一、系统基础设置

1.1、关闭防火墙

systemctl stop firewalld
systemctl disable firewalld

1.2、关闭selinux

sed -i 's/enforcing/disabled/' /etc/selinux/config  # 永久
setenforce 0  # 临时

1.3、关闭swap

swapoff -a  # 临时
sed -ri 's/.*swap.*/#&/' /etc/fstab    # 永久

1.4、设置hostname

hostnamectl set-hostname nw-master2
#192.168.0.15 是我的虚拟IP，将来做负载均衡用的
cat >> /etc/hosts << EOF
192.168.7.7 nw-master
192.168.7.5 nw-slave1
192.168.7.15 nw-slave2
192.168.7.17 nw-slave3
192.168.7.23 nw-master2
EOF

1.5、将桥接的IPv4流量传递到iptables的链

cat > /etc/sysctl.d/k8s.conf << EOF
net.bridge.bridge-nf-call-ip6tables = 1
net.bridge.bridge-nf-call-iptables = 1
EOF
sysctl --system  # 生效

1.6、 更新DNS

#有的系统没有配置dns，可以先配置下dns
vi /etc/resolv.conf
#添加一条
nameserver 114.114.114.114

1.7、 更新麒麟的yum源

cd /etc/yum.repos.d/
# 更新的内容见下方
vi kylin_x86_64.repo
#更新yum
yum update

内容如下：

###Kylin Linux Advanced Server 10 - os repo###
[ks10-adv-os]
name = Kylin Linux Advanced Server 10 - Os 
baseurl = https://update.cs2c.com.cn/NS/V10/V10SP3/os/adv/lic/base/$basearch/
gpgcheck = 0
gpgkey=file:///etc/pki/rpm-gpg/RPM-GPG-KEY-kylin
enabled = 1

[ks10-adv-updates]
name = Kylin Linux Advanced Server 10 - Updates
baseurl = https://update.cs2c.com.cn/NS/V10/V10SP3/os/adv/lic/updates/$basearch/
gpgcheck = 0
gpgkey=file:///etc/pki/rpm-gpg/RPM-GPG-KEY-kylin
enabled = 1

[ks10-adv-addons]
name = Kylin Linux Advanced Server 10 - Addons
baseurl = https://update.cs2c.com.cn/NS/V10/V10SP3/os/adv/lic/addons/$basearch/
gpgcheck = 0
gpgkey=file:///etc/pki/rpm-gpg/RPM-GPG-KEY-kylin
enabled = 0

1.8、 时间同步

yum install ntpdate -y
ntpdate time.windows.com

1.8 配置开启 ipvs 的前提条件

modprobe -- ip_vs
modprobe -- ip_vs_rr
modprobe -- ip_vs_wrr
modprobe -- ip_vs_sh
modprobe -- nf_conntrack

1.9、 安装iproute-tc和dig工具

yum install iproute-tc -y
yum -y install bind-utils

二、所有master节点部署keepalived

2.1 安装相关包和keepalived

yum install -y conntrack-tools libseccomp libtool-ltdl
yum install -y keepalived

2.2配置master节点

master1节点配置

cat > /etc/keepalived/keepalived.conf <<EOF 
! Configuration File for keepalived

global_defs {
   router_id k8s
}

vrrp_script check_haproxy {
    script "killall -0 haproxy"
    interval 3
    weight -2
    fall 10
    rise 2
}

vrrp_instance VI_1 {
    state MASTER 
    interface eth0
    virtual_router_id 51
    priority 250
    advert_int 1
    authentication {
        auth_type PASS
        auth_pass ceb1b3ec013d66163d6ab
    }
    virtual_ipaddress {
        192.168.0.15
    }
    track_script {
        check_haproxy
    }

}
EOF

master2节点配置

cat > /etc/keepalived/keepalived.conf <<EOF 
! Configuration File for keepalived

global_defs {
   router_id k8s
}

vrrp_script check_haproxy {
    script "killall -0 haproxy"
    interval 3
    weight -2
    fall 10
    rise 2
}

vrrp_instance VI_1 {
    state BACKUP
    interface eth0
    virtual_router_id 51
    priority 250
    advert_int 1
    authentication {
        auth_type PASS
        auth_pass ceb1b3ec013d66163d6ab
    }
    virtual_ipaddress {
        192.168.0.15
    }
    track_script {
        check_haproxy
    }

