一、系统设置

环境

[root@st01015vm192 /]# cat /etc/redhat-release
CentOS Linux release 7.7.1908 (Core)
[root@st01015vm192 /]# uname -a
Linux st01015vm192 3.10.0-957.el7.x86_64 #1 SMP Thu Nov 8 23:39:32 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux

默认为root用户安装

1、关闭swap

临时关闭swap

swapoff -a

永久关闭
注释掉 /etc/fstab 中的下面配置

#/dev/mapper/centos-swap swap                    swap    defaults        0 0

2、 关闭SELinux

kubelet不支持SELinux, 这里需要将SELinux设置为permissive模式

# 查看状态
# /usr/sbin/sestatus -v  
setenforce 0
sed -i 's/^SELINUX=enforcing$/SELINUX=permissive/' /etc/selinux/config

3、关闭防火墙

systemctl disable firewalld
systemctl stop firewalld

4、配置sysctl

创建文件/etc/sysctl.d/k8s.conf， 文件内容如下

net.bridge.bridge-nf-call-ip6tables = 1
net.bridge.bridge-nf-call-iptables = 1

net.ipv4.ip_forward = 1

执行

sysctl -p /etc/sysctl.d/k8s.conf

在RHEL/CentOS 7上由于 iptables 被绕过导致网络请求被错误的路由。您得保证 在您的 sysctl 配置中 net.bridge.bridge-nf-call-iptables 被设为1。
插件将容器连接到 Linux 网桥，插件必须将 net/bridge/bridge-nf-call-iptables 系统参数设置为1，以确保 iptables 代理正常工作。

最后，在内核中启用了 IP 转发（因此内核将处理桥接容器的数据包）：
sysctl net.ipv4.ip_forward=1
所有这些的结果是所有 Pods 都可以互相访问，并且可以将流量发送到互联网。

k8s网络插件
https://kubernetes.io/zh/docs/concepts/extend-kubernetes/compute-storage-net/network-plugins/

k8s 网络模型
https://kubernetes.io/zh/docs/concepts/cluster-administration/networking/

5、配置安装源为阿里

5.1 配置yum安装源

## 备份
mv /etc/yum.repos.d/CentOS-Base.repo /etc/yum.repos.d/CentOS-Base.repo.backup
## 下载阿里源
wget -O /etc/yum.repos.d/CentOS-Base.repo http://mirrors.aliyun.com/repo/Centos-7.repo

5.2 配置k8s源

vim /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

5.3 重建yum缓存

yum clean all
yum makecache fast
yum -y update

二、安装docker

1、安装docker

可以参考官网文档 https://docs.docker.com/engine/install/centos/

• 卸载旧版本

yum remove docker \
           docker-client \
           docker-client-latest \
           docker-common \
           docker-latest \
           docker-latest-logrotate \
           docker-logrotate \
           docker-engine

• 安装docker

yum install -y yum-utils device-mapper-persistent-data lvm2
yum-config-manager \
    --add-repo http://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo

yum install -y docker-ce docker-ce-cli containerd.io

如果想要安装指定版本docker

yum list docker-ce --showduplicates | sort -r
sudo yum install docker-ce-<VERSION_STRING> docker-ce-cli-<VERSION_STRING> containerd.io

2、docker配置

创建文件/etc/docker/daemon.json，写入配置
mkdir /etc/docker/
vim /etc/docker/daemon.json

{
  "exec-opts": ["native.cgroupdriver=systemd"],
  "log-driver": "json-file",
  "log-opts": {
    "max-size": "100m"
  },
//   如果在国内安装，添加以下配置
//   "registry-mirrors": [
//     "https://registry.docker-cn.com"
//   ],
  "storage-driver": "overlay2",
  "storage-opts": [
    "overlay2.override_kernel_check=true"
  ]
}

国内docker源

 "registry-mirrors": [
        "https://1nj0zren.mirror.aliyuncs.com",
        "https://docker.mirrors.ustc.edu.cn",
        "http://f1361db2.m.daocloud.io",
        "https://registry.docker-cn.com"
    ]

