kubeadm 快速部署k8s

竹流清水

已于 2023-07-22 12:18:52 修改

阅读量214

点赞数

文章标签： kubernetes 容器云原生

于 2023-07-06 08:48:50 首次发布

本文链接：https://blog.csdn.net/qq_51574973/article/details/131567852

版权

一 kubeadm 1.2的部署

master（2C/4G，cpu核心数要求大于2）       192.168.80.10       docker、kubeadm、kubelet、kubectl、flannel
node01（2C/2G）                           192.168.80.11       docker、kubeadm、kubelet、kubectl、flannel
node02（2C/2G）                           192.168.80.12       docker、kubeadm、kubelet、kubectl、flannel
Harbor节点（hub.kgc.com）               192.168.80.13       docker、docker-compose、harbor-offline-v1.2.2

1、在所有节点上安装Docker和kubeadm
2、部署Kubernetes Master
3、部署容器网络插件
4、部署 Kubernetes Node，将节点加入Kubernetes集群中
5、部署 Dashboard Web 页面，可视化查看Kubernetes资源
6、部署 Harbor 私有仓库，存放镜像资源

------------------------------ 环境准备 ------------------------------
//所有节点，关闭防火墙规则，关闭selinux，关闭swap交换
systemctl stop firewalld
systemctl disable firewalld
setenforce 0
sed -i 's/enforcing/disabled/' /etc/selinux/config
iptables -F && iptables -t nat -F && iptables -t mangle -F && iptables -X
swapoff -a #交换分区必须要关闭
sed -ri 's/.*swap.*/#&/' /etc/fstab #永久关闭swap分区，&符号在sed命令中代表上次匹配的结果
#加载 ip_vs 模块
for i in $(ls /usr/lib/modules/$(uname -r)/kernel/net/netfilter/ipvs|grep -o "^[^.]*");do echo $i; /sbin/modinfo -F filename $i >/dev/null 2>&1 && /sbin/modprobe $i;done

//修改主机名
hostnamectl set-hostname master01
hostnamectl set-hostname node01
hostnamectl set-hostname node02

//所有节点修改hosts文件
vim /etc/hosts
192.168.80.10 master01
192.168.80.11 node01
192.168.80.12 node02

//调整内核参数
cat > /etc/sysctl.d/kubernetes.conf << EOF
#开启网桥模式，可将网桥的流量传递给iptables链
net.bridge.bridge-nf-call-ip6tables=1
net.bridge.bridge-nf-call-iptables=1
#关闭ipv6协议
net.ipv6.conf.all.disable_ipv6=1
net.ipv4.ip_forward=1
EOF

//生效参数
sysctl --system

-------------------- 所有节点安装docker --------------------
yum install -y yum-utils device-mapper-persistent-data lvm2
yum-config-manager --add-repo https://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo
yum install -y docker-ce docker-ce-cli containerd.io

mkdir /etc/docker
cat > /etc/docker/daemon.json <<EOF
{
"registry-mirrors": ["https://6ijb8ubo.mirror.aliyuncs.com"],
"exec-opts": ["native.cgroupdriver=systemd"],
"log-driver": "json-file",
"log-opts": {
"max-size": "500m", "max-file": "3"
}
}
EOF
#使用Systemd管理的Cgroup来进行资源控制与管理，因为相对Cgroupfs而言，Systemd限制CPU、内存等资源更加简单和成熟稳定。
#日志使用json-file格式类型存储，大小为100M，保存在/var/log/containers目录下，方便ELK等日志系统收集和管理日志。

systemctl daemon-reload
systemctl restart docker.service
systemctl enable docker.service

docker info | grep "Cgroup Driver"
Cgroup Driver: systemd

-------------------- 所有节点安装kubeadm，kubelet和kubectl --------------------
//定义kubernetes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

yum install -y kubelet-1.20.15 kubeadm-1.20.15 kubectl-1.20.15

//开机自启kubelet
systemctl enable kubelet.service
#K8S通过kubeadm安装出来以后都是以Pod方式存在，即底层是以容器方式运行，所以kubelet必须设置开机自启

-------------------- 部署K8S集群 --------------------
//查看初始化需要的镜像
kubeadm config images list --kubernetes-version 1.20.15

//在 master 节点上传 v1.20.15.zip 压缩包至 /opt 目录
unzip v1.20.15.zip -d /opt/k8s
cd /opt/k8s/
for i in $(ls *.tar); do docker load -i $i; done

//复制镜像和脚本到 node 节点，并在 node 节点上执行脚本加载镜像文件
scp -r /opt/k8s root@node01:/opt
scp -r /opt/k8s root@node02:/opt

//初始化kubeadm
方法一：
kubeadm config print init-defaults > /opt/kubeadm-config.yaml

cd /opt/
vim kubeadm-config.yaml
......
11 localAPIEndpoint:
12 advertiseAddress: 192.168.80.10       #指定master节点的IP地址
13 bindPort: 6443
......
32 imageRepository: registry.cn-hangzhou.aliyuncs.com/google_containers #指定拉取镜像的仓库，默认是k8s.gcr.io
33 kind: ClusterConfiguration
34 kubernetesVersion: v1.20.15               #指定kubernetes版本号
35 networking:
36 dnsDomain: cluster.local
37 podSubnet: "10.244.0.0/16"               #指定pod网段，10.244.0.0/16用于匹配flannel默认网段
38 serviceSubnet: 10.96.0.0/16           #指定service网段
39 scheduler: {}
#末尾再添加以下内容
---
apiVersion: kubeproxy.config.k8s.io/v1alpha1
kind: KubeProxyConfiguration
mode: ipvs                                   #把默认的kube-proxy调度方式改为ipvs模式

