Kubeadm 方式部署K8s集群

环境

主节点CPU核数必须是 ≥2核且内存要求必须≥2G，否则k8s无法启动

主机名	地址	角色	配置
kube-master	192.168.134.165	主节点	2核4G
kube-node1	192..168.134.166????????	工作节点	2核4G
kube-node2	192.168.134.163	工作节点	2核4G

1.获取镜像

谷歌镜像[由于国内网络原因，无法下载，后续将采用阿里云镜像代替]

docker pull k8s.gcr.io/kube-apiserver:v1.22.0
docker pull k8s.gcr.io/kube-proxy:v1.22.0
docker pull k8s.gcr.io/kube-controller-manager:v1.22.0
docker pull k8s.gcr.io/kube-scheduler:v1.22.0
docker pull k8s.gcr.io/etcd:3.5.0-0
docker pull k8s.gcr.io/pause:3.5
docker pull k8s.gcr.io/coredns/coredns:v1.8.4
注意

所有机器都必须有镜像
每次部署都会有版本更新，具体版本要求，运行初始化过程失败会有版本提示
kubeadm的版本和镜像的版本必须是对应的

?2.安装docker[集群]

????

使用aliyun docker yum源安装新版docker
删除已安装的Docker

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

配置阿里云Docker Yum源
    # yum install -y yum-utils device-mapper-persistent-data lvm2 git
    # yum-config-manager --add-repo http://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo
下载docker
    #  yum install docker-ce -y
启动Docker服务：
    #systemctl enable docker
    #systemctl start docker
查看docker版本状态： 
    # docker -v

????生产docker的环境配置

sudo mkdir -p /etc/docker
sudo tee /etc/docker/daemon.json <<-'EOF'
{
  "registry-mirrors": ["https://pilvpemn.mirror.aliyuncs.com"],
  "exec-opts": ["native.cgroupdriver=systemd"],
  "log-driver": "json-file",
  "log-opts": {
    "max-size": "100m"
  },
  "storage-driver": "overlay2"
}
EOF
sudo systemctl daemon-reload
sudo systemctl restart docker
#注意：一定注意编码问题，出现错误---查看命令：journalctl -amu docker 即可发现错误

3. 阿里仓库下载[集群]

docker pull registry.cn-hangzhou.aliyuncs.com/google_containers/kube-controller-manager:v1.22.0
docker pull registry.cn-hangzhou.aliyuncs.com/google_containers/kube-proxy:v1.22.0
docker pull registry.cn-hangzhou.aliyuncs.com/google_containers/kube-apiserver:v1.22.0
docker pull registry.cn-hangzhou.aliyuncs.com/google_containers/kube-scheduler:v1.22.0
docker pull registry.cn-hangzhou.aliyuncs.com/google_containers/coredns:v1.8.4
docker pull registry.cn-hangzhou.aliyuncs.com/google_containers/etcd:3.5.0-0
docker pull registry.cn-hangzhou.aliyuncs.com/google_containers/pause:3.5

# 下载完了之后需要将aliyun下载下来的所有镜像打成k8s.gcr.io/kube-controller-manager:v1.22.0这样的tag
docker tag registry.cn-hangzhou.aliyuncs.com/google_containers/kube-controller-manager:v1.22.0 k8s.gcr.io/kube-controller-manager:v1.22.0
docker tag registry.cn-hangzhou.aliyuncs.com/google_containers/kube-proxy:v1.22.0 k8s.gcr.io/kube-proxy:v1.22.0
docker tag registry.cn-hangzhou.aliyuncs.com/google_containers/kube-apiserver:v1.22.0 k8s.gcr.io/kube-apiserver:v1.22.0
docker tag registry.cn-hangzhou.aliyuncs.com/google_containers/kube-scheduler:v1.22.0 k8s.gcr.io/kube-scheduler:v1.22.0
docker tag registry.cn-hangzhou.aliyuncs.com/google_containers/coredns:v1.8.4 k8s.gcr.io/coredns/coredns:v1.8.4
docker tag registry.cn-hangzhou.aliyuncs.com/google_containers/etcd:3.5.0-0 k8s.gcr.io/etcd:3.5.0-0
docker tag registry.cn-hangzhou.aliyuncs.com/google_containers/pause:3.5 k8s.gcr.io/pause:3.5	

# 可以清理掉aliyun的镜像标签
docker rmi -f `docker images --format {{.Repository}}:{{.Tag}} | grep aliyun`

为了方便执行脚本导入镜像

[root@kube-master ~]# rz

[root@kube-master ~]# ls
anaconda-ks.cfg  color.sh  ip_.sh  kube-1.22.0.tar.xz  yum-server.sh
[root@kube-master ~]# tar xf kube-1.22.0.tar.xz 
[root@kube-master ~]# ls
anaconda-ks.cfg  color.sh  ip_.sh  kube-1.22.0  kube-1.22.0.tar.xz  yum-server.sh
[root@kube-master ~]# cd kube-1.22.0
[root@kube-master kube-1.22.0]# ll
总用量 8
-rw-r--r-- 1 root root  915 6月  19 00:23 get-docker-image.sh
drwxr-xr-x 2 root root 4096 6月  19 00:23 images
[root@kube-master kube-1.22.0]# sh get-docker-image.sh  load