}
EOF

2.3 启动和检查

在三台master节点都执行

# 启动keepalived
$ systemctl start keepalived.service
设置开机启动
$ systemctl enable keepalived.service
# 查看启动状态
$ systemctl status keepalived.service

启动后查看master1的网卡信息

ip a s eth0

如果是云服务器搭建的话，记得云服务器管理平台上申请虚拟IP地址，然后绑定虚拟IP地址到三台主节点服务器上，然后添加相应的网络策略，否侧ping不通虚拟ip

三、 部署haproxy

3.1 安装

yum install -y haproxy

3.2 配置

两台master节点的配置均相同，配置中声明了后端代理的两个master节点服务器，指定了haproxy运行的端口为16443等，因此16443端口为集群的入口

下面的文件主要需要修改ip地址 kubernetes-apiserver

cat > /etc/haproxy/haproxy.cfg << EOF
#---------------------------------------------------------------------
# Global settings
#---------------------------------------------------------------------
global
    # to have these messages end up in /var/log/haproxy.log you will
    # need to:
    # 1) configure syslog to accept network log events.  This is done
    #    by adding the '-r' option to the SYSLOGD_OPTIONS in
    #    /etc/sysconfig/syslog
    # 2) configure local2 events to go to the /var/log/haproxy.log
    #   file. A line like the following can be added to
    #   /etc/sysconfig/syslog
    #
    #    local2.*                       /var/log/haproxy.log
    #
    log         127.0.0.1 local2
    
    chroot      /var/lib/haproxy
    pidfile     /var/run/haproxy.pid
    maxconn     4000
    user        haproxy
    group       haproxy
    daemon 
       
    # turn on stats unix socket
    stats socket /var/lib/haproxy/stats
#---------------------------------------------------------------------
# common defaults that all the 'listen' and 'backend' sections will
# use if not designated in their block
#---------------------------------------------------------------------  
defaults
    mode                    http
    log                     global
    option                  httplog
    option                  dontlognull
    option http-server-close
    option forwardfor       except 127.0.0.0/8
    option                  redispatch
    retries                 3
    timeout http-request    10s
    timeout queue           1m
    timeout connect         10s
    timeout client          1m
    timeout server          1m
    timeout http-keep-alive 10s
    timeout check           10s
    maxconn                 3000
#---------------------------------------------------------------------
# kubernetes apiserver frontend which proxys to the backends
#--------------------------------------------------------------------- 
frontend kubernetes-apiserver
    mode                 tcp
    bind                 *:16443
    option               tcplog
    default_backend      kubernetes-apiserver    
#---------------------------------------------------------------------
# round robin balancing between the various backends
#---------------------------------------------------------------------
backend kubernetes-apiserver
    mode        tcp
    balance     roundrobin
    server      zxhy-nacos   192.168.0.14:6443 check
    server      zxhy-redis   192.168.0.77:6443 check
    server      zxhy-mysql   192.168.0.222:6443 check
#---------------------------------------------------------------------
# collection haproxy statistics message
#---------------------------------------------------------------------
listen stats
    bind                 *:1080
    stats auth           admin:awesomePassword
    stats refresh        5s
    stats realm          HAProxy\ Statistics
    stats uri            /admin?stats
EOF

3.3 启动和检查

三台master都启动

# 设置开机启动
$ systemctl enable haproxy
# 开启haproxy
$ systemctl start haproxy
# 查看启动状态
$ systemctl status haproxy

四、 所有节点安装Docker/kubeadm/kubelet

Kubernetes默认CRI（容器运行时）为Docker，因此先安装Docker。

4.1 安装Docker

#添加docker源
yum-config-manager --add-repo http://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo

wget http://mirrors.aliyun.com/docker-ce/linux/static/stable/x86_64/docker-18.06.1-ce.tgz
#执行命令完成解压
tar -xvzf docker-18.06.1-ce.tgz
#移动解压后的全部内容到/usr/bin/下
mv docker/* /usr/bin/
#编辑docker.service文件
vi /usr/lib/systemd/system/docker.service

docker.service 文件复制以下内容

[Unit]
Description=Docker Application Container Engine
Documentation=https://docs.docker.com
After=network-online.target firewalld.service
Wants=network-online.target

