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:
  # This service only exists to create DNS entries for each pod in the stateful
  # set 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
  annotations:
    # This is needed to make the peer-finder work properly and to help avoid
    # edge cases where instance 0 comes up after losing its data and needs to
    # decide whether it should create a new cluster or try to join an existing
    # one. If it creates a new cluster when it should have joined an existing
    # one, we'd end up with two separate clusters listening at the same service
    # endpoint, which would be very bad.
    service.alpha.kubernetes.io/tolerate-unready-endpoints: "true"
    # 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"
spec:
  ports:
  - port: 26257
    targetPort: 26257
    name: grpc
  - port: 8080
    targetPort: 8080
    name: http
  clusterIP: None
  selector:
    app: cockroachdb
---
apiVersion: apps/v1beta1
kind: StatefulSet
metadata:
  name: cockroachdb
spec:
  serviceName: "cockroachdb"
  replicas: 3
  template:
    metadata:
      labels:
        app: cockroachdb
      annotations:
        # Init containers are run only once in the lifetime of a pod, before
        # it's started up for the first time. It has to exit successfully
        # before the pod's main containers are allowed to start.
        # This particular init container does a DNS lookup for other pods in
        # the set to help determine whether or not a cluster already exists.
        # If any other pods exist, it creates a file in the cockroach-data
        # directory to pass that information along to the primary container that
        # has to decide what command-line flags to use when starting CockroachDB.
        # This only matters when a pod's persistent volume is empty - if it has
        # data from a previous execution, that data will always be used.
        pod.alpha.kubernetes.io/init-containers: '[
            {
                "name": "bootstrap",
                "image": "cockroachdb/cockroach-k8s-init:0.1",
                "args": [
                  "-on-start=/on-start.sh",
                  "-service=cockroachdb"
                ],
                "env": [
                  {
                      "name": "POD_NAMESPACE",
                      "valueFrom": {
                          "fieldRef": {
                              "apiVersion": "v1",
                              "fieldPath": "metadata.namespace"
                          }
                      }
                   }
                ],
                "volumeMounts": [
                    {
                        "name": "datadir",
                        "mountPath": "/cockroach/cockroach-data"
                    }
                ]
            }
        ]'
    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" "$(hostname -f)" "--http-host" "0.0.0.0")
            # We only want to initialize a new cluster (by omitting the join flag)
            # if we're sure that we're the first node (i.e. index 0) and that
            # there aren't any other nodes running as part of the cluster that
            # this is supposed to be a part of (which indicates that a cluster
            # already exists and we should make sure not to create a new one).
            # It's fine to run without --join on a restart if there aren't any
            # other nodes.
            if [ ! "$(hostname)" == "cockroachdb-0" ] || \
               [ -e "/cockroach/cockroach-data/cluster_exists_marker" ]
            then
              # We don't join cockroachdb in order to avoid a node attempting
              # to join itself, which currently doesn't work
              # (https://github.com/cockroachdb/cockroach/issues/9625).
              CRARGS+=("--join" "cockroachdb-public")
            fi
            exec /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