本文将搭建一套master-node-node k8s集群环境，需要准备三台至少cpu > 2G, mem > 2G的虚拟机，步骤如下：
1. 在所有节点配置hosts并节点间的连接性
#分别在三个节点配置host，示例为master节点的配置
root@k8s-master01:~# hostnamectl set-hostname k8s-master01
root@k8s-master01:~# cat /etc/hosts
127.0.0.1 localhost
# The following lines are desirable for IPv6 capable hosts
::1 localhost ip6-localhost ip6-loopback
ff02::1 ip6-allnodes
ff02::2 ip6-allrouters
127.0.1.1 s02g07017.cloud.em160.tbsite.net s02g07017
172.18.8.211 k8s001 k8s001
172.18.8.211 k8s-master01
172.18.8.210 k8s-node01
172.18.8.212 k8s-node02
#确保节点间的连接性
root@k8s-master01:~# ping k8s-node1
root@k8s-master01:~# ping k8s-node01
root@k8s-master01:~# ping k8s-node02
2. 在所有节点安装所需应用
#安装依赖包
root@k8s-master01:~# apt-get update
root@k8s-master01:~# apt-get install conntrack ipvsadm ipset jq iptables curl sysstat libseccomp2 wget vim net-tools git
#关闭防火墙
root@k8s-master01:~# systemctl stop firewalld
root@k8s-master01:~# iptables -F ; service iptables save
#disable swap分区，以免pod运行在swap中
root@k8s-master01:~# setenforce 0 && sed -i 's/^SELINUX=.*/SELINUX=disabled/' /etc/selinux/config
setenforce: SELinux is disabled
#配置kubernetes.conf，调整内核参数，【可选
root@k8s-master01:/home/whq# cat > kubernetes.conf <<EOF
> net.bridge.bridge-nf-call-iptables=1 # 开启网桥模式
> net.bridge.bridge-nf-call-ip6tables=1 # 开启网桥模式
> 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 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
> fs.nr_open=52706963
> net.ipv6.conf.all.disable_ipv6=1 # 关闭IPV6协议
> net.netfilter.nf_conntrack_max=2310720
> EOF
root@k8s-master01:/home/whq# cp kubernetes.conf /etc/sysctl.d/kubernetes.conf
root@k8s-master01:/home/whq# sysctl -p /etc/sysctl.d/kubernetes.conf
#kube-proxy开启ipvs的前置条件
root@k8s-master01:/home/whq# modprobe br_netfilter
root@k8s-master01:/home/whq# vi /etc/modules 添加以下内容
modprobe -- ip_vs
modprobe -- ip_vs_rr
modprobe -- ip_vs_wrr
modprobe -- ip_vs_sh
#modprobe -- nf_conntrack_ipv4
modprobe -- nf_conntrack
root@k8s-master01:/home/whq# chmod 755 /etc/modules
root@k8s-master01:/home/whq# bash /etc/modules
modprobe: FATAL: Module nf_conntrack_ipv4 not found in directory /lib/modules/5.4.0-77-generic
root@k8s-master01:/home/whq# chmod 755 /etc/modules && bash /etc/modules && lsmod | grep -e ip_vs -e nf_conntrack
ip_vs_sh 16384 0
ip_vs_wrr 16384 0
ip_vs_rr 16384 0
ip_vs 155648 6 ip_vs_rr,ip_vs_sh,ip_vs_wrr
nf_conntrack 139264 1 ip_vs
nf_defrag_ipv6 24576 2 nf_conntrack,ip_vs
libcrc32c 16384 2 nf_conntrack,ip_vs
#安装docker
root@k8s-master01:/home/whq# sudo apt-get install \
> apt-transport-https \
> ca-certificates \
> curl \
> gnupg-agent \
> software-properties-common
root@k8s-master01:/home/whq# sudo add-apt-repository \
> "deb [arch=amd64] https://mirrors.ustc.edu.cn/docker-ce/linux/ubuntu/ \
> $(lsb_release -cs) \
> stable"
root@k8s-master01:/home/whq# sudo apt-get install docker-ce docker-ce-cli containerd.io
root@k8s-master01:/home/whq# sudo add-apt-repository "deb [arch=amd64] https://mirrors.ustc.edu.cn/docker-ce/linux/ubuntu/ \
$(lsb_release -cs) \
root@k8s-master01:/home/whq# cat > /etc/docker/daemon.json <<EOF
> {
> "registry-mirrors": ["https://fxr0bix2.mirror.aliyuncs.com"],
> "exec-opts": ["native.cgroupdriver=systemd"],
> "log-driver": "json-file",
> "log-opts": {
> "max-size": "100m"
> }
> }
> EOF
root@k8s-master01:/home/whq# mkdir -p /etc/systemd/system/docker.service.d
root@k8s-master01:/home/whq# systemctl daemon-reload && systemctl restart docker && systemctl enable docker
Synchronizing state of docker.service with SysV service script with /lib/systemd/systemd-sysv-install.
