备注：nfs存储参考链接
k8s 配置hadoop集群，nfs作为存储_疯飙的蜗牛的博客-CSDN博客
一、zk镜像拉取并制作为自己镜像
##官网镜像不能下载，使用如下镜像，并制作为自己镜像
docker pull mirrorgooglecontainers/kubernetes-zookeeper:1.0-3.4.10
docker tag mirrorgooglecontainers/kubernetes-zookeeper:1.0-3.4.10 registry.cn-beijing.aliyuncs.com/zhangxlei/kubernetes-zookeeper:1.0-3.4.10
二、编辑zookeeper.yaml文件
apiVersion: v1
kind: Service
metadata:
name: zk-hs
namespace: dev
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: dev
labels:
app: zk
spec:
ports:
- port: 2181
name: client
selector:
app: zk
---
apiVersion: policy/v1
kind: PodDisruptionBudget
metadata:
name: zk-pdb
namespace: dev
spec:
selector:
matchLabels:
app: zk
maxUnavailable: 1
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: zk
namespace: dev
spec:
selector:
matchLabels:
app: zk
serviceName: zk-hs
replicas: 3
updateStrategy:
type: RollingUpdate
podManagementPolicy: OrderedReady
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: IfNotPresent
image: "registry.cn-beijing.aliyuncs.com/zhangxlei/kubernetes-zookeeper:1.0-3.4.10"
resources:
requests:
memory: "1Gi"
cpu: "2"
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
spec:
accessModes: [ "ReadWriteOnce" ]
resources:
requests:
storage: 1G
storageClassName: "nfs-storage"
三、安装zk并检查状态
[root@master-01 zk+kafka]# kubectl apply -f zookeeper.yaml
[root@master-01 zk+kafka]# kubectl get pods -l app=zk -n dev -o wide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
zk-0 1/1 Running 0 11m 172.20.3.36 10.2.1.195 <none> <none>
zk-1 1/1 Running 0 10m 172.20.4.72 10.2.1.194 <none> <none>
zk-2 1/1 Running 0 9m23s 172.20.5.23 10.2.1.193 <none> <none>
[root@master-01 ~]# kubectl get pv,pvc -n dev -o wide |grep zk
persistentvolume/pvc-042d769b-3754-42fe-b537-b5c0546e61a4 1G RWO Delete Bound dev/datadir-zk-0 nfs-storage 150m Filesystem
persistentvolume/pvc-c8c036e7-e0a2-4858-8268-4cd67de25439 1G RWO Delete Bound dev/datadir-zk-2 nfs-storage 149m Filesystem
persistentvolume/pvc-e2225e7e-d923-4ddd-9c24-3f3940062471 1G RWO Delete Bound dev/datadir-zk-1 nfs-storage 149m Filesystem
persistentvolumeclaim/datadir-zk-0 Bound pvc-042d769b-3754-42fe-b537-b5c0546e61a4 1G RWO nfs-storage 150m Filesystem
persistentvolumeclaim/datadir-zk-1 Bound pvc-e2225e7e-d923-4ddd-9c24-3f3940062471 1G RWO nfs-storage 149m Filesystem
persistentvolumeclaim/datadir-zk-2 Bound pvc-c8c036e7-e0a2-4858-8268-4cd67de25439 1G RWO nfs-storage 149m Filesystem
#先来看下3个zookeeper的pod完整主机名是什么
[root@master-01 zk+kafka]# for i in 0 1 2;do kubectl exec zk-$i -n dev -- hostname -f;done
zk-0.zk-hs.dev.svc.cluster.local.
zk-1.zk-hs.dev.svc.cluster.local.
zk-2.zk-hs.dev.svc.cluster.local.
