CentOS7基于kubeadm搭建K8S集群

Published by heqiubing on

第一章 安装前必读

请不要使用带中文的服务器和克隆的虚拟机

生产环境建议使用二进制安装方式

第二章 kubeadm高可用安装k8s集群最新版

2.1 基本环境配置 Kubeadm安装方式自1.14版本以后，安装方法几乎没有任何变化，此文档可以尝试安装最新的k8s集群，centos采用的是7.x版本

K8S官网：https://kubernetes.io/docs/setup/ 最新版高可用安装：https://kubernetes.io/docs/setup/production-environment/tools/kubeadm/high-availability/

1、基本环境配置

表1-1  高可用Kubernetes集群规划
主机名IP地址说明
k8s-master01 ~ 02172.29.207.176 ~177master节点 * 2
k8s-master-lb172.29.207.175keepalived虚拟IP
k8s-node01 ~ 02172.29.207.178 ~ 179worker节点 * 2
配置信息备注
系统版本CentOS 7.9
Docker版本19.03.x
Pod网段172.168.0.0/12
Service网段10.96.0.0/12

备注：VIP（虚拟IP）不要和公司内网IP重复，首先去ping一下，不通才可用。VIP需要和主机在同一个局域网内！

公有云上搭建VIP是公有云的负载均衡的IP，比如阿里云的内网SLB的地址，腾讯云内网ELB的地址

VIP（虚拟IP）不要和公司内网IP重复，首先去ping一下，不通才可用。VIP需要和主机在同一个局域网内！ 公有云上搭建VIP是公有云的负载均衡的IP，比如阿里云的内网SLB的地址，腾讯云内网ELB的地址

2、配置HOSTS

#所有节点配置
配置hosts，修改/etc/hosts如下：
# cat /etc/hosts
127.0.0.1   localhost localhost.localdomain localhost4 localhost4.localdomain4
::1         localhost localhost.localdomain localhost6 localhost6.localdomain6
172.9.207.176 k8s-master01 
172.9.207.177 k8s-master02 
172.9.207.175 k8s-master-lb
172.9.207.178 k8s-node01
172.9.207.179 k8s-node02

3、配置CentOS 7安装yum源

#所有节点配置
# curl -o /etc/yum.repos.d/CentOS-Base.repo <https://mirrors.aliyun.com/repo/Centos-7.repo>
# yum install -y yum-utils device-mapper-persistent-data lvm2
# yum-config-manager --add-repo <https://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo>
# cat <&lt;EOF &gt; /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
# sed -i -e '/mirrors.cloud.aliyuncs.com/d' -e '/mirrors.aliyuncs.com/d' /etc/yum.repos.d/CentOS-Base.repo

4、必备工具安装

所有节点配置
# yum install wget jq psmisc vim net-tools telnet yum-utils device-mapper-persistent-data lvm2 git -y

5、关闭防火墙和selinux

#所有节点配置
# 所有节点关闭防火墙、selinux、dnsmasq、swap。服务器配置如下：
# systemctl disable --now firewalld &&
# systemctl disable --now dnsmasq   &&
# systemctl disable --now NetworkManager
​
# setenforce 0
# sed -i 's#SELINUX=enforcing#SELINUX=disabled#g' /etc/sysconfig/selinux
# sed -i 's#SELINUX=enforcing#SELINUX=disabled#g' /etc/selinux/config
​
# 关闭swap分区
# swapoff -a && sysctl -w vm.swappiness=0
# sed -ri '/^\[^#]\*swap/s@^@#@' /etc/fstab

6、安装ntpdate时间同步

#所有节点配置
# rpm -ivh <http://mirrors.wlnmp.com/centos/wlnmp-release-centos.noarch.rpm>
# yum install ntpdate -y
​
# 所有节点同步时间。时间同步配置如下：
# ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime
# echo 'Asia/Shanghai' >/etc/timezone
# ntpdate time2.aliyun.com
​
# 加入到crontab
[root@k8s-master01 dashboard]# crontab -l
​
*/5 * * * * /usr/sbin/ntpdate time2.aliyun.com

7、所有节点配置limit

#所有节点配置
# ulimit -SHn 65535
​
# vim /etc/security/limits.conf
​
# # 末尾添加如下内容
​
*   soft nofile 655360
*   hard nofile 131072
*   soft nproc 655350
*   hard nproc 655350
*   soft memlock unlimited
*   hard memlock unlimited

8、配置免密登录

#Master节点配置
Master01节点免密钥登录其他节点，安装过程中生成配置文件和证书均在Master01上操作，集群管理也在Master01上操作，阿里云或者AWS上需要单独一台kubectl服务器。密钥配置如下：
ssh-keygen -t rsa
ssh-copy-id  root@172.29.207.177
ssh-copy-id  root@172.29.207.178
ssh-copy-id  root@172.29.207.179

