基于k8s搭建kafka集群

1、下载kafka官方包

wget https://www.apache.org/dyn/closer.cgi?path=/kafka/3.5.0/kafka_2.13-3.5.0.tgz

2、制作kafka镜像

cat > Dockerfile << 'EOF'
FROM java:8-jdk-alpine
WORKDIR /app
ADD kafka_2.13-3.5.0.tgz .
RUN echo "https://mirrors.aliyun.com/alpine/v3.11/main/" > /etc/apk/repositories \
&& echo "https://mirrors.aliyun.com/alpine/v3.11/community/" >> /etc/apk/repositories \
&& apk update \
&& apk add tzdata bash \
&& ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime \
&& ln -sf kafka_2.13-3.5.0 kafka
EXPOSE 9092
EOF

docker build -t kafka:3.5.0 .

3、创建Kafka集群

apiVersion: v1
kind: Service
metadata:
  name: kafka
  labels:
    app: kafka
spec:
  clusterIP: None
  selector:
    app: kafka
  ports:
  - port: 9092
    name: server
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: kafka
spec:
  serviceName: kafka
  replicas: 3
  selector:
    matchLabels:
      app: kafka
  template:
    metadata:
      labels:
        app: kafka
    spec:
      containers:
      - name: kafka
        image: registry.cn-hangzhou.aliyuncs.com/dingliming/kafka:3.5.0
        imagePullPolicy: IfNotPresent
        ports:
        - containerPort: 9092
          name: server
        command:
        - sh
        - -c
        - "exec /app/kafka/bin/kafka-server-start.sh /app/kafka/config/server.properties --override broker.id=${HOSTNAME##*-} \
          --override listeners=PLAINTEXT://:9092 \
          --override zookeeper.connect=zookeeper-0.zookeeper.default.svc.cluster.local:2181,zookeeper-1.zookeeper.default.svc.cluster.local:2181,zookeeper-2.zookeeper.default.svc.cluster.local:2181 \
          --override log.dirs=/var/lib/kafka/data \
          --override auto.create.topics.enable=true \
          --override auto.leader.rebalance.enable=true \
          --override background.threads=10 \
          --override compression.type=producer \
          --override delete.topic.enable=true \
          --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 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 : "-Xms256M -Xmx512M"
        - name: KAFKA_OPTS
          value: "-Dlogging.level=INFO"
        volumeMounts:
        - name: data
          mountPath: /var/lib/kafka/data
  volumeClaimTemplates:
  - metadata:
      name: data
    spec:
      storageClassName: "nfs-client"
      accessModes: [ "ReadWriteOnce" ]
      resources:
        requests:
          storage: 3Gi