3、重启docker

mkdir -p /etc/systemd/system/docker.service.d
systemctl daemon-reload
systemctl restart docker

可能会报错，docker.service failed

[root@st01015vm193 ~]# journalctl -xe 
May 08 15:36:09 st01015vm193 systemd[1]: Dependency failed for Docker Application Container Engine.
-- Subject: Unit docker.service has failed
-- Defined-By: systemd
-- Support: http://lists.freedesktop.org/mailman/listinfo/systemd-devel
-- 
-- Unit docker.service has failed.
-- 
-- The result is dependency.
May 08 15:36:09 st01015vm193 systemd[1]: Job docker.service/start failed with result 'dependency'.
May 08 15:36:09 st01015vm193 systemd[1]: Unit docker.socket entered failed state.

需要给系统添加一个docker组，如果做过基线配置的话，会提示没有权限，使用 chattr -i 增加一下权限

chattr -i /etc/group
groupadd docker
systemctl enable docker  && systemctl start docker

三、集群安装

1、安装kubeadm, kubelet和kubectl

yum install -y kubelet kubeadm kubectl kubernetes-cni --disableexcludes=kubernetes
systemctl enable --now kubelet && systemctl start kubelet

2、使用kubeadm创建集群

只在master节点执行

# master节点执行：
kubeadm init \
 --apiserver-advertise-address 10.10.45.192 \
 --pod-network-cidr=10.244.0.0/16
# --kubernetes-version=v1.15.0 \
# --image-repository=registry.aliyuncs.com/google_containers
# --apiserver-advertise-address 指定与其它节点通信的接口
# --pod-network-cidr 指定pod网络子网，使用fannel网络必须使用这个CIDR

可能会报错如下

[root@st01015vm192 ~]# kubeadm init \
>  --apiserver-advertise-address 10.10.45.192 \
>  --pod-network-cidr=10.244.0.0/16
W0508 15:09:35.577282   28115 configset.go:202] WARNING: kubeadm cannot validate component configs for API groups [kubelet.config.k8s.io kubeproxy.config.k8s.io]
[init] Using Kubernetes version: v1.18.2
[preflight] Running pre-flight checks
error execution phase preflight: [preflight] Some fatal errors occurred:
	[ERROR FileAvailable--etc-kubernetes-manifests-kube-apiserver.yaml]: /etc/kubernetes/manifests/kube-apiserver.yaml already exists
	[ERROR FileAvailable--etc-kubernetes-manifests-kube-controller-manager.yaml]: /etc/kubernetes/manifests/kube-controller-manager.yaml already exists
	[ERROR FileAvailable--etc-kubernetes-manifests-kube-scheduler.yaml]: /etc/kubernetes/manifests/kube-scheduler.yaml already exists
	[ERROR FileAvailable--etc-kubernetes-manifests-etcd.yaml]: /etc/kubernetes/manifests/etcd.yaml already exists
	[ERROR Swap]: running with swap on is not supported. Please disable swap
	[ERROR DirAvailable--var-lib-etcd]: /var/lib/etcd is not empty
[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

加入这个参数：–ignore-preflight-errors=all

报错如下

[kubelet-check] It seems like the kubelet isn't running or healthy.
[kubelet-check] The HTTP call equal to 'curl -sSL http://localhost:10248/healthz' failed with error: Get http://localhost:10248/healthz: dial tcp [::1]:10248: connect: connection refused.

一般情况下是kubelet启动失败，查看状态如日志，查找原因，我这里是swap临时关闭的，导致机器重启后swap被打开了：
systemctl status kubelet
journalctl -xeu kubelet

安装成功后，有如下打印

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 10.10.45.192:6443 --token 82scon.3zopf5qra2b1s25i \
    --discovery-token-ca-cert-hash sha256:2ea38c2a269d105b09bbf2964c089c067f0c8e7b44c0504b5854fd9acac263e0 

3、用户设置权限(root用户也需要执行)

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

4、应用flannel网络

sudo kubectl apply -f https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml
## 查看flannal是否安装成功
sudo kubectl -n kube-system get po -l app=flannel -o wide