9、下载安装所有的源码文件\升级内核

#所有节点配置
# cd /root/ ; git clone <https://github.com/dotbalo/k8s-ha-install.git>
​
# 所有节点升级系统并重启，此处升级没有升级内核，下节会单独升级内核：
# yum update -y --exclude=kernel\* && reboot #CentOS7需要升级，CentOS8可以按需升级系统
​
# A 内核配置
# CentOS7 需要升级内核至4.18+，本地升级的版本为4.19
# 在master01节点下载内核
# cd /root
# wget http://193.49.22.109/elrepo/kernel/el7/x86_64/RPMS/kernel-ml-devel-4.19.12-1.el7.elrepo.x86_64.rpm
# wget http://193.49.22.109/elrepo/kernel/el7/x86_64/RPMS/kernel-ml-4.19.12-1.el7.elrepo.x86_64.rpm
# 从master01节点传到其他节点：
# for i in k8s-master02 k8s-master03 k8s-node01 k8s-node02;do scp kernel-ml-4.19.12-1.el7.elrepo.x86\_64.rpm kernel-ml-devel-4.19.12-1.el7.elrepo.x86\_64.rpm \$i:/root/ ; done
​
# 所有节点安装内核
# cd /root && yum localinstall -y kernel-ml\*
# 所有节点更改内核启动顺序
# grub2-set-default  0 && grub2-mkconfig -o /etc/grub2.cfg
​
 # grubby --args="user\_namespace.enable=1" --update-kernel="\$(grubby --default-kernel)"
# 检查默认内核是不是4.19
# grubby --default-kernel
/boot/vmlinuz-4.19.12-1.el7.elrepo.x86\_64
# 所有节点重启，然后检查内核是不是4.19
# uname -a
Linux k8s-master02 4.19.12-1.el7.elrepo.x86\_64 #1 SMP Fri Dec 21 11:06:36 EST 2018 x86\_64 x86\_64 x86\_64 GNU/Linux

10、所有节点安装ipvsadm

#所有节点配置
# yum install ipvsadm ipset sysstat conntrack libseccomp -y
# 所有节点配置ipvs模块，在内核4.19+版本nf\_conntrack\_ipv4已经改为nf\_conntrack， 4.18以下使用nf\_conntrack\_ipv4即可：
modprobe -- ip\_vs
modprobe -- ip\_vs\_rr
modprobe -- ip\_vs\_wrr
modprobe -- ip\_vs\_sh
modprobe -- nf\_conntrack
    
# cat /etc/modules-load.d/ipvs.conf     #本次操作这个
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_fo
ip_vs_nq
ip_vs_sed
ip_vs_ftp
ip_vs_sh
nf_conntrack
ip_tables
ip_set
xt_set
ipt_set
ipt_rpfilter
ipt_REJECT
ipip
# 然后执行
# systemctl enable --now systemd-modules-load.service

11、开启一些k8s集群中必须的内核参数

#所有节点配置
# 所有节点配置k8s内核：
# cat <<EOF > /etc/sysctl.d/k8s.conf
net.ipv4.ip_forward = 1
net.bridge.bridge-nf-call-iptables = 1
net.bridge.bridge-nf-call-ip6tables = 1
fs.may_detach_mounts = 1
vm.overcommit_memory=1
vm.panic_on_oom=0
fs.inotify.max_user_watches=89100
fs.file-max=52706963
fs.nr_open=52706963
net.netfilter.nf_conntrack_max=2310720
​
net.ipv4.tcp_keepalive_time = 600
net.ipv4.tcp_keepalive_probes = 3
net.ipv4.tcp_keepalive_intvl =15
net.ipv4.tcp_max_tw_buckets = 36000
net.ipv4.tcp_tw_reuse = 1
net.ipv4.tcp_max_orphans = 327680
net.ipv4.tcp_orphan_retries = 3
net.ipv4.tcp_syncookies = 1
net.ipv4.tcp_max_syn_backlog = 16384
net.ipv4.ip_conntrack_max = 65536
net.ipv4.tcp_max_syn_backlog = 16384
net.ipv4.tcp_timestamps = 0
net.core.somaxconn = 16384
EOF
​
# sysctl --system
​
# 所有节点配置完内核后，重启服务器，保证重启后内核依旧加载
​
# reboot
# lsmod | grep --color=auto -e ip_vs -e nf_conntrack