#查看3个zookeeper节点的角色
[root@master-01 zk+kafka]# for i in 0 1 2;do kubectl exec zk-$i -n dev -- 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: leader
ZooKeeper JMX enabled by default
Using config: /usr/bin/../etc/zookeeper/zoo.cfg
Mode: follower
#查看myid
[root@master-01 zk+kafka]# for i in 0 1 2;do echo -n "zk-$i " ;kubectl exec zk-$i -n dev -- cat /var/lib/zookeeper/data/myid;done
zk-0 1
zk-1 2
zk-2 3
#查看zookeeper leader的配置文件
[root@master-01 zk+kafka]# kubectl exec -it -n dev zk-1 -- cat /opt/zookeeper/conf/zoo.cfg
#This file was autogenerated DO NOT EDIT
clientPort=2181
dataDir=/var/lib/zookeeper/data
dataLogDir=/var/lib/zookeeper/data/log
tickTime=2000
initLimit=10
syncLimit=5
maxClientCnxns=60
minSessionTimeout=4000
maxSessionTimeout=40000
autopurge.snapRetainCount=3
autopurge.purgeInteval=12
server.1=zk-0.zk-hs.dev.svc.cluster.local.:2888:3888
server.2=zk-1.zk-hs.dev.svc.cluster.local.:2888:3888
server.3=zk-2.zk-hs.dev.svc.cluster.local.:2888:3888
四、验证zookeeper集群可用性
#进入容器
# kubectl exec -it -n dev zk-1 /bin/bash
#登录zk
$ zkCli.sh
#创建一个节点并写入数据
[zk: localhost:2181(CONNECTED) 0] create /zk-test hdfdf
#查看节点
[zk: localhost:2181(CONNECTED) 1] get /zk-test
hdfdf
cZxid = 0x100000002
ctime = Wed Jun 14 06:14:19 UTC 2023
mZxid = 0x100000002
mtime = Wed Jun 14 06:14:19 UTC 2023
pZxid = 0x100000002
cversion = 0
dataVersion = 0
aclVersion = 0
ephemeralOwner = 0x0
dataLength = 5
numChildren = 0
#登录其他zk节点，能看到我们上面创建的节点数据，说明zk集群是正常的
# kubectl exec -it -n dev zk-2 /bin/bash
[zk: localhost:2181(CONNECTED) 0] get /zk-test
hdfdf
cZxid = 0x100000002
ctime = Wed Jun 14 06:14:19 UTC 2023
mZxid = 0x100000002
mtime = Wed Jun 14 06:14:19 UTC 2023
pZxid = 0x100000002
cversion = 0
dataVersion = 0
aclVersion = 0
ephemeralOwner = 0x0
dataLength = 5
numChildren = 0
五、制作对应版本的kafka镜像
#kafka依赖jdk
docker pull ascdc/jdk8
docker tag ascdc/jdk8:latest registry.cn-beijing.aliyuncs.com/zhangxlei/jdk8:latest
#官网下载kafka安装包
wget https://downloads.apache.org/kafka/3.5.0/kafka_2.13-3.5.0.tgz
#创建Dockerfile
echo 'FROM registry.cn-beijing.aliyuncs.com/zhangxlei/jdk8:latest
COPY kafka_2.13-3.5.0.tgz /opt/kafka_2.13-3.5.0.tgz
WORKDIR /opt/
RUN tar -zxvf kafka_2.13-3.5.0.tgz && rm -rf kafka_2.13-3.5.0.tgz && mv kafka_2.13-3.5.0 kafka
EXPOSE 9092' >> Dockerfile
#构建kafka镜像
docker build --no-cache -t registry.cn-beijing.aliyuncs.com/zhangxlei/kafka_2.13-3.5.0 .
六、编辑kafka.yaml文件
---
apiVersion: v1
kind: Service
metadata:
name: kafka-hs
namespace: dev
labels:
app: kafka
spec:
ports:
- port: 9092
name: server
clusterIP: None
selector:
app: kafka
---
apiVersion: policy/v1
kind: PodDisruptionBudget
metadata:
name: kafka-pdb
namespace: dev
spec:
selector:
matchLabels:
app: kafka
minAvailable: 1
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: kafka
namespace: dev
spec:
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-beijing.aliyuncs.com/zhangxlei/kafka_2.13-3.5.0
resources:
requests:
memory: "1Gi"
cpu: 2
ports:
- containerPort: 9092
name: server
command:
- sh
- -c
- "exec /opt/kafka/bin/kafka-server-start.sh /opt/kafka/config/server.properties --override broker.id=${HOSTNAME##*-} \
--override listeners=PLAINTEXT://:9092 \
--override zookeeper.connect=zk-0.zk-hs.dev.svc.cluster.local:2181,zk-1.zk-hs.dev.svc.cluster.local:2181,zk-2.zk-hs.dev.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 : "-Xmx500M -Xms500M"
- name: KAFKA_OPTS
value: "-Dlogging.level=INFO"
volumeMounts:
- name: datadir
mountPath: /var/lib/kafka/data
securityContext:
runAsUser: 1000
fsGroup: 1000
volumeClaimTemplates:
- metadata:
name: datadir
spec:
accessModes: [ "ReadWriteOnce" ]
resources:
requests:
storage: 500M
storageClassName: "nfs-storage"
七、创建kafka并查看状态
