For platform and DevOps engineers cutting wasted capacity in Kubernetes. Enter what a container requests and what it really uses to get recommended requests and the CPU and RAM you can reclaim.
Build industry projects on ByteLabs and add verified proof of your skills to your public profile.
You enter
CPU requested 1000 m, CPU used p95 320 m, RAM requested 2048 MiB, RAM used p95 900 MiB, Headroom 25 percent
The tool shows
Wasted CPU today 68 percent; Recommended CPU request 400 m; Recommended RAM request 1125 MiB; CPU reclaimed 600 m; RAM reclaimed 923 MiB
Measure p95 usage over a representative period and set requests to that value plus a safety margin. This tool uses p95 plus your headroom percent.
The default is 25 percent, a common starting point. Use more for spiky or memory-sensitive services and less for steady batch work.
From your monitoring stack, such as Prometheus with Grafana or your cloud provider's container insights, queried over at least a week of normal traffic.
Yes. It is free, needs no sign-up and runs entirely in your browser, so what you type is not uploaded. You only sign in if you want to email a result to yourself or save it to your CareerByteCode profile.
