- 在k8s上通过yaml创建服务
- 1.先基于k8s部署zookeeper
- zk-cluster.yml part-1
apiVersion: v1
kind: Service
metadata:
namespace: real-time
name: zk-hs
labels:
app: zk
spec:
ports:
– port: 2888
name: server
– port: 3888
name: leader-election
clusterIP: None
selector:
app: zk
—
apiVersion: v1
kind: Service
metadata:
namespace: real-time
name: zk-cs
labels:
app: zk
spec:
#type: NodePort
ports:
– port: 2181
targetPort: 2181
name: client
#nodePort: 32181
selector:
app: zk
—
apiVersion: policy/v1beta1
kind: PodDisruptionBudget
metadata:
namespace: real-time
name: zk-pdb
spec:
selector:
matchLabels:
app: zk
maxUnavailable: 1
—
apiVersion: apps/v1
kind: StatefulSet
metadata:
namespace: real-time
name: zk
spec:
serviceName: zk-hs
replicas: 3
selector:
matchLabels:
app: zk
template:
metadata:
labels:
app: zk
spec:
containers:
– name: kubernetes-zookeeper
imagePullPolicy: Always
image: registry.cn-hangzhou.aliyuncs.com/k8s-image01/kubernetes-zookeeper:1.0-3.4.10
resources:
requests:
memory: “1024Mi”
cpu: “500m”
ports:
– containerPort: 2181
name: client
– containerPort: 2888
name: server
– containerPort: 3888
name: leader-election - zk-cluster.yml part-2
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
volumeClaimTemplates:
– metadata:
name: datadir
#annotations:
# volume.beta.kubernetes.io/storage-class: “zk-nfs-storage”
spec:
storageClassName: “bigdata-nfs-storage”
accessModes:
– ReadWriteMany
resources:
requests:
storage: 10Gi
- zk-cluster.yml part-1
- 2.再部署kafka服务
- kafka-cluster.yml part-1
apiVersion: v1
kind: Service
metadata:
namespace: real-time
name: kafka-cs
labels:
app: kafka
spec:
#type: NodePort
clusterIP: None
ports:
– port: 9092
targetPort: 9092
name: client
#nodePort: 32092
selector:
app: kafka
—
apiVersion: policy/v1beta1
kind: PodDisruptionBudget
metadata:
name: kafka-pdb
namespace: real-time
spec:
selector:
matchLabels:
app: kafka
minAvailable: 2
—
apiVersion: apps/v1
kind: StatefulSet
metadata:
namespace: real-time
name: kafka
spec:
serviceName: kafka-cs
replicas: 3
selector:
matchLabels:
app: kafka
template:
metadata:
labels:
app: kafka
spec:
containers:
– name: k8s-kafka
imagePullPolicy: IfNotPresent
image: cloudtrackinc/kubernetes-kafka:3.6.1
ports:
– containerPort: 9092
name: client
resources:
requests:
memory: “1024Mi”
cpu: “500m” - kafka-cluster.yml part-2
command:
– sh
– -c
– “exec /opt/kafka_2.11-0.10.0.1/bin/kafka-server-start.sh /opt/kafka_2.11-0.10.0.1/config/server.properties –override broker.id=${HOSTNAME##*-} \
–override listeners=PLAINTEXT://:9092 \
–override zookeeper.connect=zk-0.zk-hs.real-time.svc.cluster.local:2181,zk-1.zk-hs.real-time.svc.cluster.local:2181,zk-2.zk-hs.real-time.svc.cluster.local:2181 \
–override log.dirs=/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 \ - kafka-cluster.yml part-3
–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 \ - kafka-cluster.yml part-4
–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 \ - kafka-cluster.yml part-5
–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 “ - kafka-cluster.yml part-6
env:
– name: KAFKA_HEAP_OPTS
value : “-Xmx512M -Xms512M”
– name: KAFKA_OPTS
value: “-Dlogging.level=INFO”
volumeMounts:
– name: datadir
mountPath: /var/lib/kafka
lifecycle:
postStart:
exec:
command: [“/bin/sh”,”-c”,”touch /tmp/health”]
livenessProbe:
exec:
command: [“test”,”-e”,”/tmp/health”]
initialDelaySeconds: 5
timeoutSeconds: 5
periodSeconds: 10
readinessProbe:
tcpSocket:
port: client
initialDelaySeconds: 15
timeoutSeconds: 5
periodSeconds: 20
volumeClaimTemplates:
– metadata:
name: datadir
#annotations:
# volume.beta.kubernetes.io/storage-class: “kafka-nfs-storage”
spec:
storageClassName: “bigdata-nfs-storage”
accessModes:
– ReadWriteMany
resources:
requests:
storage: 10Gi
- kafka-cluster.yml part-1
- kafka操作指令：
- (1)–创建zyytest topic消息队列
- ./kafka-topics.sh –create –topic zyytest –zookeeper zk-cs:2181 –partitions 3 –replication-factor 3
- (2) 查看topic列表
- ./kafka-topics.sh –list –zookeeper zk-cs:2181
- (3) 查看名称为test的topic的描述信息
- ./kafka-topics.sh –describe –zookeeper zk-cs:2181 –topic zyytest
- (4) 在名称为test的topic上生产消息
- ./kafka-console-producer.sh –topic zyytest –broker-list localhost:9092
- (5)另起一个窗口，再登录到另外的一个kafka的pod实例，比如kafka-1，验证kafka数据消费
- cd /opt/kafka_2.11-0.10.0.1/bin/
- ./kafka-console-consumer.sh –topic zyytest –zookeeper zk-cs:2181 –from-beginning
- 存在数据时序性问题：
- 生产端：
- 消费端：
- 生产端：
- (1)–创建zyytest topic消息队列
作者 admin
张宴银，大数据开发工程师