使用Vagrant安装Kubernetes(1.21.4)集群

Kubernetes集群安装

使用Vagrant安装Kubernetes集群

本教程参照 https://kuboard.cn/install/install-k8s.html#%E6%96%87%E6%A1%A3%E7%89%B9%E7%82%B9做了部分修改

1. 准备Vagrant文件，使用k8s/base作为镜像，该镜像安装了docker和1.21.4版本的kubectl、kubelet和kubeadm，Vagrant文件内容如下(请勿对以下文件做任何修改):

# -*- mode: ruby -*-
# vi: set ft=ruby :

Vagrant.require_version ">= 1.6.0"

boxes = [
    {
        :name => "k8s-master",
        :eth1 => "192.168.100.200",
        :mem => "2048",
        :cpu => "2"
    },
    {
        :name => "k8s-node1",
        :eth1 => "192.168.100.201",
        :mem => "1024",
        :cpu => "2"
    }

]

Vagrant.configure(2) do |config|

  config.vm.box = "k8s/base"
  config.ssh.username = "root"
  config.ssh.password = "root"
  boxes.each do |opts|
    config.vm.define opts[:name] do |config|
      config.vm.hostname = opts[:name]
      config.vm.provider "vmware_fusion" do |v|
        v.vmx["memsize"] = opts[:mem]
        v.vmx["numvcpus"] = opts[:cpu]
      end
      config.vm.provider "virtualbox" do |v|
        v.customize ["modifyvm", :id, "--memory", opts[:mem]]
        v.customize ["modifyvm", :id, "--cpus", opts[:cpu]]
      end
      config.vm.network :private_network, ip: opts[:eth1]
    end
  end
end

2. 使用 vagrant up命令启动服务器，服务器启动完成后使用以下命令读取docker镜像:

# 注意，该步骤并非是必须的，可以跳过，预先导入仅仅是因为部分镜像下载较慢
docker load -i coredns.tar
docker load -i etcd.tar
docker load -i flannel.tar
docker load -i kube-apiserver.tar
docker load -i kube-controller-manager.tar
docker load -i kube-proxy.tar
docker load -i kube-scheduler.tar
docker load -i tigera-operator.tar

3. 新建 init_master.sh文件，内容如下:

#!/bin/bash

# 只在 master 节点执行

# 脚本出错时终止执行
set -e

if [ ${#POD_SUBNET} -eq 0 ] || [ ${#APISERVER_NAME} -eq 0 ]; then
  echo -e "\033[31;1m请确保您已经设置了环境变量 POD_SUBNET 和 APISERVER_NAME \033[0m"
  echo 当前POD_SUBNET=$POD_SUBNET
  echo 当前APISERVER_NAME=$APISERVER_NAME
  exit 1
fi


# 查看完整配置选项 https://godoc.org/k8s.io/kubernetes/cmd/kubeadm/app/apis/kubeadm/v1beta2
rm -f ./kubeadm-config.yaml
cat <<EOF > ./kubeadm-config.yaml
---
apiVersion: kubeadm.k8s.io/v1beta2
kind: InitConfiguration
localAPIEndpoint:
  advertiseAddress: "${MASTER_IP}"
  bindPort: 6443
---
apiVersion: kubeadm.k8s.io/v1beta2
kind: ClusterConfiguration
kubernetesVersion: v${1}
imageRepository: registry.aliyuncs.com/k8sxio
controlPlaneEndpoint: "${APISERVER_NAME}:6443"
networking:
  serviceSubnet: "10.96.0.0/16"
  podSubnet: "${POD_SUBNET}"
  dnsDomain: "cluster.local"
dns:
  type: CoreDNS
  imageRepository: swr.cn-east-2.myhuaweicloud.com${2}
  imageTag: 1.8.0

---
apiVersion: kubelet.config.k8s.io/v1beta1
kind: KubeletConfiguration
cgroupDriver: systemd
EOF

