Performance · Version 1.2.0 · Reviewed 2026-08-02
Kubernetes Performance Tuning Specialist
Locate and remove the dominant bottleneck in kubernetes latency attribution and kubernetes throughput optimization with evidence, explicit trade-offs, and a verification plan.
4 method steps
4 documented failure modes
4 diagnostic checks
7 quality gates
Finds the dominant measured bottleneck and designs representative benchmarks for Kubernetes using workload manifests, Services, policies, events, and cluster topology and pod states, endpoint membership, scheduler events, and resource telemetry, with explicit attention to readiness, requests, or policy disagreeing with runtime behavior and hiding the true failure layer.
₹199 one-time
Get this skill archive
What it checks first
Kubernetes Performance Tuning Specialist finds the dominant measured bottleneck and designs representative benchmarks for Kubernetes using workload manifests, Services, policies, events, and cluster topology and pod states, endpoint membership, scheduler events, and resource telemetry, with explicit attention to readiness, requests, or policy disagreeing with runtime behavior and hiding the true failure layer. Use it when the work involves Kubernetes latency attribution, Kubernetes throughput optimization, Kubernetes performance regression guard.
- A measured baseline and the user-visible target, since optimization without both is guesswork.
- Whether the cost is CPU, memory, I/O wait, or lock contention — they have opposite fixes.
- The p99 path and how many round trips it contains.
- Whether the bottleneck moves after a change, which determines if the gain is real.
Example task
Input
Apply the performance tuning specialist to our Kubernetes system before the next production change. We can provide workload manifests, Services, policies, events, and cluster topology; the main concern is readiness, requests, or policy disagreeing with runtime behavior and hiding the true failure layer.
Expected output
Define the failing percentile and workload, then attribute time with pod states, endpoint membership, scheduler events, and resource telemetry. The likely mechanism to disprove first is readiness, requests, or policy disagreeing with runtime behavior and hiding the true failure layer. Change one constraint at a time and compare resource use, tail latency, and correctness against a pinned baseline.