# This manifest deploys a PhoenixAI cluster with all supported features.

apiVersion: phoenixdata.ai/v1
kind: PhoenixAICluster
metadata:
  name: a-phoenixai-with-all-features   # change the name if needed.
spec:
  # the spec for phoenixai FE.
  phoenixAIFeSpec:
    # the image for phoenixai FE.
    image: us-west1-docker.pkg.dev/phoenix-ai-images/enterprise/fe-ubuntu:4.1.5-ee
    # number of replicas for phoenixai FE.
    replicas: 3
    # define resources requests and limits for FE pods.
    limits:
      cpu: 8
      memory: 16Gi
    requests:
      cpu: 8
      memory: 16Gi
    # reference the configMap for FE which contains the fe.conf.
    configMapInfo:
      configMapName: phoenixaicluster-sample-fe-cm
      resolveKey: fe.conf
    # fe storage volumes for persistent metadata and log
    storageVolumes:
      - name: fe-meta
        # the storageClassName represent the used storageclass name. if not set will use k8s cluster default storageclass.
        # storageClassName: ""
        # the persistent volume size. FE container stop running if the disk free space which the
        # fe meta directory residents, is less than 5Gi.
        storageSize: 10Gi
        # the mount path for FE meta.
        mountPath: /opt/starrocks/fe/meta
      - name: fe-log
        # storageClassName: ""
        # the size of storage volume for log
        storageSize: 1Gi
        # the mount path for FE log.
        mountPath: /opt/starrocks/fe/log
    # add annotations for fe pods.
    annotations: {}
    # the pod labels for user select or classify pods.
    podLabels: {}
    # schedulerName allows you to specify which scheduler will be used for your pods.
    schedulerName: ""
    # affinity for fe pod scheduling.
    affinity: {}
      # nodeAffinity:
      #   requiredDuringSchedulingIgnoredDuringExecution:
      #     nodeSelectorTerms:
      #     - matchFields:
      #       - key: metadata.name
      #         operator: In
      #         values:
      #         - target-host-name
    # Node tolerations for fe pod scheduling to nodes with taints
    # Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/
    tolerations: []
      # - key: "key"
      #   operator: "Equal|Exists"
      #   value: "value"
      #   effect: "NoSchedule|PreferNoSchedule|NoExecute(1.6 only)"
    # If specified, the pod's nodeSelector，displayName="Map of nodeSelectors to match when scheduling pods on nodes"
    # Ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#nodeselector
    nodeSelector: {}
      # kubernetes.io/arch: amd64
      # kubernetes.io/os: linux
    # Additional fe container environment variables
    # Ref: https://kubernetes.io/docs/tasks/inject-data-application/define-environment-variable-container/
    feEnvVars: []
      # e.g. static environment variable:
      # - name: DEMO_GREETING
      #   value: "Hello from the environment"
      # e.g. secret environment variable:
      # - name: USERNAME
      #   valueFrom:
      #   secretKeyRef:
      #     name: mysecret
      #     key: username
    # If runAsNonRoot is true, the container is run as non-root user.
    # The userId will be set to 1000, and the groupID will be set to 1000.
    runAsNonRoot: false
    service:
      # the fe service type, only supported ClusterIP, NodePort, LoadBalancer
      type: ClusterIP
      # the loadBalancerIP for static ip config when the type=LoadBalancer
      loadBalancerIP: ""
      # add annotations for fe service.
      annotations: {}
      # config the service port for fe service.
      # if you want to use a dedicated port for fe service, you can config the port.
      # see https://kubernetes.io/docs/concepts/services-networking/service/#field-spec-ports for more details.
      ports: []
      # e.g. use a dedicated node port for http port of fe service.
      # - name: http  # fill the name from the fe service ports
      #   nodePort: 30030 # The range of valid ports is 30000-32767
    # imagePullSecrets allows you to use secrets to pull images for pods.
    imagePullSecrets: []
    # serviceAccount for fe access cloud service.
    serviceAccount: ""
    # mount secrets if necessary.
    # see https://kubernetes.io/docs/concepts/storage/volumes/#using-subpath for more details about subPath.
    secrets: []
      # e.g. mount my-secret to /etc/my-secret
      # - name: my-secret
      #   mountPath: /etc/my-secret
      #   subPath: ""
    # mount configmaps if necessary.
    # see https://kubernetes.io/docs/concepts/storage/volumes/#using-subpath for more details about subPath.
    configMaps: []
      # e.g. mount my-configmap to /etc/my-configmap
      # - name: my-configmap
      #   mountPath: /etc/my-configmap
      #   subPath: ""
    # startupProbeFailureSeconds defines the total failure seconds of startupProbe.
    # Default failureThreshold is 60 and the periodSeconds is 5, this means the startup
    # will fail if the pod can't start in 300 seconds. Your StartupProbeFailureSeconds is
    # the total time of seconds before startupProbe give up and fail the container start.
    # If startupProbeFailureSeconds can't be divided by defaultPeriodSeconds, the failureThreshold
    # will be rounded up
    # Note: you can set it to 0 to disable the probe.
    startupProbeFailureSeconds: 300
    # LivenessProbeFailureSeconds defines the total failure seconds of liveness Probe.
    # default value is 15 seconds
    # You can set it to 0 to disable the probe.
    livenessProbeFailureSeconds: 15
    # ReadinessProbeFailureSeconds defines the total failure seconds of readiness Probe.
    # default value is 15 seconds
    # You can set it to 0 to disable the probe.
    readinessProbeFailureSeconds: 15

