k8s部署Kafka集群超详细讲解

准备部署环境

Kubernetes集群信息

Kafka：3.7.1版本，apche版本
Zookeeper：3.6.3版本

准备StorageClass

# kubectl get sc 
NAME                PROVISIONER      RECLAIMPOLICY   VOLUMEBINDINGMODE   ALLOWVOLUMEEXPANSION   AGE
nfs-csi (default)   nfs.csi.k8s.io   Delete          Immediate           false                  51d

创建namespace

Kubectl create ns kafka

部署zookeeper集群

编写zookeeper集群部署zk.yaml文件

apiVersion: v1
kind: Service
metadata:
  name: zk-hs
  namespace: kafka
  labels:
    app: zk
spec:
  ports:
  - port: 2888
    name: server
  - port: 3888
    name: leader-election
  - port: 2181
    name: client
  clusterIP: None
  selector:
    app: zk
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: zk
  namespace: kafka
spec:
  selector:
    matchLabels:
      app: zk
  serviceName: zk-hs
  replicas: 3
  updateStrategy:
    type: RollingUpdate
  podManagementPolicy: Parallel
  template:
    metadata:
      labels:
        app: zk
    spec:
      containers:
      - name: zookeeper
        imagePullPolicy: Alawys
        image: registry.cn-hangzhou.aliyuncs.com/aliyun_0612/zookeeper:3.6.3
        resources:
          requests:
            memory: "200Mi"
            cpu: "0.1"
        ports:
        - containerPort: 2181
          name: client
        - containerPort: 2888
          name: server
        - containerPort: 3888
          name: leader-election
        command:
        - sh
        - -c
        - "start-zookeeper \
          --servers=3 \
          --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
      securityContext:
        runAsUser: 0
        fsGroup: 0
  volumeClaimTemplates:
  - metadata:
      name: datadir
    spec:
      accessModes: [ "ReadWriteMany" ]
      storageClassName: nfs-csi
      resources:
        requests:
          storage: 2Gi

kafka集群部署kafka.yaml文件

---
apiVersion: v1
kind: Service
metadata:
  name: kafka-svc
  namespace: kafka
  labels:
    app: kafka
spec:
  ports:
  - port: 9092
    name: server
  clusterIP: None
  selector:
    app: kafka
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: kafka
  namespace: kafka
spec:
  selector:
     matchLabels:
        app: kafka
  serviceName: kafka-svc
  replicas: 3
  template:
    metadata:
      labels:
        app: kafka
    spec:
      containers:
      - name: k8s-kafka
        imagePullPolicy: Always 
        image: registry.cn-hangzhou.aliyuncs.com/aliyun_0612/kafka:3.7.1
        resources:
          requests:
            memory: "600Mi"
            cpu: 500m
        ports:
        - containerPort: 9092
          name: server
        command:
        - sh
        - -c
        - "exec /opt/kafka/bin/kafka-server-start.sh /opt/kafka/config/server.properties --override broker.id=${HOSTNAME##*-} \
          --override listeners=PLAINTEXT://:9092 \
          --override zookeeper.connect=zk-hs.kafka.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=2.2.0 \
          --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=3 \
          --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 : "-Xmx512M -Xms512M"
        - name: KAFKA_OPTS
          value: "-Dlogging.level=INFO"
        volumeMounts:
        - name: datadir
          mountPath: /var/lib/kafka
        readinessProbe:
          tcpSocket:
            port: 9092
          timeoutSeconds: 1
          initialDelaySeconds: 5
      securityContext:
        runAsUser: 1000
        fsGroup: 1000
  volumeClaimTemplates:
  - metadata:
      name: datadir
    spec:
      accessModes: [ "ReadWriteMany" ]
      storageClassName: nfs-csi
      resources:
        requests:
          storage: 10Gi

部署集群

部署集群

[root@k8s-master ~]# kubectl apply -f zk.yaml
[root@k8s-master ~]# kubectl apply -f kafka.yaml

检查状态

出现启动失败情况，解决不了可以下方评论，专业大神会提供解决方案

验证zk集群

进入zk pod中，查看zk集群是否正常

[root@k8s-master test]# kubectl exec -it -nkafka zk-0 bash

使用

[root@k8s-master test]# zkCli.sh

查看kafka brokers

通过验证，zk集群正常

验证Kafka集群

进入kafka pod节点中

[root@k8s-master ~]# kubectl exec -it -nkafka kafka-0 bash

创建测试topic

/opt/kafka/bin/kafka-topics.sh --bootstrap-server localhost:9092 --create --topic mytopic --replication-factor 3 --partitions 3

这里要使用绝对路径

使用describe 查看topic分区数以及副本数正常

/opt/kafka/bin/kafka-topics.sh --bootstrap-server localhost:9092 --describe --topic mytopic

这里要使用绝对路径

至此，kafka集群在kubernetes上部署已经完成。
有什么问题可以下方评论。