//在线拉取镜像
kubeadm config images pull --config /opt/kubeadm-config.yaml

//初始化 master
kubeadm init --config=/opt/kubeadm-config.yaml --upload-certs | tee kubeadm-init.log
#--upload-certs 参数可以在后续执行加入节点时自动分发证书文件
#tee kubeadm-init.log 用以输出日志

//查看 kubeadm-init 日志
less kubeadm-init.log

//kubernetes配置文件目录
ls /etc/kubernetes/

//存放ca等证书和密码的目录
ls /etc/kubernetes/pki

方法二：
kubeadm init \
--apiserver-advertise-address=192.168.80.10 \
--image-repository registry.aliyuncs.com/google_containers \
--kubernetes-version=v1.20.15 \
--service-cidr=10.96.0.0/16 \
--pod-network-cidr=10.244.0.0/16 \
--token-ttl=0
--------------------------------------------------------------------------------------------
初始化集群需使用kubeadm init命令，可以指定具体参数初始化，也可以指定配置文件初始化。
可选参数：
--apiserver-advertise-address：apiserver通告给其他组件的IP地址，一般应该为Master节点的用于集群内部通信的IP地址，0.0.0.0表示节点上所有可用地址
--apiserver-bind-port：apiserver的监听端口，默认是6443
--cert-dir：通讯的ssl证书文件，默认/etc/kubernetes/pki
--control-plane-endpoint：控制台平面的共享终端，可以是负载均衡的ip地址或者dns域名，高可用集群时需要添加
--image-repository：拉取镜像的镜像仓库，默认是k8s.gcr.io
--kubernetes-version：指定kubernetes版本
--pod-network-cidr：pod资源的网段，需与pod网络插件的值设置一致。Flannel网络插件的默认为10.244.0.0/16，Calico插件的默认值为192.168.0.0/16；
--service-cidr：service资源的网段
--service-dns-domain：service全域名的后缀，默认是cluster.local
--token-ttl：默认token的有效期为24小时，如果不想过期，可以加上 --token-ttl=0 这个参数
---------------------------------------------------------------------------------------------

方法二初始化后需要修改 kube-proxy 的 configmap，开启 ipvs
kubectl edit cm kube-proxy -n=kube-system
修改mode: ipvs

提示：
......
Your Kubernetes control-plane has initialized successfully!

To start using your cluster, you need to run the following as a regular user:

mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/config

You should now deploy a pod network to the cluster.
Run "kubectl apply -f [podnetwork].yaml" with one of the options listed at:
https://kubernetes.io/docs/concepts/cluster-administration/addons/

Then you can join any number of worker nodes by running the following on each as root:

kubeadm join 192.168.80.10:6443 --token rc0kfs.a1sfe3gl4dvopck5 \
--discovery-token-ca-cert-hash sha256:864fe553c812df2af262b406b707db68b0fd450dc08b34efb73dd5a4771d37a2

//设定kubectl
kubectl需经由API server认证及授权后方能执行相应的管理操作，kubeadm 部署的集群为其生成了一个具有管理员权限的认证配置文件 /etc/kubernetes/admin.conf，它可由 kubectl 通过默认的 “$HOME/.kube/config” 的路径进行加载。

mkdir -p $HOME/.kube
cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
chown $(id -u):$(id -g) $HOME/.kube/config

//如果 kubectl get cs 发现集群不健康，更改以下两个文件
vim /etc/kubernetes/manifests/kube-scheduler.yaml
vim /etc/kubernetes/manifests/kube-controller-manager.yaml
# 修改如下内容
把--bind-address=127.0.0.1变成--bind-address=192.168.80.10 #修改成k8s的控制节点master01的ip
把httpGet:字段下的hosts由127.0.0.1变成192.168.80.10（有两处）
#- --port=0 # 搜索port=0，把这一行注释掉

systemctl restart kubelet

//所有节点部署网络插件flannel
方法一：
//所有节点上传 flannel 镜像 flannel.tar 和网络插件 cni-plugins-linux-amd64-v0.8.6.tgz 到 /opt 目录，master节点上传 kube-flannel.yml 文件
cd /opt
docker load < flannel.tar

mv /opt/cni /opt/cni_bak
mkdir -p /opt/cni/bin
tar zxvf cni-plugins-linux-amd64-v0.8.6.tgz -C /opt/cni/bin

//在 master 节点创建 flannel 资源
kubectl apply -f kube-flannel.yml

方法二：
kubectl apply -f https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml

//在 node 节点上执行 kubeadm join 命令加入群集
kubeadm join 192.168.80.10:6443 --token rc0kfs.a1sfe3gl4dvopck5 \
--discovery-token-ca-cert-hash sha256:864fe553c812df2af262b406b707db68b0fd450dc08b34efb73dd5a4771d37a2

//在master节点查看节点状态
kubectl get nodes

kubectl get pods -n kube-system
NAME READY STATUS RESTARTS AGE
coredns-bccdc95cf-c9w6l 1/1 Running 0 71m
coredns-bccdc95cf-nql5j 1/1 Running 0 71m
etcd-master 1/1 Running 0 71m
kube-apiserver-master 1/1 Running 0 70m
kube-controller-manager-master 1/1 Running 0 70m
kube-flannel-ds-amd64-kfhwf 1/1 Running 0 2m53s
kube-flannel-ds-amd64-qkdfh 1/1 Running 0 46m
kube-flannel-ds-amd64-vffxv 1/1 Running 0 2m56s
kube-proxy-558p8 1/1 Running 0 2m53s
kube-proxy-nwd7g 1/1 Running 0 2m56s
kube-proxy-qpz8t 1/1 Running 0 71m
kube-scheduler-master 1/1 Running 0 70m

