KubeAdmin安装k8s

一、kubeadm安装

kubernetes集群大体上分为两类： 一主多从和多主多从

1、一主多从：
一台 Master节点和多台Node节点，搭建简单，有单机故障分析，适合于测试环境
2、多主多从：
多台 Master节点和多台Node节点，搭建麻烦，安全性比较高，适合于生产环境
Kubeadm 是一个K8s 部署工具，提供kubeadm init 和kubeadm join，用于快速部署Kubernetes 集群。

官方地址：

https://kubernetes.io/docs/reference/setup-tools/kubeadm/kubeadm/

要求：服务器配置至少是2G2核的。如果不是则可以在集群初始化后面增加 --ignore-preflight-errors=NumCPU

1.准备环境

1）部署软件、系统要求

软件	版本
Centos	CentOS Linux release 7.9
Docker	19.03.12
Kubernetes	V1.19.1
Flannel	V0.13.0
Kernel-lm	kernel-lt-5.4.140-1.el7.elrepo.x86_64.rpm
Kernel-lm-deve	kernel-lt-devel-4.4.245-1.el7.elrepo.x86_64.rpm

2）克隆三台机器

192.168.15.31   k8s-master-01 m1
192.168.15.32   k8s-node-01 n1
192.168.15.33   k8s-node-02 n2

3）节点规划

二、部署k8s

1、系统优化（所有节点都做）

1）关闭swap分区

#1.一旦触发 swap，会导致系统性能急剧下降，所以一般情况下，K8S 要求关闭 swap
vim /etc/fstab
用#注释掉UUID swap分区那一行

swapoff -a 
忽略kubelet的swap区
echo 'KUBELET_EXTRA_ARGS="--fail-swap-on=false"' > /etc/sysconfig/kubelet

2）关闭selinux、firewalld

sed -i 's#enforcing#disabled#g' /etc/selinux/config
setenforce 0  #临时关闭selinux
systemctl disable firewalld  #永久关闭selinux

# 如果iptables没有安装就不需要执行
# systemctl disable --now  iptables &&\

3）修改主机名并且做域名解析

#1。修改主机名
[root@k8s-master-01 ~]# hostnamectl set-hostname k8s-master-01
[root@k8s-node-01]# hostnamectl set-hostname k8s-node-01
[root@k8s-node-02]# hostnamectl set-hostname k8s-node-02



#2.修改hosts文件 (主节点)
vim /etc/hosts
192.168.15.31   k8s-master-01 m1
192.168.15.32   k8s-node-01 n1
192.168.15.33   k8s-node-02 n2

4）配置免密登录、分发公钥（主节点）

ssh-keygen -t rsa
for i in m1 n1 n2;do ssh-copy-id -i ~/.ssh/id_rsa.pub root@$i;done

5）同步集群时间

方式一：centos7
在集群中，时间是一个很重要的概念，一旦集群当中某台机器视觉按跟集群时间不一致，可能会导致集群面临很多问题。所以，在部署集群之前，需要同步集群当中的所有机器时间
yum install ntpdate -y
ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime
echo 'Asia/Shanghai' > /etc/timezone
ntpdate time2.aliyun.com
#写入定时任务
*/1 * * * * /usr/sbin/ntpdate time2.aliyun.com > /dev/null 2>&1


方式二：centos8
rpm -ivh http://mirrors.wlnmp.com/centos/wlnmp-release-centos.noarch.rpm
yum install wntp -y
ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime
echo 'Asia/Shanghai' > /etc/timezone
ntpdate time2.aliyun.com
# 写入定时任务
*/1 * * * * /usr/sbin/ntpdate time2.aliyun.com > /dev/null 2>&1

6）配置镜像源

#1.默认情况下，centos使用的是官方yum源，所以一般情况下在国内使用时非常慢的，所以我们可以替换成国内的一些比较成熟的yum源，例如：清华大学镜像源，网易云镜像源等等。
rm -rf /ect/yum.repos.d/* 
curl -o /etc/yum.repos.d/CentOS-Base.repo https://mirrors.aliyun.com/repo/Centos-7.repo
curl -o /etc/yum.repos.d/epel.repo http://mirrors.aliyun.com/repo/epel-7.repo 
yum clean all 
yum makecache 

7）更新系统

如果内核符合要求的话，排除内核升级
yum update -y --exclud=kernel*

查看
[root@k8s-master-01 ~]# cat /etc/redhat-release 
CentOS Linux release 7.9.2009 (Core)

8）安装基础常用软件

yum install wget expect vim net-tools ntp bash-completion ipvsadm ipset jq iptables conntrack sysstat libseccomp -y

9）更新系统内核（docker对系统内核要求比较高，最好用4.4+）

#这里我们是centos7采用5.4内核，#如果是centos8则不需要升级内核
官网：https://elrepo.org/

wget https://elrepo.org/linux/kernel/el7/x86_64/RPMS/kernel-lt-5.4.140-1.el7.elrepo.x86_64.rpm

wget https://elrepo.org/linux/kernel/el7/x86_64/RPMS/kernel-lt-devel-5.4.140-1.el7.elrepo.x86_64.rpm

