agent_platform_oci/deploy/oke/load-test/k8s/agent-backend.yaml

apiVersion: v1
kind: Namespace
metadata:
  name: agent-load-test
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: agent-template-backend
  namespace: agent-load-test
spec:
  replicas: 4
  strategy:
    type: RollingUpdate
    rollingUpdate:
      maxUnavailable: 0
      maxSurge: 2
  selector:
    matchLabels:
      app: agent-template-backend
  template:
    metadata:
      labels:
        app: agent-template-backend
      annotations:
        loadtest.runtime-checksum: "RUNTIME_CHECKSUM_PLACEHOLDER"
    spec:
      terminationGracePeriodSeconds: 60
      topologySpreadConstraints:
        - maxSkew: 1
          topologyKey: kubernetes.io/hostname
          whenUnsatisfiable: ScheduleAnyway
          labelSelector:
            matchLabels:
              app: agent-template-backend
      containers:
        - name: agent-template-backend
          image: IMAGE_PLACEHOLDER
          imagePullPolicy: Always
          ports:
            - containerPort: 8000
          envFrom:
            - secretRef:
                name: agent-backend-runtime
          env:
            - name: LANGFUSE_PUBLIC_KEY
              valueFrom:
                secretKeyRef:
                  name: langfuse-client
                  key: LANGFUSE_PUBLIC_KEY
            - name: LANGFUSE_SECRET_KEY
              valueFrom:
                secretKeyRef:
                  name: langfuse-client
                  key: LANGFUSE_SECRET_KEY
            - name: LANGFUSE_HOST
              valueFrom:
                secretKeyRef:
                  name: langfuse-client
                  key: LANGFUSE_HOST
          readinessProbe:
            httpGet:
              path: /health
              port: 8000
            initialDelaySeconds: 15
            periodSeconds: 10
            timeoutSeconds: 5
            failureThreshold: 6
          livenessProbe:
            httpGet:
              path: /health
              port: 8000
            initialDelaySeconds: 45
            periodSeconds: 20
            timeoutSeconds: 5
            failureThreshold: 6
          startupProbe:
            httpGet:
              path: /health
              port: 8000
            periodSeconds: 5
            failureThreshold: 36
          resources:
            requests:
              cpu: "500m"
              memory: "768Mi"
            limits:
              cpu: "2000m"
              memory: "2Gi"
          volumeMounts:
            - name: wallet
              mountPath: /app/wallet
              readOnly: true
      volumes:
        - name: wallet
          secret:
            secretName: agent-backend-wallet
---
apiVersion: v1
kind: Service
metadata:
  name: agent-template-backend
  namespace: agent-load-test
spec:
  type: ClusterIP
  sessionAffinity: None
  selector:
    app: agent-template-backend
  ports:
    - name: http
      port: 8000
      targetPort: 8000
---
apiVersion: v1
kind: Service
metadata:
  name: agent-template-backend-lb
  namespace: agent-load-test
#spec:
#  type: LoadBalancer
#  sessionAffinity: None
#  selector:
#    app: agent-template-backend
#  ports:
#    - name: http
#      port: 8000
#      targetPort: 8000
spec:
  type: NodePort
  selector:
    app: agent-template-backend
  ports:
    - name: http
      port: 8000
      targetPort: 8000
      nodePort: NODE_PORT_PLACEHOLDER
---
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: agent-template-backend
  namespace: agent-load-test
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: agent-template-backend
  minReplicas: 4
  maxReplicas: 30
  behavior:
    scaleUp:
      stabilizationWindowSeconds: 0
      policies:
        - type: Percent
          value: 100
          periodSeconds: 60
        - type: Pods
          value: 8
          periodSeconds: 60
      selectPolicy: Max
    scaleDown:
      stabilizationWindowSeconds: 300
      policies:
        - type: Percent
          value: 25
          periodSeconds: 60
  metrics:
    - type: Resource
      resource:
        name: cpu
        target:
          type: Utilization
          averageUtilization: 65
    - type: Resource
      resource:
        name: memory
        target:
          type: Utilization
          averageUtilization: 75
---
apiVersion: policy/v1
kind: PodDisruptionBudget
metadata:
  name: agent-template-backend
  namespace: agent-load-test
spec:
  minAvailable: 3
  selector:
    matchLabels:
      app: agent-template-backend