  # the spec for phoenixai CN.
  phoenixAICnSpec: # the image for phoenixai CN.
    image: us-west1-docker.pkg.dev/phoenix-ai-images/enterprise/cn-ubuntu:4.1.5-ee
    # number of replicas to deploy for a CN statefulset.
    # comment out this line if autoScalingPolicy is enabled.
    # replicas: 1
    # define resources requests and limits for CN pods.
    limits:
      cpu: 16
      memory: 64Gi
    requests:
      cpu: 16
      memory: 64Gi
    # reference to the configmap for CN which contains the cn.conf.
    configMapInfo:
      configMapName: phoenixaicluster-sample-cn-cm
      resolveKey: cn.conf
    storageVolumes:
      - name: cn-data
        # the storageClassName represent the used storageclass name. if not set will use k8s cluster default storageclass.
        # storageClassName: ""
        # the size of storage volume for data
        storageSize: 10Gi
        # the mount path of CN data
        mountPath: /opt/starrocks/cn/storage
      - name: cn-log
        # storageClassName: ""
        # the size of storage volume for log
        storageSize: 1Gi
        # the mount path of CN log
        mountPath: /opt/starrocks/cn/log
    # comment out this section if you don't want to enable autoscaling policy.
    autoScalingPolicy:
      # the max replicas for CN autoscaling.
      maxReplicas: 10
      # the min replicas for CN autoscaling.
      minReplicas: 1
      # operator creates an HPA resource based on the following field.
      # see https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/ for more information.
      hpaPolicy:
        metrics:
          - type: Resource
            resource:
              # The average memory usage of CNs is specified as a resource metric.
              name: memory
              target:
                # The elastic scaling threshold is 60%.
                # When the average memory utilization of CNs exceeds 60%, the number of CNs increases for scale-out.
                # When the average memory utilization of CNs is below 60%, the number of CNs decreases for scale-in.
                averageUtilization: 60
                type: Utilization
          - type: Resource
            resource:
              # The average CPU utilization of CNs is specified as a resource metric.
              name: cpu
              target:
                # The elastic scaling threshold is 60%.
                # When the average CPU utilization of CNs exceeds 60%, the number of CNs increases for scale-out.
                # When the average CPU utilization of CNs is below 60%, the number of CNs decreases for scale-in.
                averageUtilization: 60
                type: Utilization
        # The scaling behavior is customized according to business scenarios, helping
        # you achieve rapid or slow scaling or disable scaling.
        behavior:
          scaleUp:
            policies:
              - type: Pods
                value: 1
                periodSeconds: 10
          scaleDown:
            selectPolicy: Disabled
    # add annotations for cn pods.
    annotations: {}
    # the pod labels for user select or classify pods.
    podLabels: {}
    # schedulerName allows you to specify which scheduler will be used for your pods.
    schedulerName: ""
    # Additional cn container environment variables
    # Ref: https://kubernetes.io/docs/tasks/inject-data-application/define-environment-variable-container/
    # affinity for cn pod scheduling.
    affinity: {}
      # nodeAffinity:
      #   requiredDuringSchedulingIgnoredDuringExecution:
      #     nodeSelectorTerms:
      #     - matchFields:
      #       - key: metadata.name
      #         operator: In
      #         values:
      #         - target-host-name
    # Node tolerations for cn pod scheduling to nodes with taints
    # Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/
    tolerations: []
      # - key: "key"
      #   operator: "Equal|Exists"
      #   value: "value"
      #   effect: "NoSchedule|PreferNoSchedule|NoExecute(1.6 only)"
    # If specified, the pod's nodeSelector，displayName="Map of nodeSelectors to match when scheduling pods on nodes"
    # Ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#nodeselector
    nodeSelector: {}
      # kubernetes.io/arch: amd64
      # kubernetes.io/os: linux
    cnEnvVars: []
      # e.g. static environment variable:
      # - name: DEMO_GREETING
      #   value: "Hello from the environment"
      # e.g. secret environment variable:
      # - name: USERNAME
      #   valueFrom:
      #   secretKeyRef:
      #     name: mysecret
      #     key: username
    # If runAsNonRoot is true, the container is run as non-root user.
    # The userId will be set to 1000, and the groupID will be set to 1000.
    runAsNonRoot: false
    service:
      # the cn service type, only supported ClusterIP, NodePort, LoadBalancer
      type: ClusterIP
      # the loadBalancerIP for static ip config when the type=LoadBalancer
      loadBalancerIP: ""
      # add annotations for cn service.
      annotations: {}
      # config the service port for cn service.
      # if you want to use a dedicated port for cn service, you can config the port.
      # see https://kubernetes.io/docs/concepts/services-networking/service/#field-spec-ports for more details.
      ports: []
      # e.g. use a dedicated node port for cn service.
      # - name: webserver # fill the name from the cn service ports
      #   nodePort: 30040 # The range of valid ports is 30000-32767
    # imagePullSecrets allows you to use secrets to pull images for pods.
    imagePullSecrets: []
    # serviceAccount for cn access cloud service.
    serviceAccount: ""
    # mount secrets if necessary.
    # see https://kubernetes.io/docs/concepts/storage/volumes/#using-subpath for more details about subPath.
    secrets: []
      # e.g. mount my-secret to /etc/my-secret
      # - name: my-secret
      #   mountPath: /etc/my-secret
      #   subPath: ""
    # mount configmaps if necessary.
    # see https://kubernetes.io/docs/concepts/storage/volumes/#using-subpath for more details about subPath.
    configMaps: []
      # e.g. mount my-configmap to /etc/my-configmap
      # - name: my-configmap
      #   mountPath: /etc/my-configmap
      #   subPath: ""
    # startupProbeFailureSeconds defines the total failure seconds of startupProbe.
    # Default failureThreshold is 60 and the periodSeconds is 5, this means the startup
    # will fail if the pod can't start in 300 seconds. Your StartupProbeFailureSeconds is
    # the total time of seconds before startupProbe give up and fail the container start.
    # If startupProbeFailureSeconds can't be divided by defaultPeriodSeconds, the failureThreshold
    # will be rounded up
    # Note: you can set it to 0 to disable the probe.
    startupProbeFailureSeconds: 300
    # LivenessProbeFailureSeconds defines the total failure seconds of liveness Probe.
    # default value is 15 seconds
    # You can set it to 0 to disable the probe.
    livenessProbeFailureSeconds: 15
    # ReadinessProbeFailureSeconds defines the total failure seconds of readiness Probe.
    # default value is 15 seconds
    # You can set it to 0 to disable the probe.
    readinessProbeFailureSeconds: 15

