1. 基礎環境規划：
| 主機名 | IP地址 | 節點說明 |
|---|---|---|
| k8s-node01 | 192.168.1.154 | node1節點 |
| k8s-node02 | 192.168.1.155 | node2節點 |
| master01 | 192.168.1.151 | master1節點 |
| master02 | 192.168.1.152 | master2節點 |
| master03 | 192.168.1.153 | master3節點 |
| 虛擬vip | 192.168.1.160 | 虛擬IP |
docker配置信息：
| 配置信息 | 備注 |
|---|---|
| 系統版本 | CentOS Linux release 7.6.1810 |
| Docker版本 | 20.10 |
| Pod網段 | 172.168.0.0/12 |
| Service網段 | 10.96.0.0/12 |
注意：公有雲上搭建VIP是公有雲的負載均衡的IP，比如阿里雲的內網SLB的地址，騰訊雲內網ELB的地址
#花里胡哨的美化配置：
#命令行優化：
echo "export PS1='\[\033[01;31m\]\u\[\033[00m\]@\[\033[01;32m\]\h\[\033[00m\][\[\033[01;33m\]\t\[\033[00m\]]:\[\033[01;34m\]\w\[\033[00m\]$ '" >>/etc/profile
source /etc/profile
#歷史記錄優化：
export HISTTIMEFORMAT='%F %T '
echo "export HISTTIMEFORMAT='%F %T '" >>/etc/profile
source /etc/profile
2.前期准備工作
2.1 所有節點hosts配置
#每個節點設置主機名：
hostnamectl set-hostname [主機名]
如：
hostnamectl set-hostname k8s-master01
#所有節點配置hosts，修改/etc/hosts如下：
[root@k8s-master01 ~]# cat /etc/hosts
192.168.1.151 k8s-master01
192.168.1.152 k8s-master02
192.168.1.153 k8s-master03
192.168.1.160 k8s-master-lb # 如果不是高可用集群，該IP為Master01的IP
192.168.1.154 k8s-node01
192.168.1.155 k8s-node02
cat <<EOF > /etc/hosts
127.0.0.1 localhost localhost.localdomain localhost4 localhost4.localdomain4
::1 localhost localhost.localdomain localhost6 localhost6.localdomain6
192.168.1.151 k8s-master01
192.168.1.152 k8s-master02
192.168.1.153 k8s-master03
192.168.1.160 k8s-master-lb
192.168.1.154 k8s-node01
192.168.1.155 k8s-node02
EOF
#命令行優化：
echo "export PS1='\[\033[01;31m\]\u\[\033[00m\]@\[\033[01;32m\]\h\[\033[00m\][\[\033[01;33m\]\t\[\033[00m\]]:\[\033[01;34m\]\w\[\033[00m\]$ '" >>/etc/profile
source /etc/profile
#歷史記錄優化：
export HISTTIMEFORMAT='%F %T '
echo "export HISTTIMEFORMAT='%F %T '" >>/etc/profile
source /etc/profile
2.2 所有節點源配置[centos7]
mv /etc/yum.repos.d/* /root
cd /etc/yum.repos.d/
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 <<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
sed -i -e '/mirrors.cloud.aliyuncs.com/d' -e '/mirrors.aliyuncs.com/d' /etc/yum.repos.d/CentOS-Base.repo
yum clean all
yum install -y epel-release
#安裝必備工具：
#必備工具安裝
yum install wget jq psmisc vim net-tools telnet yum-utils device-mapper-persistent-data lvm2 git -y
2.3 所有節點優化
#所有節點關閉防火牆、selinux、dnsmasq、swap。服務器配置如下：
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
#關閉swap分區
swapoff -a && sysctl -w vm.swappiness=0
sed -ri '/^[^#]*swap/s@^@#@' /etc/fstab
#安裝ntpdate
rpm -ivh http://mirrors.wlnmp.com/centos/wlnmp-release-centos.noarch.rpm
#添加計划任務
yum install -y ntpdate
echo '*/5 * * * * ntpdate cn.pool.ntp.org' >>/var/spool/cron/root
systemctl restart crond
ntpdate time2.aliyun.com
#所有節點同步時間。時間同步配置如下：
ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime
echo 'Asia/Shanghai' >/etc/timezone
ntpdate time2.aliyun.com
# 加入到crontab
*/5 * * * * /usr/sbin/ntpdate time2.aliyun.com
#limit優化
ulimit -SHn 65535
cat <<EOF >> /etc/security/limits.conf
* soft nofile 655360
* hard nofile 131072
* soft nproc 655350
* hard nproc 655350
* soft memlock unlimited
* hard memlock unlimited
EOF
2.4 配置免密[中控機操作]
