2d • Community
New Conversion from cgroup v1 CPU Shares to v2 CPU Weight
Your Kubernetes CPU requests might not mean what you think they mean. For a long time, the conversion from cpu.shares (cgroup v1) to cpu.weight (cgroup v2) used a linear formula that unintentionally penalized smaller CPU requests.
In practice, services requesting 100m-250m CPU could receive disproportionately low weight under contention, leading to unfair throttling and unpredictable latency especially in microservice-heavy clusters.
A new conversion formula corrects that mismatch. CPU weights now align much more closely with the original intent behind Kubernetes resource requests when running on cgroup v2. Under load, workloads compete more fairly, small services are no longer excessively disadvantaged, and behavior becomes more predictable in multi-tenant environments.
This doesn't make your cluster magically faster. It makes it more honest under pressure. And in production, that's often what really matters.
0
0 comments
New Conversion from cgroup v1 CPU Shares to v2 CPU Weight
powered by
skool.com/ai-devops-ansible-community-6317
AI DevOps Mastermind by Luca Berton: AI, DevOps, Kubernetes & Terraform. Access 50+ hours of courses, hands-on labs, and career-boosting mentorship!
Suggested communities
Powered by