kafka需要依赖zookeeper,所以需要先部署zk
准备存储 参考文章:https://1335402049.github.io/2020/09/16/Kubernetes%E4%B8%AD%E4%BD%BF%E7%94%A8NFS%E7%9A%84StorageClass/
名称空间 kubectl create ns log-system
部署zookeeper集群
应用 service
apiVersion: v1 kind: Service metadata: name: zk-hs namespace: log-system labels: app: zk spec: ports: - port: 2888 name: server - port: 3888 name: leader-election clusterIP: None selector: app: zk --- apiVersion: v1 kind: Service metadata: name: zk-cs namespace: kafka labels: app: zk spec: ports: - port: 2181 name: client selector: app: zk
应用 statefulset
apiVersion: apps/v1 kind: StatefulSet metadata: name: zk namespace: log-system spec: selector: matchLabels: app: zk serviceName: zk-hs replicas: 3 updateStrategy: type: RollingUpdate podManagementPolicy: Parallel template: metadata: labels: app: zk spec: nodeSelector: travis.io/schedule-only: "kafka" tolerations: - key: "travis.io/schedule-only" operator: "Equal" value: "kafka" effect: "NoSchedule" - key: "travis.io/schedule-only" operator: "Equal" value: "kafka" effect: "NoExecute" tolerationSeconds: 3600 - key: "travis.io/schedule-only" operator: "Equal" value: "kafka" effect: "PreferNoSchedule" affinity: podAntiAffinity: requiredDuringSchedulingIgnoredDuringExecution: - labelSelector: matchExpressions: - key: "app" operator: In values: - zk topologyKey: "kubernetes.io/hostname" containers: - name: kubernetes-zookeeper imagePullPolicy: IfNotPresent image: tangweifeng/zookeeper:3.4.10 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: 1000 fsGroup: 1000 volumeClaimTemplates: - metadata: name: datadir annotations: volume.beta.kubernetes.io/storage-class: "managed-nfs-storage" spec: accessModes: [ "ReadWriteMany" ] resources: requests: storage: 200Mi
验证集群
# for i in 0 1 2; do kubectl exec zk-$i -n log-system zkServer.sh status; done ZooKeeper JMX enabled by default Using config: /usr/bin/../etc/zookeeper/zoo.cfg Mode: follower ZooKeeper JMX enabled by default Using config: /usr/bin/../etc/zookeeper/zoo.cfg Mode: follower ZooKeeper JMX enabled by default Using config: /usr/bin/../etc/zookeeper/zoo.cfg Mode: leader
部署kafka集群
应用 service
apiVersion: v1 kind: Service metadata: name: kafka-svc namespace: log-system labels: app: kafka spec: ports: - port: 9092 name: server clusterIP: None selector: app: kafka
应用 statefulset
apiVersion: apps/v1 kind: StatefulSet metadata: name: kafka namespace: log-system spec: selector: matchLabels: app: kafka serviceName: kafka-svc replicas: 3 template: metadata: labels: app: kafka spec: terminationGracePeriodSeconds: 300 containers: - name: k8s-kafka imagePullPolicy: Always image: tangweifeng/kafka:2.2.0 resources: requests: memory: "600Mi" cpu: 500m ports: - containerPort: 9092 name: server command: - sh - -c - "exec kafka-server-start.sh /opt/kafka/config/server.properties --override broker.id=${HOSTNAME##*-} \ --override listeners=PLAINTEXT://:9092 \ --override zookeeper.connect=zk-0.zk-hs.log-system.svc.cluster.local:2181,zk-1.zk-hs.log-system.svc.cluster.local:2181,zk-2.zk-hs.log-system.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=4 \ --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 annotations: volume.beta.kubernetes.io/storage-class: "managed-nfs-storage" spec: accessModes: [ "ReadWriteMany" ] resources: requests: storage: 300Mi
验证kafka集群
# 创建一个topic /opt/kafka/bin/kafka-topics.sh --create --zookeeper zk-0.zk-hs.log-system.svc.cluster.local:2181,zk-1.zk-hs.log-system.svc.cluster.local:2181,zk-2.zk-hs.log-system.svc.cluster.local:2181 --replication-factor 2 --partitions 3 --topic demo_topics
# 列出所有topic /opt/kafka/bin/kafka-topics.sh --list --zookeeper zk-0.zk-hs.log-system.svc.cluster.local:2181,zk-1.zk-hs.log-system.svc.cluster.local:2181,zk-2.zk-hs.log-system.svc.cluster.local:2181
# 查看demo_topics详细情况 /opt/kafka/bin/kafka-topics.sh --describe --zookeeper zk-0.zk-hs.log-system.svc.cluster.local:2181,zk-1.zk-hs.log-system.svc.cluster.local:2181,zk-2.zk-hs.log-system.svc.cluster.local:2181 --topic demo_topics