4.集群环境相关配置【集群】

4.1配置本地解析

cat >> /etc/hosts <<EOF
192.168.134.165   kube-master
192.168.134.166   kube-node1
192.168.134.163   kube-node2
EOF

4.2防火墙和时间

1.关闭防火墙：
# systemctl disable firewalld --now
2.禁用SELinux：
# setenforce 0
3.编辑文件/etc/selinux/config，将SELINUX修改为disabled，如下：
# sed -i 's/SELINUX=enforcing/SELINUX=disabled/' /etc/sysconfig/selinux
SELINUX=disabled
4.时间同步
# timedatectl set-timezone Asia/Shanghai
# yum install -y ntpdate
# ntpdate ntp.aliyun.com
# hwclock --systohc
5.配置静态ip

4.3关闭系统Swap[集群]

1.关闭swap分区
# swapoff -a
修改/etc/fstab文件，注释掉SWAP的自动挂载，使用free -m确认swap已经关闭。
2.注释掉swap分区：
# sed -i 's/.*swap.*/#&/' /etc/fstab
# free -m
             total        used        free      shared  buff/cache   available
Mem:           3935         144        3415           8         375        3518
Swap:             0           0           0

?5.安装Kubeadm包[集群]

配置阿里云源
cat <<EOF > /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
EOF

所有节点：

1.安装依赖包及常用软件包
# yum install -y conntrack ntpdate ntp ipvsadm ipset jq iptables curl sysstat libseccomp wget vim net-tools git iproute lrzsz bash-completion tree bridge-utils unzip bind-utils gcc

2.安装对应版本
# yum install -y kubelet-1.22.0-0.x86_64 kubeadm-1.22.0-0.x86_64 kubectl-1.22.0-0.x86_64

3.加载ipvs相关内核模块
# cat <<EOF > /etc/modules-load.d/ipvs.conf?
ip_vs
ip_vs_lc
ip_vs_wlc
ip_vs_rr
ip_vs_wrr
ip_vs_lblc
ip_vs_lblcr
ip_vs_dh
ip_vs_sh
ip_vs_nq
ip_vs_sed
ip_vs_ftp
ip_vs_sh
nf_conntrack_ipv4
ip_tables
ip_set
xt_set
ipt_set
ipt_rpfilter
ipt_REJECT
ipip
EOF

4.配置：
配置转发相关参数，否则可能会出错
# cat <<EOF > ?/etc/sysctl.d/k8s.conf
net.bridge.bridge-nf-call-iptables=1
net.bridge.bridge-nf-call-ip6tables=1
net.ipv4.ip_forward=1
net.ipv4.tcp_tw_recycle=0
vm.swappiness=0
vm.overcommit_memory=1
vm.panic_on_oom=0
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
net.netfilter.nf_conntrack_max=2310720
EOF

5.使配置生效
# sysctl --system

6.如果net.bridge.bridge-nf-call-iptables报错，加载br_netfilter模块
# modprobe br_netfilter
# modprobe ip_conntrack
# sysctl -p x/etc/sysctl.d/k8s.conf

7.查看是否加载成功
# lsmod | grep ip_vs? ?#如果什么都不显示，重启服务器后再查看

?

?6.配置启动kubelet[集群]

配置变量：
[root@k8s-master ~]# DOCKER_CGROUPS=`docker info |grep 'Cgroup' | awk ' NR==1 {print $3}'`
[root@k8s-master ~]# echo $DOCKER_CGROUPS
cgroupfs

2.配置kubelet的cgroups
# cat >/etc/sysconfig/kubelet<<EOF
KUBELET_EXTRA_ARGS="--cgroup-driver=$DOCKER_CGROUPS --pod-infra-container-image=k8s.gcr.io/pause:3.5"
EOF

3.启动
# systemctl daemon-reload
# systemctl enable kubelet && systemctl restart kubelet
在这里使用 # systemctl status kubelet，你会发现报错误信息；

10月 11 00:26:43 node1 systemd[1]: kubelet.service: main process exited, code=exited, status=255/n/a
10月 11 00:26:43 node1 systemd[1]: Unit kubelet.service entered failed state.
10月 11 00:26:43 node1 systemd[1]: kubelet.service failed.

