k8s_template.yml

### Ingress Deployment
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    app: ingress
  name: ingress
  namespace: default
spec:
  replicas: 1
  selector:
    matchLabels:
      app: ingress
  strategy:
    rollingUpdate:
      maxSurge: 25%
      maxUnavailable: 25%
    type: RollingUpdate
  template:
    metadata:
      labels:
        app: ingress
    spec:
      containers:
      ### Actual Ingress image
      - image: gcr.io/${GOOGLE_PROJECT_ID}/ingress:${CIRCLE_SHA1}
        name: ingress
        resources:
          requests:
            cpu: "250m"
      ### CloudSQL Proxy (db connection)
      - name: cloudsql-proxy
        image: gcr.io/cloudsql-docker/gce-proxy:1.16
        command: ["/cloud_sql_proxy",
                  "-instances=reflect-backend:us-central1:reflect-db=tcp:3306",
                  "-credential_file=/secrets/cloudsql/key.json"]
        securityContext:
          runAsUser: 2
          allowPrivilegeEscalation: false
        volumeMounts:
          - name: cloudsql-instance-credentials
            mountPath: /secrets/cloudsql
            readOnly: true
      volumes:
      - name: cloudsql-instance-credentials
        secret:
          secretName: cloudsql-instance-credentials
      - name: cloudsql-db-credentials
        secret:
          secretName: cloudsql-db-credentials
      dnsPolicy: ClusterFirst
      restartPolicy: Always
      schedulerName: default-scheduler
      securityContext: {}
      terminationGracePeriodSeconds: 30

---
### Ingress Service
apiVersion: "v1"
kind: "Service"
metadata:
  name: "ingress-service"
  namespace: "default"
  labels:
    app: "ingress"
spec:
  ports:
  - protocol: "TCP"
    port: 80
    targetPort: 8080
  selector:
    app: "ingress"
  type: "LoadBalancer"

---
### Ingress HPA
apiVersion: autoscaling/v1
kind: HorizontalPodAutoscaler
metadata:
  name: ingress
  annotations:
    kubernetes.io/ingress.global-static-ip-name: "static-ip"
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: ingress
  minReplicas: 1
  maxReplicas: 3
  targetCPUUtilizationPercentage: 80


---
### NLP Deployment
apiVersion: apps/v1
kind: Deployment
metadata:
  generation: 1
  labels:
    app: nlp
  name: nlp
  namespace: default
spec:
  replicas: 1
  selector:
    matchLabels:
      app: nlp
  strategy:
    rollingUpdate:
      maxSurge: 25%
      maxUnavailable: 25%
    type: RollingUpdate
  template:
    metadata:
      creationTimestamp: null
      labels:
        app: nlp
    spec:
      containers:
      - image: gcr.io/${GOOGLE_PROJECT_ID}/nlp:${CIRCLE_SHA1}
        name: nlp
        resources:
          requests:
            cpu: "250m"
      dnsPolicy: ClusterFirst
      restartPolicy: Always
      schedulerName: default-scheduler
      securityContext: {}
      terminationGracePeriodSeconds: 30

---
### NLP Service
apiVersion: v1
kind: Service
metadata:
  labels:
    app: nlp
  name: nlp-service
  namespace: default
spec:
  externalTrafficPolicy: Cluster
  ports:
  - nodePort: 32610
    port: 30000
    protocol: TCP
    targetPort: 5000
  selector:
    app: nlp
  sessionAffinity: None
  type: NodePort
---
### NLP HPA
apiVersion: autoscaling/v1
kind: HorizontalPodAutoscaler
metadata:
  name: nlp
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: nlp
  minReplicas: 1
  maxReplicas: 10
  targetCPUUtilizationPercentage: 50