kubectl apply -f kafka.yaml
[root@master-01 zk+kafka]# kubectl get pods -n dev -o wide |grep kafka
kafka-0 1/1 Running 0 6m48s 172.20.3.38 10.2.1.195 <none> <none>
kafka-1 1/1 Running 0 6m46s 172.20.4.74 10.2.1.194 <none> <none>
kafka-2 1/1 Running 0 6m45s 172.20.5.25 10.2.1.193 <none> <none>
[root@master-01 zk+kafka]# kubectl get pv,pvc -n dev |grep kafka
persistentvolume/pvc-b2a9dc2e-3283-4e17-97c6-e3fcda75c643 500M RWO Delete Bound dev/datadir-kafka-0 nfs-storage 20m
persistentvolume/pvc-e1769233-45da-4409-9bfd-78dc796ba509 500M RWO Delete Bound dev/datadir-kafka-2 nfs-storage 11m
persistentvolume/pvc-f5bd1100-8c79-4fc5-8250-4003cadbfcaa 500M RWO Delete Bound dev/datadir-kafka-1 nfs-storage 13m
persistentvolumeclaim/datadir-kafka-0 Bound pvc-b2a9dc2e-3283-4e17-97c6-e3fcda75c643 500M RWO nfs-storage 20m
persistentvolumeclaim/datadir-kafka-1 Bound pvc-f5bd1100-8c79-4fc5-8250-4003cadbfcaa 500M RWO nfs-storage 13m
persistentvolumeclaim/datadir-kafka-2 Bound pvc-e1769233-45da-4409-9bfd-78dc796ba509 500M RWO nfs-storage 11m
八、zk与kafka连通性查看
#查看zookeeper是否已经注册了kafka
[root@master-01 zk+kafka]# kubectl exec -it zk-0 -n dev /bin/bash
zookeeper@zk-0:/$ zkCli.sh
Connecting to localhost:2181
[zk: localhost:2181(CONNECTED) 0] ls /
[cluster, controller, brokers, zookeeper, admin, isr_change_notification, log_dir_event_notification, zk-test, controller_epoch, feature, consumers, latest_producer_id_block, config]
[zk: localhost:2181(CONNECTED) 1] ls /brokers
[ids, topics, seqid]
[zk: localhost:2181(CONNECTED) 2] ls /brokers/ids
[0, 1, 2]
[zk: localhost:2181(CONNECTED) 3]
#在kafka创建topic
[root@master-02 data]# kubectl get pods -n dev |grep kafka
kafka-0 1/1 Running 0 19m
kafka-1 1/1 Running 0 19m
kafka-2 1/1 Running 0 19m
[root@master-02 data]# kubectl exec -it kafka-0 -n dev /bin/bash
I have no name!@kafka-0:/opt$ cd /opt/kafka/bin
I have no name!@kafka-0:/opt/kafka/bin$ ./kafka-topics.sh --bootstrap-server localhost:9092 --topic first --create --partitions 1 --replication-factor 3
Created topic first.
I have no name!@kafka-0:/opt/kafka/bin$ ./kafka-topics.sh --bootstrap-server localhost:9092 --topic first --describe
Topic: first TopicId: 64nWxI4AQTmwI-fn4mbMig PartitionCount: 1 ReplicationFactor: 3 Configs: compression.type=producer,min.insync.replicas=1,cleanup.policy=delete,segment.bytes=1073741824,flush.messages=9223372036854775807,file.delete.delay.ms=60000,max.message.bytes=1000012,min.compaction.lag.ms=0,message.timestamp.type=CreateTime,preallocate=false,min.cleanable.dirty.ratio=0.5,index.interval.bytes=4096,unclean.leader.election.enable=true,retention.bytes=-1,delete.retention.ms=86400000,message.timestamp.difference.max.ms=9223372036854775807,segment.index.bytes=10485760
Topic: first Partition: 0 Leader: 2 Replicas: 2,1,0 Isr: 2,1,0
#在nfs共享存储查看后端是否有数据
# ll dev-datadir-kafka-0-pvc-b2a9dc2e-3283-4e17-97c6-e3fcda75c643/
total 16
-rw-r--r-- 1 ops root 0 Jun 14 16:59 cleaner-offset-checkpoint
drwxr-xr-x 2 ops root 167 Jun 14 17:20 first-0
-rw-r--r-- 1 ops root 4 Jun 14 17:21 log-start-offset-checkpoint
-rw-r--r-- 1 ops root 88 Jun 14 16:59 meta.properties
-rw-r--r-- 1 ops root 14 Jun 14 17:21 recovery-point-offset-checkpoint
-rw-r--r-- 1 ops root 14 Jun 14 17:21 replication-offset-checkpoint
九、错误&解决
1、error: unable to recognize "zookeeper.yaml": no matches for kind "PodDisruptionBudget" in version "policy/v1"
解决：修改为apiVersion: policy/v1beta1
apiVersion: policy/v1beta1
kind: PodDisruptionBudget
metadata:
name: zk-pdb
namespace: dev
spec:
selector:
matchLabels:
app: zk
maxUnavailable: 1
本文转载自: https://blog.csdn.net/zhangxueleishamo/article/details/131204994
版权归原作者 疯飙的蜗牛 所有， 如有侵权，请联系我们删除。
版权归原作者 疯飙的蜗牛 所有， 如有侵权，请联系我们删除。