运行 # journalctl -xefu kubelet 命令查看systemd日志才发现，真正的错误是：
    unable to load client CA file /etc/kubernetes/pki/ca.crt: open /etc/kubernetes/pki/ca.crt: no such file or directory
#这个错误在运行kubeadm init 生成CA证书后会被自动解决，此处可先忽略。
#简单地说就是在kubeadm init 之前kubelet会不断重启。

7.配置master节点[master]

运行初始化过程如下:
[root@kube-master ~]# kubeadm init --kubernetes-version=v1.22.0 --pod-network-cidr=10.244.0.0/16 --apiserver-advertise-address=192.168.134.165
[init] Using Kubernetes version: v1.22.0
[preflight] Running pre-flight checks
	[WARNING SystemVerification]: this Docker version is not on the list of validated versions: 24.0.2. Latest validated version: 20.10
[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'
[certs] Using certificateDir folder "/etc/kubernetes/pki"
[certs] Generating "ca" certificate and key
[certs] Generating "apiserver" certificate and key
[certs] apiserver serving cert is signed for DNS names [kube-master kubernetes kubernetes.default kubernetes.default.svc kubernetes.default.svc.cluster.local] and IPs [10.96.0.1 192.168.134.165]
[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 [kube-master localhost] and IPs [192.168.134.165 127.0.0.1 ::1]
[certs] Generating "etcd/peer" certificate and key
[certs] etcd/peer serving cert is signed for DNS names [kube-master localhost] and IPs [192.168.134.165 127.0.0.1 ::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"
[wait-control-plane] Waiting for the kubelet to boot up the control plane as static Pods from directory "/etc/kubernetes/manifests". This can take up to 4m0s
[apiclient] All control plane components are healthy after 29.002496 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
[mark-control-plane] Marking the node kube-master as control-plane by adding the labels: [node-role.kubernetes.io/master(deprecated) node-role.kubernetes.io/control-plane node.kubernetes.io/exclude-from-external-load-balancers]
[mark-control-plane] Marking the node kube-master as control-plane by adding the taints [node-role.kubernetes.io/master:NoSchedule]
[bootstrap-token] Using token: eb813a.0nffrc9cij8a6i3x
[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 192.168.134.165:6443 --token eb813a.0nffrc9cij8a6i3x \
	--discovery-token-ca-cert-hash sha256:564306d7275eb8f39579ea14787098698f8b4c0a67bb09887cec6c3af41f7561

上面记录了完成的初始化输出的内容，根据输出的内容基本上可以看出手动初始化安装一个Kubernetes集群所需要的关键步骤。
其中有以下关键内容：
    [kubelet] 生成kubelet的配置文件”/var/lib/kubelet/config.yaml”
    [certificates]生成相关的各种证书
    [kubeconfig]生成相关的kubeconfig文件
    [bootstraptoken]生成token记录下来，后边使用kubeadm join往集群中添加节点时会用到
  
配置使用kubectl
如下操作在master节点操作
[root@kube-master ~]#   mkdir -p $HOME/.kube
[root@kube-master ~]#   sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
[root@kube-master ~]#   sudo chown $(id -u):$(id -g) $HOME/.kube/config

8.node加入集群[node]

配置node节点加入集群：
如果报错开启ip转发：
# sysctl -w net.ipv4.ip_forward=1


在所有node节点操作，此命令为初始化master成功后返回的结果
[root@kube-node1 ~]# kubeadm join 192.168.134.165:6443 --token eb813a.0nffrc9cij8a6i3x \
> --discovery-token-ca-cert-hash sha256:564306d7275eb8f39579ea14787098698f8b4c0a67bb09887cec6c3af41f7561

9.配置使用网络插件[master]

#> 部署calico网络插件
curl -L https://docs.projectcalico.org/v3.22/manifests/calico.yaml -O
kubectl apply -f ?calico.yaml

# kubectl get pod -A

[root@kube-master ~]# kubectl  get pod -A
NAMESPACE     NAME                                       READY   STATUS    RESTARTS        AGE
kube-system   calico-kube-controllers-7c87c5f9b8-klb7d   1/1     Running   1 (3m41s ago)   28m
kube-system   calico-node-4nkrw                          1/1     Running   1 (3m41s ago)   28m
kube-system   calico-node-hdlqc                          1/1     Running   0               27m
kube-system   calico-node-pxrbf                          1/1     Running   0               27m
kube-system   coredns-78fcd69978-6ncn4                   1/1     Running   1 (3m41s ago)   29m
kube-system   coredns-78fcd69978-m742f                   1/1     Running   1 (3m41s ago)   29m
kube-system   etcd-kube-master                           1/1     Running   2 (3m41s ago)   29m
kube-system   kube-apiserver-kube-master                 1/1     Running   2 (3m41s ago)   29m
kube-system   kube-controller-manager-kube-master        1/1     Running   2 (3m41s ago)   29m
kube-system   kube-proxy-4c98v                           1/1     Running   0               25m
kube-system   kube-proxy-fngss                           1/1     Running   0               27m
kube-system   kube-proxy-kfp5w                           1/1     Running   1 (3m41s ago)   29m
kube-system   kube-scheduler-kube-master                 1/1     Running   2 (3m41s ago)   29m