Kubeadm - K8S1.20 - 高可用集群部署（博客）

Kubeadm - K8S1.20 - 高可用集群部署

一.环境准备

1.系统设置

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）

//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//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
192.168.82.100 master01
192.168.82.101 master02
192.168.82.102 master03
192.168.82.103 node01
192.168.82.104 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.comsystemctl enable --now crondcrontab -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.rpmcd /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=2310720net.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

二.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.iomkdir /etc/docker
cat > /etc/docker/daemon.json <<EOF
{"registry-mirrors": ["https://xxxxxxx.mirror.aliyuncs.com"],"exec-opts": ["native.cgroupdriver=systemd"],"log-driver": "json-file","log-opts": {"max-size": "500m", "max-file": "3"}
}
EOFsystemctl daemon-reload
systemctl restart docker.service
systemctl enable docker.service docker info | grep "Cgroup Driver"
Cgroup Driver: systemd

三.所有节点安装kubeadm，kubelet和kubectl

1.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
EOFyum 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

2.高可用组件安装、配置

//所有 master 节点部署 Haproxy
yum -y install haproxy keepalivedcat > /etc/haproxy/haproxy.cfg << EOF
globallog         127.0.0.1 local0 infolog         127.0.0.1 local1 warningchroot      /var/lib/haproxypidfile     /var/run/haproxy.pidmaxconn     4000user        haproxygroup       haproxydaemonstats socket /var/lib/haproxy/statsdefaultsmode                    tcplog                     globaloption                  tcplogoption                  dontlognulloption                  redispatchretries                 3timeout queue           1mtimeout connect         10stimeout client          1mtimeout server          1mtimeout check           10smaxconn                 3000frontend monitor-inbind *:33305mode httpoption httplogmonitor-uri /monitorfrontend k8s-masterbind *:6444   mode tcpoption tcplogdefault_backend k8s-masterbackend k8s-mastermode tcpoption tcplogoption tcp-checkbalance roundrobinserver k8s-master1 192.168.82.100:6443  check inter 10000 fall 2 rise 2 weight 1server k8s-master2 192.168.82.101:6443  check inter 10000 fall 2 rise 2 weight 1server k8s-master3 192.168.82.102:6443  check inter 10000 fall 2 rise 2 weight 1
EOF

//所有 master 节点部署 keepalived
yum -y install keepalivedcd /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 2weight 2
}vrrp_instance VI_1 {state MASTER				#本机实例状态，MASTER/BACKUP，备机配置文件中设置BACKUPinterface ens33virtual_router_id 51priority 100				#本机初始权重，备机设置小于主机的值advert_int 1virtual_ipaddress {192.168.82.200          #设置VIP地址}track_script {chk_haproxy}
}vim check_haproxy.sh
#!/bin/bash
if ! killall -0 haproxy; thensystemctl stop keepalived
fisystemctl enable --now haproxy
systemctl enable --now keepalived

四.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.yamlcd /opt/
vim kubeadm-config.yaml
......
11 localAPIEndpoint:
12   advertiseAddress: 192.168.82.100		#指定当前master节点的IP地址
13   bindPort: 6443                         #注意haproxy中的后端端口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   - 192.168.82.200
24   - 192.168.82.100
25   - 192.168.82.101
26   - 192.168.82.10230 clusterName: kubernetes
31 controlPlaneEndpoint: "192.168.82.200:6444"		#指定集群VIP地址，注意与haproxy的前端访问端口一致
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/; donekubeadm 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/.kubesudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/configsudo chown $(id -u):$(id -g) $HOME/.kube/configAlternatively, if you are the root user, you can run:export KUBECONFIG=/etc/kubernetes/admin.confYou 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 192.168.82.200:6444 --token 7t2weq.bjbawausm0jaxury \--discovery-token-ca-cert-hash sha256:e76e4525ca29a9ccd5c24142a724bdb6ab86512420215242c4313fb830a4eb98 \--control-plane --certificate-key 0f2a7ff2c46ec172f834e237fcca8a02e7c29500746594c25d995b78c92dde96Please 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 192.168.82.200:6444 --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.tarmv /opt/cni /opt/cni_bak
mkdir -p /opt/cni/bin
tar zxvf cni-plugins-linux-amd64-v0.8.6.tgz -C /opt/cni/binkubectl apply -f kube-flannel.yml //所有节点加入集群
#master 节点加入集群
kubeadm join 192.168.82.200:6444 --token 7t2weq.bjbawausm0jaxury \--discovery-token-ca-cert-hash sha256:e76e4525ca29a9ccd5c24142a724bdb6ab86512420215242c4313fb830a4eb98 \--control-plane --certificate-key 0f2a7ff2c46ec172f834e237fcca8a02e7c29500746594c25d995b78c92dde96mkdir -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 192.168.82.200:6444 --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   v1.20.15kubectl 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

五.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 192.168.82.200:16443 --token menw99.1hbsurvl5fiz119n     --discovery-token-ca-cert-hash sha256:e76e4525ca29a9ccd5c24142a724bdb6ab865	12420215242c4313fb830a4eb981.2、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 192.168.82.200:16443 --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:NoSchedule2.2、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 untaintedkubectl  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.yamlcd /opt/
vim kubeadm-config.yaml
apiVersion: kubeadm.k8s.io/v1beta2
bootstrapTokens:
- groups:- system:bootstrappers:kubeadm:default-node-tokentoken: abcdef.0123456789abcdefttl: 24h0m0susages:- signing- authentication
kind: InitConfiguration
localAPIEndpoint:advertiseAddress: 192.168.82.104bindPort: 6443
nodeRegistration:criSocket: /var/run/dockershim.sockname: master01taints:- effect: NoSchedulekey: 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- 192.168.82.200- 192.168.82.100- 192.168.82.101- 192.168.82.102- master01- master02- master03timeoutForControlPlane: 4m0s
apiVersion: kubeadm.k8s.io/v1beta2
certificatesDir: /etc/kubernetes/pki
clusterName: kubernetes
controlPlaneEndpoint: 192.168.82.200:16443
controllerManager: {}
dns:type: CoreDNS
etcd:external:                                #使用外部etcd的方式endpoints:- https://192.168.82.100:2379- https://192.168.82.101:2379- https://192.168.82.102:2379caFile: /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.pemkeyFile: /opt/etcd/ssl/server-key.pem
imageRepository: registry.cn-hangzhou.aliyuncs.com/google_containers
kind: ClusterConfiguration
kubernetesVersion: v1.20.15
networking:dnsDomain: cluster.localpodSubnet: "10.244.0.0/16"serviceSubnet: 10.96.0.0/16
scheduler: {}
---
apiVersion: kubeproxy.config.k8s.io/v1alpha1
kind: KubeProxyConfiguration
mode: ipvs