Lightning Talk: OpenKruise: Advancing Kubernetes Workload Auto...
summary
OpenKruise extends Kubernetes with concrete features: in-place pod updates that change CPU/memory without recreating pods, claiming ~90% faster rollout and no IP changes; workload objects like CloneSet and AdvancedStatefulSet plus workload spread with named subsets that let replicas scale vertically (example: CPU 6→12, memory 15GB→26GB) for cost saving; safety via a deleteProtection label on namespaces/Deployments/StatefulSets; and an imagePullJob parallelism=10 that cuts a 6m9s node pull to ~5s by prefetching images.
AI-written summary · about
related talks
21m07 Lightning talks
06m⚡ Lightning Talk: Colocating Data Workloads and Web Services on Kubernetes to Improve Resource Utilization
09mLightning Talk: Optimize the Ray Schedule and Autoscaling on Kubernetes Cloud: A Hetero...
09mLightning Talk: Sailing Kubernetes Operation with AI Power
06mProject Lightning Talk: What’s New in K0s: Lightweight Kubernetes Without Compromise
33mKubernetes at Cruise: Two Years of Multitenancy
05mLightning Talk: 7 Tips for Tricks to Enjoy Your Kubernetes Journey
05mLightning Talk - Realizing the Multi-Cloud Promise of Kubernetes