[Service]
Type=notify
ExecStart=/usr/bin/dockerd
ExecReload=/bin/kill -s HUP $MAINPID
LimitNOFILE=infinity
LimitNPROC=infinity
TimeoutStartSec=0
Delegate=yes
KillMode=process
Restart=on-failure
StartLimitBurst=3
StartLimitInterval=60s

[Install]
WantedBy=multi-user.target

#添加docker.service文件的权限
chmod +x /usr/lib/systemd/system/docker.service
#刷新
systemctl daemon-reload

#创建daemon.json文件
mkdir /etc/docker
vi /etc/docker/daemon.json

#daemon.json文件内容
{
  "registry-mirrors": ["https://6f09bd673d1d4e8d98dab0ab278fc7c2.mirror.swr.myhuaweicloud.com"],
  "log-driver": "json-file",
  "log-opts": {
    "max-size": "100m",
    "max-file": "5"
   },
   "data-root": "/ydata/docker/"
}
# 注意：docker的cri-dockerd默认Cgroup驱动，所以需要修改native.cgroupdriver为systemd。

#启动docker
systemctl enable docker && systemctl start docker
docker --version
Docker version 18.06.1-ce, build e68fc7a

#如果有报错，可以运行下面命令  查看日志，排查错误
#docker服务的状态
systemctl status docker
#启动的报错日志
journalctl -u docker.service

4.2 cri-dockerd安装

下载 cri-dockerd 安装包

cd  /opt
wget https://github.com/Mirantis/cri-dockerd/releases/download/v0.2.1/cri-dockerd-0.2.1.20220525024524.cb92d7b-0.el7.x86_64.rpm

安装服务

yum install container-selinux
#安装containerd.io
yum install -y https://mirrors.aliyun.com/docker-ce/linux/centos/7/x86_64/edge/Packages/containerd.io-1.2.6-3.3.el7.x86_64.rpm
yum install -y cri-dockerd-0.2.1.20220525024524.cb92d7b-0.el7.x86_64.rpm
vi /usr/lib/systemd/system/cri-docker.service
#添加镜像源
#在这一句后面添加
 ExecStart=/usr/bin/cri-dockerd --container-runtime-endpoint fd:// --network-plugin= --pod-infra-container-image=registry.aliyuncs.com/google_containers/pause:3.7

systemctl daemon-reload
#添加一个docker的用户组
groupadd docker

查看服务启动状态

# 设置开机启动
$ systemctl enable cri-docker
# 开启cri-docker
$ systemctl start cri-docker
# 查看启动状态
$ systemctl status cri-docker

查看CRI服务是否被禁止

vi /etc/containerd/config.toml 
#如果disabled_plugins中包含cri，删除“cri”即可
#disabled_plugins = [“cri”]
disabled_plugins = []

重启容器运行时

systemctl restart containerd 

4.3 添加阿里云YUM软件源

$ cat > /etc/yum.repos.d/kubernetes.repo << EOF
[kubernetes]
name=Kubernetes
baseurl=https://mirrors.aliyun.com/kubernetes/yum/repos/kubernetes-el7-x86_64
enabled=1
gpgcheck=0
repo_gpgcheck=0
gpgkey=https://mirrors.aliyun.com/kubernetes/yum/doc/yum-key.gpg https://mirrors.aliyun.com/kubernetes/yum/doc/rpm-package-key.gpg
EOF

4.4 安装kubeadm，kubelet和kubectl

由于版本更新频繁，这里指定版本号部署：

$ yum install -y kubelet-1.20.7 kubeadm-1.20.7 kubectl-1.20.7
$ systemctl start kubelet && systemctl enable kubelet