Executing: /lib/systemd/systemd-sysv-install enable docker
#安装kubeadm, kubectl, kubelet
root@k8s-master01:/usr/local/dockerjdk8# curl -s https://mirrors.aliyun.com/kubernetes/apt/doc/apt-key.gpg | sudo apt-key add -
OK
root@k8s-master01:/usr/local/dockerjdk8# sudo tee /etc/apt/sources.list.d/kubernetes.list <<EOF
> deb https://mirrors.aliyun.com/kubernetes/apt/ kubernetes-xenial main
> EOF
deb https://mirrors.aliyun.com/kubernetes/apt/ kubernetes-xenial main
root@k8s-master01:/usr/local/dockerjdk8# sudo apt-get update
root@k8s-master01:/usr/local/dockerjdk8# sudo apt-get install -y kubelet kubeadm kubectl
#下载必须镜像到master&nodes
root@k8s-master01:~# kubeadm config images list #查看需下载哪些镜像
root@k8s-master01:~# sudo kubeadm init --image-repository=fxr0bix2.mirror.aliyuncs.com #执行完这条后发现coredns还是没有下载成功
root@k8s-master01:~# docker pull coredns/coredns #手动下载并更新tag
root@k8s-master01:~# docker tag coredns/coredns:latest registry.aliyuncs.com/google_containers/coredns:v1.8.4
root@k8s-master01:~# sudo kubeadm reset #仅在nodes执行，此目的是在nodes上下载需要的镜像包，记得删除对应的文件(提示中有)，另外可以自己通过pull image然后更改tag的方式来下载
3. master配置kubeadm
#初始化kubeadm
root@k8s-master01:~# kubeadm init --image-repository=fxr0bix2.mirror.aliyuncs.com --ignore-preflight-errors=ImagePull --pod-network-cidr=10.244.0.0/16
[init] Using Kubernetes version: v1.22.0
[preflight] Running pre-flight checks
[preflight] Pulling images required for setting up a Kubernetes cluster
[preflight] This might take a minute or two, depending on the speed of your internet connection
[preflight] You can also perform this action in beforehand using 'kubeadm config images pull'
st for registry.aliyuncs.com/google_containers/coredns:v1.8.4 not found: manifest unknown: manifest unknown
, error: exit status 1
[certs] Using certificateDir folder "/etc/kubernetes/pki"
[certs] Generating "ca" certificate and key
[certs] Generating "apiserver" certificate and key
ster.local] and IPs [10.96.0.1 172.18.8.211]
[certs] Generating "apiserver-kubelet-client" certificate and key
[certs] Generating "front-proxy-ca" certificate and key
[certs] Generating "front-proxy-client" certificate and key
[certs] Generating "etcd/ca" certificate and key
[certs] Generating "etcd/server" certificate and key
[certs] etcd/server serving cert is signed for DNS names [k8s-master01 localhost] and IPs [172.18.8.211 127.0.0.1 ::1]
[certs] Generating "etcd/peer" certificate and key
[certs] etcd/peer serving cert is signed for DNS names [k8s-master01 localhost] and IPs [172.18.8.211 127.0.0.1 ::1]
[certs] Generating "etcd/healthcheck-client" certificate and key
[certs] Generating "apiserver-etcd-client" certificate and key
[certs] Generating "sa" key and public key
[kubeconfig] Using kubeconfig folder "/etc/kubernetes"
[kubeconfig] Writing "admin.conf" kubeconfig file
[kubeconfig] Writing "kubelet.conf" kubeconfig file
[kubeconfig] Writing "controller-manager.conf" kubeconfig file
[kubeconfig] Writing "scheduler.conf" kubeconfig file
[kubelet-start] Writing kubelet environment file with flags to file "/var/lib/kubelet/kubeadm-flags.env"
[kubelet-start] Writing kubelet configuration to file "/var/lib/kubelet/config.yaml"
[kubelet-start] Starting the kubelet
[control-plane] Using manifest folder "/etc/kubernetes/manifests"
[control-plane] Creating static Pod manifest for "kube-apiserver"
[control-plane] Creating static Pod manifest for "kube-controller-manager"
[control-plane] Creating static Pod manifest for "kube-scheduler"
[etcd] Creating static Pod manifest for local etcd in "/etc/kubernetes/manifests"
p to 4m0s
[apiclient] All control plane components are healthy after 8.506664 seconds
[upload-config] Storing the configuration used in ConfigMap "kubeadm-config" in the "kube-system" Namespace
[kubelet] Creating a ConfigMap "kubelet-config-1.22" in namespace kube-system with the configuration for the kubelets in the cluster
[upload-certs] Skipping phase. Please see --upload-certs