4、验证并测试

注：查看日志如下，表示kafka服务已启动。

[root@k8s-master1 kafka]# kubectl logs -f kafka-0
[2023-10-18 17:17:31,420] INFO [ZooKeeperClient Kafka server] Connected. (kafka.zookeeper.ZooKeeperClient)
[2023-10-18 17:17:31,731] INFO Cluster ID = GFC9eRi5TeG8vZiNgW3Jog (kafka.server.KafkaServer)
[2023-10-18 17:17:31,739] WARN No meta.properties file under dir /var/lib/kafka/data/meta.properties (kafka.server.BrokerMetadataCheckpoint)
[2023-10-18 17:17:31,806] INFO KafkaConfig values: 
        advertised.listeners = null
        alter.config.policy.class.name = null
        alter.log.dirs.replication.quota.window.num = 11
        alter.log.dirs.replication.quota.window.size.seconds = 1
        authorizer.class.name = 
        auto.create.topics.enable = true
        auto.include.jmx.reporter = true
        auto.leader.rebalance.enable = true
        background.threads = 10
        broker.heartbeat.interval.ms = 2000
        broker.id = 0
        broker.id.generation.enable = true
        broker.rack = null
        broker.session.timeout.ms = 9000
        client.quota.callback.class = null
        compression.type = producer
        connection.failed.authentication.delay.ms = 100
        connections.max.idle.ms = 600000
        connections.max.reauth.ms = 0
        control.plane.listener.name = null
        controlled.shutdown.enable = true
        controlled.shutdown.max.retries = 3
        controlled.shutdown.retry.backoff.ms = 5000
        controller.listener.names = null
        controller.quorum.append.linger.ms = 25
        controller.quorum.election.backoff.max.ms = 1000
        controller.quorum.election.timeout.ms = 1000
        controller.quorum.fetch.timeout.ms = 2000
        controller.quorum.request.timeout.ms = 2000
        controller.quorum.retry.backoff.ms = 20
        controller.quorum.voters = []
        controller.quota.window.num = 11
        controller.quota.window.size.seconds = 1
        controller.socket.timeout.ms = 30000
        create.topic.policy.class.name = null
        default.replication.factor = 1
        delegation.token.expiry.check.interval.ms = 3600000
        delegation.token.expiry.time.ms = 86400000
        delegation.token.master.key = null
        delegation.token.max.lifetime.ms = 604800000
        delegation.token.secret.key = null
        delete.records.purgatory.purge.interval.requests = 1
        delete.topic.enable = true
        early.start.listeners = null
        fetch.max.bytes = 57671680
        fetch.purgatory.purge.interval.requests = 1000
        group.consumer.assignors = []
        group.consumer.heartbeat.interval.ms = 5000
        group.consumer.max.heartbeat.interval.ms = 15000
        group.consumer.max.session.timeout.ms = 60000
        group.consumer.max.size = 2147483647
        group.consumer.min.heartbeat.interval.ms = 5000
        group.consumer.min.session.timeout.ms = 45000
        group.consumer.session.timeout.ms = 45000
        group.coordinator.new.enable = false
        group.coordinator.threads = 1
        group.initial.rebalance.delay.ms = 0
        group.max.session.timeout.ms = 300000
        group.max.size = 2147483647
        group.min.session.timeout.ms = 6000
        initial.broker.registration.timeout.ms = 60000
        inter.broker.listener.name = null
        inter.broker.protocol.version = 3.5-IV2
        kafka.metrics.polling.interval.secs = 10
        kafka.metrics.reporters = []
        leader.imbalance.check.interval.seconds = 300
        leader.imbalance.per.broker.percentage = 10
        listener.security.protocol.map = PLAINTEXT:PLAINTEXT,SSL:SSL,SASL_PLAINTEXT:SASL_PLAINTEXT,SASL_SSL:SASL_SSL
        listeners = PLAINTEXT://:9092
        log.cleaner.backoff.ms = 15000
        log.cleaner.dedupe.buffer.size = 134217728
        log.cleaner.delete.retention.ms = 86400000
        log.cleaner.enable = true
        log.cleaner.io.buffer.load.factor = 0.9
        log.cleaner.io.buffer.size = 524288
        log.cleaner.io.max.bytes.per.second = 1.7976931348623157E308
        log.cleaner.max.compaction.lag.ms = 9223372036854775807
        log.cleaner.min.cleanable.ratio = 0.5
        log.cleaner.min.compaction.lag.ms = 0
        log.cleaner.threads = 1
        log.cleanup.policy = [delete]
        log.dir = /tmp/kafka-logs
        log.dirs = /var/lib/kafka/data
        log.flush.interval.messages = 9223372036854775807
        log.flush.interval.ms = null
        log.flush.offset.checkpoint.interval.ms = 60000
        log.flush.scheduler.interval.ms = 9223372036854775807