//测试 pod 资源创建
kubectl create deployment nginx --image=nginx

kubectl get pods -o wide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
nginx-554b9c67f9-zr2xs 1/1 Running 0 14m 10.244.1.2 node01 <none> <none>

//暴露端口提供服务
kubectl expose deployment nginx --port=80 --type=NodePort

kubectl get svc
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
kubernetes ClusterIP 10.96.0.1 <none> 443/TCP 25h
nginx NodePort 10.96.15.132 <none> 80:32698/TCP 4s

//测试访问
curl http://node01:32698

//扩展3个副本
kubectl scale deployment nginx --replicas=3
kubectl get pods -o wide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
nginx-554b9c67f9-9kh4s 1/1 Running 0 66s 10.244.1.3 node01 <none> <none>
nginx-554b9c67f9-rv77q 1/1 Running 0 66s 10.244.2.2 node02 <none> <none>
nginx-554b9c67f9-zr2xs 1/1 Running 0 17m 10.244.1.2 node01 <none> <none>

------------------------------ 部署 Dashboard ------------------------------
//在 master01 节点上操作
#上传 recommended.yaml 文件到 /opt/k8s 目录中
cd /opt/k8s
vim recommended.yaml
#默认Dashboard只能集群内部访问，修改Service为NodePort类型，暴露到外部：
kind: Service
apiVersion: v1
metadata:
labels:
k8s-app: kubernetes-dashboard
name: kubernetes-dashboard
namespace: kubernetes-dashboard
spec:
ports:
- port: 443
targetPort: 8443
nodePort: 30001 #添加
type: NodePort #添加
selector:
k8s-app: kubernetes-dashboard

kubectl apply -f recommended.yaml

#创建service account并绑定默认cluster-admin管理员集群角色
kubectl create serviceaccount dashboard-admin -n kube-system
kubectl create clusterrolebinding dashboard-admin --clusterrole=cluster-admin --serviceaccount=kube-system:dashboard-admin
kubectl describe secrets -n kube-system $(kubectl -n kube-system get secret | awk '/dashboard-admin/{print $1}')

#使用输出的token登录Dashboard
https://NodeIP:30001

-------------------- 安装Harbor私有仓库 --------------------
//修改主机名
hostnamectl set-hostname hub.kgc.com

//所有节点加上主机名映射
echo '192.168.80.13 hub.kgc.com' >> /etc/hosts

//安装 docker
yum install -y yum-utils device-mapper-persistent-data lvm2
yum-config-manager --add-repo https://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo
yum install -y docker-ce docker-ce-cli containerd.io

systemctl start docker
systemctl enable docker

//所有 node 节点都修改 docker 配置文件，加上私有仓库配置
cat > /etc/docker/daemon.json <<EOF
{
"registry-mirrors": ["https://6ijb8ubo.mirror.aliyuncs.com"],
"exec-opts": ["native.cgroupdriver=systemd"],
"log-driver": "json-file",
"log-opts": {
"max-size": "500m", "max-file": "3"
},
"insecure-registries": ["https://hub.kgc.com"]
}
EOF

systemctl daemon-reload
systemctl restart docker

//安装 Harbor
//上传 harbor-offline-installer-v1.2.2.tgz 和 docker-compose 文件到 /opt 目录
cd /opt
cp docker-compose /usr/local/bin/
chmod +x /usr/local/bin/docker-compose

tar zxvf harbor-offline-installer-v1.2.2.tgz
cd harbor/
vim harbor.cfg
5 hostname = hub.kgc.com
9 ui_url_protocol = https
24 ssl_cert = /data/cert/server.crt
25 ssl_cert_key = /data/cert/server.key
59 harbor_admin_password = Harbor12345

//生成证书
mkdir -p /data/cert
cd /data/cert
#生成私钥
openssl genrsa -des3 -out server.key 2048
输入两遍密码：123456

#生成证书签名请求文件
openssl req -new -key server.key -out server.csr
输入私钥密码：123456
输入国家名：CN
输入省名：BJ
输入市名：BJ
输入组织名：KGC
输入机构名：KGC
输入域名：hub.kgc.com
输入管理员邮箱：admin@kgc.com
其它全部直接回车

#备份私钥
cp server.key server.key.org

#清除私钥密码
openssl rsa -in server.key.org -out server.key
输入私钥密码：123456

#签名证书
openssl x509 -req -days 1000 -in server.csr -signkey server.key -out server.crt

chmod +x /data/cert/*

cd /opt/harbor/
./install.sh

在本地使用火狐浏览器访问：https://hub.kgc.com
添加例外 -> 确认安全例外
用户名：admin
密码：Harbor12345

//在一个node节点上登录harbor
docker login -u admin -p Harbor12345 https://hub.kgc.com

//上传镜像
docker tag nginx:latest hub.kgc.com/library/nginx:v1
docker push hub.kgc.com/library/nginx:v1

//在master节点上删除之前创建的nginx资源
kubectl delete deployment nginx

kubectl run nginx-deployment --image=hub.kgc.com/library/nginx:v1 --port=80 --replicas=3

kubectl expose deployment nginx-deployment --port=30000 --target-port=80
kubectl get svc,pods
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
service/kubernetes ClusterIP 10.96.0.1 <none> 443/TCP 10m
service/nginx-deployment ClusterIP 10.96.222.161 <none> 30000/TCP 3m15s

