k8s集群安装部署kafka、zookeeper集群
k8s集群安装部署kafka、zookeeper集群
注： 有状态、可持续换集成
redis集群有两种部署方式
StatefulSet
Service&Deployment
（每个PV的容量根据自己的机器实际情况改写，集群节点的CPU、内存、容量也根据实际情况自己改写）
一、创建NFS存储
找一个k8s节点安装（我是在master节点安装）
- 创建NFS存储
创建NFS存储主要是为了给kafka、zookeeper提供稳定的后端存储，当kafka、zookeeper的Pod发生故障重启或迁移后，依然能获得原先的数据。
这里，我们先要创建NFS，然后通过使用PV为kafka、zookeeper挂载一个远程的NFS路径。 - 安装NFS
yum -y install nfs-utils （提供文件系统）
yum -y install rpcbind （提供rpc协议）
- 创建共享文件
mkdir -p /usr/local/k8s/zookeeper/pv{1..3}
mkdir -p /usr/local/k8s/kafka/pv{1..3}
vim /etc/exports
#添加共享路径，增加权限
/usr/local/k8s/kafka/pv1 192.168.2.0/24(rw,sync,no_root_squash)
/usr/local/k8s/kafka/pv2 192.168.2.0/24(rw,sync,no_root_squash)
/usr/local/k8s/kafka/pv3 192.168.2.0/24(rw,sync,no_root_squash)
/usr/local/k8s/zookeeper/pv1 192.168.2.0/24(rw,sync,no_root_squash)
/usr/local/k8s/zookeeper/pv2 192.168.2.0/24(rw,sync,no_root_squash)
/usr/local/k8s/zookeeper/pv3 192.168.2.0/24(rw,sync,no_root_squash
- 重启服务
systemctl restart rpcbind
systemctl restart nfs
systemctl enable nfs
- 查看exportfs
exportfs -v
- 在其他的节点安装nfs-utils客户端（我是在其他的node节点安装）
yum -y install nfs-util
- 在其他及诶单查看存储共享
showmount -e 192.168.2.228
二、创建zookeeper集群
- 创建zookeeper PV
vim pv.yaml
kind: PersistentVolume
apiVersion: v1
metadata:
name: k8s-pv-zk1
annotations:
volume.beta.kubernetes.io/storage-class: "anything"
labels:
type: local
spec:
capacity:
storage: 2Gi
accessModes:
- ReadWriteOnce
nfs:
server: 192.168.2.228
path: "/usr/local/k8s/zookeeper/pv1"
---
kind: PersistentVolume
apiVersion: v1
metadata:
name: k8s-pv-zk2
annotations:
volume.beta.kubernetes.io/storage-class: "anything"
labels:
type: local
spec:
capacity:
storage: 2Gi
accessModes:
- ReadWriteOnce
nfs:
server: 192.168.2.228
path: "/usr/local/k8s/zookeeper/pv2"
---
kind: PersistentVolume
apiVersion: v1
metadata:
name: k8s-pv-zk3
annotations:
volume.beta.kubernetes.io/storage-class: "anything"
labels:
type: local
spec:
capacity:
storage: 2Gi
accessModes:
- ReadWriteOnce
nfs:
server: 192.168.2.228
path: "/usr/local/k8s/zookeeper/pv3"
创建pv
kubectl create -f pv.yaml
- 创建zookeeper集群节点
vim zookeeper.yaml
apiVersion: v1
kind: Service
metadata:
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:
name: zk-cs
labels:
app: zk
spec:
ports:
- port: 2181
name: client
selector:
app: zk
---
apiVersion: policy/v1beta1
kind: PodDisruptionBudget
metadata:
name: zk-pdb
spec:
selector:
matchLabels:
app: zk
maxUnavailable: 1
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: zk
spec:
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: IfNotPresent
image: "leolee32/kubernetes-library:kubernetes-zookeeper1.0-3.4.10"
command: [ "/bin/bash", "-ce", "tail -f /dev/null" ]
resources:
requests:
memory: "500M"
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: "anything"
spec:
accessModes: [ "ReadWriteOnce" ]
resources:
requests:
storage: 500M
创建节点
kubectl create -f zookeeper.yaml
查看集群
for i in 0 1 2; do kubectl exec zk-$i zkServer.sh status; done
三、创建kafka集群
- 创建kafka PV
vim pv.yaml
apiVersion: v1
kind: PersistentVolume
metadata:
name: k8s-pv-kafka01
namespace: tools
labels:
app: kafka
annotations:
volume.beta.kubernetes.io/storage-class: "mykafka"
spec:
capacity:
storage: 500M
accessModes:
- ReadWriteOnce
nfs:
server: 192.168.2.228
path: "/usr/local/k8s/kafka/pv1"
---
apiVersion: v1
kind: PersistentVolume
metadata:
name: k8s-pv-kafka02
namespace: tools
labels:
app: kafka
annotations:
volume.beta.kubernetes.io/storage-class: "mykafka"
spec:
capacity:
storage: 500M
accessModes:
- ReadWriteOnce
nfs:
server: 192.168.2.228
path: "/usr/local/k8s/kafka/pv2"
---
apiVersion: v1
kind: PersistentVolume
metadata:
name: k8s-pv-kafka03
namespace: tools
labels:
app: kafka
annotations:
volume.beta.kubernetes.io/storage-class: "mykafka"
spec:
capacity:
storage: 500M
accessModes:
- ReadWriteOnce
nfs:
server: 192.168.2.228
path: "/usr/local/k8s/kafka/pv3"
---
创建pv
kubectl create -f pv.yaml
- 创建namespace
kubectl create namespace tools
- 创建kafka集群节点
vim kafak.yaml
---
apiVersion: v1
kind: Service
metadata:
name: kafka-hs
namespace: tools
labels:
app: kafka
spec:
ports:
- port: 9092
name: server
clusterIP: None
selector:
app: kafka
---
apiVersion: v1
kind: Service
metadata:
name: kafka-cs
namespace: tools
labels:
app: kafka
spec:
selector:
app: kafka
type: NodePort
ports:
- name: client
port: 9092
# nodePort: 19092
---
apiVersion: policy/v1beta1
kind: PodDisruptionBudget
metadata:
name: kafka-pdb
namespace: tools
spec:
selector:
matchLabels:
app: kafka
minAvailable: 2
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: kafka
namespace: tools
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-hangzhou.aliyuncs.com/jaxzhai/k8skafka:v1
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.default.svc.cluster.local:2181,zk-1.zk-hs.default.svc.cluster.local:2181,zk-2.zk-hs.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=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:
exec:
command:
- sh
- -c
- "/opt/kafka/bin/kafka-broker-api-versions.sh --bootstrap-server=localhost:9092"
securityContext:
runAsUser: 1000
fsGroup: 1000
volumeClaimTemplates:
- metadata:
name: datadir
annotations:
volume.beta.kubernetes.io/storage-class: "mykafka"
spec:
accessModes: [ "ReadWriteOnce" ]
resources:
requests:
storage: 200M
创建kafka集群节点
kubectl create -f kafka.yaml
查看集群
#进入其中一个容器
kubectl exec -it -n tools kafka-0 /bin/bash
#创建一个topic
kafka-topics.sh --create --topic mytest --zookeeper 10.1.89.29:2181 --partitions 1 --replication-factor 1
#随便发一些消息
kafka-console-producer.sh --topic test --broker-list localhost:9092
#接收一些消息
kafka-console-consumer.sh --topic test --bootstrap-server localhost:9092
也可以根据service的ip+port连接kafka和zookeeper集群
可能中间还会出现问题，请谅解，谢谢大家支持！！！！