10）安装系统内核内容

yum localinstall -y kernel-lt*

grub2-set-default  0 && grub2-mkconfig -o /etc/grub2.cfg  #调到默认启动

grubby --default-kernel  #查看当前默认启动的内核

reboot  #重启

查看
[root@k8s-master-01 ~]# uname -r
5.4.140-1.el7.elrepo.x86_64

11）安装IPVS

#IPVS是系统内核中的一个模块，其网络转发性能很高。一般情况下我们首选ipvs
yum install -y conntrack-tools ipvsadm ipset conntrack libseccomp

vim /etc/sysconfig/modules/ipvs.modules  #加载IPVS模块
#!/bin/bash
    ipvs_modules="ip_vs ip_vs_lc ip_vs_wlc ip_vs_rr ip_vs_wrr ip_vs_lblc ip_vs_lblcr ip_vs_dh ip_vs_sh ip_vs_fo ip_vs_nq ip_vs_sed ip_vs_ftp nf_conntrack"
    for kernel_module in ${ipvs_modules}; do
      /sbin/modinfo -F filename ${kernel_module} > /dev/null 2>&1
      if [ $? -eq 0 ]; then
        /sbin/modprobe ${kernel_module}
      fi
    done



#给文件修改权限
chmod 755 /etc/sysconfig/modules/ipvs.modules && bash   /etc/sysconfig/modules/ipvs.modules && lsmod | grep ip_vs

12）修改内核启动参数

#加载IPVS 模块、生效配置
#内核参数优化的主要目的是使其更合适kubernetes的正常运行
vim /etc/sysctl.d/k8s.conf
net.ipv4.ip_forward = 1
net.bridge.bridge-nf-call-iptables = 1
net.bridge.bridge-nf-call-ip6tables = 1
fs.may_detach_mounts = 1
vm.overcommit_memory=1
vm.panic_on_oom=0
fs.inotify.max_user_watches=89100
fs.file-max=52706963
fs.nr_open=52706963
net.ipv4.tcp_keepalive_time = 600
net.ipv4.tcp.keepaliv.probes = 3
net.ipv4.tcp_keepalive_intvl = 15
net.ipv4.tcp.max_tw_buckets = 36000
net.ipv4.tcp_tw_reuse = 1
net.ipv4.tcp.max_orphans = 327680
net.ipv4.tcp_orphan_retries = 3
net.ipv4.tcp_syncookies = 1
net.ipv4.tcp_max_syn_backlog = 16384
net.ipv4.ip_conntrack_max = 65536
net.ipv4.tcp_max_syn_backlog = 16384
net.ipv4.top_timestamps = 0
net.core.somaxconn = 16384


#立即生效
sysctl --system  



内核优化参数解释
#开启端口转发
net.ipv4.ip_forward = 1 
net.bridge.bridge-nf-call-iptables = 1 
# 可以之间修改这两个
net.bridge.bridge-nf-call-ip6tables = 1 
# 可以之间修改这两个
fs.may_detach_mounts = 1 
vm.overcommit_memory=1 
# 不检查物理内存是否够用
vm.swappiness=0 
# 禁止使用 swap 空间，只有当系统 OOM 时才允许使用它
vm.panic_on_oom=0 
# 开启 OOM
fs.inotify.max_user_watches=89100 
fs.file-max=52706963  开启 OOM
fs.nr_open=52706963 
net.ipv4.tcp_keepalive_time = 600 
net.ipv4.tcp.keepaliv.probes = 3 
net.ipv4.tcp_keepalive_intvl = 15 
net.ipv4.tcp.max_tw_buckets = 36000 
net.ipv4.tcp_tw_reuse = 1 
net.ipv4.tcp.max_orphans = 327680 
net.ipv4.tcp_orphan_retries = 3 
net.ipv4.tcp_syncookies = 1 
net.ipv4.tcp_max_syn_backlog = 16384 
net.ipv4.ip_conntrack_max = 65536 
net.ipv4.tcp_max_syn_backlog = 16384 
net.ipv4.top_timestamps = 0 
net.core.somaxconn = 16384

2.安装docker（所有节点）

docker主要是作为k8s管理得常用的容器工具之一

#1.卸载之前安装过的docker
sudo yum remove docker docker-common docker-selinux docker-engine

#2.安装docker需要的依赖包
sudo yum install -y yum-utils device-mapper-persistent-data lvm2

#3.安装docker的yum源
wget -O /etc/yum.repos.d/docker-ce.repo https://repo.huaweicloud.com/docker-ce/linux/centos/docker-ce.repo

#4.安装docker
yum install docker-ce -y

#5.设置开机自启
systemctl enable --now docker.service

# 6.docker加速优化
sudo mkdir -p /etc/docker
sudo tee /etc/docker/daemon.json <<-'EOF'
{
  "registry-mirrors": ["https://k7eoap03.mirror.aliyuncs.com"]
}
EOF