NAME READY STATUS RESTARTS AGE
pod/nginx-deployment-77bcbfbfdc-bv5bz 1/1 Running 0 16s
pod/nginx-deployment-77bcbfbfdc-fq8wr 1/1 Running 0 16s
pod/nginx-deployment-77bcbfbfdc-xrg45 1/1 Running 0 3m39s

yum install ipvsadm -y
ipvsadm -Ln

curl 10.96.222.161:30000

kubectl edit svc nginx-deployment
25 type: NodePort #把调度策略改成NodePort

kubectl get svc
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
service/kubernetes ClusterIP 10.96.0.1 <none> 443/TCP 29m
service/nginx-deployment NodePort 10.96.222.161 <none> 30000:32340/TCP 22m

浏览器访问：
192.168.80.10:32340
192.168.80.11:32340
192.168.80.12:32340

#将cluster-admin角色权限授予用户system:anonymous
kubectl create clusterrolebinding cluster-system-anonymous --clusterrole=cluster-admin --user=system:anonymous

########### 内核参数优化方案 ##########
cat > /etc/sysctl.d/kubernetes.conf <<EOF
net.bridge.bridge-nf-call-iptables=1
net.bridge.bridge-nf-call-ip6tables=1
net.ipv4.ip_forward=1
net.ipv4.tcp_tw_recycle=0
vm.swappiness=0                                   #禁止使用 swap 空间，只有当系统内存不足（OOM）时才允许使用它
vm.overcommit_memory=1                           #不检查物理内存是否够用
vm.panic_on_oom=0                               #开启 OOM
fs.inotify.max_user_instances=8192
fs.inotify.max_user_watches=1048576
fs.file-max=52706963                           #指定最大文件句柄数
fs.nr_open=52706963                               #仅4.4以上版本支持
net.ipv6.conf.all.disable_ipv6=1
net.netfilter.nf_conntrack_max=2310720
EOF

初始化失败，进行的操作
# kubeadm reset -f
# ipvsadm --clear
# rm -rf ~/.kube
# 再次进行初始化

二 K8S1.20 - 高可用集群部署

注意事项：
master节点cpu核心数要求大于2
●最新的版本不一定好，但相对于旧版本，核心功能稳定，但新增功能、接口相对不稳
●学会一个版本的高可用部署，其他版本操作都差不多
●宿主机尽量升级到CentOS 7.9
●内核kernel升级到 4.19+ 这种稳定的内核
●部署k8s版本时，尽量找 1.xx.5 这种大于5的小版本（这种一般是比较稳定的版本）

//修改主机名
hostnamectl set-hostname master01
hostnamectl set-hostname master02
hostnamectl set-hostname master03
hostnamectl set-hostname node01
hostnamectl set-hostname node02

//所有节点修改hosts文件
vim /etc/hosts
192.168.80.10 master01
192.168.80.11 master02
192.168.80.12 master03
192.168.80.20 node01
192.168.80.30 node02

//所有节点时间同步
yum -y install ntpdate
ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime
echo 'Asia/Shanghai' >/etc/timezone
ntpdate time2.aliyun.com

systemctl enable --now crond

crontab -e
*/30 * * * * /usr/sbin/ntpdate time2.aliyun.com

//所有节点实现Linux的资源限制
vim /etc/security/limits.conf
* soft nofile 65536
* hard nofile 131072
* soft nproc 65535
* hard nproc 655350
* soft memlock unlimited
* hard memlock unlimited

//所有节点升级内核
wget http://193.49.22.109/elrepo/kernel/el7/x86_64/RPMS/kernel-ml-devel-4.19.12-1.el7.elrepo.x86_64.rpm -O /opt/kernel-ml-devel-4.19.12-1.el7.elrepo.x86_64.rpm
wget http://193.49.22.109/elrepo/kernel/el7/x86_64/RPMS/kernel-ml-4.19.12-1.el7.elrepo.x86_64.rpm -O /opt/kernel-ml-4.19.12-1.el7.elrepo.x86_64.rpm

cd /opt/
yum localinstall -y kernel-ml*

#更改内核启动方式
grub2-set-default 0 && grub2-mkconfig -o /etc/grub2.cfg
grubby --args="user_namespace.enable=1" --update-kernel="$(grubby --default-kernel)"
grubby --default-kernel
reboot

//调整内核参数
cat > /etc/sysctl.d/k8s.conf <<EOF
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.netfilter.nf_conntrack_max=2310720

net.ipv4.tcp_keepalive_time = 600
net.ipv4.tcp_keepalive_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.tcp_timestamps = 0
net.core.somaxconn = 16384
EOF

#生效参数
sysctl --system

//加载 ip_vs 模块
for i in $(ls /usr/lib/modules/$(uname -r)/kernel/net/netfilter/ipvs|grep -o "^[^.]*");do echo $i; /sbin/modinfo -F filename $i >/dev/null 2>&1 && /sbin/modprobe $i;done

systemctl daemon-reload
systemctl restart docker.service
systemctl enable docker.service

docker info | grep "Cgroup Driver"
Cgroup Driver: systemd

yum install -y kubelet-1.20.15 kubeadm-1.20.15 kubectl-1.20.15

#配置Kubelet使用阿里云的pause镜像
cat > /etc/sysconfig/kubelet <<EOF
KUBELET_EXTRA_ARGS="--cgroup-driver=systemd --pod-infra-container-image=registry.cn-hangzhou.aliyuncs.com/google_containers/pause-amd64:3.2"
EOF