#Master01節點免密鑰登錄其他節點，安裝過程中生成配置文件和證書均在Master01上操作，集群管理也在Master01上操作，阿里雲或者AWS上需要單獨一台kubectl服務器。密鑰配置如下：
cd /root
ssh-keygen -t rsa
for i in k8s-master01 k8s-master02 k8s-master03 k8s-node01 k8s-node02;do ssh-copy-id -i .ssh/id_rsa.pub $i;done
2.5 升級內核 [中控機操作]
#下載安裝所有的源碼文件
cd /root/
git clone https://github.com/dotbalo/k8s-ha-install.git
#如果無法下載請使用下面的重試：
git clone https://gitee.com/dukuan/k8s-ha-install.git
# 在master01節點下載內核,並緩存 [所有機器升級]
#CentOS7需要升級系統，CentOS8可以按需升級系統
yum update -y --exclude=kernel* && reboot
# 內核配置
#CentOS7 需要升級內核至4.18+，本地升級的版本為4.19
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
#從master01節點傳到其他節點：
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 $i:/root/ ; done
#所有節點安裝內核
cd /root && yum localinstall -y kernel-ml*
#所有節點更改內核啟動順序
grub2-set-default 0 && grub2-mkconfig -o /etc/grub2.cfg
grubby --args="user_namespace.enable=1" --update-kernel="$(grubby --default-kernel)"
#檢查默認內核是不是4.19
root@k8s-master01[17:05:33]:~$ grubby --default-kernel
/boot/vmlinuz-4.19.12-1.el7.elrepo.x86_64
#所有節點重啟，然后檢查內核是不是4.19
root@k8s-master01[17:09:20]:~$ grubby --default-kernel
/boot/vmlinuz-4.19.12-1.el7.elrepo.x86_64
#如果是，則說明內核配置正確
2.6 所有節點安裝ipvsadm
yum install ipvsadm ipset sysstat conntrack libseccomp -y
#所有節點配置ipvs模塊，在內核4.19+版本nf_conntrack_ipv4已經改為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
#創建 /etc/modules-load.d/ipvs.conf 並加入以下內容：
cat >/etc/modules-load.d/ipvs.conf <<EOF
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
EOF
#設置為開機啟動
systemctl enable --now systemd-modules-load.service
2.7 k8s內核優化
#開啟一些k8s集群中必須的內核參數，所有節點配置k8s內核：
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
#所有節點配置完內核后，重啟服務器，保證重啟后內核依舊加載
reboot
lsmod | grep --color=auto -e ip_vs -e nf_conntrack
#重啟后結果如下代表正常：
root@k8s-master01[17:19:15]:~$ lsmod | grep --color=auto -e ip_vs -e nf_conntrack
ip_vs_ftp 16384 0
nf_nat 32768 1 ip_vs_ftp
ip_vs_sed 16384 0
ip_vs_nq 16384 0
ip_vs_fo 16384 0
ip_vs_sh 16384 0
ip_vs_dh 16384 0
ip_vs_lblcr 16384 0
ip_vs_lblc 16384 0
ip_vs_wrr 16384 0
ip_vs_rr 16384 0
ip_vs_wlc 16384 0
ip_vs_lc 16384 0
ip_vs 151552 24 ip_vs_wlc,ip_vs_rr,ip_vs_dh,ip_vs_lblcr,ip_vs_sh,ip_vs_fo,ip_vs_nq,ip_vs_lblc,ip_vs_wrr,ip_vs_lc,ip_vs_sed,ip_vs_ftp
nf_conntrack 143360 2 nf_nat,ip_vs
nf_defrag_ipv6 20480 1 nf_conntrack
nf_defrag_ipv4 16384 1 nf_conntrack
libcrc32c 16384 4 nf_conntrack,nf_nat,xfs,ip_vs
3. 基本組件安裝
本節主要安裝的是集群中用到的各種組件，比如Docker-ce、Kubernetes各組件等。
3.1 所有節點安裝 docker-ce 20.10
yum install -y docker-ce-20.10.6-* docker-ce-cli-20.10.6-*.x86_64
rm -f /etc/docker/*
sudo mkdir -p /etc/docker
sudo tee /etc/docker/daemon.json <<-'EOF'
{
"registry-mirrors": ["https://ajvcw8qn.mirror.aliyuncs.com"],
"exec-opts": ["native.cgroupdriver=systemd"]
}
EOF
sudo systemctl daemon-reload
sudo systemctl restart docker
systemctl enable --now docker.service
3.2 所有機器安裝k8s組件kubeadm
yum list kubeadm.x86_64 --showduplicates | sort -r
#所有節點安裝最新版本kubeadm：
yum install kubeadm-1.21* kubelet-1.21* kubectl-1.21* -y
#默認配置的pause鏡像使用gcr.io倉庫，國內可能無法訪問，所以這里配置Kubelet使用阿里雲的pause鏡像
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
#設置開機啟動
systemctl daemon-reload
systemctl enable --now kubelet
3.3 安裝高可用組件[master相關服務器執行]
注意：如果不是高可用集群，haproxy和keepalived無需安裝）