5、节点加入

按照在master节点上构建集群后的打印，执行节点加入集群操作
kubeadm join 10.10.45.192:6443 --token 82scon.3zopf5qra2b1s25i
–discovery-token-ca-cert-hash sha256:2ea38c2a269d105b09bbf2964c089c067f0c8e7b44c0504b5854fd9acac263e0

W0508 15:42:29.235510    5131 join.go:346] [preflight] WARNING: JoinControlPane.controlPlane settings will be ignored when control-plane flag is not set.
[preflight] Running pre-flight checks
	[WARNING Hostname]: hostname "st01015vm194" could not be reached
	[WARNING Hostname]: hostname "st01015vm194": lookup st01015vm194 on 192.168.16.24:53: no such host

修改/etc/hosts，添加hosts

10.10.45.192 st01015vm192
10.10.45.193 st01015vm193
10.10.45.194 st01015vm194

分别在节点上执行加入集群操作，执行完成后，在master节点上查看节点状态：

[root@st01015vm192 ~]# kubectl get nodes
NAME           STATUS     ROLES    AGE     VERSION
st01015vm192   Ready      master   16d     v1.18.2
st01015vm193   NotReady   <none>   29s     v1.18.2
st01015vm194   NotReady   <none>   6m43s   v1.18.2

发现节点状态一直是NotReady，检查pod状态
kubectl get pods -n kube-system -o wide

kube-flannel-ds-amd64-sdvpf            0/1     Init:ImagePullBackOff   0          8m12s   10.10.45.193   st01015vm193   <none>           <none>
kube-flannel-ds-amd64-x58td            0/1     Init:ImagePullBackOff   0          14m     10.10.45.194   st01015vm194   <none>           <none>

发现子节点上的flannel pod报错，查看详细信息
kubectl describe pod -n kube-system kube-flannel-ds-amd64-sdvpf

Events:
  Type     Reason     Age                    From                   Message
  ----     ------     ----                   ----                   -------
  Normal   Scheduled  <unknown>              default-scheduler      Successfully assigned kube-system/kube-flannel-ds-amd64-sdvpf to st01015vm193
  Warning  Failed     2m22s (x2 over 4m33s)  kubelet, st01015vm193  Failed to pull image "quay.io/coreos/flannel:v0.12.0-amd64": rpc error: code = Unknown desc = context canceled
  Warning  Failed     2m22s (x2 over 4m33s)  kubelet, st01015vm193  Error: ErrImagePull
  Normal   BackOff    2m11s (x2 over 4m33s)  kubelet, st01015vm193  Back-off pulling image "quay.io/coreos/flannel:v0.12.0-amd64"
  Warning  Failed     2m11s (x2 over 4m33s)  kubelet, st01015vm193  Error: ImagePullBackOff
  Normal   Pulling    118s (x3 over 7m28s)   kubelet, st01015vm193  Pulling image "quay.io/coreos/flannel:v0.12.0-amd64"

Event中显示镜像拉取失败，这个可能是网络问题，pod运行失败后，会尝试重新运行，所以耐心等待一会，或者在失败的节点上手动拉取一下镜像，并且修改deployment中的imagePullPolicy: Always

By default, the kubelet will try to pull each image from the specified registry. However, if the imagePullPolicy property of the container is set to IfNotPresent or Never, then a local image is used (preferentially or exclusively, respectively).

修改为 imagePullPolicy: IfNotPresent

docker pull quay.io/coreos/flannel:v0.12.0-amd64

[root@st01015vm192 ~]# kubectl get nodes
NAME           STATUS   ROLES    AGE   VERSION
st01015vm192   Ready    master   17d   v1.18.2
st01015vm193   Ready    <none>   33m   v1.18.2
st01015vm194   Ready    <none>   39m   v1.18.2

四、安装网页界面 (Dashboard)

默认情况下不会部署 Dashboard。可以通过以下命令部署：

kubectl apply -f https://raw.githubusercontent.com/kubernetes/dashboard/v2.0.0/aio/deploy/recommended.yaml
为了保护您的集群数据，默认情况下，Dashboard 会使用最少的 RBAC 配置进行部署。 当前，Dashboard 仅支持使用 Bearer 令牌登录。

