K8s的版本是1.7.6
采用nfs的nas存储模式
NFS的问题
- 建立zk集群的时候总是发现myid绑定一个id,先describe pod确认每个绑定不同的pvc,然后就确认是pv创建的问题，pv创建不能直接挂在一个大的存储上面，因为大家最后的目录相同/var/lib/zookeeper/data目录，所以无论哪个pvc挂上去都是同样的目录,解决办法，建立不同的存储挂载目录，然后分别挂载pv
- 建立pv的时候，指明storageClassName,比如
apiVersion: v1 kind: PersistentVolume metadata: name: pv0003 spec: capacity: storage: 5Gi accessModes: - ReadWriteOnce persistentVolumeReclaimPolicy: Recycle storageClassName: nas-zk nfs: path: /k8s/weblogic server: 192.168.0.103
在使用pvc的时候，也指明storageClassName,比如
volumeClaimTemplates: - metadata: name: datadir spec: accessModes: [ "ReadWriteOnce" ] resources: requests: storage: 10Gi storageClassName: nas-zk
这样就可以控制zk的存储使用的是带这个标签的pv
- pv和pvc的accessModes一定要保持一致，否则找不到
建立zk集群脚本
https://github.com/kubernetes/contrib/blob/master/statefulsets/zookeeper/zookeeper.yaml
也可以参考
https://kubernetes.io/docs/tutorials/stateful-application/zookeeper/
但是我的机器版本是1.7.6运行起来总是有问题,居然都不是一个个建立起来，而是一次性把所有的都建立起来。
改用脚本和镜像后问题才消失。
zk集群验证
for i in 0 1 2; do kubectl exec zk-$i -- hostname; done zk-0 zk-1 zk-2 for i in 0 1 2; do echo "myid zk-$i";kubectl exec zk-$i -- cat /var/lib/zookeeper/data/myid; done myid zk-0 1 myid zk-1 2 myid zk-2 3 for i in 0 1 2; do kubectl exec zk-$i -- hostname -f; done zk-0.zk-hs.default.svc.cluster.local zk-1.zk-hs.default.svc.cluster.local zk-2.zk-hs.default.svc.cluster.local
暴露服务给集群外
kubectl label pod zk-0 zkInst=0 kubectl label pod zk-1 zkInst=1 kubectl label pod zk-2 zkInst=2 kubectl expose po zk-0 --port=2181 --target-port=2181 --name=zk-0 --selector=zkInst=0 --type=NodePort kubectl expose po zk-1 --port=2181 --target-port=2181 --name=zk-1 --selector=zkInst=1 --type=NodePort kubectl expose po zk-2 --port=2181 --target-port=2181 --name=zk-2 --selector=zkInst=2 --type=NodePort
建立kafka集群
构建脚本
https://github.com/kubernetes/contrib/blob/master/statefulsets/kafka/kafka.yaml
验证
root@kafka-0:/opt/kafka/config# kafka-topics.sh --create \ > --topic test \ > --zookeeper zoo-0.zk.default.svc.cluster.local:2181,zoo-1.zk.default.svc.cluster.local:2181,zoo-2.zk.default.svc.cluster.local:2181 \ > --partitions 3 \ > --replication-factor 2 Created topic "test".
root@kafka-0:/opt/kafka/config# kafka-console-consumer.sh --topic test --bootstrap-server localhost:9093 root@kafka-1:/# kafka-console-producer.sh --topic test --broker-list localhost:9093 I like kafka hello world #在消费者侧显示为： I like kafka hello world
参考
https://cloud.tencent.com/developer/article/1005492
zk.yaml
--- apiVersion: v1 kind: Service metadata: name: zk-svc labels: app: zk-svc spec: ports: - port: 2888 name: server - port: 3888 name: leader-election clusterIP: None selector: app: zk --- apiVersion: v1 kind: ConfigMap metadata: name: zk-cm data: jvm.heap: "1G" tick: "2000" init: "10" sync: "5" client.cnxns: "60" snap.retain: "3" purge.interval: "0" --- apiVersion: policy/v1beta1 kind: PodDisruptionBudget metadata: name: zk-pdb spec: selector: matchLabels: app: zk minAvailable: 2 --- apiVersion: apps/v1beta1 kind: StatefulSet metadata: name: zk spec: serviceName: zk-svc replicas: 3 template: metadata: labels: app: zk spec: affinity: podAntiAffinity: requiredDuringSchedulingIgnoredDuringExecution: - labelSelector: matchExpressions: - key: "app" operator: In values: - zk topologyKey: "kubernetes.io/hostname" containers: - name: k8szk imagePullPolicy: Always image: gcr.io/google_samples/k8szk:v3 resources: requests: memory: "2Gi" cpu: "500m" ports: - containerPort: 2181 name: client - containerPort: 2888 name: server - containerPort: 3888 name: leader-election env: - name : ZK_REPLICAS value: "3" - name : ZK_HEAP_SIZE valueFrom: configMapKeyRef: name: zk-cm key: jvm.heap - name : ZK_TICK_TIME valueFrom: configMapKeyRef: name: zk-cm key: tick - name : ZK_INIT_LIMIT valueFrom: configMapKeyRef: name: zk-cm key: init - name : ZK_SYNC_LIMIT valueFrom: configMapKeyRef: name: zk-cm key: tick - name : ZK_MAX_CLIENT_CNXNS valueFrom: configMapKeyRef: name: zk-cm key: client.cnxns - name: ZK_SNAP_RETAIN_COUNT valueFrom: configMapKeyRef: name: zk-cm key: snap.retain - name: ZK_PURGE_INTERVAL valueFrom: configMapKeyRef: name: zk-cm key: purge.interval - name: ZK_CLIENT_PORT value: "2181" - name: ZK_SERVER_PORT value: "2888" - name: ZK_ELECTION_PORT value: "3888" command: - sh - -c - zkGenConfig.sh && zkServer.sh start-foreground readinessProbe: exec: command: - "zkOk.sh" initialDelaySeconds: 10 timeoutSeconds: 5 livenessProbe: exec: command: - "zkOk.sh" initialDelaySeconds: 10 timeoutSeconds: 5 volumeMounts: - name: datadir mountPath: /var/lib/zookeeper securityContext: runAsUser: 1000 fsGroup: 1000 volumeClaimTemplates: - metadata: name: datadir spec: accessModes: [ "ReadWriteOnce" ] resources: requests: storage: 10Gi
kafka.yaml
--- apiVersion: v1 kind: Service metadata: name: kafka-svc labels: app: kafka spec: ports: - port: 9093 name: server clusterIP: None selector: app: kafka --- apiVersion: policy/v1beta1 kind: PodDisruptionBudget metadata: name: kafka-pdb spec: selector: matchLabels: app: kafka minAvailable: 2 --- apiVersion: apps/v1beta1 kind: StatefulSet metadata: name: kafka spec: serviceName: kafka-svc replicas: 3 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: k8skafka imagePullPolicy: Always image: gcr.io/google_samples/k8skafka:v1 resources: requests: memory: "1Gi" cpu: 500m 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=zk-0.zk-svc.default.svc.cluster.local:2181,zk-1.zk-svc.default.svc.cluster.local:2181,zk-2.zk-svc.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 : "-Xmx512M -Xms512M" - 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" securityContext: runAsUser: 1000 fsGroup: 1000 volumeClaimTemplates: - metadata: name: datadir spec: accessModes: [ "ReadWriteOnce" ] resources: requests: storage: 10Gi