公有雲要用公有雲自帶的負載均衡，比如阿里雲的SLB，騰訊雲的ELB，用來替代haproxy和keepalived，因為公有雲大部分都是不支持keepalived的，另外如果用阿里雲的話，kubectl控制端不能放在master節點，推薦使用騰訊雲，因為阿里雲的slb有回環的問題，也就是slb代理的服務器不能反向訪問SLB，但是騰訊雲修復了這個問題。
#所有Master節點通過yum安裝HAProxy和KeepAlived：
root@k8s-master01[17:44:47]:~$ yum install keepalived haproxy -y
#配置HAProxy：
#所有Master節點配置HAProxy（詳細配置參考HAProxy文檔，所有Master節點的HAProxy配置相同）：
mkdir /etc/haproxy
cat >/etc/haproxy/haproxy.cfg<<"EOF"
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 192.168.1.151:6443 check
server k8s-master02 192.168.1.152:6443 check
server k8s-master03 192.168.1.153:6443 check
EOF
#所有Master節點配置KeepAlived，配置不一樣，注意區分
#[root@k8s-master01 pki]# vim /etc/keepalived/keepalived.conf ，注意每個節點的IP和網卡（interface參數）
#注意修改配置，下面IP替換為master的IP地址：
server k8s-master01 192.168.1.151:6443 check
server k8s-master02 192.168.1.152:6443 check
server k8s-master03 192.168.1.153:6443 check
#配置keepalived
#所有Master節點配置KeepAlived，配置不一樣，注意區分
#每台服務器 優先級必須不同 priority 100 其他機器設置為 99 98
#master01 配置：
[root@k8s-master01 pki]# mkdir -p /etc/keepalived
[root@k8s-master01 pki]# cat >/etc/keepalived/keepalived.conf<<"EOF"
! 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 eth0
mcast_src_ip 192.168.1.151
virtual_router_id 51
priority 101
advert_int 2
authentication {
auth_type PASS
auth_pass K8SHA_KA_AUTH
}
virtual_ipaddress {
192.168.1.160
}
track_script {
chk_apiserver
}
}
EOF
#Master02 配置：
[root@k8s-master02 pki]# cat >/etc/keepalived/keepalived.conf<<"EOF"
! 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 eth0
mcast_src_ip 192.168.1.152
virtual_router_id 51
priority 100
advert_int 2
authentication {
auth_type PASS
auth_pass K8SHA_KA_AUTH
}
virtual_ipaddress {
192.168.1.160
}
track_script {
chk_apiserver
}
}
EOF
#Master03 配置：
[root@k8s-master03 pki]# cat >/etc/keepalived/keepalived.conf<<"EOF"
! 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 eth0
mcast_src_ip 192.168.1.153
virtual_router_id 51
priority 100
advert_int 2
authentication {
auth_type PASS
auth_pass K8SHA_KA_AUTH
}
virtual_ipaddress {
192.168.1.160
}
EOF
#快捷辦法[變量獲取本機IP]：
host=$(hostname -i)
cat >/etc/keepalived/keepalived.conf<<EOF
! 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 eth0
mcast_src_ip $(hostname -i)
virtual_router_id 51
priority 101
advert_int 2
authentication {
auth_type PASS
auth_pass K8SHA_KA_AUTH
}
virtual_ipaddress {
192.168.1.160
}
track_script {
chk_apiserver
}
}
EOF
3.4 健康檢查配置[所有master服務器添加健康檢查腳本]
cat > /etc/keepalived/check_apiserver.sh <<"EOF"
#!/bin/bash
err=0
for k in $(seq 1 3)
do
check_code=$(pgrep haproxy)
if [[ $check_code == "" ]]; then
err=$(expr $err + 1)
sleep 1
continue
else
err=0
break
fi
done
if [[ $err != "0" ]]; then
echo "systemctl stop keepalived"
/usr/bin/systemctl stop keepalived
exit 1
else
exit 0
fi
EOF
chmod +x /etc/keepalived/check_apiserver.sh
3.5 啟動haproxy和keepalived[每台master啟用]
systemctl daemon-reload
systemctl enable --now haproxy
systemctl enable --now keepalived
3.6 測試haproxy與keepalived是否正常
重要：如果安裝了keepalived和haproxy，需要測試keepalived是否是正常的
所以這里需要測試VIP是否通
ping 192.168.1.160 -c 4
root@k8s-master01[18:17:06]:~$ ping 192.168.1.160 -c 4
PING 192.168.1.160 (192.168.1.160) 56(84) bytes of data.