#查看是否安装成功 
docker info 


注意：
# 官方软件源默认启用了最新的软件，您可以通过编辑软件源的方式获取各个版本的软件包。例如官方并没有将测试版本的软件源置为可用，您可以通过以下方式开启。同理可以开启各种测试版本等。
 vim /etc/yum.repos.d/docker-ce.repo
 将[docker-ce-test]下方的enabled=0修改为enabled=1

安装指定版本的Docker-CE:
#Step 1: 查找Docker-CE的版本:
yum list docker-ce.x86_64 --showduplicates | sort -r

# Step2: 安装指定版本的Docker-CE: (VERSION例如上面的19.03.0.ce.1-1.el7.centos)
 sudo yum -y install docker-ce-[VERSION]

3.安装kubele(所有节点)

#1.安装kebenetes  yum源
方式一  #华为源
cat <<EOF > /etc/yum.repos.d/kubernetes.repo
[kubernetes] 
name=Kubernetes 
baseurl=https://repo.huaweicloud.com/kubernetes/yum/repos/kubernetes-el7-\$basearch 
enabled=1 
gpgcheck=1 
repo_gpgcheck=0
gpgkey=https://repo.huaweicloud.com/kubernetes/yum/doc/yum-key.gpg https://repo.huaweicloud.com/kubernetes/yum/doc/rpm-package-key.gpg 
EOF
方式二 #阿里源
[root@k8s-node-02 yum.repos.d]# cat < /etc/yum.repos.d/kubernetes.repo
[kubernetes]
name=Kubernetes
baseurl=https://mirrors.aliyun.com/kubernetes/yum/repos/kubernetes-el7-x86_64/
enabled=1
gpgcheck=1
repo_gpgcheck=1
gpgkey=https://mirrors.aliyun.com/kubernetes/yum/doc/yum-key.gpg https://mirrors.aliyun.com/kubernetes/yum/doc/rpm-package-key.gpg
EOF
setenforce 0
yum install -y kubelet kubeadm kubectl 
# 版本是kubelet-1.21.3
systemctl enable kubelet && systemctl start kubelet
方式三 #清华源
[root@k8s-master-01 yum.repos.d]# cat >> kubernetes.repo <
[kubernetes]
name=kubernetes
baseurl=https://mirrors.tuna.tsinghua.edu.cn/kubernetes/yum/repos/kubernetes-el7-\$basearch
enabled=1
gpgcheck=0
EOF

# 2、重新生成源
yum clean all 
yum makecache 
# 3、此处指定版本下载为了与下边初始化节点版本对应
yum install kubectl-1.20.2 kubeadm-1.20.2 kubelet-1.20.2 -y
# 此处下载最新版本为了与下边初始化节点版本对应
yum install kubectl-1.20.2 kubeadm-1.20.2 kubelet-1.20.2 -y 
# 4、此时只需开机自启，无需启动，因为还未初始化
systemctl enable --now kubelet.service
# 5、查看版本
[root@k8s-master-01 ~]# kubectl version 
Client Version: version.Info{Major:"1", Minor:"20", GitVersion:"v1.20.2"

4.初始化master节点（只在master节点执行）

# 1、查看镜像列表
[root@k8s-master-01 ~]# kubeadm config images list
I0818 15:34:59.667298   63989 version.go:251] remote version is much newer: v1.22.0; falling back to: stable-1.20
k8s.gcr.io/kube-apiserver:v1.20.2
k8s.gcr.io/kube-controller-manager:v1.20.2
k8s.gcr.io/kube-scheduler:v1.20.2
k8s.gcr.io/kube-proxy:v1.20.2
k8s.gcr.io/pause:3.2
k8s.gcr.io/etcd:3.4.13-0
k8s.gcr.io/coredns:1.7.0


初始化：
 kubeadm init \
 --image-repository=registry.cn-hangzhou.aliyuncs.com/k8sos \
--kubernetes-version=v1.20.2 \
--service-cidr=10.96.0.0/12 \
--pod-network-cidr=10.244.0.0/16

注：初始化节点需注意版本问题，yum不指定版本下载默认下载最新版本，所以初始化需指定对应版本
    所有节点版本都需对应，node节点与master节点版本不对应会导致node节点加入集群失败
注：避免导致上述问题可以指定版本下载
yum install kubectl-1.20.2 kubeadm-1.20.2 kubelet-1.20.2 -y




ps ： 可以先使用手动先下载镜像： kubeadm config images pull --image-repository=registry.cn-hangzhou.aliyuncs.com/google_containers

#参数详解：
–apiserver-advertise-address        #集群通告地址
–image-repository                   #由于默认拉取镜像地址k8s.gcr.io国内无法访问，这里指定阿里云镜像仓库地址
–kubernetes-version                 #K8s版本，与安装的一致
–service-cidr                       #集群内部虚拟网络，Pod统一访问入口
–pod-network-cidr                   #Pod网络，，与下面部署的CNI网络组件yaml中保持一致