12、基本组件安装

#所有节点配置
本节主要安装的是集群中用到的各种组件，比如Docker-ce、Kubernetes各组件等。
# 所有节点安装Docker-ce 19.03
# yum install docker-ce-19.03.* docker-cli-19.03.* -y
​
# 温馨提示：
# 由于新版kubelet建议使用systemd，所以可以把docker的CgroupDriver改成systemd
# mkdir /etc/docker
# cat > /etc/docker/daemon.json <<EOF
{
  "exec-opts": ["native.cgroupdriver=systemd"]
}
EOF
​
# 所有节点设置开机自启动Docker：
# systemctl daemon-reload && systemctl enable --now docker
​
# 安装k8s组件：
# yum list kubeadm.x86_64 --showduplicates | sort -r
​
# 所有节点安装最新版本kubeadm：
# yum install kubeadm-1.20* kubelet-1.20* kubectl-1.20* -y
​
# 默认配置的pause镜像使用gcr.io仓库，国内可能无法访问，所以这里配置Kubelet使用阿里云的pause镜像：
# cat >/etc/sysconfig/kubelet<<EOF
KUBELET_EXTRA_ARGS="--cgroup-driver=systemd --pod-infra-container-image=registry.cn-hangzhou.aliyuncs.com/google_containers/pause-amd64:3.2"
EOF
​
# 设置Kubelet开机自启动：
# systemctl daemon-reload
# systemctl enable --now kubelet

13、高可用组件安装

# （注意：如果不是高可用集群，haproxy和keepalived无需安装）
公有云要用公有云自带的负载均衡，比如阿里云的SLB，腾讯云的ELB，用来替代haproxy和keepalived，因为公有云大部分都是不支持keepalived的，另外如果用阿里云的话，kubectl控制端不能放在master节点，推荐使用腾讯云，因为阿里云的slb有回环的问题，也就是slb代理的服务器不能反向访问SLB，但是腾讯云修复了这个问题。
# 所有Master节点通过yum安装HAProxy和KeepAlived：
# yum install keepalived haproxy -y
# 所有Master节点配置HAProxy（详细配置参考HAProxy文档，所有Master节点的HAProxy配置相同）：
# mkdir /etc/haproxy
#备份
# cp /etc/haproxy/haproxy.cfg  /etc/haproxy/haproxy.cfg.bak 
# cat /etc/haproxy/haproxy.cfg
global
  maxconn  2000
  ulimit-n  16384
  log  127.0.0.1 local0 err
  stats timeout 30s
​
defaults
  log global
  mode  http
  option  httplog
  timeout connect 5000
  timeout client  50000
  timeout server  50000
  timeout http-request 15s
  timeout http-keep-alive 15s
​
frontend monitor-in
  bind *:33305
  mode http
  option httplog
  monitor-uri /monitor
​
frontend k8s-master
  bind 0.0.0.0:16443
  bind 127.0.0.1:16443
  mode tcp
  option tcplog
  tcp-request inspect-delay 5s
  default_backend k8s-master
​
backend k8s-master
  mode tcp
  option tcplog
  option tcp-check
  balance roundrobin
  default-server inter 10s downinter 5s rise 2 fall 2 slowstart 60s maxconn 250 maxqueue 256 weight 100
  server k8s-master01   172.29.207.176:6443  check
  server k8s-master02   172.29.207.177:6443  check
​
# 所有Master节点配置KeepAlived，配置不一样，注意区分 [root@k8s-master01 pki]# vim /etc/keepalived/keepalived.conf ，注意每个节点的IP和网卡（interface参数）
Master01节点的配置：
# mkdir /etc/keepalived
# cp /etc/keepalived/keepalived.conf  /etc/keepalived/keepalived.conf.bak
# cat /etc/keepalived/keepalived.conf 
​
! Configuration File for keepalived
global_defs {
    router_id LVS_DEVEL
script_user root
    enable_script_security
}
vrrp_script chk_apiserver {
    script "/etc/keepalived/check_apiserver.sh"
