I made a Kubernetes Cluster which has 3 master nodes and 2 worker nodes. (All the nodes are on cloud service VM)

I'm trying to make Kafka Cluster using K8S.

First, I made zookeeper cluster, and it looks working properly(I made local Storage Class)

And now, I'm trying to run Kafka Cluster, but I always get the error

"readiness probe failed: exception in thread "main" java.lang.runtimeexception: request metadata failed on brokers list(localhost:9093"

Is there any problem with my Zookeeper.yaml or Kafka.yaml?

This is my zookeeper.yaml

zookeeper-headless.yaml

apiVersion: v1
kind: Service
metadata:
  name: zookeeper-headless
  labels:
    app: zookeeper
spec:
  ports:
  - port: 2888
    name: server
  - port: 3888
    name: leader-election
  clusterIP: None
  selector:
    app: zookeeper

zookeeper-poddisruption.yaml

apiVersion: policy/v1beta1
kind: PodDisruptionBudget
metadata:
  name: zookeeper-pdb
spec:
  selector:
    matchLabels:
      app: zookeeper
  maxUnavailable: 1

zookeeper-client.yaml

apiVersion: v1
kind: Service
metadata:
  name: zookeeper-client-service
  labels:
    app: zookeeper
spec:
  ports:
  - port: 2181
    name: client
  selector:
    app: zookeeper

zookeeper-statsfulset.yaml

apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: zookeeper
spec:
  selector:
    matchLabels:
      app: zookeeper
  serviceName: zookeeper-headless
  replicas: 2
  updateStrategy:
    type: RollingUpdate
  podManagementPolicy: Parallel
  template:
    metadata:
      labels:
        app: zookeeper
    spec:
      containers:
      - name: kubernetes-zookeeper
        imagePullPolicy: Always
        image: "k8s.gcr.io/kubernetes-zookeeper:1.0-3.4.10"
        resources:
          requests:
            memory: "1Gi"
            cpu: "0.5"
        ports:
        - containerPort: 2181
          name: client
        - containerPort: 2888
          name: server
        - containerPort: 3888
          name: leader-election
        command:
        - sh
        - -c
        - "start-zookeeper \
          --servers=2 \
          --data_dir=/var/lib/zookeeper/data \
          --data_log_dir=/var/lib/zookeeper/data/log \
          --conf_dir=/opt/zookeeper/conf \
          --client_port=2181 \
          --election_port=3888 \
          --server_port=2888 \
          --tick_time=2000 \
          --init_limit=10 \
          --sync_limit=5 \
          --heap=512M \
          --max_client_cnxns=60 \
          --snap_retain_count=3 \
          --purge_interval=12 \
          --max_session_timeout=40000 \
          --min_session_timeout=4000 \
          --log_level=INFO"
        readinessProbe:
          exec:
            command:
            - sh
            - -c
            - "zookeeper-ready 2181"
          initialDelaySeconds: 10
          timeoutSeconds: 5
        livenessProbe:
          exec:
            command:
            - sh
            - -c
            - "zookeeper-ready 2181"
          initialDelaySeconds: 10
          timeoutSeconds: 5
        volumeMounts:
        - name: datadir
          mountPath: /var/lib/zookeeper
      volumes:
      - name: datadir
        persistentVolumeClaim:
          claimName: zookeeper-pvc

kafka-headless.yaml

apiVersion: v1
kind: Service
metadata:
  name: kafka-headless
  labels:
    app: kafka
spec:
  ports:
  - port: 9093
    name: server
  clusterIP: None
  selector:
    app: kafka

kafka-pod.yaml

apiVersion: policy/v1beta1
kind: PodDisruptionBudget
metadata:
  name: kafka-pdb
spec:
  selector:
    matchLabels:
      app: kafka
  maxUnavailable: 2

