Kubernetes 调度与资源

resources:
  requests:
    cpu: "250m"      # 调度时保证分配到 0.25 核
    memory: "256Mi"  # 保证 256Mi 内存
  limits:
    cpu: "500m"      # 最多用 0.5 核
    memory: "512Mi"  # 最多用 512Mi 内存

kubectl get pod web -o jsonpath='{.status.qosClass}'

affinity:
  nodeAffinity:
    requiredDuringSchedulingIgnoredDuringExecution:
      nodeSelectorTerms:
        - matchExpressions:
            - key: disktype
              operator: In
              values:
                - ssd        # 只调度到 disktype=ssd 的节点

affinity:
  podAntiAffinity:
    requiredDuringSchedulingIgnoredDuringExecution:
      - topologyKey: kubernetes.io/hostname   # 按节点维度分散
        labelSelector:
          matchLabels:
            app: web        # 不和同为 web 的 Pod 同节点

# 给节点打污点,标记为 GPU 专用
kubectl taint nodes gpu-node dedicated=gpu:NoSchedule

tolerations:
  - key: "dedicated"
    operator: "Equal"
    value: "gpu"
    effect: "NoSchedule"     # 容忍该污点,可以调度到 GPU 节点

topologySpreadConstraints:
  - maxSkew: 1                        # 各区域 Pod 数量最多差 1
    topologyKey: topology.kubernetes.io/zone
    whenUnsatisfiable: DoNotSchedule  # 不满足就暂不调度
    labelSelector:
      matchLabels:
        app: web

apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: web-hpa
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: web
  minReplicas: 2
  maxReplicas: 10
  metrics:
    - type: Resource
      resource:
        name: cpu
        target:
          type: Utilization
          averageUtilization: 60   # CPU 利用率超 60% 就扩容
    - type: Resource
      resource:
        name: memory
        target:
          type: Utilization
          averageUtilization: 70   # 内存利用率超 70% 也扩容

kubectl get hpa web-hpa --watch   # 观察副本数变化