# 过程中可监控初始化日志，出现successfully即为成功！
tail -f /var/log/messages
[root@k8s-master1 ~] cat /var/log/messages | grep successfully
# Mar 24 21:02:07 k8s-master1 containerd: time="2021-03-24T21:02:07.063840628+08:00" level=info msg="containerd successfully booted in 0.181480s"

5.初始化后续（只在master节点执行）=====针对于用户集群权限，集群网络插件

1）建立用户集群权限

mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/config
 #如果是root用户，则可以使用：export KUBECONFIG=/etc/kubernetes/admin.conf

2） 增加命令提示（选做）

所有节点执行
yum install -y bash-completion
source /usr/share/bash-completion/bash_completion
source <(kubectl completion bash)
echo "source <(kubectl completion bash)" >> ~/.bashrc

3）安装集群网络插件（flannel.yaml）

kubernetes 需要使用第三方的网络插件来实现 kubernetes 的网络功能，这样一来，安装网络插件成为必要前提
第三方网络插件有多种，常用的有 flanneld、calico 和 cannel（flanneld+calico），不同的网络组件，都提供基本的网络功能，为各个 Node 节点提供 IP 网络等

插件文件下载（方式一）：
[root@m01 ~]#wget https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml
[root@m01 ~]#  kubectl apply -f kube-flannel.yml              #指定文件进行部署集群网络

cat >> /root/flannel.yaml <<EOF
---
apiVersion: policy/v1beta1
kind: PodSecurityPolicy
metadata:
  name: psp.flannel.unprivileged
  annotations:
    seccomp.security.alpha.kubernetes.io/allowedProfileNames: docker/default
    seccomp.security.alpha.kubernetes.io/defaultProfileName: docker/default
    apparmor.security.beta.kubernetes.io/allowedProfileNames: runtime/default
    apparmor.security.beta.kubernetes.io/defaultProfileName: runtime/default
spec:
  privileged: false
  volumes:
  - configMap
  - secret
  - emptyDir
  - hostPath
  allowedHostPaths:
  - pathPrefix: "/etc/cni/net.d"
  - pathPrefix: "/etc/kube-flannel"
  - pathPrefix: "/run/flannel"
  readOnlyRootFilesystem: false
  # Users and groups
  runAsUser:
    rule: RunAsAny
  supplementalGroups:
    rule: RunAsAny
  fsGroup:
    rule: RunAsAny
  # Privilege Escalation
  allowPrivilegeEscalation: false
  defaultAllowPrivilegeEscalation: false
  # Capabilities
  allowedCapabilities: ['NET_ADMIN', 'NET_RAW']
  defaultAddCapabilities: []
  requiredDropCapabilities: []
  # Host namespaces
  hostPID: false
  hostIPC: false
  hostNetwork: true
  hostPorts:
  - min: 0
    max: 65535
  # SELinux
  seLinux:
    # SELinux is unused in CaaSP
    rule: 'RunAsAny'
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: flannel
rules:
- apiGroups: ['extensions']
  resources: ['podsecuritypolicies']
  verbs: ['use']
  resourceNames: ['psp.flannel.unprivileged']
- apiGroups:
  - ""
  resources:
  - pods
  verbs:
  - get
- apiGroups:
  - ""
  resources:
  - nodes
  verbs:
  - list
  - watch
- apiGroups:
  - ""
  resources:
  - nodes/status
  verbs:
  - patch
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: flannel
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: flannel
subjects:
- kind: ServiceAccount
  name: flannel
  namespace: kube-system
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: flannel
  namespace: kube-system
---
kind: ConfigMap
apiVersion: v1
metadata:
  name: kube-flannel-cfg
  namespace: kube-system
  labels:
    tier: node
    app: flannel
data:
  cni-conf.json: |
    {
      "name": "cbr0",
      "cniVersion": "0.3.1",
      "plugins": [
        {
          "type": "flannel",
          "delegate": {
            "hairpinMode": true,
            "isDefaultGateway": true
          }
        },
        {
          "type": "portmap",
          "capabilities": {
            "portMappings": true
          }
        }
      ]
    }
  net-conf.json: |
    {
      "Network": "10.244.0.0/16",
      "Backend": {
        "Type": "vxlan"
      }
    }
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: kube-flannel-ds
  namespace: kube-system
  labels:
    tier: node
    app: flannel
spec:
  selector:
    matchLabels:
      app: flannel
  template:
    metadata:
      labels:
        tier: node
        app: flannel
    spec:
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
            - matchExpressions:
              - key: kubernetes.io/os
                operator: In
                values:
                - linux
      hostNetwork: true
      priorityClassName: system-node-critical
      tolerations:
      - operator: Exists
        effect: NoSchedule
      serviceAccountName: flannel
      initContainers:
      - name: install-cni
        image: registry.cn-hangzhou.aliyuncs.com/alvinos/flanned:v0.13.1-rc1
        command:
        - cp
        args:
        - -f
        - /etc/kube-flannel/cni-conf.json
        - /etc/cni/net.d/10-flannel.conflist
        volumeMounts:
        - name: cni
          mountPath: /etc/cni/net.d
        - name: flannel-cfg
          mountPath: /etc/kube-flannel/
      containers:
      - name: kube-flannel
        image: registry.cn-hangzhou.aliyuncs.com/alvinos/flanned:v0.13.1-rc1
        command:
        - /opt/bin/flanneld
        args:
        - --ip-masq
        - --kube-subnet-mgr
        resources:
          requests:
            cpu: "100m"
            memory: "50Mi"
          limits:
            cpu: "100m"
            memory: "50Mi"
        securityContext:
          privileged: false
          capabilities:
            add: ["NET_ADMIN", "NET_RAW"]
        env:
        - name: POD_NAME
          valueFrom:
            fieldRef:
              fieldPath: metadata.name
        - name: POD_NAMESPACE
          valueFrom:
            fieldRef:
              fieldPath: metadata.namespace
        volumeMounts:
        - name: run
          mountPath: /run/flannel
        - name: flannel-cfg
          mountPath: /etc/kube-flannel/
      volumes:
      - name: run
        hostPath:
          path: /run/flannel
      - name: cni
        hostPath:
          path: /etc/cni/net.d
      - name: flannel-cfg
        configMap:
          name: kube-flannel-cfg
EOF

