分布式系统关键技术：服务调度 [2026重制版]

# hpa-example.yaml
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: api-server-hpa
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: api-server
  minReplicas: 3
  maxReplicas: 100
  metrics:
  - type: Resource
    resource:
      name: cpu
      target:
        type: Utilization
        averageUtilization: 70
  - type: Resource
    resource:
      name: memory
      target:
        type: Utilization
        averageUtilization: 80
  - type: Pods
    pods:
      metric:
        name: requests-per-second
      target:
        type: AverageValue
        averageValue: "1k"
  behavior:
    scaleDown:
      stabilizationWindowSeconds: 300
      policies:
      - type: Percent
        value: 10
        periodSeconds: 60
    scaleUp:
      stabilizationWindowSeconds: 0
      policies:
      - type: Percent
        value: 100
        periodSeconds: 15
      selectPolicy: Max

# keda-scaler.yaml - 基于Kafka消费者延迟伸缩
apiVersion: keda.sh/v1alpha1
kind: ScaledObject
metadata:
  name: kafka-consumer-scaler
spec:
  scaleTargetRef:
    name: order-processor
  minReplicaCount: 2
  maxReplicaCount: 50
  triggers:
  - type: kafka
    metadata:
      bootstrapServers: kafka-headless:9092
      consumerGroup: order-group
      topic: orders
      lagThreshold: "100"
      offsetResetPolicy: latest

// OrderWorkflow.go - 订单处理工作流
func OrderWorkflow(ctx workflow.Context, order Order) error {
    // 步骤1：校验库存
    var inventoryAvailable bool
    err := workflow.ExecuteActivity(ctx, CheckInventory, order.ProductID, order.Quantity).Get(ctx, &inventoryAvailable)
    if err != nil || !inventoryAvailable {
        return errors.New("inventory not available")
    }
    
    // 步骤2：预留库存
    err = workflow.ExecuteActivity(ctx, ReserveInventory, order.ProductID, order.Quantity).Get(ctx, nil)
    
    // 步骤3：处理支付（带超时和重试）
    ctxWithTimeout := WithActivityOptions(ctx, 
        ActivityOptions{
            StartToCloseTimeout: time.Minute * 5,
            RetryPolicy: &RetryPolicy{
                InitialInterval: time.Second,
                BackoffCoefficient: 2.0,
                MaximumAttempts: 3,
            },
        })
    var paymentResult PaymentResult
    err = workflow.ExecuteActivity(ctxWithTimeout, ProcessPayment, order.PaymentInfo).Get(ctx, &paymentResult)
    
    if err != nil || !paymentResult.Success {
        // 补偿：释放库存
        workflow.ExecuteActivity(ctx, ReleaseInventory, order.ProductID, order.Quantity)
        return errors.New("payment failed")
    }
    
    // 步骤4：确认订单
    return workflow.ExecuteActivity(ctx, ConfirmOrder, order.ID).Get(ctx, nil)
}

# service-template.yaml - 标准化服务定义
apiVersion: apps/v1
kind: Deployment
metadata:
  name: {{ .Values.serviceName }}
  labels:
    app: {{ .Values.serviceName }}
    team: {{ .Values.team }}
    tier: application
    criticality: {{ .Values.criticality }}  # P0/P1/P2/P3
spec:
  replicas: {{ .Values.replicas.min }}
  strategy:
    type: RollingUpdate
    rollingUpdate:
      maxSurge: 25%
      maxUnavailable: 0
  selector:
    matchLabels:
      app: {{ .Values.serviceName }}
  template:
    metadata:
      annotations:
        prometheus.io/scrape: "true"
        prometheus.io/port: "{{ .Values.port }}"
        sidecar.istio.io/inject: "true"
    spec:
      serviceAccountName: {{ .Values.serviceName }}
      securityContext:
        runAsNonRoot: true
        runAsUser: 1000
        fsGroup: 1000
      containers:
      - name: app
        image: {{ .Values.image.repository }}:{{ .Values.image.tag }}
        ports:
        - containerPort: {{ .Values.port }}
        resources:
          requests:
            cpu: "{{ .Values.resources.requests.cpu }}"
            memory: "{{ .Values.resources.requests.memory }}"
          limits:
            cpu: "{{ .Values.resources.limits.cpu }}"
            memory: "{{ .Values.resources.limits.memory }}"
        livenessProbe:
          httpGet:
            path: /health/live
            port: {{ .Values.port }}
          initialDelaySeconds: 30
          periodSeconds: 10
        readinessProbe:
          httpGet:
            path: /health/ready
            port: {{ .Values.port }}
          initialDelaySeconds: 5
          periodSeconds: 5
        env:
        - name: SERVICE_NAME
          value: {{ .Values.serviceName }}
        - name: OTEL_EXPORTER_OTLP_ENDPOINT
          value: "otel-collector:4317"
        volumeMounts:
        - name: config
          mountPath: /app/config
          readOnly: true
      volumes:
      - name: config
        configMap:
          name: {{ .Values.serviceName }}-config