k8s 的etcd备份、CoreDNS和dashboard安装，集群升级，yaml详解

前言：本文k8s环境搭建是采用kubeasz 3.2.0方式二进制部署的，这个种部署方式是经过CNCF(云原生基金会)认证的，可以用在生产上，本演示环境已装好k8s和calico
安装包链接：https://github.com/easzlab/kubeasz/releases

一、在kubernetes内部署coredns和官方dashboard

1.安装CoreDNS

将下载好的kubernetes-server-linux-amd64.tar.gz传到/usr/local/src下

[root@k8s-master1 yaml]# cd /usr/local/src/

##解压server包
[root@k8s-master1 src]# tar -xf kubernetes-server-linux-amd64.tar.gz 
[root@k8s-master1 ~]# cd /usr/local/src/kubernetes
[root@k8s-master1 kubernetes]# tar -xf kubernetes-src.tar.gz 

##寻找CoreDNS yaml模板文件
[root@k8s-master1 kubernetes]# cd  cluster/addons/dns/coredns/\
[root@k8s-master1 coredns]# mkdir /root/yaml
[root@k8s-master1 coredns]# mv coredns.yaml.sed /root/yaml/
[root@k8s-master1 coredns]# cd /root/yaml
[root@k8s-master1 yaml]# mv coredns.yaml.sed coredns.yaml

[root@k8s-master1 yaml]# vim  coredns.yaml 
# Warning: This is a file generated from the base underscore template file: coredns.yaml.base

apiVersion: v1
kind: ServiceAccount
metadata:
  name: coredns
  namespace: kube-system
  labels:
      kubernetes.io/cluster-service: "true"
      addonmanager.kubernetes.io/mode: Reconcile
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    kubernetes.io/bootstrapping: rbac-defaults
    addonmanager.kubernetes.io/mode: Reconcile
  name: system:coredns
rules:
- apiGroups:
  - ""
  resources:
  - endpoints
  - services
  - pods
  - namespaces
  verbs:
  - list
  - watch
- apiGroups:
  - ""
  resources:
  - nodes
  verbs:
  - get
- apiGroups:
  - discovery.k8s.io
  resources:
  - endpointslices
  verbs:
  - list
  - watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  annotations:
    rbac.authorization.kubernetes.io/autoupdate: "true"
  labels:
    kubernetes.io/bootstrapping: rbac-defaults
    addonmanager.kubernetes.io/mode: EnsureExists
  name: system:coredns
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: system:coredns
subjects:
- kind: ServiceAccount
  name: coredns
  namespace: kube-system
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: coredns
  namespace: kube-system
  labels:
      addonmanager.kubernetes.io/mode: EnsureExists
data:
  Corefile: |
    .:53 {
        errors
        health {
            lameduck 5s
        }
        ready
        kubernetes cluster.local. in-addr.arpa ip6.arpa {
            pods insecure
            fallthrough in-addr.arpa ip6.arpa
            ttl 30
        }
        prometheus :9153
        forward . 192.168.10.101 {   #直接指向外部dns地址
            max_concurrent 1000
        }
        cache 30
        loop
        reload
        loadbalance
    }
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: coredns
  namespace: kube-system
  labels:
    k8s-app: kube-dns
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
    kubernetes.io/name: "CoreDNS"
spec:
  # replicas: not specified here:
  # 1. In order to make Addon Manager do not reconcile this replicas parameter.
  # 2. Default is 1.
  # 3. Will be tuned in real time if DNS horizontal auto-scaling is turned on.
  strategy:
    type: RollingUpdate
    rollingUpdate:
      maxUnavailable: 1
  selector:
    matchLabels:
      k8s-app: kube-dns
  template:
    metadata:
      labels:
        k8s-app: kube-dns
    spec:
      securityContext:
        seccompProfile:
          type: RuntimeDefault
      priorityClassName: system-cluster-critical
      serviceAccountName: coredns
      affinity:
        podAntiAffinity:
          preferredDuringSchedulingIgnoredDuringExecution:
          - weight: 100
            podAffinityTerm:
              labelSelector:
                matchExpressions:
                  - key: k8s-app
                    operator: In
                    values: ["kube-dns"]
              topologyKey: kubernetes.io/hostname
      tolerations:
        - key: "CriticalAddonsOnly"
          operator: "Exists"
      nodeSelector:
        kubernetes.io/os: linux
      containers:
      - name: coredns
        image: registry.aliyuncs.com/google_containers/coredns:v1.8.6
        imagePullPolicy: IfNotPresent
        resources:
          limits:
            cpu: 300m
            memory: 200Mi
          requests:
            cpu: 100m
            memory: 70Mi
        args: [ "-conf", "/etc/coredns/Corefile" ]
        volumeMounts:
        - name: config-volume
          mountPath: /etc/coredns
          readOnly: true
        ports:
        - containerPort: 53
          name: dns
          protocol: UDP
        - containerPort: 53
          name: dns-tcp
          protocol: TCP
        - containerPort: 9153
          name: metrics
          protocol: TCP
        livenessProbe:
          httpGet:
            path: /health
            port: 8080
            scheme: HTTP
          initialDelaySeconds: 60
          timeoutSeconds: 5
          successThreshold: 1
          failureThreshold: 5
        readinessProbe:
          httpGet:
            path: /ready
            port: 8181
            scheme: HTTP
        securityContext:
          allowPrivilegeEscalation: false
          capabilities:
            add:
            - NET_BIND_SERVICE
            drop:
            - all
          readOnlyRootFilesystem: true
      dnsPolicy: Default
      volumes:
        - name: config-volume
          configMap:
            name: coredns
            items:
            - key: Corefile
              path: Corefile
---
apiVersion: v1
kind: Service
metadata:
  name: kube-dns
  namespace: kube-system
  annotations:
    prometheus.io/port: "9153"
    prometheus.io/scrape: "true"
  labels:
    k8s-app: kube-dns
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
    kubernetes.io/name: "CoreDNS"
spec:
  selector:
    k8s-app: kube-dns
  clusterIP: 10.100.0.2 #修改成service网络第二个地址
  ports:
  - name: dns
    port: 53
    protocol: UDP
  - name: dns-tcp
    port: 53
    protocol: TCP
  - name: metrics
    port: 9153
    protocol: TCP