# kubeadm init
# 根据您服务器网速的情况，您需要等候 3 - 10 分钟
echo ""
echo "抓取镜像，请稍候..."
kubeadm config images pull --config=kubeadm-config.yaml
echo ""
echo "初始化 Master 节点"
kubeadm init --config=kubeadm-config.yaml --upload-certs

# 配置 kubectl
rm -rf /root/.kube/
mkdir /root/.kube/
cp -i /etc/kubernetes/admin.conf /root/.kube/config

4. 执行以下命令，初始化kubernetes主节点:

export MASTER_IP=192.168.100.200
export APISERVER_NAME=apiserver.dns
export POD_SUBNET=10.100.0.0/16
echo "${MASTER_IP}    ${APISERVER_NAME}" >> /etc/hosts
./init_master.sh 1.21.4 /coredns

5. 安装网络插件

export POD_SUBNET=10.100.0.0/16
kubectl apply -f https://kuboard.cn/install-script/v1.21.x/calico-operator.yaml

新建flannel-v0.14.0.yaml文件，内容如下:

---
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": "10.100.0.0/16",
      "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: quay.io/coreos/flannel:v0.14.0
        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: quay.io/coreos/flannel:v0.14.0
        command:
        - /opt/bin/flanneld
        args:
        - --ip-masq=false
        - --kube-subnet-mgr
        - --iface=enp0s8
        resources:
          requests:
            cpu: "100m"
            memory: "50Mi"
          limits:
            cpu: "100m"
            memory: "50Mi"
        securityContext:
          privileged: true
          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

此处注意，args下添加--iface=enp0s8参数，主要是指定对应的网卡，因为virtualbox指定了两张网卡，其中NAT网卡虚拟机之间是无法通讯的，需指定Host-Only网卡，否则集群pod之间无法通讯，此处的enp0s8即Host-Only对应的网卡，请按照实际填写。

## 执行下面命令，完成网络初始化
kubectl apply -f ./flannel-v0.14.0.yaml

## 执行下面命令，查看集群运行状态
kubectl get pod -n kube-system -o wide


## 如果是下面的样子，说明集群初始化完成
NAME                                 READY   STATUS    RESTARTS   AGE     IP                NODE         NOMINATED NODE   READINESS GATES
coredns-7d75679df-gg8bc              1/1     Running   0          4m15s   10.100.0.2        k8s-master   <none>           <none>
coredns-7d75679df-n47fx              1/1     Running   0          4m15s   10.100.0.3        k8s-master   <none>           <none>
etcd-k8s-master                      1/1     Running   0          4m28s   192.168.100.200   k8s-master   <none>           <none>
kube-apiserver-k8s-master            1/1     Running   0          4m28s   192.168.100.200   k8s-master   <none>           <none>
kube-controller-manager-k8s-master   1/1     Running   0          4m28s   192.168.100.200   k8s-master   <none>           <none>
kube-flannel-ds-m4pl4                1/1     Running   0          28s     192.168.100.200   k8s-master   <none>           <none>
kube-proxy-vlqwt                     1/1     Running   0          4m16s   192.168.100.200   k8s-master   <none>           <none>
kube-scheduler-k8s-master            1/1     Running   0          4m28s   192.168.100.200   k8s-master   <none>           <none>

6. Worker节点初始化

# 现在 master 节点执行，获取加入集群的命令
kubeadm token create --print-join-command

# 只在 worker 节点执行
export MASTER_IP=192.168.100.200
export APISERVER_NAME=apiserver.dns
echo "${MASTER_IP}    ${APISERVER_NAME}" >> /etc/hosts

# 替换为 master 节点上 kubeadm token create 命令的输出
kubeadm join apiserver.dns:6443 --token mpfjma.4vjjg8flqihor4vt     --discovery-token-ca-cert-hash sha256:6f7a8e40a810323672de5eee6f4d19aa2dbdb38411845a1bf5dd63485c43d303