4.4 安装kubeadm-cni

network plugin is not ready: cni config uninitialized

# 备份 CNI 配置
 cp -r /etc/cni /etc/cni.bak
 cp -r /opt/cni /opt/cni.bak

# 删除 CNI 二进制文件和配置
 rm -rf /etc/cni/net.d/*
 rm -rf /opt/cni/bin/*

# 清理网络接口
 ip link delete cni0 2>/dev/null
 ip link delete flannel.1 2>/dev/null

# 重启容器运行时
 systemctl restart docker
 
 # 下载并安装最新兼容版本 并解压到/opt/cni/bin
 curl -L "https://github.com/containernetworking/plugins/releases/download/v0.8.2/cni-plugins-linux-x86_64-v0.8.2.tgz" | sudo tar -C /opt/cni/bin -xz
 # 重启kubelet
 systemctl restart kubelet
mkdir -p /etc/cni/net.d

五、部署Kubernetes Master

5.1 创建kubeadm配置文件

在具有vip的master上操作，这里为master1

$ mkdir /usr/local/kubernetes/manifests -p

$ cd /usr/local/kubernetes/manifests/

$ vi kubeadm-config.yaml

apiVersion: kubeadm.k8s.io/v1beta2
bootstrapTokens:
- groups:
  - system:bootstrappers:kubeadm:default-node-token
  token: abcdef.0123456789abcdef
  ttl: 24h0m0s
  usages:
  - signing
  - authentication
kind: InitConfiguration
localAPIEndpoint:
  advertiseAddress: 192.168.7.23
  bindPort: 6443
nodeRegistration:
  criSocket: /var/run/dockershim.sock
  name: nw-master2
  taints: null
---
apiServer:
  certSANs:
    - 192.168.7.23
    - 192.168.7.17
    - 127.0.0.1
    - 192.168.7.7
  extraArgs:
    authorization-mode: Node,RBAC
  timeoutForControlPlane: 4m0s
apiVersion: kubeadm.k8s.io/v1beta2
certificatesDir: /etc/kubernetes/pki
clusterName: kubernetes
controllerManager: {}
dns: {}
etcd:
  local:
    dataDir: /var/lib/etcd
imageRepository: registry.aliyuncs.com/google_containers
kind: ClusterConfiguration
kubernetesVersion: v1.20.0
networking:
  dnsDomain: cluster.local
  podSubnet: 10.244.0.0/16
  serviceSubnet: 10.1.0.0/16
scheduler: {}

5.2 在master1节点执行

$ kubeadm init --config kubeadm-config.yaml

export KUBECONFIG=/etc/kubernetes/admin.conf

按照提示配置环境变量，使用kubectl工具：

mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/config
$ kubectl get nodes
$ kubectl get pods -n kube-system

按照提示保存以下内容，一会要使用：

kubeadm join zxhy-vip:16443 --token gp4qgj.3x8wal0o2gmbcpis --discovery-token-ca-cert-hash sha256:af5fe3bb4f2ada51967c34053e94ed4c703287e3e26487d6d8dbe450a2550013 --cri-socket=unix:///var/run/cri-dockerd.sock
#如果忘记复制，也可以利用这个命令重新生成下加入命令
kubeadm token create --print-join-command
#测试etcd的性能
fio --filename=/var/lib/etcd/fio-test --size=100M --bs=4k --iodepth=32 --rw=randread --time_based --runtime=10s --name=etcd-read-test

六、安装集群网络

从官方地址获取到flannel的yaml，在master1上执行

mkdir /usr/local/kubernetes/manifests/flannel
cd /usr/local/kubernetes/manifests/flannel
wget -c https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml
#安装cni
#设置环境变量
export CNI_PATH=/opt/cni/bin
mkdir -p /etc/cni/net.d/
#下载安装包
curl -L "https://github.com/containernetworking/plugins/releases/download/v0.8.2/cni-plugins-linux-x86_64-v0.8.2.tgz" | sudo tar -C /opt/cni/bin -xz
# 更改mode为“”
kubectl edit cm -n kube-system kube-proxy
mode:"ipvs"
#重启kubelet
systemctl restart kubelet
 