    interval 5
    weight -5
    fall 2  
rise 1
}
vrrp_instance VI_1 {
    state MASTER
    interface ens33
    mcast_src_ip 172.29.207.176
    virtual_router_id 51
    priority 101
    advert_int 2
    authentication {
        auth_type PASS
        auth_pass K8SHA_KA_AUTH
    }
    virtual_ipaddress {
        172.29.207.175
    }
    track_script {
       chk_apiserver
    }
}
Master02节点的配置：
! Configuration File for keepalived
global_defs {
    router_id LVS_DEVEL
script_user root
    enable_script_security
}
vrrp_script chk_apiserver {
    script "/etc/keepalived/check_apiserver.sh"
   interval 5
    weight -5
    fall 2  
rise 1
}
vrrp_instance VI_1 {
    state BACKUP
    interface ens33
    mcast_src_ip 172.29.207.177
    virtual_router_id 51
    priority 100
    advert_int 2
    authentication {
        auth_type PASS
        auth_pass K8SHA_KA_AUTH
    }
    virtual_ipaddress {
        172.29.207.175
    }
    track_script {
       chk_apiserver
    }
}
#所有master节点配置KeepAlived健康检查文件：
# cat /etc/keepalived/check_apiserver.sh 
#!/bin/bash
​
err=0
for k in $(seq 1 2)
do
    check_code=$(pgrep haproxy)
    if [[ $check_code == "" ]]; then
        err=$(expr $err + 1)
        sleep 1
        continue
    else
        err=0
        break
    fi
done
​
if [[ $err != "0" ]]; then
    echo "systemctl stop keepalived"
    /usr/bin/systemctl stop keepalived
    exit 1
else
    exit 0
fi
# chmod +x /etc/keepalived/check_apiserver.sh
启动haproxy和keepalived
# systemctl daemon-reload
# systemctl enable --now haproxy
# systemctl enable --now keepalived
​
重要：如果安装了keepalived和haproxy，需要测试keepalived是否是正常的
测试VIP
[root@k8s-master01 ~]# ping 172.29.207.175 -c 4
PING 172.29.207.175 (172.29.207.175) 56(84) bytes of data.
64 bytes from 172.29.207.175: icmp_seq=1 ttl=64 time=0.464 ms
64 bytes from 172.29.207.175: icmp_seq=2 ttl=64 time=0.063 ms
64 bytes from 172.29.207.175: icmp_seq=3 ttl=64 time=0.062 ms
64 bytes from 172.29.207.175: icmp_seq=4 ttl=64 time=0.063 ms
​
--- 172.29.207.175 ping statistics ---
4 packets transmitted, 4 received, 0% packet loss, time 3106ms
rtt min/avg/max/mdev = 0.062/0.163/0.464/0.173 ms
[root@k8s-master01 ~]# telnet 172.29.207.175 16443
Trying 172.29.207.175...
Connected to 172.29.207.175.
Escape character is '^]'.
Connection closed by foreign host.
​
# 如果ping不通且telnet没有出现 ] ，则认为VIP不可以，不可在继续往下执行，需要排查keepalived的问题，比如防火墙和selinux，haproxy和keepalived的状态，监听端口等
所有节点查看防火墙状态必须为disable和inactive：systemctl status firewalld
所有节点查看selinux状态，必须为disable：getenforce
master节点查看haproxy和keepalived状态：systemctl status keepalived haproxy
master节点查看监听端口：netstat -lntp