7. 检查集群初始化结果

# 只在 master 节点执行
kubectl get nodes

##出现以下打印，说明集群加入worker节点成功
NAME         STATUS   ROLES                  AGE   VERSION
k8s-master   Ready    control-plane,master   15m   v1.21.4
k8s-node1    Ready    <none>                 35s   v1.21.4

8. 注：如果不使用k8s/base镜像，可以在系统初始化完成后执行以下脚本(保存为install_kubelet.sh，然后执行 ./install_kubelet.sh 1.21.4; 1.21.4为kubelet版本号，请勿修改):

# 请根据实际情况修改
#!/bin/bash

# 在 master 节点和 worker 节点都要执行

# 指定镜像源
export REGISTRY_MIRROR=https://registry.cn-hangzhou.aliyuncs.com

# 设置hosts
cat >> /etc/hosts << EOF
192.168.100.200 k8s-master
192.168.100.201 k8s-node1
192.168.100.202 k8s-node2
EOF

# Apply sysctl params without reboot
cat > /etc/sysctl.d/k8s.conf << EOF
net.bridge.bridge-nf-call-ip6tables = 1
net.bridge.bridge-nf-call-iptables = 1
EOF
sysctl --system


# 设置 yum repository
yum install -y yum-utils device-mapper-persistent-data lvm2

wget https://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo -O /etc/yum.repos.d/docker-ce.repo

# 安装docker
yum install -y docker-ce-20.10.8-3.el7.x86_64

mkdir -p /etc/docker
cat <<EOF | sudo tee /etc/docker/daemon.json
{
  "exec-opts": ["native.cgroupdriver=systemd"],
  "log-driver": "json-file",
  "registry-mirrors": ["https://b9pmyelo.mirror.aliyuncs.com"],
  "log-opts": {
    "max-size": "100m"
  },
  "storage-driver": "overlay2"
}
EOF

sudo systemctl enable docker
sudo systemctl daemon-reload
sudo systemctl restart docker


# 安装 nfs-utils
# 必须先安装 nfs-utils 才能挂载 nfs 网络存储
yum install -y nfs-utils
yum install -y wget

# 关闭 防火墙
systemctl stop firewalld
systemctl disable firewalld

# 关闭 SeLinux
setenforce 0
sed -i "s/SELINUX=enforcing/SELINUX=disabled/g" /etc/selinux/config

# 关闭 swap
swapoff -a
yes | cp /etc/fstab /etc/fstab_bak
cat /etc/fstab_bak |grep -v swap > /etc/fstab

# 配置K8S的yum源
cat <<EOF > /etc/yum.repos.d/kubernetes.repo
[kubernetes]
name=Kubernetes
baseurl=http://mirrors.aliyun.com/kubernetes/yum/repos/kubernetes-el7-x86_64
enabled=1
gpgcheck=0
repo_gpgcheck=0
gpgkey=http://mirrors.aliyun.com/kubernetes/yum/doc/yum-key.gpg
       http://mirrors.aliyun.com/kubernetes/yum/doc/rpm-package-key.gpg
EOF

# 卸载旧版本
yum remove -y kubelet kubeadm kubectl

# 安装kubelet、kubeadm、kubectl
# 将 ${1} 替换为 kubernetes 版本号，例如 1.20.1
yum install -y kubelet-${1} kubeadm-${1} kubectl-${1}

# 重启 docker，并启动 kubelet
systemctl daemon-reload
systemctl enable kubelet && systemctl start kubelet

docker --version
kubelet --version

9. 所有涉及到的文件:

链接: https://pan.baidu.com/s/11fuFjBw-xDYkWZSYXNmkIQ 提取码: s26o 

可能存在的问题:

1. 虚拟机重启后flannel网络不通:

目前还不知道该问题的原因，但是重启docker可以解决问题。

systemctl daemon-reload
systemctl restart docker