Technology · Ebook

Pixie: eBPF Observability for Kubernetes

by Shriira Press

Pixie is an open-source observability platform that gives you deep visibility into Kubernetes applications without changing a single line of code. It uses eBPF to automatically capture full-body requests, service metrics, network traces, and continuous CPU profiles directly in the kernel, stores that telemetry on each node inside the cluster rather than shipping it off to a vendor, and lets you query all of it with PxL, a Pythonic scripting language. This book builds Pixie up one layer at a time — eBPF auto-instrumentation, protocol tracing and data tables, the PEM, Vizier, Kelvin, and Cloud architecture, the in-cluster edge data store and distributed query engine, the PxL language, the Live UI and CLI, profiling and dynamic logging, and how teams adopt it in practice.

Contents

1. 1Preface
2. 2Chapter 1 — What Pixie Is
3. 3Chapter 2 — Auto-Instrumentation with eBPF
4. 4Chapter 3 — Protocol Tracing and Data Tables
5. 5Chapter 4 — Architecture: PEM, Vizier, Kelvin, Cloud
6. 6Chapter 5 — The In-Cluster Edge Data Store
7. 7Chapter 6 — PxL: The Pixie Language
8. 8Chapter 7 — The Live UI, CLI, and Scripts
9. 9Chapter 8 — Profiles, Dynamic Logs, and Encrypted Traffic
10. 10Chapter 9 — Pixie in Practice