14、集群初始化

# 官方初始化文档：
# https://kubernetes.io/docs/setup/production-environment/tools/kubeadm/high-availability/
​
# Master01节点创建kubeadm-config.yaml配置文件如下：
# Master01：（# 注意，如果不是高可用集群，172.29.207.175:16443改为master01的地址，16443改为apiserver的端口，默认是6443，注意更改v1.18.5自己服务器kubeadm的版本：kubeadm version）
​
注意
以下文件内容，宿主机网段、podSubnet网段、serviceSubnet网段不能重复，具体看课程资料的【安装前必看】集群安装网段划分
apiVersion: kubeadm.k8s.io/v1beta2
bootstrapTokens:
- groups:
  - system:bootstrappers:kubeadm:default-node-token
  token: 7t2weq.bjbawausm0jaxury
  ttl: 24h0m0s
  usages:
  - signing
  - authentication
kind: InitConfiguration
localAPIEndpoint:
  advertiseAddress: 172.29.207.176
  bindPort: 6443
nodeRegistration:
  criSocket: /var/run/dockershim.sock
  name: k8s-master01
  taints:
  - effect: NoSchedule
    key: node-role.kubernetes.io/master
---
apiServer:
  certSANs:
  - 172.29.207.175
  timeoutForControlPlane: 4m0s
apiVersion: kubeadm.k8s.io/v1beta2
certificatesDir: /etc/kubernetes/pki
clusterName: kubernetes
controlPlaneEndpoint: 172.29.207.175:16443
controllerManager: {}
dns:
  type: CoreDNS
etcd:
  local:
    dataDir: /var/lib/etcd
imageRepository: registry.cn-hangzhou.aliyuncs.com/google_containers
kind: ClusterConfiguration
kubernetesVersion: v1.20.0
networking:
  dnsDomain: cluster.local
  podSubnet: 172.168.0.0/12
  serviceSubnet: 10.96.0.0/12
scheduler: {}
​
# 更新kubeadm文件
# kubeadm config migrate --old-config kubeadm-config.yaml --new-config new.yaml
# 将new.yaml文件复制到其他master节点，之后所有Master节点提前下载镜像，可以节省初始化时间：
# kubeadm config images pull --config /root/new.yaml 
# 所有节点设置开机自启动kubelet
# systemctl enable --now kubelet（如果启动失败无需管理，初始化成功以后即可启动）
​
# Master01节点初始化，初始化以后会在/etc/kubernetes目录下生成对应的证书和配置文件，之后其他Master节点加入Master01即可：
# kubeadm init --config /root/new.yaml  --upload-certs
​
# 如果初始化失败，重置后再次初始化，命令如下：
# kubeadm reset -f ; ipvsadm --clear  ; rm -rf ~/.kube
# 初始化成功以后，会产生Token值，用于其他节点加入时使用，因此要记录下初始化成功生成的token值（令牌值）：
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/
​
You can now join any number of the control-plane node running the following command on each as root:
​
  kubeadm join 172.29.207.175:16443 --token 7t2weq.bjbawausm0jaxury \
    --discovery-token-ca-cert-hash sha256:8c92ecb336be2b9372851a9af2c7ca1f7f60c12c68f6ffe1eb513791a1b8a908 \
    --control-plane --certificate-key ac2854de93aaabdf6dc440322d4846fc230b290c818c32d6ea2e500fc930b0aa
​
Please note that the certificate-key gives access to cluster sensitive data, keep it secret!
As a safeguard, uploaded-certs will be deleted in two hours; If necessary, you can use
"kubeadm init phase upload-certs --upload-certs" to reload certs afterward.
​
Then you can join any number of worker nodes by running the following on each as root:
​
kubeadm join 172.29.207.175:16443 --token 7t2weq.bjbawausm0jaxury \
    --discovery-token-ca-cert-hash sha256:8c92ecb336be2b9372851a9af2c7ca1f7f60c12c68f6ffe1eb513791a1b8a908
​
# Master01节点配置环境变量，用于访问Kubernetes集群：
# cat <<EOF >> /root/.bashrc
export KUBECONFIG=/etc/kubernetes/admin.conf
EOF
# source /root/.bashrc
​
# 查看节点状态：
# kubectl get nodes
NAME           STATUS     ROLES                  AGE   VERSION
k8s-master01   NotReady   control-plane,master   74s   v1.20.0
# 采用初始化安装方式，所有的系统组件均以容器的方式运行并且在kube-system命名空间内，此时可以查看Pod状态：
# kubectl get pods -n kube-system -o wide
NAME                                   READY     STATUS    RESTARTS   AGE       IP              NODE
coredns-777d78ff6f-kstsz               0/1       Pending   0          14m       <none>          <none>
coredns-777d78ff6f-rlfr5               0/1       Pending   0          14m       <none>          <none>
etcd-k8s-master01                      1/1       Running   0          14m       172.29.207.176   k8s-master01
kube-apiserver-k8s-master01            1/1       Running   0          13m       172.29.207.176   k8s-master01
kube-controller-manager-k8s-master01   1/1       Running   0          13m       172.29.207.176   k8s-master01
kube-proxy-8d4qc                       1/1       Running   0          14m       172.29.207.176   k8s-master01
kube-scheduler-k8s-master01            1/1       Running   0          13m       172.29.207.176   k8s-master01

15、高可用Master

# 注意：以下步骤是上述init命令产生的Token过期了才需要执行以下步骤，如果没有过期不需要执行
# Token过期后生成新的token：
# kubeadm token create --print-join-command
​
# Master需要生成--certificate-key
# kubeadm init phase upload-certs  --upload-certs
# Token没有过期直接执行Join就行了
# 初始化其他master加入集群（master01和02操作）
kubeadm join 172.29.207.175:16443 --token fgtxr1.bz6dw1tci1kbj977     --discovery-token-ca-cert-hash sha256:06ebf46458a41922ff1f5b3bc49365cf3dd938f1a7e3e4a8c8049b5ec5a3aaa5 \
    --control-plane --certificate-key 03f99fb57e8d5906e4b18ce4b737ce1a055de1d144ab94d3cdcf351dfcd72a8b

16、node节点的配置

# Node节点上主要部署公司的一些业务应用，生产环境中不建议Master节点部署系统组件之外的其他Pod，测试环境可以允许Master节点部署Pod以节省系统资源。
# kubeadm join 172.29.207.175:16443 --token 7t2weq.bjbawausm0jaxury \
    --discovery-token-ca-cert-hash sha256:8c92ecb336be2b9372851a9af2c7ca1f7f60c12c68f6ffe1eb513791a1b8a908
​
# 所有节点初始化完成后，查看集群状态
# kubectl  get node
NAME           STATUS     ROLES                  AGE     VERSION
k8s-master01   NotReady   control-plane,master   8m53s   v1.20.0
k8s-master02   NotReady   control-plane,master   2m25s   v1.20.0
k8s-master03   NotReady   control-plane,master   31s     v1.20.0
k8s-node01     NotReady   <none>                 32s     v1.20.0
k8s-node02     NotReady   <none>                 88s     v1.20.0