rnetes.io/control-plane node.kubernetes.io/exclude-from-external-load-balancers]
[mark-control-plane] Marking the node k8s-master01 as control-plane by adding the taints [node-role.kubernetes.io/master:NoSchedule]
[bootstrap-token] Using token: l7k6l0.68injj34gkc1pi7p
[bootstrap-token] Configuring bootstrap tokens, cluster-info ConfigMap, RBAC Roles
[bootstrap-token] configured RBAC rules to allow Node Bootstrap tokens to get nodes
[bootstrap-token] configured RBAC rules to allow Node Bootstrap tokens to post CSRs in order for nodes to get long term certificate credentials
[bootstrap-token] configured RBAC rules to allow the csrapprover controller automatically approve CSRs from a Node Bootstrap Token
[bootstrap-token] configured RBAC rules to allow certificate rotation for all node client certificates in the cluster
[bootstrap-token] Creating the "cluster-info" ConfigMap in the "kube-public" namespace
[kubelet-finalize] Updating "/etc/kubernetes/kubelet.conf" to point to a rotatable kubelet client certificate and key
[addons] Applied essential addon: CoreDNS
[addons] Applied essential addon: kube-proxy
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/
Then you can join any number of worker nodes by running the following on each as root:
kubeadm join 172.18.8.211:6443 --token l7k6l0.68injj34gkc1pi7p \
--discovery-token-ca-cert-hash sha256:d103ddd3e24e279a725af4e84095535b327f2f815fa226ea2c31ed573b16e76d
#将上行kubeadmin join记录下来
#配置kube
root@k8s-master01:~# mkdir -p $HOME/.kube
root@k8s-master01:~# sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
root@k8s-master01:~# sudo chown $(id -u):$(id -g) $HOME/.kube/config
root@k8s-master01:~# kubectl get node
NAME STATUS ROLES AGE VERSION
k8s-master01 NotReady control-plane,master 75s v1.22.0
#部署flannel
root@k8s-master01:~# cd /home/whq/
root@k8s-master01:/home/whq# cd install-k8s/
root@k8s-master01:/home/whq/install-k8s# cd plugin/flannel/
#从官网下载的kube-flannel.yml https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml
root@k8s-master01:/home/whq/install-k8s/plugin/flannel# cat > kube-flannel.yml <<EOF
> ---
> 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": "10.244.0.0/16",
> "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
> - --kube-subnet-mgr
> resources:
> requests:
> cpu: "100m"
> memory: "50Mi"
> limits:
> cpu: "100m"
> memory: "50Mi"
> securityContext:
> privileged: false
> 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
> EOF
root@k8s-master01:/home/whq/install-k8s/plugin/flannel# kubectl apply -f kube-flannel.yml
Warning: policy/v1beta1 PodSecurityPolicy is deprecated in v1.21+, unavailable in v1.25+
podsecuritypolicy.policy/psp.flannel.unprivileged configured
clusterrole.rbac.authorization.k8s.io/flannel created
clusterrolebinding.rbac.authorization.k8s.io/flannel created
serviceaccount/flannel created
configmap/kube-flannel-cfg created
daemonset.apps/kube-flannel-ds created
root@k8s-master01:/home/whq/install-k8s/plugin/flannel# kubectl get pod -n kube-system #全部为running表示成功
NAME READY STATUS RESTARTS AGE
coredns-7f6cbbb7b8-5s4f2 0/1 Running 0 82m
coredns-7f6cbbb7b8-7zw47 1/1 Running 0 82m
etcd-k8s-master01 1/1 Running 2 82m
kube-apiserver-k8s-master01 1/1 Running 2 82m
kube-controller-manager-k8s-master01 1/1 Running 0 82m
kube-flannel-ds-np6xp 1/1 Running 0 52m
kube-proxy-pnq8b 1/1 Running 0 82m
kube-scheduler-k8s-master01 1/1 Running 3 82m
root@k8s-master01:/home/whq/install-k8s/plugin/flannel# kubectl get node #ready表示成功
NAME STATUS ROLES AGE VERSION
k8s-master01 Ready control-plane,master 101m v1.22.0
4. Node配置kubeadm
#执行master kubeadm init时的join命令，让node加入集群
root@k8s-node01:~# kubeadm join 172.18.8.211:6443 --token l7k6l0.68injj34gkc1pi7p \
> --discovery-token-ca-cert-hash sha256:d103ddd3e24e279a725af4e84095535b327f2f815fa226ea2c31ed573b16e76d
[preflight] Running pre-flight checks
^C
535b327f2f815fa226ea2c31ed573b16e76d
[preflight] Running pre-flight checks
[preflight] Reading configuration from the cluster...