64 bytes from 192.168.1.160: icmp_seq=1 ttl=64 time=0.045 ms
root@k8s-master02[18:17:10]:~$ ping 192.168.1.160 -c 4
PING 192.168.1.160 (192.168.1.160) 56(84) bytes of data.
64 bytes from 192.168.1.160: icmp_seq=1 ttl=64 time=1.00 ms
root@k8s-master03[18:17:13]:~$ ping 192.168.1.160 -c 4
PING 192.168.1.160 (192.168.1.160) 56(84) bytes of data.
64 bytes from 192.168.1.160: icmp_seq=1 ttl=64 time=2.48 ms
telnet測試：
root@k8s-master03[18:19:51]:~$ telnet 192.168.1.160 16443
Trying 192.168.1.160...
Connected to 192.168.1.160.
Escape character is '^]'.
Connection closed by foreign host.
注意： 如果ping不通且telnet沒有出現 ] ，則認為VIP不可以，不可在繼續往下執行，需要排查keepalived的問題，比如防火牆和selinux，haproxy和keepalived的狀態，監聽端口等
所有節點查看防火牆狀態必須為disable和inactive：systemctl status firewalld
所有節點查看selinux狀態，必須為disable：getenforce
master節點查看haproxy和keepalived狀態：systemctl status keepalived haproxy
master節點查看監聽端口：netstat -lntp
排查思路：
keepalived的問題，比如防火牆和selinux，haproxy和keepalived的狀態，監聽端口等
所有節點查看防火牆狀態必須為disable和inactive：systemctl status firewalld
所有節點查看selinux狀態，必須為disable：getenforce
master節點查看haproxy和keepalived狀態：systemctl status keepalived haproxy
master節點查看監聽端口：netstat -lntp
4.0 kubernetes集群初始化
官方初始化文檔：
https://kubernetes.io/docs/setup/production-environment/tools/kubeadm/high-availability/
Master01節點創建 kubeadm-config.yaml 配置文件如下：
Master01：（# 注意，如果不是高可用集群，192.168.1.160:16443改為master01的地址，16443改為apiserver的端口，默認是6443，注意更改v1.18.5自己服務器kubeadm的版本：kubeadm version）
#查看辦法：
kubectl version
root@k8s-master01[18:25:48]:~$ kubectl version
Client Version: version.Info{Major:"1", Minor:"21", GitVersion:"v1.21.0", GitCommit:"cb303e613a121a29364f75cc67d3d580833a7479", GitTreeState:"clean", BuildDate:"2021-04-08T16:31:21Z", GoVersion:"go1.16.1", Compiler:"gc", Platform:"linux/amd64"}
因為安裝的版本是 GitVersion:"v1.21.0"
下面的yaml文件中的對應版本需要改為 v1.21.0
cat kubeadm-config.yaml
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: 192.168.1.151
bindPort: 6443
nodeRegistration:
criSocket: /var/run/dockershim.sock
name: k8s-master01
taints:
- effect: NoSchedule
key: node-role.kubernetes.io/master
---
apiServer:
certSANs:
- 192.168.1.160
timeoutForControlPlane: 4m0s
apiVersion: kubeadm.k8s.io/v1beta2
certificatesDir: /etc/kubernetes/pki
clusterName: kubernetes
controlPlaneEndpoint: 192.168.1.160:16443
controllerManager: {}
dns:
type: CoreDNS
etcd:
local:
dataDir: /var/lib/etcd
imageRepository: registry.cn-hangzhou.aliyuncs.com/google_containers
kind: ClusterConfiguration
kubernetesVersion: v1.21.0
networking:
dnsDomain: cluster.local
podSubnet: 172.16.0.0/12
serviceSubnet: 192.168.0.0/16
scheduler: {}
更新kubeadm文件[只有master01執行] 注意：需要修改的地方是 網段和版本 網段可以保持默認，但是版本建議與當前安裝版本一致 kubeadm-config.yaml中的網段需要修改為 172.168.0.0/12 通過grep 'podSubnet:' /root/kubeadm-config.yaml
#更新kubeadm文件: kubeadm-config.yaml
kubeadm config migrate --old-config kubeadm-config.yaml --new-config new.yaml
#將new.yaml文件復制到其他master節點，之后所有Master節點提前下載鏡像，可以節省初始化時間：
for i in k8s-master02 k8s-master03; do scp new.yaml $i:/root/; done
#在其他master節點提前下載鏡像，用於解決初始化時間
kubeadm config images pull --config /root/new.yaml
systemctl enable --now kubelet
#執行kubeadm config images pull --config /root/new.yaml如果出現如下報錯