17、Calico组件的安装

# 以下步骤只在master01执行
# cd /root/k8s-ha-install && git checkout manual-installation-v1.20.x && cd calico/
# 修改calico-etcd.yaml的以下位置
# sed -i 's#etcd_endpoints: "http://<ETCD_IP>:<ETCD_PORT>"#etcd_endpoints: "https://172.29.207.176:2379,https://172.29.207.177:2379,https://172.29.207.x:2379"#g' calico-etcd.yaml
ETCD_CA=`cat /etc/kubernetes/pki/etcd/ca.crt | base64 | tr -d '\n'`
ETCD_CERT=`cat /etc/kubernetes/pki/etcd/server.crt | base64 | tr -d '\n'`
ETCD_KEY=`cat /etc/kubernetes/pki/etcd/server.key | base64 | tr -d '\n'`
sed -i "s@# etcd-key: null@etcd-key: ${ETCD_KEY}@g; s@# etcd-cert: null@etcd-cert: ${ETCD_CERT}@g; s@# etcd-ca: null@etcd-ca: ${ETCD_CA}@g" calico-etcd.yaml
sed -i 's#etcd_ca: ""#etcd_ca: "/calico-secrets/etcd-ca"#g; s#etcd_cert: ""#etcd_cert: "/calico-secrets/etcd-cert"#g; s#etcd_key: "" #etcd_key: "/calico-secrets/etcd-key" #g' calico-etcd.yaml
​
POD_SUBNET=`cat /etc/kubernetes/manifests/kube-controller-manager.yaml | grep cluster-cidr= | awk -F= '{print $NF}'`
​
# 注意下面的这个步骤是把calico-etcd.yaml文件里面的CALICO_IPV4POOL_CIDR下的网段改成自己的Pod网段，也就是把192.168.x.x/16改成自己的集群网段，并打开注释：
​
所以更改的时候请确保这个步骤的这个网段没有被统一替换掉，如果被替换掉了，还请改回来：
​
# sed -i 's@# - name: CALICO_IPV4POOL_CIDR@- name: CALICO_IPV4POOL_CIDR@g; s@#   value: "192.168.0.0/16"@  value: '"${POD_SUBNET}"'@g' calico-etcd.yaml
​
# kubectl apply -f calico-etcd.yaml
​
查看容器状态
# kubectl  get po -n kube-system
NAME                                       READY   STATUS    RESTARTS   AGE
calico-kube-controllers-5f6d4b864b-pwvnb   1/1     Running   0          3m29s
calico-node-5lz9m                          1/1     Running   0          3m29s
calico-node-8z4bg                          1/1     Running   0          3m29s
calico-node-lmzvf                          1/1     Running   0          3m29s
calico-node-mpngv                          1/1     Running   0          3m29s
calico-node-vmqsl                          1/1     Running   0          3m29s
coredns-54d67798b7-8525g                   1/1     Running   0          39m
coredns-54d67798b7-fxs72                   1/1     Running   0          39m
etcd-k8s-master01                          1/1     Running   0          39m
etcd-k8s-master02                          1/1     Running   0          33m
etcd-k8s-master03                          1/1     Running   0          31m
kube-apiserver-k8s-master01                1/1     Running   0          39m
kube-apiserver-k8s-master02                1/1     Running   0          33m
kube-apiserver-k8s-master03                1/1     Running   0          30m
kube-controller-manager-k8s-master01       1/1     Running   1          39m
kube-controller-manager-k8s-master02       1/1     Running   0          33m
kube-controller-manager-k8s-master03       1/1     Running   0          31m
kube-proxy-hnkmj                           1/1     Running   0          39m
kube-proxy-jk4dm                           1/1     Running   0          32m
kube-proxy-nbcg2                           1/1     Running   0          32m
kube-proxy-qv9k7                           1/1     Running   0          32m
kube-proxy-x6xdc                           1/1     Running   0          33m
kube-scheduler-k8s-master01                1/1     Running   1          39m
kube-scheduler-k8s-master02                1/1     Running   0          33m
kube-scheduler-k8s-master03                1/1     Running   0          30m