4）安装网络插件

kubectl apply -f flannel.yaml

5）将其他节点加入集群

1）主节点创建集群

node节点要查看token，主节点生成token可重复执行查看，不会改变

[root@k8s-master-01~]# kubeadm token create    --print-join-command 
kubeadm join 192.168.15.31:6443 --token s6svmh.lw88lchyl6m24tts     --discovery-token-ca-cert-hash sha256:4d7e3e37e73176a97322e26fe501d2c27830a7bf3550df56f3a55b68395b507b 

2）从节点上执行

[root@k8s-node-01~]# kubeadm join 192.168.15.31:6443 --token s6svmh.lw88lchyl6m24tts     --discovery-token-ca-cert-hash sha256:4d7e3e37e73176a97322e26fe501d2c27830a7bf3550df56f3a55b68395b507b 

[root@k8s-node-02~]# kubeadm join 192.168.15.31:6443 --token s6svmh.lw88lchyl6m24tts     --discovery-token-ca-cert-hash sha256:4d7e3e37e73176a97322e26fe501d2c27830a7bf3550df56f3a55b68395b507b 

3）查看token值命令

[root@gdx1 ~]# kubeadm token list
kubeadm join 192.168.12.11:6443 --token fm0387.iqixomz5jmsukwsi     --discovery-token-ca-cert-hash sha256:d8ff83ffed5967000034d07b3da738ae4f1f0254e8417bb30c21f3ed15ac5d18 
注：每生成一次token值都不一样，一次token值有效期24小时

#扩展：生成永久Token（node加入的时候会用到）
kubeadm token create --ttl 0 --print-join-command
`kubeadm join 192.168.233.3:6443 --token rpi151.qx3660ytx2ixq8jk     --discovery-token-ca-cert-hash sha256:5cf4e801c903257b50523af245f2af16a88e78dc00be3f2acc154491ad4f32a4`#这是生成的Token,node加入时使用，此``是起到注释作用，无其他用途。

6.检查集群状态（主节点）

#1.第一种方式
[root@k8s-master-01 opt]# kubectl get nodes  后者  kubectl get nodes -o wide
NAME            STATUS   ROLES                  AGE     VERSION
k8s-master-01   Ready    control-plane,master   3h13m   v1.20.2
k8s-node-01     Ready    <none>                 3h3m    v1.20.2
k8s-nonde-02    Ready    <none>                 3h3m    v1.20.2
注：都出现ready的状态就证明成功

#1.第二种方式
[root@k8s-master-01 opt]# kubectl get pods -n kube-system
NAME                                    READY   STATUS    RESTARTS   AGE
coredns-f68b4c98f-527gt                 1/1     Running   0          3h15m
coredns-f68b4c98f-hmm8j                 1/1     Running   0          3h15m
etcd-k8s-master-01                      1/1     Running   0          3h15m
kube-apiserver-k8s-master-01            1/1     Running   0          3h15m
kube-controller-manager-k8s-master-01   1/1     Running   0          3h15m
kube-flannel-ds-44r9l                   1/1     Running   0          3h13m
kube-flannel-ds-h755r                   1/1     Running   0          3h5m
kube-flannel-ds-ntdz5                   1/1     Running   0          3h5m
kube-proxy-8k9nt                        1/1     Running   0          3h5m
kube-proxy-jbm5l                        1/1     Running   0          3h5m
kube-proxy-xkpxj                        1/1     Running   0          3h15m
kube-scheduler-k8s-master-01            1/1     Running   0          3h15m