[config/images] Pulled registry.cn-hangzhou.aliyuncs.com/google_containers/pause:3.4.1
[config/images] Pulled registry.cn-hangzhou.aliyuncs.com/google_containers/etcd:3.4.13-0
failed to pull image "registry.cn-hangzhou.aliyuncs.com/google_containers/coredns/coredns:v1.8.0": output: Error response from daemon: manifest for registry.cn-hangzhou.aliyuncs.com/google_containers/coredns/coredns:v1.8.0 not found: manifest unknown: manifest unknown
, error: exit status 1
To see the stack trace of this error execute with --v=5 or higher
#coredns如果沒有成功
出現ImagePullBackOff：
coredns-57d4cbf879-gnh6j 0/1 ImagePullBackOff 0 6m
coredns-57d4cbf879-z79bt 0/1 ImagePullBackOff 0 6m
#請所有節點執行，用於下載鏡像即可：
docker pull registry.cn-beijing.aliyuncs.com/dotbalo/coredns:1.8.0
docker tag registry.cn-beijing.aliyuncs.com/dotbalo/coredns:1.8.0 registry.cn-hangzhou.aliyuncs.com/google_containers/coredns/coredns:v1.8.0
#再次查看就會自動拉起
coredns-57d4cbf879-gnh6j 1/1 Running 0 16h
coredns-57d4cbf879-z79bt 1/1 Running 0 16h
所有節點設置開機自啟動kubelet systemctl daemon-reload systemctl enable --now kubelet
4.2 master01初始化
Master01節點初始化，初始化以后會在/etc/kubernetes目錄下生成對應的證書和配置文件，之后其他Master節點加入Master01即可：
#master01節點執行初始化：
kubeadm init --config /root/new.yaml --upload-certs
#如果初始化失敗，重置后再次初始化，命令如下：
kubeadm reset -f ; ipvsadm --clear ; rm -rf ~/.kube
關鍵提示信息：
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:
[其他master加入集群]
kubeadm join 192.168.1.160:16443 --token 7t2weq.bjbawausm0jaxury \
--discovery-token-ca-cert-hash sha256:aeb438bb077768d6626fbc5f2ff61a903bfea24c2eaaa3fde49bace433176384 \
--control-plane --certificate-key 530a5f56ce32e4ab69b384f41e6165327e23577f4924558b36efb6bb08a883e5
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:
[其他node加入集群]
kubeadm join 192.168.1.160:16443 --token 7t2weq.bjbawausm0jaxury \
--discovery-token-ca-cert-hash sha256:aeb438bb077768d6626fbc5f2ff61a903bfea24c2eaaa3fde49bace433176384
#優化
mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/config
cat <<EOF >> /root/.bashrc
export KUBECONFIG=/etc/kubernetes/admin.conf
EOF
source /root/.bashrc
4.3 master02 master03 加入master集群
#Token過期后生成新的token：
kubeadm token create --print-join-command
#Master需要生成-certificate-key
root@k8s-master01[15:36:45]:~$ kubeadm init phase upload-certs --upload-certs
[upload-certs] Storing the certificates in Secret "kubeadm-certs" in the "kube-system" Namespace
[upload-certs] Using certificate key:
9b5153fe13fe5a9286eb68fae35311f7357b854a2f8ad925bc7e45b16d2b886e
#其他master加入集群
kubeadm join 192.168.1.160:16443 --token fgtxr1.bz6dw1tci1kbj977 --discovery-token-ca-cert-hash sha256:06ebf46458a41922ff1f5b3bc49365cf3dd938f1a7e3e4a8c8049b5ec5a3aaa5 \
--control-plane --certificate-key 9b5153fe13fe5a9286eb68fae35311f7357b854a2f8ad925bc7e45b16d2b886e
4.4 node01 node02 加入node集群
kubeadm join 192.168.1.160:16443 --token 7t2weq.bjbawausm0jaxury --discovery-token-ca-cert-hash sha256:aeb438bb077768d6626fbc5f2ff61a903bfea24c2eaaa3fde49bace433176384
#過程
root@k8s-node01[15:29:45]:~$ kubeadm join 192.168.1.160:16443 --token 7t2weq.bjbawausm0jaxury \
> --discovery-token-ca-cert-hash sha256:aeb438bb077768d6626fbc5f2ff61a903bfea24c2eaaa3fde49bace433176384
[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.