18、Metrics部署

# 在新版的Kubernetes中系统资源的采集均使用Metrics-server，可以通过Metrics采集节点和Pod的内存、磁盘、CPU和网络的使用率。
​
# 将Master01节点的front-proxy-ca.crt复制到所有Node节点
# scp /etc/kubernetes/pki/front-proxy-ca.crt k8s-node01:/etc/kubernetes/pki/front-proxy-ca.crt
# scp /etc/kubernetes/pki/front-proxy-ca.crt k8s-node(其他节点自行拷贝):/etc/kubernetes/pki/front-proxy-ca.crt
​
# 安装metrics server
# cd /root/k8s-ha-install/metrics-server-0.4.x-kubeadm/
​
# kubectl  create -f comp.yaml 
serviceaccount/metrics-server created
clusterrole.rbac.authorization.k8s.io/system:aggregated-metrics-reader created
clusterrole.rbac.authorization.k8s.io/system:metrics-server created
rolebinding.rbac.authorization.k8s.io/metrics-server-auth-reader created
clusterrolebinding.rbac.authorization.k8s.io/metrics-server:system:auth-delegator created
clusterrolebinding.rbac.authorization.k8s.io/system:metrics-server created
service/metrics-server created
deployment.apps/metrics-server created
apiservice.apiregistration.k8s.io/v1beta1.metrics.k8s.io created
# 查看状态
# kubectl  top node
NAME           CPU(cores)   CPU%   MEMORY(bytes)   MEMORY%   
k8s-master01   109m         2%     1296Mi          33%       
k8s-master02   99m          2%     1124Mi          29%       
k8s-master03   104m         2%     1082Mi          28%       
k8s-node01     55m          1%     761Mi           19%       
k8s-node02     53m          1%     663Mi           17%

19、Dashboard部署

# Dashboard用于展示集群中的各类资源，同时也可以通过Dashboard实时查看Pod的日志和在容器中执行一些命令等。
​
# 安装指定版本dashboard
# cd /root/k8s-ha-install/dashboard/
​
# kubectl  create -f .
serviceaccount/admin-user created
clusterrolebinding.rbac.authorization.k8s.io/admin-user created
namespace/kubernetes-dashboard created
serviceaccount/kubernetes-dashboard created
service/kubernetes-dashboard created
secret/kubernetes-dashboard-certs created
secret/kubernetes-dashboard-csrf created
secret/kubernetes-dashboard-key-holder created
configmap/kubernetes-dashboard-settings created
role.rbac.authorization.k8s.io/kubernetes-dashboard created
clusterrole.rbac.authorization.k8s.io/kubernetes-dashboard created
rolebinding.rbac.authorization.k8s.io/kubernetes-dashboard created
clusterrolebinding.rbac.authorization.k8s.io/kubernetes-dashboard created
deployment.apps/kubernetes-dashboard created
service/dashboard-metrics-scraper created
deployment.apps/dashboard-metrics-scraper created
​
# 安装最新版
# 官方GitHub地址：<https://github.com/kubernetes/dashboard>
# 可以在官方dashboard查看到最新版dashboard
​
# kubectl apply -f <https://raw.githubusercontent.com/kubernetes/dashboard/v2.0.3/aio/deploy/recommended.yaml>
​
# 创建管理员用户
# vim admin.yaml
# cat admin.yaml 
apiVersion: v1
kind: ServiceAccount
metadata:
  name: admin-user
  namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding 
metadata: 
  name: admin-user
  annotations:
    rbac.authorization.kubernetes.io/autoupdate: "true"
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: cluster-admin
subjects:
- kind: ServiceAccount
  name: admin-user
  namespace: kube-system
      