//开机自启kubelet
systemctl enable --now kubelet

-------------------- 高可用组件安装、配置 --------------------
//所有 master 节点部署 Haproxy
yum -y install haproxy keepalived

cat > /etc/haproxy/haproxy.cfg << EOF
global
log 127.0.0.1 local0 info
log 127.0.0.1 local1 warning
chroot /var/lib/haproxy
pidfile /var/run/haproxy.pid
maxconn 4000
user haproxy
group haproxy
daemon
stats socket /var/lib/haproxy/stats

defaults
mode tcp
log global
option tcplog
option dontlognull
option redispatch
retries 3
timeout queue 1m
timeout connect 10s
timeout client 1m
timeout server 1m
timeout check 10s
maxconn 3000

frontend monitor-in
bind *:33305
mode http
option httplog
monitor-uri /monitor

frontend k8s-master
bind *:16443
mode tcp
option tcplog
default_backend k8s-master

backend k8s-master
mode tcp
option tcplog
option tcp-check
balance roundrobin
server k8s-master1 192.168.80.10:6443 check inter 10000 fall 2 rise 2 weight 1
server k8s-master2 192.168.80.11:6443 check inter 10000 fall 2 rise 2 weight 1
server k8s-master3 192.168.80.12:6443 check inter 10000 fall 2 rise 2 weight 1
EOF

//所有 master 节点部署 keepalived
yum -y install keepalived

cd /etc/keepalived/
vim keepalived.conf
! Configuration File for keepalived
global_defs {
router_id LVS_HA1 #路由标识符，每个节点配置不同
}

vrrp_script chk_haproxy {
script "/etc/keepalived/check_haproxy.sh"
interval 2
weight 2
}

vrrp_instance VI_1 {
state MASTER #本机实例状态，MASTER/BACKUP，备机配置文件中设置BACKUP
interface ens33
virtual_router_id 51
priority 100 #本机初始权重，备机设置小于主机的值
advert_int 1
virtual_ipaddress {
192.168.80.100 #设置VIP地址
}
track_script {
chk_haproxy
}
}

vim check_haproxy.sh
#!/bin/bash
if ! killall -0 haproxy; then
systemctl stop keepalived
fi

systemctl enable --now haproxy
systemctl enable --now keepalived

-------------------- 部署K8S集群 --------------------
//在 master01 节点上设置集群初始化配置文件
kubeadm config print init-defaults > /opt/kubeadm-config.yaml

cd /opt/
vim kubeadm-config.yaml
......
11 localAPIEndpoint:
12 advertiseAddress: 192.168.80.10 #指定当前master节点的IP地址
13 bindPort: 6443

21 apiServer:
22 certSANs: #在apiServer属性下面添加一个certsSANs的列表，添加所有master节点的IP地址和集群VIP地址
23 - 192.168.80.100
24 - 192.168.80.10
25 - 192.168.80.11
26 - 192.168.80.12

30 clusterName: kubernetes
31 controlPlaneEndpoint: "192.168.80.100:6444" #指定集群VIP地址
32 controllerManager: {}

38 imageRepository: registry.cn-hangzhou.aliyuncs.com/google_containers           #指定镜像下载地址
39 kind: ClusterConfiguration
40 kubernetesVersion: v1.20.15               #指定kubernetes版本号
41 networking:
42 dnsDomain: cluster.local
43 podSubnet: "10.244.0.0/16"               #指定pod网段，10.244.0.0/16用于匹配flannel默认网段
44 serviceSubnet: 10.96.0.0/16           #指定service网段
45 scheduler: {}
#末尾再添加以下内容
---
apiVersion: kubeproxy.config.k8s.io/v1alpha1
kind: KubeProxyConfiguration
mode: ipvs                                   #把默认的kube-proxy调度方式改为ipvs模式

#更新集群初始化配置文件
kubeadm config migrate --old-config kubeadm-config.yaml --new-config new.yaml

//所有节点拉取镜像
#拷贝yaml配置文件给其他主机，通过配置文件进行拉取镜像
for i in master02 master03 node01 node02; do scp /opt/new.yaml $i:/opt/; done

kubeadm config images pull --config /opt/new.yaml

//master01 节点进行初始化
kubeadm init --config new.yaml --upload-certs | tee kubeadm-init.log
#提示：
.........
Your Kubernetes control-plane has initialized successfully!

To start using your cluster, you need to run the following as a regular user:

mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/config

Alternatively, if you are the root user, you can run:

export KUBECONFIG=/etc/kubernetes/admin.conf

You should now deploy a pod network to the cluster.
Run "kubectl apply -f [podnetwork].yaml" with one of the options listed at:
https://kubernetes.io/docs/concepts/cluster-administration/addons/

You can now join any number of the control-plane node running the following command on each as root:
#master节点加入使用的命令，记录！
kubeadm join 192.168.80.100:16443 --token 7t2weq.bjbawausm0jaxury \
--discovery-token-ca-cert-hash sha256:e76e4525ca29a9ccd5c24142a724bdb6ab86512420215242c4313fb830a4eb98 \
--control-plane --certificate-key 0f2a7ff2c46ec172f834e237fcca8a02e7c29500746594c25d995b78c92dde96

Please note that the certificate-key gives access to cluster sensitive data, keep it secret!
As a safeguard, uploaded-certs will be deleted in two hours; If necessary, you can use
"kubeadm init phase upload-certs --upload-certs" to reload certs afterward.