  # the spec for phoenixai FE proxy.
  phoenixAIFeProxySpec:
    replicas: 1
    # define resources requests and limits for FE proxy pods.
    limits:
      cpu: 1
      memory: 2Gi
    requests:
      cpu: 1
      memory: 2Gi
    service:
      type: NodePort   # export fe proxy service
      ports:
        - name: http-port   # the name is from fe proxy service ports
          nodePort: 30180   # The range of valid ports is 30000-32767
    # set the resolver for nginx server, default kube-dns.kube-system.svc.cluster.local
    resolver: "kube-dns.kube-system.svc.cluster.local"
    # LivenessProbeFailureSeconds defines the total failure seconds of liveness Probe.
    # default value is 15 seconds
    # You can set it to 0 to disable the probe.
    livenessProbeFailureSeconds: 15
    # ReadinessProbeFailureSeconds defines the total failure seconds of readiness Probe.
    # default value is 15 seconds
    # You can set it to 0 to disable the probe.
    readinessProbeFailureSeconds: 15

---

# fe config
apiVersion: v1
kind: ConfigMap
metadata:
  name: phoenixaicluster-sample-fe-cm
  labels:
    cluster: phoenixaicluster-sample
data:
  fe.conf: |
    LOG_DIR = ${STARROCKS_HOME}/log
    DATE = "$(date +%Y%m%d-%H%M%S)"
    JAVA_OPTS="-Dlog4j2.formatMsgNoLookups=true -Xmx8192m -XX:+UseG1GC -Xlog:gc*:${LOG_DIR}/fe.gc.log.$DATE:time"
    http_port = 8030
    rpc_port = 9020
    query_port = 9030
    edit_log_port = 9010
    mysql_service_nio_enabled = true
    sys_log_level = INFO

---

# cn config
apiVersion: v1
kind: ConfigMap
metadata:
  name: phoenixaicluster-sample-cn-cm
  labels:
    cluster: phoenixaicluster-sample
data:
  cn.conf: |
    sys_log_level = INFO
    # ports for admin, web, heartbeat service
    thrift_port = 9060
    webserver_port = 8040
    heartbeat_service_port = 9050
    brpc_port = 8060