前言
环境:
centos 7.9 k8s集群
在k8s上面安装zookeeper集群,我们还是按照k8s的官方文档来安装吧,这样比较好,网上有各种各样的安装方式,这里使用
https://kubernetes.io/docs/tutorials/stateful-application/zookeeper/
k8s的官方文档来安装。
使用k8s官方安装文档安装zookeeper集群
#下载k8s官网的zk的yaml文件,也可以自己去https://kubernetes.io/docs/tutorials/stateful-application/zookeeper/上面自己查看wget https://raw.githubusercontent.com/kubernetes/website/main/content/en/examples/application/zookeeper/zookeeper.yaml
#查看zookeeper.yamlcat zookeeper.yaml文件会发现有一个PodDisruptionBudget资源,需要限定k8s集群中zookeeper集群最小pod数,通过PDB定义最大失效数;
还有官网的镜像下载不下来,可以拉取下面的这个镜像,然后再大标签即可:
docker pull mirrorgooglecontainers/kubernetes-zookeeper:1.0-3.4.10
docker tag mirrorgooglecontainers/kubernetes-zookeeper:1.0-3.4.10 registry.k8s.io/kubernetes-zookeeper:1.0-3.4.10
docker rmi mirrorgooglecontainers/kubernetes-zookeeper:1.0-3.4.10
#编辑zookeeper.yaml文件,我们需要根据我们实际情况做一下修改vim zookeeper.yaml
apiVersion: v1
kind: Service #创建了一个无头server,名称叫zk-hs,目标端口是2888和3888
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 #还创建了一个client的service
metadata:
name: zk-cs
labels:
app: zk
spec:
ports:
- port: 2181
name: client
selector:
app: zk
---
apiVersion: policy/v1
kind: PodDisruptionBudget #定义PodDisruptionBudget资源
metadata:
name: zk-pdb
spec:
selector:
matchLabels:
app: zk
maxUnavailable: 1#最大不可用数1
---
apiVersion: apps/v1 #使用sts启动部署的zk集群
kind: StatefulSet
metadata:
name: zk
spec:
selector:
matchLabels:
app: zk
serviceName: zk-hs
replicas: 3#3个副本
updateStrategy:
type: RollingUpdate
podManagementPolicy: OrderedReady
template:
metadata:
labels:
app: zk
spec:
# affinity: #这里pod反亲和性被我注释掉了,因为我只有2个node节点# podAntiAffinity:# requiredDuringSchedulingIgnoredDuringExecution:# - labelSelector:# matchExpressions:# - key: "app"# operator: In# values:# - zk# topologyKey: "kubernetes.io/hostname"
containers:
- name: kubernetes-zookeeper
imagePullPolicy: IfNotPresent #镜像拉取策略原来是Always,改为IfNotPresent
image: "registry.k8s.io/kubernetes-zookeeper:1.0-3.4.10"#这个镜像拉取不下来,等下我们换个镜像
resources:
requests:
memory: "300M"#这里原本是1Gi的,被我改成300M
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
spec:
accessModes: ["ReadWriteOnce"]
resources:
requests:
storage: 500M #这里原来是10G的,被我改成500M
storageClassName: "nfs-storageclass"#这句是我新加的,指定使用的存储类[root@matser zookeeper-cluster]# #部署zookeeper集群
kubectl apply -f zookeeper.yaml
#查看状态,均是running
kubectl get pods -l app=zk
NAME READY STATUS RESTARTS AGE
zk-0 1/1 Running 0 6m54s
zk-1 1/1 Running 0 6m31s
zk-2 1/1 Running 0 6m19s
验证zookeeper是否正常
#先来看下3个zookeeper的pod完整主机名是什么[root@matser /]# for i in 0 1 2;do kubectl exec zk-$i -n default -- hostname -f;done
zk-0.zk-hs.default.svc.cluster.local
zk-1.zk-hs.default.svc.cluster.local
zk-2.zk-hs.default.svc.cluster.local
[root@matser /]# #我们发现,在其他pod直接ping zk-0这个pod的主机名,可以ping通[root@matser /]# kubectl exec -it deployment-busybox-567674bd67-lklvf -- ping zk-0.zk-hs.default.svc.cluster.local
PING zk-0.zk-hs.default.svc.cluster.local (10.244.166.134): 56 data bytes #64 bytes from 10.244.166.134: seq=0ttl=63time=0.071 ms
[root@matser /]# kubectl get pods -o wide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
zk-0 1/1 Running 0 36m 10.244.166.134 node1 <none><none>[root@matser /]#
