A Scheduling Simulator for Capacity Estimation of Kubernetes Clusters
summary
Introduces the open-source tool cluster-capacity for Kubernetes, which estimates how many pods of a given resource size (CPU, memory, storage) can be scheduled on a cluster. Explains the tool’s use cases and architecture by describing its implementation as a scheduling simulator, and includes a live demo showing different ways to run the simulator against a Kubernetes cluster and notes on future development.
AI-written summary · about
chapters (9)
- 0:00Start
- 0:39Introduction
- 1:40Motivation: Why?
- 6:58Design: Resource based approach
- 8:59Design: Impact on Scheduling
- 14:24Design: Scheduler based
- 16:02Features
- 21:12Usage (Best Practices)
- 23:49Status
related talks
36mA Toolkit for Simulating Kubernetes Scheduling at Scale
27mUnderstanding Kube-Scheduler-Simulator
36mCapacity Scheduling for Elastic Resource Sharing in Kubernetes
47mOptimizing Kubernetes Resource Requests/Limits for Cost-Efficiency and Latency
29mRight-Size Your Kubernetes Deployments
40mLimits, Requests, QoS... Rethinking What You Thought You Knew About Scheduling in Kubernetes
45mLimits, Requests, QoS, PriorityClasses: Demystifying Scheduling in K8s!
11mCost and Resource Optimization In Kubernetes