Then you can join any number of worker nodes by running the following on each as root:
#node节点加入使用的命令。记录！
kubeadm join 192.168.80.100:16443 --token 7t2weq.bjbawausm0jaxury \
--discovery-token-ca-cert-hash sha256:e76e4525ca29a9ccd5c24142a724bdb6ab86512420215242c4313fb830a4eb98

#若初始化失败，进行的操作
kubeadm reset -f
ipvsadm --clear
rm -rf ~/.kube
再次进行初始化

//master01 节点进行环境配置
#配置 kubectl
mkdir -p $HOME/.kube
cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
chown $(id -u):$(id -g) $HOME/.kube/config

#修改controller-manager和scheduler配置文件
vim /etc/kubernetes/manifests/kube-scheduler.yaml
vim /etc/kubernetes/manifests/kube-controller-manager.yaml
......
#- --port=0 #搜索port=0，把这一行注释掉

systemctl restart kubelet

#部署网络插件flannel
所有节点上传 flannel 镜像 flannel.tar 和网络插件 cni-plugins-linux-amd64-v0.8.6.tgz 到 /opt 目录，master节点上传 kube-flannel.yml 文件
cd /opt
docker load < flannel.tar

mv /opt/cni /opt/cni_bak
mkdir -p /opt/cni/bin
tar zxvf cni-plugins-linux-amd64-v0.8.6.tgz -C /opt/cni/bin

kubectl apply -f kube-flannel.yml

//所有节点加入集群
#master 节点加入集群
kubeadm join 192.168.80.100:16443 --token 7t2weq.bjbawausm0jaxury \
--discovery-token-ca-cert-hash sha256:e76e4525ca29a9ccd5c24142a724bdb6ab86512420215242c4313fb830a4eb98 \
--control-plane --certificate-key 0f2a7ff2c46ec172f834e237fcca8a02e7c29500746594c25d995b78c92dde96

mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/config

#node 节点加入集群
kubeadm join 192.168.80.100:16443 --token 7t2weq.bjbawausm0jaxury \
--discovery-token-ca-cert-hash sha256:e76e4525ca29a9ccd5c24142a724bdb6ab86512420215242c4313fb830a4eb98

#在 master01 查看集群信息
kubectl get nodes
NAME STATUS ROLES AGE VERSION
master01 Ready control-plane,master 2h5m v1.20.15
master02 Ready control-plane,master 2h5m v1.20.15
master03 Ready control-plane,master 2h5m v1.20.15
node01 Ready <none> 2h5m v1.20.15
node02 Ready <none> 2h5m v1.20.15

kubectl get pod -n kube-system
NAME READY STATUS RESTARTS AGE
coredns-74ff55c5b-4fg44 1/1 Running 2 2h5m
coredns-74ff55c5b-jsdxz 1/1 Running 0 2h5m
etcd-master01 1/1 Running 1 2h5m
etcd-master02 1/1 Running 1 2h5m
etcd-master03 1/1 Running 1 2h5m
kube-apiserver-master01 1/1 Running 1 2h5m
kube-apiserver-master02 1/1 Running 1 2h5m
kube-apiserver-master03 1/1 Running 1 2h5m
kube-controller-manager-master01 1/1 Running 3 2h5m
kube-controller-manager-master02 1/1 Running 1 2h5m
kube-controller-manager-master03 1/1 Running 2 2h5m
kube-flannel-ds-8qtx6 1/1 Running 2 2h4m
kube-flannel-ds-lmzdz 1/1 Running 0 2h4m
kube-flannel-ds-nb9qx 1/1 Running 1 2h4m
kube-flannel-ds-t4l4x 1/1 Running 1 2h4m
kube-flannel-ds-v592x 1/1 Running 1 2h4m
kube-proxy-6gd5j 1/1 Running 1 2h5m
kube-proxy-f8k96 1/1 Running 3 2h5m
kube-proxy-h7nrf 1/1 Running 1 2h5m
kube-proxy-j96b6 1/1 Running 1 2h5m
kube-proxy-mgmx6 1/1 Running 0 2h5m
kube-scheduler-master01 1/1 Running 1 2h5m
kube-scheduler-master02 1/1 Running 2 2h5m
kube-scheduler-master03 1/1 Running 2 2h5m

//问题解决
1、加入集群的 Token 过期
注意：Token值在集群初始化后，有效期为 24小时，过了24小时过期。进行重新生成Token，再次加入集群，新生成的Token为 2小时。

1.1、生成Node节点加入集群的 Token
kubeadm token create --print-join-command
kubeadm join 192.168.80.100:16443 --token menw99.1hbsurvl5fiz119n --discovery-token-ca-cert-hash sha256:e76e4525ca29a9ccd5c24142a724bdb6ab865 12420215242c4313fb830a4eb98

1.2、生成Master节点加入集群的 --certificate-key
kubeadm init phase upload-certs --upload-certs
I1105 12:33:08.201601 93226 version.go:254] remote version is much newer: v1.22.3; falling back to: stable-1.20
[upload-certs] Storing the certificates in Secret "kubeadm-certs" in the "kube-system" Namespace
[upload-certs] Using certificate key:
38dba94af7a38700c3698b8acdf8e23f273be07877f5c86f4977dc023e333deb

#master节点加入集群的命令
kubeadm join 192.168.80.100:16443 --token menw99.1hbsurvl5fiz119n --discovery-token-ca-cert-hash sha256:e76e4525ca29a9ccd5c24142a724bdb6ab86512420215242c4313fb830a4eb98 \
--control-plane --certificate-key 38dba94af7a38700c3698b8acdf8e23f273be07877f5c86f4977dc023e333deb