4.5 加入結果概覽
root@k8s-master01[16:06:10]:~$ kubectl get nodes
NAME STATUS ROLES AGE VERSION
k8s-master01 NotReady control-plane,master 6m15s v1.21.0
k8s-master02 NotReady control-plane,master 5m23s v1.21.0
k8s-master03 NotReady control-plane,master 4m21s v1.21.0
k8s-node01 NotReady <none> 11s v1.21.0
k8s-node02 NotReady <none> 0s v1.21.0
采用初始化安裝方式，所有的系統組件均以容器的方式運行並且在kube-system命名空間內，此時可以查看Pod狀態：
root@k8s-master01[20:18:57]:~$ kubectl get pod -n kube-system
NAME READY STATUS RESTARTS AGE
coredns-57d4cbf879-8vs6c 0/1 Pending 0 75m
coredns-57d4cbf879-p99nc 0/1 Pending 0 75m
etcd-k8s-master01 1/1 Running 0 75m
etcd-k8s-master02 1/1 Running 0 4m45s
etcd-k8s-master03 1/1 Running 0 4m23s
kube-apiserver-k8s-master01 1/1 Running 0 75m
kube-apiserver-k8s-master02 1/1 Running 0 4m45s
kube-apiserver-k8s-master03 1/1 Running 0 4m10s
kube-controller-manager-k8s-master01 1/1 Running 1 75m
kube-controller-manager-k8s-master02 1/1 Running 0 4m45s
kube-controller-manager-k8s-master03 1/1 Running 0 4m21s
kube-proxy-2zc6p 1/1 Running 0 4m46s
kube-proxy-djtbn 1/1 Running 0 3m30s
kube-proxy-g2ddr 1/1 Running 0 75m
kube-proxy-gf7w8 1/1 Running 0 3m34s
kube-proxy-mfsbz 1/1 Running 0 3m59s
kube-scheduler-k8s-master01 1/1 Running 1 75m
kube-scheduler-k8s-master02 1/1 Running 0 4m45s
kube-scheduler-k8s-master03 1/1 Running 0 4m19s
#出現 coredns Pending狀態 重新下載這個包，然后再次查看
docker pull registry.cn-beijing.aliyuncs.com/dotbalo/coredns:1.8.0
docker tag registry.cn-beijing.aliyuncs.com/dotbalo/coredns:1.8.0 registry.cn-hangzhou.aliyuncs.com/google_containers/coredns/coredns:v1.8.0
#此時 coredns已經啟動完畢
root@k8s-master01[20:44:59]:~$ kubectl get pod -n kube-system
NAME READY STATUS RESTARTS AGE
calico-kube-controllers-cdd5755b9-tfhp8 1/1 Running 0 7m31s
calico-node-4rsfw 1/1 Running 0 7m31s
calico-node-cgjjw 1/1 Running 0 7m31s
calico-node-gw2zz 1/1 Running 0 7m31s
calico-node-hzjn7 1/1 Running 0 7m31s
calico-node-sbjx4 1/1 Running 0 7m31s
coredns-57d4cbf879-8vs6c 1/1 Running 0 100m
coredns-57d4cbf879-p99nc 1/1 Running 0 100m
etcd-k8s-master01 1/1 Running 0 100m
etcd-k8s-master02 1/1 Running 0 29m
etcd-k8s-master03 1/1 Running 0 29m
kube-apiserver-k8s-master01 1/1 Running 0 100m
kube-apiserver-k8s-master02 1/1 Running 0 29m
kube-apiserver-k8s-master03 1/1 Running 0 29m
kube-controller-manager-k8s-master01 1/1 Running 1 100m
kube-controller-manager-k8s-master02 1/1 Running 0 29m
kube-controller-manager-k8s-master03 1/1 Running 0 29m
kube-proxy-2zc6p 1/1 Running 0 29m
kube-proxy-djtbn 1/1 Running 0 28m
kube-proxy-g2ddr 1/1 Running 0 100m
kube-proxy-gf7w8 1/1 Running 0 28m
kube-proxy-mfsbz 1/1 Running 0 28m
kube-scheduler-k8s-master01 1/1 Running 1 100m
kube-scheduler-k8s-master02 1/1 Running 0 29m
kube-scheduler-k8s-master03 1/1 Running 0 29m
4.6 Master01節點配置環境變量，用於訪問Kubernetes集群：
cat <<EOF >> /root/.bashrc
export KUBECONFIG=/etc/kubernetes/admin.conf
EOF
source /root/.bashrc
4.7 安裝calico網絡組件[master01操作]
