The Spice Must Flow: The Fremen guide to sustainable observability
summary
A demo front-end game (Chrome Dino style) runs on NGINX, instrumented with Faro and forwarded via Alloy to Prometheus, Loki and Tempo, visualized in Grafana; autoscaling uses KEDA for pods and GKE cluster autoscaler for nodes with min node 1 max 10 and pod min replicas 0 max 200, observed scaling to eight nodes and ~37 RPS; Kepler reports energy and estimated CO2 (Kepler ~80% accuracy) and the concrete actions are scale to zero and drop high‑volume debug telemetry.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 6:30Spice as telemetry
- 10:42Energy costs of data centers
- 15:17Autoscaling demo
- 22:09Load testing and scaling
- 27:06Energy with Kepler
- 30:01SPICE principles
- 33:56Tools for impact
- 36:28Telemetry versus sustainability
- 37:52Conclusion
related talks
40mBuilding a Scalable Observability Platform for Edge Compute Nodes
11mBuilding lightweight observability system for Lean Teams
36mObservability at Scale With Monitoring as Code...
28mImprove Monitoring and Observability for Kubernetes with OSS Tools
27mFrom Zero Visibility to Full Observability with Grafana
01h 29mTutorial: A Hitchhiker's Guide to CNCF/OSS Observability So...
09mFun and Games: Using Prometheus to aggregate disparate metric dat...
40mSustainability the Container Native Way