# kubectl apply -f admin.yaml -n kube-system
# 更改dashboard的svc为NodePort：
# kubectl edit svc kubernetes-dashboard -n kubernetes-dashboard
​
# 将ClusterIP更改为NodePort（如果已经为NodePort忽略此步骤）：
# 查看端口号：
# kubectl get svc kubernetes-dashboard -n kubernetes-dashboard
# kubectl get svc kubernetes-dashboard -n kubernetes-dashboard
NAME                   TYPE       CLUSTER-IP       EXTERNAL-IP   PORT(S)         AGE
kubernetes-dashboard   NodePort   10.111.208.184   <none>        443:32439/TCP   117m
​
# 根据自己的实例端口号，通过任意安装了kube-proxy的宿主机或者VIP的IP+端口即可访问到dashboard：
# 访问Dashboard：<https://172.29.207.175:32439（请更改为自己的端口），选择登录方式为令牌（即token方式）
​
# 查看token值：
# kubectl -n kube-system describe secret $(kubectl -n kube-system get secret | grep admin-user | awk '{print $1}')
Name:         admin-user-token-fq494
Namespace:    kube-system
Labels:       <none>
Annotations:  kubernetes.io/service-account.name: admin-user
              kubernetes.io/service-account.uid: 05f5fe77-22ac-4084-893e-8e6b039e2013
​
Type:  kubernetes.io/service-account-token
​
Data
====
ca.crt:     1066 bytes
namespace:  11 bytes
token:      eyJhbGciOiJSUzI1NiIsImtpZCI6ImRxenIzZmFwVWRDRUI3bTZVeVJKSGo0RUN3U0VxSUJ1NDZZeWZibUE3LXcifQ.eyJpc3MiOiJrdWJlcm5ldGVzL3NlcnZpY2VhY2NvdW50Iiwia3ViZXJuZXRlcy5pby9zZXJ2aWNlYWNjb3VudC9uYW1lc3BhY2UiOiJrdWJlLXN5c3RlbSIsImt1YmVybmV0ZXMuaW8vc2VydmljZWFjY291bnQvc2VjcmV0Lm5hbWUiOiJhZG1pbi11c2VyLXRva2VuLWZxNDk0Iiwia3ViZXJuZXRlcy5pby9zZXJ2aWNlYWNjb3VudC9zZXJ2aWNlLWFjY291bnQubmFtZSI6ImFkbWluLXVzZXIiLCJrdWJlcm5ldGVzLmlvL3NlcnZpY2VhY2NvdW50L3NlcnZpY2UtYWNjb3VudC51aWQiOiIwNWY1ZmU3Ny0yMmFjLTQwODQtODkzZS04ZTZiMDM5ZTIwMTMiLCJzdWIiOiJzeXN0ZW06c2VydmljZWFjY291bnQ6a3ViZS1zeXN0ZW06YWRtaW4tdXNlciJ9.XBEUxdMbEroOD78w3WnNpn3cwNCUnTh5aBn3Zs2m4V9uIF4SfrcBbgGHaFrQxkt-P5mVpvia8PhNoq_Cd1Mh7cWJPFYHdVF_TF7xn20OV1BtagRlzd1IfFYW-3bKYPkW0BdhKcocvoSZl1U74HzWrXU-DlwTwhjKedSJfbYvTeVfJYU_Pb2nXS9XZLfrHgxA3zUpT0qy_Ldpd8XGmAQe5dA4aaFNx-Nws-AeZwCeJI78-omCJyFp7dZZQxA8t2rnWgTpNfMmrSuQEmekGNe863UVQkdrEY-ptnVndV14VXf6OCSJvoGBmNzXTvbboXkUE8-x2FlhbrnaBbt1loC-jw

<!—->

登录dashboard
推荐firefox
将token值输入到令牌后，单击登录即可访问Dashboard

20、一些必须的配置更改

# 将Kube-proxy改为ipvs模式，因为在初始化集群的时候注释了ipvs配置，所以需要自行修改一下：
# 在master01节点执行
# kubectl edit cm kube-proxy -n kube-system
mode: “ipvs”
# 更新Kube-Proxy的Pod：
# kubectl patch daemonset kube-proxy -p "{\"spec\":{\"template\":{\"metadata\":{\"annotations\":{\"date\":\"`date +'%s'`\"}}}}}" -n kube-system
# 验证Kube-Proxy模式
# curl 127.0.0.1:10249/proxyMode
ipvs

第三章 注意事项

注意：kubeadm安装的集群，证书有效期默认是一年。master节点的kube-apiserver、kube-scheduler、kube-controller-manager、etcd都是以容器运行的。可以通过kubectl get po -n kube-system查看。 启动和二进制不同的是， kubelet的配置文件在/etc/sysconfig/kubelet和/var/lib/kubelet/config.yaml 其他组件的配置文件在/etc/Kubernetes/manifests目录下，比如kube-apiserver.yaml，该yaml文件更改后，kubelet会自动刷新配置，也就是会重启pod。不能再次创建该文件

Kubeadm安装后，master节点默认不允许部署pod，可以通过以下方式打开：
查看Taints：
# kubectl describe node -l node-role.kubernetes.io/master= | grep Taints
Taints:             node-role.kubernetes.io/master:NoSchedule
Taints:             node-role.kubernetes.io/master:NoSchedule
Taints:             node-role.kubernetes.io/master:NoSchedule
​
# 删除Taint：
# kubectl taint node -l node-role.kubernetes.io/master node-role.kubernetes.io/master:NoSchedule-
node/k8s-master01 untainted
node/k8s-master02 untainted
node/k8s-master03 untainted
​
# kubectl describe node -l node-role.kubernetes.io/master= | grep Taints
Taints:             <none>
Taints:             <none>
Taints:             <none>

分类： Linux技术类

0 条评论

发表回复

Avatar placeholder

您的邮箱地址不会被公开。 必填项已用 * 标注

相关文章

Linux技术类

🚨 故障复盘：WordPress 网站频繁崩溃？原来是 MySQL 被系统“杀死”了！

关键词：OOM Killer、MySQL 被杀、内存不足、PHP-FP 阅读更多

Linux技术类

CentOS 7.4搭建NFS

NFS就是Network File System的缩写，它最大的功能就 阅读更多

Linux技术类

centos7.9安装zabbix5.0

1 rpm -Uvh https://repo.zabbix.com/ 阅读更多