        log.flush.start.offset.checkpoint.interval.ms = 60000
        log.index.interval.bytes = 4096
        log.index.size.max.bytes = 10485760
        log.message.downconversion.enable = true
        log.message.format.version = 3.0-IV1
        log.message.timestamp.difference.max.ms = 9223372036854775807
        log.message.timestamp.type = CreateTime
        log.preallocate = false
        log.retention.bytes = -1
        log.retention.check.interval.ms = 300000
        log.retention.hours = 168
        log.retention.minutes = null
        log.retention.ms = null
        log.roll.hours = 168
        log.roll.jitter.hours = 0
        log.roll.jitter.ms = null
        log.roll.ms = null
        log.segment.bytes = 1073741824
        log.segment.delete.delay.ms = 60000
        max.connection.creation.rate = 2147483647
        max.connections = 2147483647
        max.connections.per.ip = 2147483647
        max.connections.per.ip.overrides = 
        max.incremental.fetch.session.cache.slots = 1000
        message.max.bytes = 1000012
        metadata.log.dir = null
        metadata.log.max.record.bytes.between.snapshots = 20971520
        metadata.log.max.snapshot.interval.ms = 3600000
        metadata.log.segment.bytes = 1073741824
        metadata.log.segment.min.bytes = 8388608
        metadata.log.segment.ms = 604800000
        metadata.max.idle.interval.ms = 500
        metadata.max.retention.bytes = 104857600
        metadata.max.retention.ms = 604800000
        metric.reporters = []
        metrics.num.samples = 2
        metrics.recording.level = INFO
        metrics.sample.window.ms = 30000
        min.insync.replicas = 1
        node.id = 0
        num.io.threads = 8
        num.network.threads = 3
        num.partitions = 1
        num.recovery.threads.per.data.dir = 1
        num.replica.alter.log.dirs.threads = null
        num.replica.fetchers = 1
        offset.metadata.max.bytes = 4096
        offsets.commit.required.acks = -1
        offsets.commit.timeout.ms = 5000
        offsets.load.buffer.size = 5242880
        offsets.retention.check.interval.ms = 600000
        offsets.retention.minutes = 1440
        offsets.topic.compression.codec = 0
        offsets.topic.num.partitions = 50
        offsets.topic.replication.factor = 3
        offsets.topic.segment.bytes = 104857600
        password.encoder.cipher.algorithm = AES/CBC/PKCS5Padding
        password.encoder.iterations = 4096
        password.encoder.key.length = 128
        password.encoder.keyfactory.algorithm = null
        password.encoder.old.secret = null
        password.encoder.secret = null
        principal.builder.class = class org.apache.kafka.common.security.authenticator.DefaultKafkaPrincipalBuilder
        process.roles = []
        producer.id.expiration.check.interval.ms = 600000
        producer.id.expiration.ms = 86400000
        producer.purgatory.purge.interval.requests = 1000
        queued.max.request.bytes = -1
        queued.max.requests = 500
        quota.window.num = 11
        quota.window.size.seconds = 1
        remote.log.index.file.cache.total.size.bytes = 1073741824
        remote.log.manager.task.interval.ms = 30000
        remote.log.manager.task.retry.backoff.max.ms = 30000
        remote.log.manager.task.retry.backoff.ms = 500
        remote.log.manager.task.retry.jitter = 0.2
        remote.log.manager.thread.pool.size = 10
        remote.log.metadata.manager.class.name = null
        remote.log.metadata.manager.class.path = null
        remote.log.metadata.manager.impl.prefix = null
        remote.log.metadata.manager.listener.name = null
        remote.log.reader.max.pending.tasks = 100
        remote.log.reader.threads = 10
        remote.log.storage.manager.class.name = null
        remote.log.storage.manager.class.path = null
        remote.log.storage.manager.impl.prefix = null
        remote.log.storage.system.enable = false
        replica.fetch.backoff.ms = 1000
        replica.fetch.max.bytes = 1048576
        replica.fetch.min.bytes = 1
        replica.fetch.response.max.bytes = 10485760
        replica.fetch.wait.max.ms = 500
        replica.high.watermark.checkpoint.interval.ms = 5000
        replica.lag.time.max.ms = 10000
        replica.selector.class = null
        replica.socket.receive.buffer.bytes = 65536
        replica.socket.timeout.ms = 30000
        replication.quota.window.num = 11
        replication.quota.window.size.seconds = 1
        request.timeout.ms = 30000
        reserved.broker.max.id = 1000