所以，我们需要下载yaml并进行配置
我们将以下配置进行修改

kind: Service
apiVersion: v1
metadata:
  labels:
    k8s-app: kubernetes-dashboard
  name: kubernetes-dashboard
  namespace: kubernetes-dashboard
spec:
  ports:
    - port: 443
      targetPort: 8443

  selector:
    k8s-app: kubernetes-dashboard

修改后如下

kind: Service
apiVersion: v1
metadata:
  labels:
    k8s-app: kubernetes-dashboard
  name: kubernetes-dashboard
  namespace: kubernetes-dashboard
spec:
  type: NodePort
  ports:
    - port: 443
      targetPort: 8443
      nodePort: 30001
  selector:
    k8s-app: kubernetes-dashboard

修改镜像拉取策略为IfNotPresent或Never，并在k8s所有节点上拉取镜像，这一步是为了避免pod创建时因为网络原因拉取镜像失败
docker pull kubernetesui/metrics-scraper:v1.0.4
docker pull kubernetesui/dashboard:v2.0.0

如果某一台机器上已经拉取镜像成功了，而其他机器一直拉取不成功，可以将镜像备份后在不成功的机器上还原
备份

docker save -o dashboard.tar kubernetesui/dashboard:v2.0.0
docker save -o metrics-scraper.tar kubernetesui/metrics-scraper:v1.0.4

还原

docker load -i dashboard.tar 
docker load -i metrics-scraper.tar 

应用

kubectl apply -f recommended.yaml

检查状态

kubectl get pod,svc,ing,deploy -n kubernetes-dashboard

待所有pod都运行起来后，查看

https://10.10.45.192:30001/

安装完成后，在master节点上获取token

[root@st01015vm192 ~]# kubectl -n kubernetes-dashboard  get secret
NAME                               TYPE                                  DATA   AGE
default-token-25jb9                kubernetes.io/service-account-token   3      23m
kubernetes-dashboard-certs         Opaque                                0      23m
kubernetes-dashboard-csrf          Opaque                                1      23m
kubernetes-dashboard-key-holder    Opaque                                2      23m
kubernetes-dashboard-token-fm795   kubernetes.io/service-account-token   3      23m
[root@st01015vm192 ~]# kubectl -n kubernetes-dashboard describe  secret kubernetes-dashboard-token-fm795
Name:         kubernetes-dashboard-token-fm795
Namespace:    kubernetes-dashboard
Labels:       <none>
Annotations:  kubernetes.io/service-account.name: kubernetes-dashboard
              kubernetes.io/service-account.uid: af7a61cf-901f-42f9-bcbe-6f521d026bc2

Type:  kubernetes.io/service-account-token

Data
====
ca.crt:     1025 bytes
namespace:  20 bytes
token:      eyJhbGciOiJSUzI1NiIsImtpZCI6IlhCZGZQa0MtaVFmMHJ0YTRBS083emppS0tKSENvb24xeW9scHIxY19zU0kifQ.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.haW6XvBAyog0BasqbaWJxPqWjTJKiemVBwP3J8dwFE43Q93Jx41yjxK41NRNaUflL8xL3Aj4CNIJ0YUQwlpIutIzOJq7rXWkneRI6tmgr3jsCarFtjwETph7-spg-WQAHXRQxt7hwMyxcNkJprEc13q6zGO_ycx9ei_hjjliXo0O8JMuQsL0rlm2zXrWOpRer5U77Hj33dnVSGrjvlD3X_5NsI0dlzG2MmKMFZHM0_PVbYFnSvWcEmLl_04_u5CJPtPfp9Pu6RTjy1lMOZtsHgBxqDC-oXxm0UP2Tcn2qlu_UDfIPhiL3r-QrwWFy7b3WpxJCcXwcm07pfUzijQ77A

在 https://10.10.45.192:30001/ 上使用token登录即可。

参考资料

https://my.oschina.net/u/2539854/blog/3023384
https://juejin.im/post/5d089f49f265da1baa1e7611