[preflight] FYI: You can look at this config file with 'kubectl -n kube-system get cm kubeadm-config -o yaml'
[kubelet-start] Writing kubelet configuration to file "/var/lib/kubelet/config.yaml"
[kubelet-start] Writing kubelet environment file with flags to file "/var/lib/kubelet/kubeadm-flags.env"
[kubelet-start] Starting the kubelet
[kubelet-start] Waiting for the kubelet to perform the TLS Bootstrap...
This node has joined the cluster:
* Certificate signing request was sent to apiserver and a response was received.
* The Kubelet was informed of the new secure connection details.
Run 'kubectl get nodes' on the control-plane to see this node join the cluster.
#配置kube
root@k8s-node01:~# mkdir -p $HOME/.kube
root@k8s-node01:~# chown $(id -u):$(id -g) $HOME/.kube/config
#查看node状态
root@k8s-node01:~# kubectl get node #全部为ready状态即可
NAME STATUS ROLES AGE VERSION
k8s-master01 Ready control-plane,master 103m v1.22.0
k8s-node01 Ready <none> 2m25s v1.22.0
k8s-node02 Ready <none> 4m30s v1.22.0
5. 尝试创建pod
root@k8s-master01:/home/whq/install-k8s/plugin/flannel# kubectl run nginx-off --image=nginx
pod/nginx-off created
root@k8s-master01:/home/whq/install-k8s/plugin/flannel# kubectl get pod --all-namespaces -o wide
TES
default nginx-off 1/1 Running 0 3m9s 192.168.2.50 k8s-node01 <none> <none>
kube-system coredns-7f6cbbb7b8-5s4f2 1/1 Running 0 118m 192.168.0.73 k8s-master01 <none> <none>
kube-system coredns-7f6cbbb7b8-7zw47 1/1 Running 0 118m 192.168.0.74 k8s-master01 <none> <none>
kube-system etcd-k8s-master01 1/1 Running 2 118m 172.18.8.211 k8s-master01 <none> <none>
kube-system kube-apiserver-k8s-master01 1/1 Running 2 118m 172.18.8.211 k8s-master01 <none> <none>
kube-system kube-controller-manager-k8s-master01 1/1 Running 0 118m 172.18.8.211 k8s-master01 <none> <none>
kube-system kube-flannel-ds-8w45l 1/1 Running 0 19m 172.18.8.212 k8s-node02 <none> <none>
kube-system kube-flannel-ds-np6xp 1/1 Running 0 88m 172.18.8.211 k8s-master01 <none> <none>
kube-system kube-flannel-ds-z7t6x 1/1 Running 0 17m 172.18.8.210 k8s-node01 <none> <none>
kube-system kube-proxy-g7bp5 1/1 Running 0 19m 172.18.8.212 k8s-node02 <none> <none>
kube-system kube-proxy-njjb8 1/1 Running 0 17m 172.18.8.210 k8s-node01 <none> <none>
kube-system kube-proxy-pnq8b 1/1 Running 0 118m 172.18.8.211 k8s-master01 <none> <none>
kube-system kube-scheduler-k8s-master01 1/1 Running 3 118m 172.18.8.211 k8s-master01 <none> <none>
#查看连接性
root@k8s-master01:/home/whq/install-k8s/plugin/flannel# ping 192.168.2.50
来自 192.168.2.50 的回复: 字节=32 时间<1ms TTL=128