/** 以下步驟只在master01執行 **/
cd /root/k8s-ha-install && git checkout manual-installation-v1.21.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://192.168.1.151:2379,https://192.168.1.152:2379,https://192.168.1.153:2379"#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'`
#修改網段
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 $NF}'`
注意下面的這個步驟是把calico-etcd.yaml文件里面的CALICO_IPV4POOL_CIDR下的網段改成自己的Pod網段，也就是把192.168.x.x/16改成自己的集群網段，並打開注釋：
所以更改的時候請確保這個步驟的這個網段沒有被統一替換掉，如果被替換掉了，還請改回來：
cd /root/k8s-ha-install/calico
sed -i 's@# - name: CALICO_IPV4POOL_CIDR@- name: CALICO_IPV4POOL_CIDR@g; s@# value: "192.168.0.0/16"@ value: '"${POD_SUBNET}"'@g' calico-etcd.yaml
修改完成后執行：
kubectl apply -f calico-etcd.yaml
查看容器和節點狀態:
kubectl get pod -n kube-system
5. Metrics部署
在新版的Kubernetes中系統資源的采集均使用Metrics-server，可以通過Metrics采集節點和Pod的內存、磁盤、CPU和網絡的使用率
#將Master01節點的front-proxy-ca.crt復制到所有Node節點
scp -r /etc/kubernetes/pki/front-proxy-ca.crt k8s-node01:/etc/kubernetes/pki/front-proxy-ca.crt
scp -r /etc/kubernetes/pki/front-proxy-ca.crt k8s-node02:/etc/kubernetes/pki/front-proxy-ca.crt
scp -r /etc/kubernetes/pki/front-proxy-ca.crt k8s-master02:/etc/kubernetes/pki/front-proxy-ca.crt
scp -r /etc/kubernetes/pki/front-proxy-ca.crt k8s-master03:/etc/kubernetes/pki/front-proxy-ca.crt
#安裝Metrics
cd /root/k8s-ha-install/metrics-server-0.4.x-kubeadm/
kubectl create -f comp.yaml
#輸出結果：
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
#查看安裝結果：
命令：kubectl get po -n kube-system -l k8s-app=metrics-server
結果：
NAME READY STATUS RESTARTS AGE
metrics-server-d6c46b546-4sxb8 1/1 Running 0 114s
命令：kubectl top po --use-protocol-buffers -A
NAMESPACE NAME CPU(cores) MEMORY(bytes)
kube-system calico-kube-controllers 2m 20Mi
kube-system calico-node-4rsfw 22m 78Mi
kube-system calico-node-cgjjw 26m 75Mi
kube-system calico-node-gw2zz 22m 72Mi
kube-system calico-node-hzjn7 24m 75Mi
kube-system calico-node-sbjx4 23m 70Mi
kube-system coredns-57d4cbf879-8vs6c 2m 17Mi
kube-system coredns-57d4cbf879-p99nc 2m 18Mi
kube-system etcd-k8s-master01 29m 80Mi
kube-system etcd-k8s-master02 25m 79Mi
kube-system etcd-k8s-master03 25m 80Mi
kube-system kube-apiserver-k8s-master01 45m 360Mi
kube-system kube-apiserver-k8s-master02 31m 352Mi
kube-system kube-apiserver-k8s-master03 28m 344Mi
kube-system kube-controller-manager-k8s-master01 2m 27Mi
kube-system kube-controller-manager-k8s-master02 9m 63Mi
kube-system kube-controller-manager-k8s-master03 1m 29Mi
kube-system kube-proxy-2zc6p 1m 26Mi
kube-system kube-proxy-djtbn 1m 25Mi
kube-system kube-proxy-g2ddr 1m 24Mi
kube-system kube-proxy-gf7w8 1m 26Mi
kube-system kube-proxy-mfsbz 1m 23Mi
kube-system kube-scheduler-k8s-master01 2m 26Mi
kube-system kube-scheduler-k8s-master02 2m 30Mi
kube-system kube-scheduler-k8s-master03 2m 27Mi
kube-system metrics-server-d6c46b546-4sxb8 4m 23Mi
5.1 安裝dashboard
#1. 安裝老版本
cd /root/k8s-ha-install/dashboard/
kubectl create -f .
