#建议:先全部在一台master上执行完成集群的安装,最后node节点再加入集群
#硬件环境的要求: cpu:2c memory:4G/2G #软件环境的要求: 三天
docker环境准备
准备3台虚拟机(centos-8.2)并运行以下脚本:
新建 脚本文件
#!/bin/bash
#解决依赖关系
yum install -y yum-utils zlib zlib-devel openssl openssl-devel pcre pcre-devel gcc gcc-c++ autoconf automake make psmisc lsof net-tools vim python3#关闭防火墙
systemctl stop firewalld
systemctl disable firewalld#关闭selinux
setenforce 0 #临时关闭
#永久关闭
sed -i '/^SELINUX/ s/enforcing/disabled/' /etc/selinux/config
安装docker
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yum-utils软件包(提供yum-config-manager 实用程序),配置加速源
yum install -y yum-utils
yum-config-manager \
--add-repo \
http://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo
安装docker,设置开机自启
yum install -y docker-ce docker-ce-cli containerd.io #安装docker
systemctl start docker #启动docker
systemctl enable docker #设置docker自启动
配置 Docker使用systemd作为默认Cgroup驱动
每台服务器上都要操作,master和node上都要操作
cat <<EOF > /etc/docker/daemon.json
{
"exec-opts": ["native.cgroupdriver=systemd"]
}
EOF#重启docker
systemctl restart docker
关闭swap分区
每台服务器都需要操作
swapoff -a # 临时 vim /etc/fstab 永久 #sed -i '/ swap / s/^\(.*\)$/#\1/g' /etc/fstab #对这条语句进行注释 就是前面加个#号
重新命名主机,在所有主机上上添加如下命令,修改hosts文件
hostnamectl set-hostname master hostnamectl set-hostname node1 hostnamectl set-hostname node2
修改主机名后使用su - root重新登陆
每台机器上的/etc/hosts文件都需要修改
su - root cat >> /etc/hosts << EOF 192.168.10.133 master 192.168.10.132 node1 192.168.10.134 node2 192.168.10.135 node3 EOF
安装kubeadm,kubelet和kubectl
kubeadm --》k8s的管理程序--》在master上运行的--》建立整个k8s集群,背后是执行了大量的脚本,帮助我们去启动k8s
kubelet --》在node节点上用来管理容器的--》管理docker,告诉docker程序去启动容器 master和node通信用的--》管理docker,告诉docker程序去启动容器 一个在集群中每个节点(node)上运行的代理。 它保证容器(containers)都 运行在 Pod 中。
kubectl --》在master上用来给node节点发号施令的程序,用来控制node节点的,告诉它们做什么事情的,是命令行操作的工具
集群里的每台服务器都需要安装 # 添加kubernetes YUM软件源 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 #==== ubuntu里修改源,使用阿里云的源,参考文档 https://blog.csdn.net/wangyijieonline/article/details/105360138 #===ubuntu系统里 安装kubelet,kubeadm,kubectl 添加apt key以及源(所有主机) #下载相关软件 sudo apt update && sudo apt install -y apt-transport-https curl #下载apt-key.gpg curl -s https://mirrors.aliyun.com/kubernetes/apt/doc/apt-key.gpg | sudo apt-key add - #添加k8s的阿里云的源 echo "deb https://mirrors.aliyun.com/kubernetes/apt/ kubernetes-xenial main" >>/etc/apt/sources.list.d/kubernetes.list sudo apt update apt install -y kubelet kubeadm kubectl systemctl enable --now kubelet #===centos里执行 #安装kubeadm,kubelet和kubectl yum install -y kubelet kubeadm kubectl #设置开机自启 systemctl enable kubelet
master主机执行
部署Kubernetes Master
# 部署Kubernetes Master
#提前准备coredns:1.8.4的镜像,后面需要使用,需要在每台机器上下载镜像
[root@master ~]# docker pull coredns/coredns:1.8.4
[root@master ~]# docker tag coredns/coredns:1.8.4 registry.aliyuncs.com/google_containers/coredns:v1.8.4#初始化操作在master服务器上执行
[root@master ~]#kubeadm init \
--apiserver-advertise-address=192.168.10.133 \
--image-repository registry.aliyuncs.com/google_containers \
--service-cidr=10.1.0.0/16 \
--pod-network-cidr=10.244.0.0/16
#192.168.0.17 是master的ip
# --service-cidr string Use alternative range of IP address for service VIPs. (default "10.96.0.0/12")
# --pod-network-cidr string Specify range of IP addresses for the pod network. If set, the control plane will automatically allocate CIDRs for every node.