#############配置注解#########
errors: 错误信息标准输出,如kubectl logs   coredns-xxxx-xxx   -n kube-system所看到日志，没error信息代表正常
health: 在CoreDNS的 http://localhost:8080/health 端口提供CoreDNS服务的健康报告
ready: 监听8181端口，当CoreDNS的插件都已经就绪时，访问该接口会返回200 OK 
kubernetes：Coredns 将基于kubernetes service name 进行dns查询并返回查询记录给客户端
prometheus: Coredns 的度量指标数据以Prometheus的key-value的格式在http://localhost:9153/metrics URI上提供
forward：转发域名查询到上游dns服务器
cache: 启用service解析缓存，单位为秒。
loop: 检测域名解析是否死循环,如corends转发给内网服务器，而内网DNS服务器又转发给Coredns,如果发现死循环，则强制中止coredns进程（kubernetes会重建）
reload：检测corefile是否更改，在重新编辑后configmap配置后，默认2分钟后会优雅的自动加载
loadbalance：轮询DNS域名解析，如果一个域名存在多个记录轮询解析。
[root@k8s-master1 yaml]# kubectl apply -f coredns.yaml

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-RhzOI53D-1652025842384)(C:\Users\Administrator\AppData\Roaming\Typora\typora-user-images\image-20220425215420803.png)]

验证CoreDNS的功能

[root@k8s-master1 ~]# kubectl get pod 
NAME     READY   STATUS    RESTARTS        AGE
centos   1/1     Running   3 (4h21m ago)   7h22m
nginx    1/1     Running   1 (10h ago)     10h
[root@k8s-master1 ~]# kubectl exec -it centos -- /bin/bash
[root@centos /]# nslookup www.baidu.com
;; Truncated, retrying in TCP mode.
Server:		10.100.0.2
Address:	10.100.0.2#53

www.baidu.com	canonical name = www.a.shifen.com.
Name:	www.a.shifen.com
Address: 163.177.151.110
Name:	www.a.shifen.com
Address: 163.177.151.109

[root@centos /]# nslookup kubernetes.default.svc.cluster.local
Server:		10.100.0.2
Address:	10.100.0.2#53

Name:	kubernetes.default.svc.cluster.local
Address: 10.100.0.1
解析外部和内部域名都没问题，功能正常

成功跑起来的CoreDNS pod 只有一个，可以给它建多一个副本

[root@k8s-master1 yaml]# kubectl get deployment -n kube-system
NAME                      READY   UP-TO-DATE   AVAILABLE   AGE
calico-kube-controllers   1/1     1            1           8d
coredns                   1/1     1            1           27m

[root@k8s-master1 yaml]# kubectl edit deployment coredns -n kube-system -o yaml

[root@k8s-master1 yaml]# kubectl get pod -n kube-system
NAME                                       READY   STATUS    RESTARTS       AGE
calico-kube-controllers-754966f84c-fg4rg   1/1     Running   0              10h
calico-node-6s22k                          1/1     Running   13 (11h ago)   8d
calico-node-fqltt                          1/1     Running   25 (11h ago)   8d
calico-node-rk6gk                          1/1     Running   11 (11h ago)   8d
calico-node-smbxl                          1/1     Running   13 (11h ago)   8d
coredns-5f6db67669-