#2. 安裝最新版：
kubectl apply -f https://raw.githubusercontent.com/kubernetes/dashboard/v2.2.0/aio/deploy/recommended.yaml
#授權：
vim admin.yaml
#--------------------------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
#--------------------------admin.yaml--------------------------#
#執行安裝
kubectl apply -f admin.yaml -n kube-system
5.2 登錄dashboard
在谷歌瀏覽器（Chrome）啟動文件中加入啟動參數，用於解決無法訪問Dashboard的問題，參考圖1-1：
谷歌瀏覽器添加參數：
--test-type --ignore-certificate-errors
2.更改dashboard的svc為NodePort：
kubectl edit svc kubernetes-dashboard -n kubernetes-dashboard
spec:
clusterIP: 10.108.157.21
clusterIPs:
- 10.108.157.21
externalTrafficPolicy: Cluster
ports:
- nodePort: 30195
port: 443
protocol: TCP
targetPort: 8443
selector:
k8s-app: kubernetes-dashboard
sessionAffinity: None
type: ClusterIP #改為 NodePort
#修改完成后如下：
spec:
clusterIP: 10.108.157.21
clusterIPs:
- 10.108.157.21
externalTrafficPolicy: Cluster
ports:
- nodePort: 30195
port: 443
protocol: TCP
targetPort: 8443
selector:
k8s-app: kubernetes-dashboard
sessionAffinity: None
type: NodePort #已經改為NodePort
修改完成后訪問dashboard：
#查看端口號：
kubectl get svc kubernetes-dashboard -n kubernetes-dashboard
通過https協議進行訪問
https://192.168.1.151:32234/
#查看token值：
kubectl -n kube-system describe secret $(kubectl -n kube-system get secret | grep admin-user | awk '{print $1}')
#得到 token:
eyJhbGciOiJSUzI1NiIsImtpZCI6IlFkM3BUd0xxVEZ6a0t4Njl2QnVaMWhLNUl4NFlzUkVrQngzbmlQeG4zczgifQ.eyJpc3MiOiJrdWJlcm5ldGVzL3NlcnZpY2VhY2NvdW50Iiwia3ViZXJuZXRlcy5pby9zZXJ2aWNlYWNjb3VudC9uYW1lc3BhY2UiOiJrdWJlLXN5c3RlbSIsImt1YmVybmV0ZXMuaW8vc2VydmljZWFjY291bnQvc2VjcmV0Lm5hbWUiOiJhZG1pbi11c2VyLXRva2VuLXRidjRkIiwia3ViZXJuZXRlcy5pby9zZXJ2aWNlYWNjb3VudC9zZXJ2aWNlLWFjY291bnQubmFtZSI6ImFkbWluLXVzZXIiLCJrdWJlcm5ldGVzLmlvL3NlcnZpY2VhY2NvdW50L3NlcnZpY2UtYWNjb3VudC51aWQiOiI0MzI2NDM1My1iNzY4LTRlNTEtYjljZS0wY2FlMzJlNThmOTgiLCJzdWIiOiJzeXN0ZW06c2VydmljZWFjY291bnQ6a3ViZS1zeXN0ZW06YWRtaW4tdXNlciJ9.jKtz39e-9EBlLhIW571Ms63ywad2z0s2hEa0ZalBRcEDXDKLN7jDejTLrrcyeNY5pRa8AUtbS1ckiYWI7OOlR3PBjD5Tgaz2HEKFw0FEoNMQnU8uLzR5WbUX4obOpzAyB4WYmCS9vK-ud98mmMHOT15Ee2BeaxIWTBL715m-NJcIxxByvsBtogVj7zWJayAVLOspMLps8hWk8XJDXpWEx0J8uU9KUPOey3YMiO5gNlk5TRHcZJOGg_7HV8_55MqKTQ8K9Jhsu5uVieB3kuJdwJdcGCGrMi1UVGx-RgJwGbZqMkXgy55QAp2he_sNFZmThhuxvz7FIclUyyoUZ43V9Q
將token粘貼到web頁面上的token輸入欄
登錄成功界面：
6. 配置修改
將Kube-proxy改為ipvs模式，因為在初始化集群的時候注釋了ipvs配置，所以需要自行修改一下：
在master01節點執行
kubectl edit cm kube-proxy -n kube-system
mode： 修改為 mode: ipvs
更新Kube-Proxy的Pod：
kubectl patch daemonset kube-proxy -p "{\"spec\":{\"template\":{\"metadata\":{\"annotations\":{\"date\":\"`date +'%s'`\"}}}}}" -n kube-system
驗證Kube-Proxy模式：
root@k8s-master01[14:52:28]:~/k8s-ha-install/dashboard$ curl 127.0.0.1:10249/proxyMode
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
驗證Kube-Proxy模式：
[root@k8s-master01 1.1.1]# curl 127.0.0.1:10249/proxyMode
ipvs
集群部署完成狀態:
root@k8s-master01[21:29:32]:~$ kubectl get nodes
NAME STATUS ROLES AGE VERSION
k8s-master01 Ready control-plane,master 145m v1.21.0
k8s-master02 Ready control-plane,master 73m v1.21.0
k8s-master03 Ready control-plane,master 73m v1.21.0
k8s-node01 Ready <none> 72m v1.21.0
k8s-node02 Ready <none> 72m v1.21.0
root@k8s-master01[21:29:33]:~$ cat /etc/hosts
127.0.0.1 localhost localhost.localdomain localhost4 localhost4.localdomain4
::1 localhost localhost.localdomain localhost6 localhost6.localdomain6
192.168.1.151 k8s-master01
192.168.1.152 k8s-master02
192.168.1.153 k8s-master03
192.168.1.160 k8s-master-lb
192.168.1.154 k8s-node01
192.168.1.155 k8s-node02
7. 高可用測試
k8s-master01是vip地址，停止eth0后vip消失
停止后，vip地址在master02上漂移成功