输出结果
[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 192.168.10.133:6443 --token 6plcy7.ulwz2zxqidc01h0k \
--discovery-token-ca-cert-hash sha256:045c432d3a01cd63da84d2b0239b8fe805e0eec04c99f07f24667e9b849bdc91
[root@master ~]#
按照提示操作
mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/config
## node节点执行
建议:不要现在node节点上运行kubelet服务,不然会导致join失败,如果已经运行了,建议关闭,然后删除提示失败的文件和目录
/etc/kubernetes/kubelet.conf
/etc/kubernetes/pki/ca.crt
rm -rf etc/kubernetes/{pki,kubelet.conf}
###########
[root@node1 ~]# kubeadm join 192.168.0.17:6443 --token sxzm95.4blvhq1mnk3goyjo --discovery-token-ca-cert-hash sha256:419d644656e24a113f94d7f8e01a820bb4030e3c0a19a32542bc27730103189a
[root@node1 ~]#
第2台也加入集群
[root@node3 ~]# kubeadm join 192.168.0.17:6443 --token sxzm95.4blvhq1mnk3goyjo --discovery-token-ca-cert-hash sha256:419d644656e24a113f94d7f8e01a820bb4030e3c0a19a32542bc27730103189a#k8s里删除节点k8s-node1
kubectl drain k8s-node1 --delete-emptydir-data --force --ignore-daemonsets node/k8s-node1
kubectl delete node k8s-node1
输出结果
[preflight] Running pre-flight checks
[WARNING FileExisting-tc]: tc not found in system path
[WARNING SystemVerification]: this Docker version is not on the list of validated versions: 20.10.5. Latest validated version: 19.03
[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.
## 安装网络插件(在master节点执行)
kube-flannel.yml
在master服务器上执行
[root@master ~]# cat kube-flannel.yml
---
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:v0.13.1-rc2
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:v0.13.1-rc2
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
部署flannel
[root@master ~]# kubectl apply -f kube-flannel.yml
podsecuritypolicy.policy/psp.flannel.unprivileged created
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@master ~]# ps aux|grep flannel
root 320372 1.8 1.4 1265920 26824 ? Ssl 11:12 0:00 /opt/bin/flanneld --ip-masq --kube-subnet-mgr
root 321071 0.0 0.0 12324 1088 pts/0 S+ 11:13 0:00 grep --color=auto flannel
查看集群状态
#等待节点准备完毕
[root@master ~]# kubectl get nodes
NAME STATUS ROLES AGE VERSION
master Ready control-plane,master 161m v1.20.4
node1 Ready <none> 135m v1.20.4
node2 NotReady <none> 39s v1.20.4
过一段时间,再次查看node节点会是ready状态,大概2-3分钟时间
[root@master ~]# kubectl get nodes
NAME STATUS ROLES AGE VERSION
master Ready control-plane,master 163m v1.20.4
node1 Ready <none> 136m v1.20.4
node2 Ready <none> 2m5s v1.20.4
[root@master ~]# kubectl get nodes -n kube-system -o wide
NAME STATUS ROLES AGE VERSION INTERNAL-IP EXTERNAL-IP OS-IMAGE KERNEL-VERSION CONTAINER-RUNTIME
master Ready control-plane,master 136m v1.22.1 192.168.0.17 <none> CentOS Linux 8 4.18.0-305.3.1.el8.x86_64 docker://20.10.8
node1 Ready <none> 131m v1.22.1 192.168.0.89 <none> CentOS Linux 7 (Core) 3.10.0-1062.el7.x86_64 docker://20.10.8
node2 Ready <none> 111s v1.22.1 192.168.0.11 <none> Ubuntu 20.04.3 LTS 5.4.0-80-generic docker://20.10.8
node3 Ready <none> 130m v1.22.1 192.168.0.19 <none> CentOS Linux 8 4.18.0-305.3.1.el8.x86_64 docker://20.10.8
[root@master ~]#
[root@master ~]# kubectl get pod -n kube-system
NAME READY STATUS RESTARTS AGE
coredns-7f89b7bc75-fjq7n 1/1 Running 0 48m
coredns-7f89b7bc75-t5hnq 1/1 Running 0 48m
etcd-master 1/1 Running 0 48m
kube-apiserver-master 1/1 Running 0 48m
kube-controller-manager-master 1/1 Running 0 48m
kube-flannel-ds-kz8t9 1/1 Running 0 17m
kube-flannel-ds-r2q5s 1/1 Running 0 17m
kube-proxy-4jlr6 1/1 Running 0 48m
kube-proxy-ppsr6 1/1 Running 0 22m
kube-scheduler-master 1/1 Running 0 48m
测试
创建nginx的pod
启动一个pod,背后是运行nginx镜像
[root@new-k8s-master ~]# kubectl run sc-nginx --image=nginx --port=8080
pod/sc-nginx created
[root@new-k8s-master ~]# kubectl get pod
NAME READY STATUS RESTARTS AGE
sc-nginx 0/1 ContainerCreating 0 5s
[root@new-k8s-master ~]#
等一下,会启动pod,因为需要去下载镜像文件
[root@new-k8s-master ~]# kubectl get pod
NAME READY STATUS RESTARTS AGE
sc-nginx 1/1 Running 0 64s
[root@new-k8s-master ~]#
[root@new-k8s-master ~]# kubectl get pod -o wide 显示详细的内容
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
sc-nginx 1/1 Running 0 97s 10.244.1.2 node1 <none> <none>
[root@new-k8s-master ~]#