#查看3个zookeeper节点的角色[root@matser /]# for i in 0 1 2;do kubectl exec zk-$i -n default -- 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: follower
ZooKeeper JMX enabled by default
Using config: /usr/bin/../etc/zookeeper/zoo.cfg
Mode: leader
[root@matser /]##查看myid[root@matser /]# for i in 0 1 2;do echo -n "zk-$i " ;kubectl exec zk-$i -n default -- cat /var/lib/zookeeper/data/myid;done
zk-0 1
zk-1 2
zk-2 3
#查看zookeeper的配置文件[root@matser /]# kubectl exec -it -n default zk-0 -- cat /opt/zookeeper/conf/zoo.cfg#This file was autogenerated DO NOT EDITclientPort=2181dataDir=/var/lib/zookeeper/data
dataLogDir=/var/lib/zookeeper/data/log
tickTime=2000initLimit=10syncLimit=5maxClientCnxns=60minSessionTimeout=4000maxSessionTimeout=40000
autopurge.snapRetainCount=3
autopurge.purgeInteval=12
server.1=zk-0.zk-hs.default.svc.cluster.local:2888:3888
server.2=zk-1.zk-hs.default.svc.cluster.local:2888:3888
server.3=zk-2.zk-hs.default.svc.cluster.local:2888:3888
[root@matser /]#
验证zookeeper集群可用性
#进入容器
kubectl exec -it -n default zk-0 -- bash
zookeeper@zk-0:/$ zkCli.sh #登录,直接回车 [zk: localhost:2181(CONNECTED)11] create /zk-test hdfdf #创建一个节点并写入数据[zk: localhost:2181(CONNECTED)11] get /zk-test #查看节点
hdfdf #这是数据
cZxid = 0x100000003
ctime = Wed Nov 09 10:55:15 UTC 2022
mZxid = 0x100000003
mtime = Wed Nov 09 10:55:15 UTC 2022
pZxid = 0x100000003
cversion =0
dataVersion =0
aclVersion =0
ephemeralOwner = 0x0
dataLength =5
numChildren =0[zk: localhost:2181(CONNE
#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 default zk-1 -- bash
zkCli.sh
[zk: localhost:2181(CONNECTED)0] get /zk-test
hdfdf
cZxid = 0x100000003
ctime = Wed Nov 09 10:55:15 UTC 2022
mZxid = 0x100000003
mtime = Wed Nov 09 10:55:15 UTC 2022
pZxid = 0x100000003
cversion =0
dataVersion =0
aclVersion =0
ephemeralOwner = 0x0
dataLength =5
numChildren =0[zk: localhost:2181(CONNECTED)1]
删掉pod,模拟pod挂掉验证集群是否正常
[root@matser /]# kubectl delete pods zk-2 zk-0
pod "zk-2" deleted
pod "zk-0" deleted
[root@matser /]# kubectl get pods -l app=zk
NAME READY STATUS RESTARTS AGE
zk-0 1/1 Running 0 25s
zk-1 1/1 Running 0 63m
zk-2 0/1 Running 0 4s
#验证集群状态(正常)[root@matser /]# for i in 0 1 2;do kubectl exec zk-$i -n default -- zkServer.sh status;done
ZooKeeper JMX enabled by default
Using config: /usr/bin/../etc/zookeeper/zoo.cfg
Mode: follower
ZooKeeper JMX enabled by default
Using config: /usr/bin/../etc/zookeeper/zoo.cfg
Mode: leader
ZooKeeper JMX enabled by default
Using config: /usr/bin/../etc/zookeeper/zoo.cfg
Mode: follower
[root@matser /]# #验证我们上面创建的节点是否还存在,数据是否还存在
kubectl exec -it -n default zk-2 -- bash#进入pod的容器
zookeeper@zk-2:/$ zkCli.sh #登录zk集群[zk: localhost:2181(CONNECTED)0]ls / #节点还在[zk-test, zookeeper][zk: localhost:2181(CONNECTED)1] get /zk-test #数据也在
hdfdf
cZxid = 0x100000003
ctime = Wed Nov 09 10:55:15 UTC 2022
mZxid = 0x100000003
mtime = Wed Nov 09 10:55:15 UTC 2022
pZxid = 0x100000003
cversion =0
dataVersion =0
aclVersion =0
ephemeralOwner = 0x0
dataLength =5
numChildren =0[zk: localhost:2181(CONNECTED)2]
本文转载自: https://blog.csdn.net/MssGuo/article/details/127773132
版权归原作者 MssGuo 所有, 如有侵权,请联系我们删除。
版权归原作者 MssGuo 所有, 如有侵权,请联系我们删除。