#第三种方式：直接验证集群DNS
[root@k8s-master-01 opt]# kubectl run test -it --rm --image=busybox:1.28.3
If you don't see a command prompt, try pressing enter.
/ # nslookup kubernetes
Server:    10.96.0.10
Address 1: 10.96.0.10 kube-dns.kube-system.svc.cluster.local

Name:      kubernetes
Address 1: 10.96.0.1 kubernetes.default.svc.cluster.local
/ # 


解决办法：
# 默认下载是最新版本，难免出现版本不一致的问题，所以下载时指定同一版本才行
# 1.从节点删除下载版本重新指定版本格式：
yum remove kubectl kubeadm kubelet -y
yum install kubectl-1.20.2 kubeadm-1.20.2 kubelet-1.20.2 -y

#2.设置开机自启
systemctl enable --now kubelet

#3.重置nonde节点配置（因为上述已经加入过集群，会报错证书，配置文件，端口号已存在，需要格式化子节点配置）
[ERROR FileAvailable--etc-kubernetes-kubelet.conf]: /etc/kubernetes/kubelet.conf already exists
[ERROR Port-10250]: Port 10250 is in use
[ERROR FileAvailable--etc-kubernetes-pki-ca.crt]: /etc/kubernetes/pki/ca.crt already exists
[root@gdx2 ~]# kubectl reset  #报错以上内容执行此命令格式化子节点

#4.从集群移除状态为notready的node节点
[root@gdx1 ~]# kubectl delete node gdx3

#5.重新将node节点加入集群，此时需注意token值是否相同，如果多次生成token值，需确认最后生成的token值
注：此处做好在master节点重新生成一次token值用来node节点加入集群使用
[root@gdx1 ~]# kubeadm token create    --print-join-command 
kubeadm join 192.168.12.11:6443 --token fm0387.iqixomz5jmsukwsi     --discovery-token-ca-cert-hash sha256:d8ff83ffed5967000034d07b3da738ae4f1f0254e8417bb30c21f3ed15ac5d18
注：将生成结果在node节点执行

#6.将node节点重新加入集群
[root@gdx2 ~]# kubeadm join 192.168.12.11:6443 --token fm0387.iqixomz5jmsukwsi     --discovery-token-ca-cert-hash sha256:d8ff83ffed5967000034d07b3da738ae4f1f0254e8417bb30c21f3ed15ac5d18

查看get pods报错：server localhost：8080 was refused

原因：家目录下的.kube被移除走了，就没有影虎管理集群权限了

7.如果测试成功，无需执行以下命令

node节点加入集群失败，状态为NotReady 解决方法

# 1、加入集群报错解决
 1> 报错原因1
[ERROR FileContent--proc-sys-net-bridge-bridge-nf-call-iptables]: /proc/sys/net/bridge/bridge-nf-call-iptables contents are not set to 1

# 解决方法： echo "1" >/proc/sys/net/bridge/bridge-nf-call-iptables

# 2、然后重新生成，再次测试，加入集群
[root@k8s-m-01 ~]#  kubeadm token create    --print-join-command 
kubeadm join 192.168.15.111:6443 --token fm0387.iqixomz5jmsukwsi     --discovery-token-ca-cert-hash sha256:d8ff83ffed5967000034d07b3da738ae4f1f0254e8417bb30c21f3ed15ac5d18
注：将生成结果在node节点执行

# 3、将node节点重新加入集群
[root@k8s-m-01 ~]#  kubeadm join 192.168.15.111:6443 --token fm0387.iqixomz5jmsukwsi     --discovery-token-ca-cert-hash sha256:d8ff83ffed5967000034d07b3da738ae4f1f0254e8417bb30c21f3ed15ac5d18

2> 报错原因1
从节点加入集群可能会出现如下报错：
[ERROR FileContent--proc-sys-net-bridge-bridge-nf-call-iptables]: /proc/sys/net/bridge/bridge-nf-call-iptables contents are not set to 1
[preflight] If you know what you are doing, you can make a check non-fatal with `--ignore-preflight-errors=...`
To see the stack trace of this error execute with --v=5 or higher

PS：前提安装Docker+启动，再次尝试加入节点！
# 1、报错原因：
swap没关，一旦触发 swap，会导致系统性能急剧下降，所以一般情况下，所以K8S 要求关闭 swap
# 2、解决方法：
1>  执行以下三条命令后再次执行添加到集群命令：
modprobe br_netfilter
echo 1 > /proc/sys/net/bridge/bridge-nf-call-iptables
echo 1 > /proc/sys/net/ipv4/ip_forward

2> 追加 --ignore-preflight-errors=Swap 参数重新执行即可！
[root@k8s-n-1 ~] kubeadm join 192.168.15.11:6443 --token iypm65.p5nmdzzw1zifxy6c --discovery-token-ca-cert-hash sha256:8bdbe324980e3350aaa3b9cea58edf576dc0a6d937da6b7bff6dbe6a01e0b525 --ignore-preflight-errors=Swap

