k8s-7:kafka+zookeeper的单节点与集群的持久化

之前在k8s环境中有这个需求，看了好多的文档，都有坑，踩了一边总结一下，需要的朋友可自取

一、单节点部署

建议开发环境使用，且此处采用动态挂载的，生产不建议

1、安装zk

cat > zk.yaml <

2.安装kafka

cat > kafka.yaml <

3.验证

 进入容器 创建生产者消费者测试

生产者：

kafka-console-producer.sh --broker-list 127.0.0.1:9092 --topic demo

 

消费者：

kafka-console-consumer.sh --bootstrap-server 127.0.0.1:9092 --topic demo --from-beginning

 

 

二、集群部署

这里是生产使用的。直接采用pv-pvc的挂载方式

1.zook的pv-pvc.yaml

kind: PersistentVolumeapiVersion: v1metadata: name: k8s-pv-zk0 annotations: volume.beta.kubernetes.io/storage-class: "wms-zook" labels: type: localspec: capacity: storage: 5Gi accessModes: - ReadWriteonce nfs: server: 192.168.XX.XX path: "/mnt/nas/zmj_pord/nfs/wms-zookeeper/pv0"---kind: PersistentVolumeapiVersion: v1metadata: name: k8s-pv-zk1 annotations: volume.beta.kubernetes.io/storage-class: "wms-zook" labels: type: localspec: capacity: storage: 5Gi accessModes: - ReadWriteonce nfs: server: 192.168.XX.XX path: "/mnt/nas/zmj_pord/nfs/wms-zookeeper/pv1"---kind: PersistentVolumeapiVersion: v1metadata: name: k8s-pv-zk2 annotations: volume.beta.kubernetes.io/storage-class: "wms-zook" labels: type: localspec: capacity: storage: 5Gi accessModes: - ReadWriteonce nfs: server: 192.168.XX.XX path: "/mnt/nas/zmj_pord/nfs/wms-zookeeper/pv2"

2.zk的all.yaml

---apiVersion: v1kind: Servicemetadata: name: zk-hs labels: app: zkspec: ports: - port: 2888 name: server - port: 3888 name: leader-election clusterIP: None selector: app: zk---apiVersion: v1kind: Servicemetadata: name: zk-cs labels: app: zkspec: type: NodePort ports: - port: 2181 name: client selector: app: zk---apiVersion: policy/v1beta1kind: PodDisruptionBudgetmetadata: name: zk-pdbspec: selector: matchLabels: app: zk maxUnavailable: 1---apiVersion: apps/v1kind: StatefulSetmetadata: name: zkspec: selector: matchLabels: app: zk serviceName: zk-hs replicas: 3 updateStrategy: type: RollingUpdate podManagementPolicy: Parallel template: metadata: labels: app: zk spec: affinity: podAntiAffinity: requiredDuringSchedulingIgnoredDuringExecution: - labelSelector: matchexpressions: - key: "app" operator: In values: - zk topologyKey: "kubernetes.io/hostname" containers: - name: kubernetes-zookeeper imagePullPolicy: Always image: "mirrorgooglecontainers/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=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: "wms-zook" spec: accessModes: [ "ReadWriteOnce" ] resources: requests: storage: 5Gi

3.kafka的pv-pvc

apiVersion: v1kind: PersistentVolumemetadata: name: k8s-pv-kafka0 namespace: tools labels: app: kafka annotations: volume.beta.kubernetes.io/storage-class: "wms-kafka"spec: capacity: storage: 5G accessModes: - ReadWriteonce nfs: server: 192.168.XX.XX path: "/mnt/nas/zmj_pord/nfs/wms-kafk/pv0"---apiVersion: v1kind: PersistentVolumemetadata: name: k8s-pv-kafka1 namespace: tools labels: app: kafka annotations: volume.beta.kubernetes.io/storage-class: "wms-kafka"spec: capacity: storage: 5G accessModes: - ReadWriteonce nfs: server: 192.168.XX.XX path: "/mnt/nas/zmj_pord/nfs/wms-kafka/pv1"---apiVersion: v1kind: PersistentVolumemetadata: name: k8s-pv-kafka2 namespace: tools labels: app: kafka annotations: volume.beta.kubernetes.io/storage-class: "wms-kafka"spec: capacity: storage: 5G accessModes: - ReadWriteonce nfs: server: 192.168.xx.XX path: "/mnt/nas/zmj_pord/nfs/wms-kafka/pv2"

4.kafka的all.yaml

（这里要把健康检查#掉）

---apiVersion: v1kind: Servicemetadata: name: kafka-hs labels: app: kafkaspec: ports: - port: 9092 name: server clusterIP: None selector: app: kafka---apiVersion: v1kind: Servicemetadata: name: kafka-cs labels: app: kafkaspec: selector: app: kafka type: NodePort ports: - name: client port: 9092 # nodePort: 19092---apiVersion: policy/v1beta1kind: PodDisruptionBudgetmetadata: name: kafka-pdbspec: selector: matchLabels: app: kafka minAvailable: 2---apiVersion: apps/v1kind: StatefulSetmetadata: name: kafkaspec: serviceName: kafka-hs replicas: 3 selector: matchLabels: app: kafka 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: - zk topologyKey: "kubernetes.io/hostname" terminationGracePeriodSeconds: 300 containers: - name: kafka # imagePullPolicy: IfNotPresent image: registry.cn-hangzhou.aliyuncs.com/jaxzhai/k8skafka:v1 #image: wurstmeister/kafka command: [ "/bin/bash", "-ce", "tail -f /dev/null" ] resources: requests: memory: "200M" 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.prod-zmj-wms.svc.cluster.local:2181,zk-1.zk-hs.prod-zmj-wms.svc.cluster.local:2181,zk-2.zk-hs.prod-zmj-wms.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=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 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 : "-Xmx300M -Xms200M" - name: KAFKA_OPTS value: "-Dlogging.level=INFO" volumeMounts: - name: datadir mountPath: /var/lib/kafka readinessProbe: tcpSocket: port: 9092 timeoutSeconds: 5 initialDelaySeconds: 20 # exec: # command: # - sh # - -c # - "/opt/kafka/bin/kafka-broker-api-versions.sh --bootstrap-server=0.0.0.0:9092" securityContext: runAsUser: 1000 fsGroup: 1000 volumeClaimTemplates: - metadata: name: datadir annotations: volume.beta.kubernetes.io/storage-class: "wms-kafka" spec: accessModes: [ "ReadWriteOnce" ] resources: requests: storage: 5G

5.测试

略，参考单节点