Maximizing the Value of Your Rados Gateway with Ingress Strategies
summary
Envoy sits in front of RADOS Gateway as an ingress proxy implementing distributed rate limiting via Envoy’s gRPC external rate‑limit service backed by Redis, with Prometheus/Grafana for per‑user/bucket metrics and header‑based region routing; demo runs across two Ceph clusters and three VMs and operates live, showing global rejects and retries. Measured overhead is about 2–4 ms per request. Also compared: HAProxy+keepalived ingress (SEF ADM), BGP/ECMP routing scaling to 64–128 hosts, and planned TLS + auto cert rotation.
AI-written summary · about
chapters (6)
- 0:00Introduction
- 1:41Load balancing strategies
- 10:22Cephadm ingress service
- 16:22Envoy proxy capabilities
- 25:25Live demo and monitoring
- 35:37Conclusion and Q&A
related talks
26mRedesigning Ingress: Docker’s Transition To the Next-Gen Gateway API
27mEnvoy Proxy: Evolved for Serving LLMs
33mGet to know Envoy - the modern proxy for cloud-native infrastructure - Baptiste Collard
15mFrom ingress-nginx to Envoy Gateway at Zapier: The...
34mIntro: Envoy
29mgRPC load balancing and Service Mesh
41mEffortless Secure and Control Traffic Using Kubernetes Gateway API for Ingress, Egress an...
28mBeyond Kubernetes Ingress (with Gateway API)