K8s Under Fire: Igniting Performance & Burning Through Bottlenecks with Kube-Burner
summary
Kube-burner is a CNCF Sandbox tool that orchestrates large-scale K8s workloads, creates namespaces and thousands of objects (demo runs 10 iterations creating routes, builds, deployments, services and pods), scrapes Prometheus and pushes JSON-indexed metrics to OpenSearch for Grafana visualization, and records custom measurements like pod readiness latency and service/network latency plus pprof profiling for flamegraphs. It runs on vanilla K8s and OpenShift, supports OVN CNI and VM workloads, and reports whether clusters or apps hit breaking points under load.
AI-written summary · about
chapters (7)
- 0:00Kube-Burner introduction
- 2:52Kube-Burner load testing
- 7:07Kube-Burner configuration
- 13:24Kube-Burner job types
- 17:43Kube-Burner community
- 19:33Kube-Burner demo on OpenShift
- 26:47Q&A
related talks
22mThe House is on fire: mysteries of on-call K8s engineering
44mPerformance and Scalability Tuning Kubernetes for OpenShift and Docker
32mDeep Dive: Kubespray (a sig-cluster-lifecycle's project)
32mDeep Dive: Kubespray (a sig-cluster-lifecycle's project)
32mOptimizing Application Performance on Kubernetes
02h 26mKubernetes Performance Tuning Workshop
27mBuilding Applications to Increase Kubernetes Adoption, and Make Life Easier
27mThe Kubernetes Hunger Games: Distro Performance in the Edge