/gke-workload-scaling-troubleshooting
診斷 GKE HorizontalPodAutoscaler（HPA）失敗，如指標顯示 <unknown>、FailedGetResourceMetric 事件、缺少 Pod 資源 request，以及自訂或外部指標管線故障。
- 安裝次數
- 1800
- 專案星數
- 2.2 萬 ★
- 授權
- Apache-2.0
- 專案更新
- 2026-11-02
怎麼裝
npx skills add https://github.com/google/skills --skill gke-workload-scaling-troubleshooting安裝前請先看過原文內容。中文說明是 AI 翻譯，不保證安全。
原文
Diagnoses GKE HorizontalPodAutoscaler (HPA) failures — metrics showing as <unknown>, FailedGetResourceMetric / FailedGetScale / FailedComputeMetricsReplicas events, missing Pod resource requests, custom/external metrics-pipeline breakage (FailedGetExternalMetric / FailedGetCustomMetric, unavailable metrics adapter, control-plane firewall blocking the adapter), HPA that won't scale up or down (tolerance / stabilization window / unavailable rate metrics), scale-to/from-zero problems, and slow HPA reaction on large clusters. Use when an HPA isn't scaling a workload as expected or reports metric errors. Don't use for configuring or authoring new HPA/VPA objects or scaling best practices (see the gke-workload-scaling skill), or for Cluster Autoscaler / node-pool sizing.