2、master节点无法部署非系统Pod
解析：主要是因为master节点被加上污点，污点是不允许部署非系统 Pod，在测试环境，可以将污点去除，节省资源，可利用率。

2.1、查看污点
kubectl describe node -l node-role.kubernetes.io/master= | grep Taints
Taints: node-role.kubernetes.io/master:NoSchedule
Taints: node-role.kubernetes.io/master:NoSchedule
Taints: node-role.kubernetes.io/master:NoSchedule

2.2、取消污点
kubectl taint node -l node-role.kubernetes.io/master node-role.kubernetes.io/master:NoSchedule-
node/master01 untainted
node/master02 untainted
node/master03 untainted

kubectl describe node -l node-role.kubernetes.io/master= | grep Taints
Taints: <none>
Taints: <none>
Taints: <none>

3、修改NodePort的默认端口
原理：默认k8s的使用端口的范围为30000左右，作为对外部提供的端口。我们也可以通过对配置文件的修改去指定默认的对外端口的范围。

#报错
The Service "nginx-svc" is invalid: spec.ports[0].nodePort: Invalid value: 80: provided port is not in the valid range. The range of valid ports is 30000-32767

[root@k8s-master1 ~]# vim /etc/kubernetes/manifests/kube-apiserver.yaml
- --service-cluster-ip-range=10.96.0.0/16
- --service-node-port-range=1-65535 #找到后进行添加即可

#无需重启，k8s会自动生效

4、外部 etcd 部署配置
kubeadm config print init-defaults > /opt/kubeadm-config.yaml

cd /opt/
vim 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: 192.168.80.14
bindPort: 6443
nodeRegistration:
criSocket: /var/run/dockershim.sock
name: master01
taints:
- effect: NoSchedule
key: node-role.kubernetes.io/master
---
apiServer:
certSANs:
- 10.96.0.1
- 127.0.0.1
- localhost
- kubernetes
- kubernetes.default
- kubernetes.default.svc
- kubernetes.default.svc.cluster.local
- 192.168.80.100
- 192.168.80.10
- 192.168.80.11
- 192.168.80.12
- master01
- master02
- master03
timeoutForControlPlane: 4m0s
apiVersion: kubeadm.k8s.io/v1beta2
certificatesDir: /etc/kubernetes/pki
clusterName: kubernetes
controlPlaneEndpoint: 192.168.80.100:16443
controllerManager: {}
dns:
type: CoreDNS
etcd:
external: #使用外部etcd的方式
endpoints:
- https://192.168.80.10:2379
- https://192.168.80.11:2379
- https://192.168.80.12:2379
caFile: /opt/etcd/ssl/ca.pem #需要把etcd的证书都复制到所有master节点上
certFile: /opt/etcd/ssl/server.pem
keyFile: /opt/etcd/ssl/server-key.pem
imageRepository: registry.cn-hangzhou.aliyuncs.com/google_containers
kind: ClusterConfiguration
kubernetesVersion: v1.20.15
networking:
dnsDomain: cluster.local
podSubnet: "10.244.0.0/16"
serviceSubnet: 10.96.0.0/16
scheduler: {}
---
apiVersion: kubeproxy.config.k8s.io/v1alpha1
kind: KubeProxyConfiguration
mode: ipvs

三 k8s1.25部署

------------------------------ 环境准备 ------------------------------
//所有节点，关闭防火墙规则，关闭selinux，关闭swap交换
systemctl stop firewalld
systemctl disable firewalld
setenforce 0
sed -i 's/enforcing/disabled/' /etc/selinux/config
iptables -F && iptables -t nat -F && iptables -t mangle -F && iptables -X
swapoff -a
sed -ri 's/.*swap.*/#&/' /etc/fstab
#加载 ip_vs 模块
for i in $(ls /usr/lib/modules/$(uname -r)/kernel/net/netfilter/ipvs|grep -o "^[^.]*");do echo $i; /sbin/modinfo -F filename $i >/dev/null 2>&1 && /sbin/modprobe $i;done

//修改主机名
hostnamectl set-hostname master01
hostnamectl set-hostname node01
hostnamectl set-hostname node02

//所有节点修改hosts文件
vim /etc/hosts
192.168.80.10 master01
192.168.80.11 node01
192.168.80.12 node02

//生效参数
sysctl --system

mkdir /etc/docker
cat > /etc/docker/daemon.json <<EOF
{
"registry-mirrors": ["https://6ijb8ubo.mirror.aliyuncs.com"],
"exec-opts": ["native.cgroupdriver=systemd"],
"log-driver": "json-file",
"log-opts": {
"max-size": "100m"
}
}
EOF
#使用Systemd管理的Cgroup来进行资源控制与管理，因为相对Cgroupfs而言，Systemd限制CPU、内存等资源更加简单和成熟稳定。
#日志使用json-file格式类型存储，大小为100M，保存在/var/log/containers目录下，方便ELK等日志系统收集和管理日志。

systemctl daemon-reload
systemctl restart docker.service
systemctl enable docker.service

docker info | grep "Cgroup Driver"
Cgroup Driver: systemd

//所有主机安装 cri-dockerd
Kubernetes自v1.24移除了对docker-shim的支持，而Docker Engine默认又不支持CRI规范，因而二者将无法直接完成整合。为此，Mirantis和Docker联合创建了cri-dockerd项目，用于为Docker Engine提供一个能够支持到CRI规范的垫片，从而能够让Kubernetes基于CRI控制Docker 。

