apiVersion: v1
kind: Service
metadata:
  # This service is meant to be used by clients of the database. It exposes a ClusterIP that will
  # automatically load balance connections to the different database pods.
  name: cockroachdb-public
  labels:
    app: cockroachdb
spec:
  ports:
  # The main port, served by gRPC, serves Postgres-flavor SQL, internode
  # traffic and the cli.
  - port: 26257
    targetPort: 26257
    name: grpc
  # The secondary port serves the UI as well as health and debug endpoints.
  - port: 8080
    targetPort: 8080
    name: http
  selector:
    app: cockroachdb
---
apiVersion: v1
kind: Service
metadata:
  annotations:
    # Enable automatic monitoring of all instances when Prometheus is running in the cluster.
    prometheus.io/scrape: "true"
    prometheus.io/path: "_status/vars"
    prometheus.io/port: "8080"
  # This service only exists to create DNS entries for each pet in the petset such that they can resolve
  # each other's IP addresses. It does not create a load-balanced ClusterIP and should not be used
  # directly by clients in most circumstances.
  name: cockroachdb
  labels:
    app: cockroachdb
spec:
  ports:
  - port: 26257
    targetPort: 26257
    name: grpc
  - port: 8080
    targetPort: 8080
    name: http
  clusterIP: None
  selector:
    app: cockroachdb
---
apiVersion: apps/v1alpha1
kind: PetSet
metadata:
  name: cockroachdb
spec:
  serviceName: "cockroachdb"
  replicas: 5
  template:
    metadata:
      labels:
        app: cockroachdb
      annotations:
        pod.alpha.kubernetes.io/initialized: "true"
    spec:
      containers:
      - name: cockroachdb
        # Runs the master branch. Not recommended for production, but since
        # CockroachDB is in Beta, you don't want to run it in production
        # anyway. See
        # https://hub.docker.com/r/cockroachdb/cockroach/tags/
        # if you prefer to run a beta release.
        image: cockroachdb/cockroach
        imagePullPolicy: IfNotPresent
        ports:
        - containerPort: 26257
          name: grpc
        - containerPort: 8080
          name: http
        livenessProbe:
          httpGet:
            path: /_admin/v1/health
            port: http
          initialDelaySeconds: 30
        readinessProbe:
          httpGet:
            path: /_admin/v1/health
            port: http
          initialDelaySeconds: 10
        volumeMounts:
        - name: datadir
          mountPath: /cockroach/cockroach-data
        command:
          - "/bin/bash"
          - "-ecx"
          - |
            # The use of qualified `hostname -f` is crucial:
            # Other nodes aren't able to look up the unqualified hostname.
            CRARGS=("start" "--logtostderr" "--insecure" "--host" "$(hostname -f)")
            # TODO(tschottdorf): really want to use an init container to do
            # the bootstrapping. The idea is that the container would know
            # whether it's on the first node and could check whether there's
            # already a data directory. If not, it would bootstrap the cluster.
            # We will need some version of `cockroach init` back for this to
            # work. For now, just do the same in a shell snippet.
            # Of course this isn't without danger - if node0 loses its data,
            # upon restarting it will simply bootstrap a new cluster and smack
            # it into our existing cluster.
            # There are likely ways out. For example, the init container could
            # query the kubernetes API and see whether any other nodes are
            # around, etc. Or, of course, the admin can pre-seed the lost
            # volume somehow (and in that case we should provide a better way,
            # for example a marker file).
            if [ ! "$(hostname)" == "cockroachdb-0" ] || \
               [ -e "/cockroach/cockroach-data/COCKROACHDB_VERSION" ]
            then
              CRARGS+=("--join" "cockroachdb")
            fi
            /cockroach/cockroach ${CRARGS[*]}
      # No pre-stop hook is required, a SIGTERM plus some time is all that's
      # needed for graceful shutdown of a node.
      terminationGracePeriodSeconds: 60
      volumes:
      - name: datadir
        persistentVolumeClaim:
          claimName: datadir
  volumeClaimTemplates:
  - metadata:
      name: datadir
      annotations:
        volume.alpha.kubernetes.io/storage-class: anything
    spec:
      accessModes:
        - "ReadWriteOnce"
      resources:
        requests:
          storage: 1Gi