        sasl.client.callback.handler.class = null
        sasl.enabled.mechanisms = [GSSAPI]
        sasl.jaas.config = null
        sasl.kerberos.kinit.cmd = /usr/bin/kinit
        sasl.kerberos.min.time.before.relogin = 60000
        sasl.kerberos.principal.to.local.rules = [DEFAULT]
        sasl.kerberos.service.name = null
        sasl.kerberos.ticket.renew.jitter = 0.05
        sasl.kerberos.ticket.renew.window.factor = 0.8
        sasl.login.callback.handler.class = null
        sasl.login.class = null
        sasl.login.connect.timeout.ms = null
        sasl.login.read.timeout.ms = null
        sasl.login.refresh.buffer.seconds = 300
        sasl.login.refresh.min.period.seconds = 60
        sasl.login.refresh.window.factor = 0.8
        sasl.login.refresh.window.jitter = 0.05
        sasl.login.retry.backoff.max.ms = 10000
        sasl.login.retry.backoff.ms = 100
        sasl.mechanism.controller.protocol = GSSAPI
        sasl.mechanism.inter.broker.protocol = GSSAPI
        sasl.oauthbearer.clock.skew.seconds = 30
        sasl.oauthbearer.expected.audience = null
        sasl.oauthbearer.expected.issuer = null
        sasl.oauthbearer.jwks.endpoint.refresh.ms = 3600000
        sasl.oauthbearer.jwks.endpoint.retry.backoff.max.ms = 10000
        sasl.oauthbearer.jwks.endpoint.retry.backoff.ms = 100
        sasl.oauthbearer.jwks.endpoint.url = null
        sasl.oauthbearer.scope.claim.name = scope
        sasl.oauthbearer.sub.claim.name = sub
        sasl.oauthbearer.token.endpoint.url = null
        sasl.server.callback.handler.class = null
        sasl.server.max.receive.size = 524288
        security.inter.broker.protocol = PLAINTEXT
        security.providers = null
        server.max.startup.time.ms = 9223372036854775807
        socket.connection.setup.timeout.max.ms = 30000
        socket.connection.setup.timeout.ms = 10000
        socket.listen.backlog.size = 50
        socket.receive.buffer.bytes = 102400
        socket.request.max.bytes = 104857600
        socket.send.buffer.bytes = 102400
        ssl.cipher.suites = []
        ssl.client.auth = none
        ssl.enabled.protocols = [TLSv1.2]
        ssl.endpoint.identification.algorithm = https
        ssl.engine.factory.class = null
        ssl.key.password = null
        ssl.keymanager.algorithm = SunX509
        ssl.keystore.certificate.chain = null
        ssl.keystore.key = null
        ssl.keystore.location = null
        ssl.keystore.password = null
        ssl.keystore.type = JKS
        ssl.principal.mapping.rules = DEFAULT
        ssl.protocol = TLSv1.2
        ssl.provider = null
        ssl.secure.random.implementation = null
        ssl.trustmanager.algorithm = PKIX
        ssl.truststore.certificates = null
        ssl.truststore.location = null
        ssl.truststore.password = null
        ssl.truststore.type = JKS
        transaction.abort.timed.out.transaction.cleanup.interval.ms = 10000
        transaction.max.timeout.ms = 900000
        transaction.remove.expired.transaction.cleanup.interval.ms = 3600000
        transaction.state.log.load.buffer.size = 5242880
        transaction.state.log.min.isr = 1
        transaction.state.log.num.partitions = 50
        transaction.state.log.replication.factor = 1
        transaction.state.log.segment.bytes = 104857600
        transactional.id.expiration.ms = 604800000
        unclean.leader.election.enable = true
        unstable.api.versions.enable = false
        zookeeper.clientCnxnSocket = null
        zookeeper.connect = zookeeper-0.zookeeper.default.svc.cluster.local:2181,zookeeper-1.zookeeper.default.svc.cluster.local:2181,zookeeper-2.zookeeper.default.svc.cluster.local:2181
        zookeeper.connection.timeout.ms = 18000
        zookeeper.max.in.flight.requests = 10
        zookeeper.metadata.migration.enable = false
        zookeeper.session.timeout.ms = 6000
        zookeeper.set.acl = false
        zookeeper.ssl.cipher.suites = null
        zookeeper.ssl.client.enable = false
        zookeeper.ssl.crl.enable = false
        zookeeper.ssl.enabled.protocols = null
        zookeeper.ssl.endpoint.identification.algorithm = HTTPS
        zookeeper.ssl.keystore.location = null
        zookeeper.ssl.keystore.password = null
        zookeeper.ssl.keystore.type = null
        zookeeper.ssl.ocsp.enable = false
        zookeeper.ssl.protocol = TLSv1.2
        zookeeper.ssl.truststore.location = null
        zookeeper.ssl.truststore.password = null
        zookeeper.ssl.truststore.type = null
 (kafka.server.KafkaConfig)