then shows how to use eBPF to observe network communications inside a Kubernetes cluster. Demonstrates writing an eBPF program, compiling and deploying it with the open-source BumbleBee project, exporting network metrics to Prometheus, and running a service that correlates metrics with pod and service IPs to visualize all cluster communications.
AI-written summary · about
chapters (17)
- 0:00Introduction
- 0:15Start
- 2:00Presentation by D. Jannot
- 3:15Recap on BPF
- 4:30Observability use cases
- 6:00Flexibility use cases
- 6:27Bidirectional use cases
- 7:48Creating your own BPF program
- 8:05BPF in Python
- 9:12BPF in production
- 11:19Example
- 13:32Observability
- 16:06Bumblebee
- 23:01Demo graph
- 23:11Demo check
- 23:39Prometheus deployment
- 34:51Limitations
related talks
27mStep By Step Kubernetes Observability with eBPF
29mKubernetes Observability with eBPF
23mAn Intro to eBPF with Go : The Foundation of Modern Kubernetes Networking
22mRole of eBPF in Kubernetes Networking and Security
30mObservability in Kubernetes: Unlocking the Power of eBPF
35mAn Introduction to eBPF - Superpowers for Networking, Observability & Security
31mBridging Dev and Ops with eBPF: Extending Observability Upwards and Downwards
27mLow-Overhead Tracing Using eBPF for Observability into Kubernetes Apps and Services