kafka-statefulset.yaml

apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: kafka
spec:
  selector:
    matchLabels:
     app: kafka
  serviceName: kafka-headless
  replicas: 2
  podManagementPolicy: Parallel
  updateStrategy:
      type: RollingUpdate
  template:
    metadata:
      labels:
        app: kafka
    spec:
      #affinity:
      #  podAntiAffinity:
      #    requiredDuringSchedulingIgnoredDuringExecution:
      #      - labelSelector:
      #          matchExpressions:
      #            - key: "app"
      #              operator: In
      #              values:
      #              - kafka
      #        topologyKey: "kubernetes.io/hostname"
      #  podAffinity:
      #    preferredDuringSchedulingIgnoredDuringExecution:
      #       - weight: 1
      #         podAffinityTerm:
      #           labelSelector:
      #              matchExpressions:
      #                - key: "app"
      #                  operator: In
      #                  values:
      #                  - zookeeper
      #           topologyKey: "kubernetes.io/hostname"
      terminationGracePeriodSeconds: 300
      containers:
      - name: k8skafka
        imagePullPolicy: Always
        image: gcr.io/google_containers/kubernetes-kafka:1.0-10.2.1
        resources:
          requests:
            memory: "1Gi"
            cpu: 1
        ports:
        - containerPort: 9093
          name: server
        command:
        - sh
        - -c
        - "exec kafka-server-start.sh /opt/kafka/config/server.properties --override broker.id=${HOSTNAME##*-} \
          --override listeners=PLAINTEXT://:9093 \
          --override zookeeper.connect=zookeeper-0.zookeeper-client-service.default.svc.cluster.local:2181,zookeeper-1.zookeeper-client-service.default.svc.cluster.local:2181 \
          --override log.dir=/var/lib/kafka \
          --override auto.create.topics.enable=true \
          --override auto.leader.rebalance.enable=true \
          --override background.threads=10 \
          --override compression.type=producer \
          --override delete.topic.enable=false \
          --override leader.imbalance.check.interval.seconds=300 \
          --override leader.imbalance.per.broker.percentage=10 \
          --override log.flush.interval.messages=9223372036854775807 \
          --override log.flush.offset.checkpoint.interval.ms=60000 \
          --override log.flush.scheduler.interval.ms=9223372036854775807 \
          --override log.retention.bytes=-1 \
          --override log.retention.hours=168 \
          --override log.roll.hours=168 \
          --override log.roll.jitter.hours=0 \
          --override log.segment.bytes=1073741824 \
          --override log.segment.delete.delay.ms=60000 \
          --override message.max.bytes=1000012 \
          --override min.insync.replicas=1 \
          --override num.io.threads=8 \
          --override num.network.threads=3 \
          --override num.recovery.threads.per.data.dir=1 \
          --override num.replica.fetchers=1 \
          --override offset.metadata.max.bytes=4096 \
          --override offsets.commit.required.acks=-1 \
          --override offsets.commit.timeout.ms=5000 \
          --override offsets.load.buffer.size=5242880 \
          --override offsets.retention.check.interval.ms=600000 \
          --override offsets.retention.minutes=1440 \
          --override offsets.topic.compression.codec=0 \
          --override offsets.topic.num.partitions=50 \
          --override offsets.topic.replication.factor=3 \
          --override offsets.topic.segment.bytes=104857600 \
          --override queued.max.requests=500 \
          --override quota.consumer.default=9223372036854775807 \
          --override quota.producer.default=9223372036854775807 \
          --override replica.fetch.min.bytes=1 \
          --override replica.fetch.wait.max.ms=500 \
          --override replica.high.watermark.checkpoint.interval.ms=5000 \
          --override replica.lag.time.max.ms=10000 \
          --override replica.socket.receive.buffer.bytes=65536 \
          --override replica.socket.timeout.ms=30000 \
          --override request.timeout.ms=30000 \
          --override socket.receive.buffer.bytes=102400 \
          --override socket.request.max.bytes=104857600 \
          --override socket.send.buffer.bytes=102400 \
          --override unclean.leader.election.enable=true \
          --override zookeeper.session.timeout.ms=6000 \
          --override zookeeper.set.acl=false \
          --override broker.id.generation.enable=true \
          --override connections.max.idle.ms=600000 \
          --override controlled.shutdown.enable=true \
          --override controlled.shutdown.max.retries=3 \
          --override controlled.shutdown.retry.backoff.ms=5000 \
          --override controller.socket.timeout.ms=30000 \
          --override default.replication.factor=1 \
          --override fetch.purgatory.purge.interval.requests=1000 \
          --override group.max.session.timeout.ms=300000 \
          --override group.min.session.timeout.ms=6000 \
          --override inter.broker.protocol.version=0.10.2-IV0 \
          --override log.cleaner.backoff.ms=15000 \
          --override log.cleaner.dedupe.buffer.size=134217728 \
          --override log.cleaner.delete.retention.ms=86400000 \
          --override log.cleaner.enable=true \
          --override log.cleaner.io.buffer.load.factor=0.9 \
          --override log.cleaner.io.buffer.size=524288 \
          --override log.cleaner.io.max.bytes.per.second=1.7976931348623157E308 \
          --override log.cleaner.min.cleanable.ratio=0.5 \
          --override log.cleaner.min.compaction.lag.ms=0 \
          --override log.cleaner.threads=1 \
          --override log.cleanup.policy=delete \
          --override log.index.interval.bytes=4096 \
          --override log.index.size.max.bytes=10485760 \
          --override log.message.timestamp.difference.max.ms=9223372036854775807 \
          --override log.message.timestamp.type=CreateTime \
          --override log.preallocate=false \
          --override log.retention.check.interval.ms=300000 \
          --override max.connections.per.ip=2147483647 \
          --override num.partitions=1 \
          --override producer.purgatory.purge.interval.requests=1000 \
          --override replica.fetch.backoff.ms=1000 \
          --override replica.fetch.max.bytes=1048576 \
          --override replica.fetch.response.max.bytes=10485760 \
          --override reserved.broker.max.id=1000 "
        env:
        - name: KAFKA_HEAP_OPTS
          value : "-Xmx1G -Xms1G"
        - name: KAFKA_OPTS
          value: "-Dlogging.level=INFO"
        volumeMounts:
        - name: datadir
          mountPath: /var/lib/kafka
        readinessProbe:
          exec:
           command:
            - sh
            - -c
            - "/opt/kafka/bin/kafka-broker-api-versions.sh --bootstrap-server=localhost:9093"
      volumes:
      - name: datadir
        persistentVolumeClaim:
          claimName: kafka-pvc

I tried lots of different values in kafka-statefulset.yaml "zookeeper.connect"

• zookeeper-0.zookeeper-client-service.service.default.svc.cluster.local:2181
• or zookeeper-0.zookeeper-headless.service.default.svc.cluster.local:2181
• or zookeeper-client-service.service.default.svc.cluster.local:2181
• or zookeeper-headless.service.default.svc.cluster.local:2181

Can you please help me ?