安装flannel网络

kubectl apply -f /usr/local/kubernetes/manifests/flannel/kube-flannel.yml 

添加 controlPlaneEndpoint 字段

kubectl -n kube-system edit cm kubeadm-config

#添加本机地址及端口 ClusterConfiguration下面
controlPlaneEndpoint: 192.168.7.23:6443

检查

kubectl get pods -n kube-system

#删除污点
kubectl taint node nw-master node-role.kubernetes.io/master:NoSchedule-

七、master2节点加入集群

7.1 复制密钥及相关文件

从master1复制密钥及相关文件到master2

# ssh root@192.168.0.222 mkdir -p /etc/kubernetes/pki/etcd

# scp /etc/kubernetes/admin.conf root@192.168.0.222:/etc/kubernetes
   
# scp /etc/kubernetes/pki/{ca.*,sa.*,front-proxy-ca.*} root@192.168.0.222:/etc/kubernetes/pki
   
# scp /etc/kubernetes/pki/etcd/ca.* root@192.168.0.222:/etc/kubernetes/pki/etcd

7.2 master2加入集群

执行在master1上init后输出的join命令,需要带上参数--control-plane表示把master控制节点加入集群

#如果忘记了加入集群的命令，可以使用下面命令生成
kubeadm token create --print-join-command
#然后再进行加入
kubeadm join zxhy-vip:16443 --token gp4qgj.3x8wal0o2gmbcpis --discovery-token-ca-cert-hash sha256:af5fe3bb4f2ada51967c34053e94ed4c703287e3e26487d6d8dbe450a2550013 --control-plane --cri-socket=unix:///var/run/cri-dockerd.sock

按照提示配置环境变量，使用kubectl工具：

mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/config
$ kubectl get nodes
$ kubectl get pods -n kube-system

7.3master3加入集群

跟节点2同样的操作

7.4检查状态

kubectl get node

kubectl get pods --all-namespaces

八、加入Kubernetes Node

8.1在node1、node2、node3上执行join命令

向集群添加新节点，执行在kubeadm init输出的kubeadm join命令：

kubeadm join zxhy-vip:16443 --token gp4qgj.3x8wal0o2gmbcpis --discovery-token-ca-cert-hash sha256:af5fe3bb4f2ada51967c34053e94ed4c703287e3e26487d6d8dbe450a2550013 --cri-socket=unix:///var/run/cri-dockerd.sock

8.2集群网络重新安装，因为添加了新的node节点

所有节点加入完成后安装flannel网络

#进入flannel网络
cd /usr/local/kubernetes/manifests/flannel
#删除之前的网络
kubectl delete -f kube-flannel.yml 
#重新初始化的网络
kubectl apply -f kube-flannel.yml 

8.3检查状态

kubectl get node

kubectl get pods --all-namespaces

九、测试kubernetes集群

在Kubernetes集群中创建一个pod，验证是否正常运行：

$ kubectl create deployment nginx --image=nginx
$ kubectl expose deployment nginx --port=80 --type=NodePort
$ kubectl get pod,svc

十、修改 kube-proxy网络模式，并重启kube-proxy

1、编辑kube-proxy 配置

kubectl edit cm kube-proxy -n kube-system

将mode: iptables 修改成 mode: ipvs

2、重启kube-proxy

kubectl get pod -n kube-system | grep kube-proxy |awk '{system("kubectl delete pod "$1" -n kube-system")}'

3、查看日志

kubectl logs -f -n kube-system kube-proxy-62fk7

十一、常用命令

#进入容器
kubectl exec -it nacos-0 bash
#查看dns服务器
cat /etc/resolv.conf
#查看无头服务访问地址
dig @10.1.0.10 nacos-headless.default.svc.cluster.local

#添加 尽量不调度 PreferNoSchedule 
kubectl taint nodes zxhy-mysql node-role.kubernetes.io/master:PreferNoSchedule
#去除污点NoSchedule，最后一个"-"代表删除
kubectl taint nodes zxhy-mysql node-role.kubernetes.io/master:NoSchedule-