3> 报错原因3
# 1、报错原因：
可能是内核参数忘记优化所有节点都需优化
# 2、解决方法：
回到上面第七小节，复制粘贴优化参数即可： cat > /etc/sysctl.d/k8s.conf <<EOF

4> 报错原因4
ode节点加入集群失败，状态为NotReady
情况1：软件版本不一致
[root@k8s-m-01 ~]#  kubectl get node
NAME       STATUS     ROLES                  AGE      VERSION
k8s-m-01   Ready    control-plane,master     16m      v1.21.2
k8s-n-01   NotReady   <none>                 22m      v1.20.2
k8s-n-02   NotReady   <none>                 22m      v1.20.2

# 1、原因分析：
默认下载是最新版本，难免出现版本不一致的问题，所以下载时指定同一版本才行
# 2、解决方法：
yum install kubectl-1.21.2 kubeadm-1.21.2 kubelet-1.21.2 -y	# 主从节点安装指定版本格式
kubectl reset	# 重新初始化
kubeadm join 192.168.15.111:6443 --token fm0387.iqixomz5jmsukwsi     --discovery-token-ca-cert-hash sha256:d8ff83ffed5967000034d07b3da738ae4f1f0254e8417bb30c21f3ed15ac5d18	# 重新将node节点加入集群

# PS：查看token值命令
[root@k8s-m-01 ~]# kubeadm token list
kubeadm join 192.168.15.111:6443 --token fm0387.iqixomz5jmsukwsi     --discovery-token-ca-cert-hash sha256:d8ff83ffed5967000034d07b3da738ae4f1f0254e8417bb30c21f3ed15ac5d18 
8ff83ffed5967000034d07b3da738ae4f1f0254e8417bb30c21f3ed15ac5d18

情况2：软件版本一致，touken值可能不对
[root@k8s-m-01 ~]#  kubectl get node
NAME       STATUS     ROLES                  AGE      VERSION
k8s-m-01   Ready    control-plane,master     16m      v1.21.2
k8s-n-01   NotReady   <none>                 22m      v1.20.2
k8s-n-02   NotReady   <none>                 22m      v1.20.2

# node节点为notready状态，加入从节点时报错：
[ERROR FileAvailable--etc-kubernetes-kubelet.conf]: /etc/kubernetes/kubelet.conf already exists
[ERROR Port-10250]: Port 10250 is in use
[ERROR FileAvailable--etc-kubernetes-pki-ca.crt]: /etc/kubernetes/pki/ca.crt already exists
# 原因分析：因为多次生成主节点的token值，导致token值加入不一致或输入错误

# 解决方法：
# 从集群移除状态为notready的node节点
[root@k8s-m-01 ~]#  kubectl delete n2

# node节点重置touken值以及证书端口号等信息
[root@k8s-n-01 ~]#  kubeadm reset
[root@k8s-n-02 ~]#  kubeadm reset

# 主节点重新创建token
[root@k8s-m-01 ~]#  kubeadm token create    --print-join-command 
kubeadm join 192.168.15.111:6443 --token fm0387.iqixomz5jmsukwsi     --discovery-token-ca-cert-hash sha256:d8ff83ffed5967000034d07b3da738ae4f1f0254e8417bb30c21f3ed15ac5d18 

# 将node节点重新加入集群
kubeadm join 192.168.15.111:6443 --token fm0387.iqixomz5jmsukwsi     --discovery-token-ca-cert-hash sha256:d8ff83ffed5967000034d07b3da738ae4f1f0254e8417bb30c21f3ed15ac5d18

# 报错 3、STATUS 状态是Healthy
[root@k8s-m-01 ~]# kubectl get cs
Warning: v1 ComponentStatus is deprecated in v1.19+
NAME                 STATUS      MESSAGE                                                                                       ERROR
scheduler            Unhealthy   Get "http://127.0.0.1:10251/healthz": dial tcp 127.0.0.1:10251: connect: connection refused   
controller-manager   Unhealthy   Get "http://127.0.0.1:10252/healthz": dial tcp 127.0.0.1:10252: connect: connection refused   
etcd-0               Healthy     {"health":"true"}    
1、解决方式
[root@k8s-m-01 ~]# vim /etc/kubernetes/manifests/kube-controller-manager.yaml 
 #- --port=0
[root@k8s-m-01 ~]# vim /etc/kubernetes/manifests/kube-scheduler.yaml 
 #- --port=0
 [root@k8s-m-01 ~]# systemctl restart kubelet.service

 2、查看状态
[root@k8s-m-01 ~]# kubectl get cs
Warning: v1 ComponentStatus is deprecated in v1.19+
NAME                 STATUS    MESSAGE             ERROR
controller-manager   Healthy   ok                  
scheduler            Healthy   ok                  
etcd-0               Healthy   {"health":"true"}  