项目地址：https://github.com/Mirantis/cri-dockerd

cd /opt/

wget https://github.com/Mirantis/cri-dockerd/releases/download/v0.2.6/cri-dockerd-0.2.6-3.el7.x86_64.rpm

yum localinstall -y cri-dockerd-0.2.6-3.el7.x86_64.rpm

vim /lib/systemd/system/cri-docker.service
#修改ExecStart行如下
ExecStart=/usr/bin/cri-dockerd --network-plugin=cni --pod-infra-container-image=registry.aliyuncs.com/google_containers/pause:3.8

systemctl daemon-reload
systemctl enable --now cri-docker

yum install -y kubelet-1.25.4 kubeadm-1.25.4 kubectl-1.25.4

kubeadm version

//开机自启kubelet
systemctl enable kubelet.service
#K8S通过kubeadm安装出来以后都是以Pod方式存在，即底层是以容器方式运行，所以kubelet必须设置开机自启

-------------------- 部署K8S集群 --------------------
//在 master01 节点上设置集群初始化配置文件
kubeadm config print init-defaults > /opt/kubeadm-config.yaml

cd /opt/
vim kubeadm-config.yaml
apiVersion: kubeadm.k8s.io/v1beta3
bootstrapTokens:
- groups:
- system:bootstrappers:kubeadm:default-node-token
token: abcdef.0123456789abcdef
ttl: 24h0m0s
usages:
- signing
- authentication
kind: InitConfiguration
localAPIEndpoint:
advertiseAddress: 192.168.80.10
bindPort: 6443
nodeRegistration:
criSocket: unix:///var/run/cri-dockerd.sock
imagePullPolicy: IfNotPresent
name: master01
taints:
- effect: NoSchedule
key: node-role.kubernetes.io/master
---
apiServer:
timeoutForControlPlane: 4m0s
apiVersion: kubeadm.k8s.io/v1beta3
certificatesDir: /etc/kubernetes/pki
clusterName: kubernetes
controllerManager: {}
dns: {}
etcd:
local:
dataDir: /var/lib/etcd
imageRepository: registry.aliyuncs.com/google_containers
kind: ClusterConfiguration
kubernetesVersion: v1.25.4
networking:
dnsDomain: cluster.local
podSubnet: 10.244.0.0/16
serviceSubnet: 10.96.0.0/16
scheduler: {}
---
apiVersion: kubeproxy.config.k8s.io/v1alpha1
kind: KubeProxyConfiguration
mode: ipvs

//查看初始化需要的镜像
kubeadm config images list --kubernetes-version 1.25.4

//所有节点拉取镜像
#拷贝yaml配置文件给其他主机，通过配置文件进行拉取镜像
for i in node01 node02; do scp /opt/kubeadm-config.yaml $i:/opt/; done

kubeadm config images pull --config /opt/kubeadm-config.yaml

//master01 节点初始化kubeadm
方法一：
kubeadm init --config=kubeadm-config.yaml --upload-certs | tee kubeadm-init.log
#--upload-certs 参数可以在后续执行加入节点时自动分发证书文件
#tee kubeadm-init.log 用以输出日志

//查看 kubeadm-init 日志
less kubeadm-init.log

//kubernetes配置文件目录
ls /etc/kubernetes/

//存放ca等证书和密码的目录
ls /etc/kubernetes/pki

方法二：
kubeadm init \
--apiserver-advertise-address=192.168.80.10 \
--image-repository registry.aliyuncs.com/google_containers \
--kubernetes-version v1.25.4 \
--service-cidr=10.96.0.0/16 \
--pod-network-cidr=10.244.0.0/16 \
--cri-socket /var/run/cri-dockerd.sock \
--upload-certs

--------------------------------------------------------------------------------------------
初始化集群需使用kubeadm init命令，可以指定具体参数初始化，也可以指定配置文件初始化。
可选参数：
--apiserver-advertise-address：apiserver通告给其他组件的IP地址，一般应该为Master节点的用于集群内部通信的IP地址，0.0.0.0表示节点上所有可用地址
--apiserver-bind-port：apiserver的监听端口，默认是6443
--cert-dir：通讯的ssl证书文件，默认/etc/kubernetes/pki
--control-plane-endpoint：多主节点必选项，用于指定控制平面的固定访问地址。注意:kubeadm不支持将没有--control-plane-endpoint参数的单个控制平面集群转换为高可用性集群
--image-repository：拉取镜像的镜像仓库，默认是k8s.gcr.io
--kubernetes-version：指定kubernetes版本
--pod-network-cidr：pod资源的网段，需与pod网络插件的值设置一致。Flannel网络插件的默认为10.244.0.0/16，Calico插件的默认值为192.168.0.0/16；
--service-cidr：service资源的网段
--service-dns-domain：service全域名的后缀，默认是cluster.local
--token-ttl：默认token的有效期为24小时，0表示永不过期
--cri-socket #v1.24版之后指定连接cri的socket文件路径,注意;不同的CRI连接文件不同
#如果是cRI是containerd，则使用--cri-socket unix:///run/containerd/containerd.sock
#如果是cRI是docker，则使用--cri-socket unix:///var/run/cri-dockerd.sock
#如果是CRI是CRI-o，则使用--cri-socket unix:///var/run/crio/crio.sock
#注意:CRI-o与containerd的容器管理机制不一样，所以镜像文件不能通用。
---------------------------------------------------------------------------------------------