报错4：
# 加入集群是种失败，一直未NotReady状态，没什么报错，只是显示部分提醒

# 解决方法：
	查看node节点是否缺失bin目录即里面的文件，若缺失，将其他节点或master节点的bin推送过来即可
	建议直接scp覆盖,node节点再重新执行：
		kubeadm reset
		kubeadm join ··· 重新加入集群即可

[root@k8s-m1 code] ls -l /opt/cni/bin/
总用量 56484
-rwxr-xr-x 1 root root 3254624 9月  10 2020 bandwidth
-rwxr-xr-x 1 root root 3581192 9月  10 2020 bridge
-rwxr-xr-x 1 root root 9837552 9月  10 2020 dhcp
-rwxr-xr-x 1 root root 4699824 9月  10 2020 firewall
-rwxr-xr-x 1 root root 2650368 9月  10 2020 flannel
-rwxr-xr-x 1 root root 3274160 9月  10 2020 host-device
-rwxr-xr-x 1 root root 2847152 9月  10 2020 host-local
-rwxr-xr-x 1 root root 3377272 9月  10 2020 ipvlan
-rwxr-xr-x 1 root root 2715600 9月  10 2020 loopback
-rwxr-xr-x 1 root root 3440168 9月  10 2020 macvlan
-rwxr-xr-x 1 root root 3048528 9月  10 2020 portmap
-rwxr-xr-x 1 root root 3528800 9月  10 2020 ptp
-rwxr-xr-x 1 root root 2849328 9月  10 2020 sbr
-rwxr-xr-x 1 root root 2503512 9月  10 2020 static
-rwxr-xr-x 1 root root 2820128 9月  10 2020 tuning
-rwxr-xr-x 1 root root 3377120 9月  10 2020 vlan
[root@k8s-m1 code] scp -r /opt/cni/bin n2:/opt/cni/

8.新增Master节点

• 新节点准备目录

rm -rf /etc/kubernetes
mkdir -p /etc/kubernetes/pki/etcd

• 推送原Master节点的配置文件到新节点

scp /etc/kubernetes/pki/{ca.crt,ca.key,sa.key,sa.pub,front-proxy-ca.crt,front-proxy-ca.key} m2:/etc/kubernetes/pki/
scp /etc/kubernetes/pki/etcd/{ca.crt,ca.key} m2:/etc/kubernetes/pki/etcd/{ca.crt,ca.key} m2:/etc/kubernetes/pki/etcd
scp /etc/kubernetes/pki/etcd/{ca.crt,ca.key} m2:/etc/kubernetes/pki/etcd/
scp /etc/kubernetes/admin.conf m2:/etc/kubernetes/

• 原Master节点查看token值，并复制到新节点执行

kubeadm token create --print-join-command

# 复制到新节点执行
kubeadm join 172.23.0.241:6443 --token lnvj7t.c7mc3254dnz3kp0u     --discovery-token-ca-cert-hash sha256:2c0cdaae024d5668cece036cca6e2696eee92da5a92188b89da74c8364bb5251 --ignore-preflight-errors=Swap

加入报错解决：
# 报错1：
	[preflight] If you know what you are doing, you can make a check non-fatal with `--ignore-preflight-errors=...`
# 解决：关闭Swap配置
	增加 --ignore-preflight-errors=Swap 选项即可

# 报错2
	[ERROR Port-10250]: Port 10250 is in use
	可能还有报错1的提示，添加选项后可无视
# 解决：提示端口占用，可能是因为之前加入过集群，加入失败残留端口占用，重置后重新加入即刻
	kubeadmin reset
	kubeadm join 172.23.0.241:6443 --token lnvj7t.c7mc3254dnz3kp0u     --discovery-token-ca-cert-hash sha256:2c0cdaae024d5668cece036cca6e2696eee92da5a92188b89da74c8364bb5251 --ignore-preflight-errors=Swap

此时m2新master节点已成功加入集群！
[root@k8s-m1 ~]# kubectl get nodes
NAME     STATUS   ROLES                  AGE   VERSION
k8s-m1   Ready    control-plane,master   15d   v1.20.2
k8s-m2   Ready    <none>                 15m   v1.20.2
k8s-n1   Ready    <none>                 15d   v1.20.2
k8s-n2   Ready    <none>                 15d   v1.20.2

9、让其他节点可用kubectl获取状态

• 让其他节点可用kubectl获取nodes、cs等状态信息

# 将master1节点的admin.conf推送至其他节点对应目录
for i in m1 m2 n1 n2 ;do scp /etc/kubernetes/admin.conf $i:/etc/kubernetes/

# 其他节点加入环境变量，即可使用
echo "export KUBECONFIG=/etc/kubernetes/admin.conf" >> ~/.bash_profile
source ~/.bash_profile

# 查看
kubectl get nodes
NAME     STATUS   ROLES                  AGE    VERSION
k8s-m1   Ready    control-plane,master   18d    v1.20.2
k8s-m2   Ready    <none>                 3d4h   v1.20.2
k8s-n1   Ready    <none>                 18d    v1.20.2
k8s-n2   Ready    <none>                 18d    v1.20.2