环境准备

软件版本

系统：Ubuntu 22.04.3 TLS
内核：5.15.0-88-generic
kubernetes：1.27.8
etcd：etcd v3.5.9
containerd: v1.6.23
calico: v3.24.6

生产建议：
kubernetes版本版本大于5，如1.27.6
etcd集群应独立运行，部署5台服务器
k8s-master 服务器数量5台或部署3台运行着，预留扩容节点

规划部署三主两从，master也充当node(安装kubelet,kube-proxy)，这里硬件资源紧张，apiserver和etcd安装在同一服务器(生产不建议)。

IP规划

内网IP规划

hostname	IP/VIP	software
k8s-master01	192.168.77.81	etcd、apiserver、scheduler、controller-manager、kubelet、kube-proxy
k8s-master02	192.168.77.82	etcd、apiserver、scheduler、controller-manager、kubelet、kube-proxy
k8s-master03	192.168.77.83	etcd、apiserver、scheduler、controller-manager、kubelet、kube-proxy
k8s-node01	192.168.77.86	kubelet、kube-proxy
k8s-node02	192.168.77.87	kubelet、kube-proxy
haproxy01	192.168.77.101	haproxy、keepalived
haproxy02	192.168.77.102	haproxy、keepalived
VIP	192.168.77.100

集群内部IP规划

kubernetes Service网段：10.96.0.0/16
kubernetes Pod网段：10.244.0.0/16
kubernetes CoreDns IP地址: 10.96.0.10

配置静态IP

root@k8s-master01:~# cat /etc/netplan/00-installer-config.yaml 
# This is the network config written by 'subiquity'
network:
  ethernets:
    ens160:
      dhcp4: false
      addresses: [192.168.77.81/24]
      nameservers:
        addresses:
          - 223.5.5.5
      routes:
        - to: default
          via: 192.168.77.1
  version: 2

配置hosts解析

cat >> /etc/hosts << EOF
192.168.77.81 k8s-master01
192.168.77.82 k8s-master02
192.168.77.83 k8s-master03
192.168.77.86 k8s-node01
192.168.77.87 k8s-node02
EOF

配置主机名

hostnamectl set-hostname k8s-master01
bash

配置默认编辑器为vim

EDITOR_OPTION=3 # vim.basic
sudo update-alternatives --config editor <<< $EDITOR_OPTION

配置sudo 免密码

ubuntu 默认禁止root ssh登陆，这里使用ssh普通用户sudo权限操作

visudo

修改47行

# Members of the admin group may gain root privileges
%admin ALL=(ALL) NOPASSWD: ALL

这里使用sunday用户,注意需切换用户su -或退出终端重新sudo免密码才会生效

groupadd admin
usermod -G admin sunday

配置apt加速

sed -i 's@archive.ubuntu.com@mirrors.aliyun.com@g' /etc/apt/sources.list
apt-get update

安装必备包

apt-get update
apt-get install -y psmisc ca-certificates curl net-tools gnupg lsb-release nfs-kernel-server apt-transport-https telnet lvm2 ca-certificates gcc bash-completion ntpdate ipvsadm ipset sysstat conntrack libseccomp2 chrony -y

配置ssh密钥登陆

在master01配置
这里假设所有服务器的ssh用户为sunday 密码为123456，请根据需求自行更改

apt-get install -y expect
ssh-keygen -t rsa -P "" -f /root/.ssh/id_rsa
export user=sunday
export pass=123456
name=(k8s-master01 k8s-master02 k8s-master03 k8s-node01 k8s-node02)

for host in ${name[@]};do expect -c "
spawn ssh-copy-id -i /root/.ssh/id_rsa.pub $user@$host
    expect {
        \"*yes/no*\" {send \"yes\r\"; exp_continue}
        \"*password*\" {send \"$pass\r\"; exp_continue}
        \"*Password*\" {send \"$pass\r\";}
    }";
done

ssh首次连接公钥确认

apt install -y sshpass
export SSHPASS="123456"
user=sunday
name=(k8s-master01 k8s-master02 k8s-master03 k8s-node01 k8s-node02)
for host in ${name[@]};do
    sshpass -e ssh-copy-id -o StrictHostKeyChecking=no $user@$host
done

关闭防火墙

systemctl stop ufw.service

关闭swap分区

sed -ri '/^[^#]*swap/s@^@#@' /etc/fstab
swapoff -a
sysctl --w vm.swappiness=0

配置chrony时间同步

timedatectl set-timezone Asia/Shanghai
timedatectl set-local-rtc 0
echo "LC_TIME=en_DK.UTF-8" >> /etc/default/locale # 24小时制 切换用户生效 su - 或重新连接
apt-get install -y chrony

服务端配置(k8s-master01)

ntp="ntp.aliyun.com"
sed -i "s@^pool ntp.ubuntu.com.*@pool $ntp iburst@g" /etc/chrony/chrony.conf

# 重启服务
systemctl restart chronyd

# 使用客户端进行验证
chronyc sources -v

客户端配置
其他服务器chrony ntp指向这个服务器(k8s-master01)

ntp="192.168.77.81"
sed -i "s@^pool@#pool@g" /etc/chrony/chrony.conf
sed -i "s@^#pool ntp.ubuntu.com.*@server $ntp iburst@g" /etc/chrony/chrony.conf

# 重启服务
systemctl restart chronyd

# 使用客户端进行验证
chronyc sources -v

#查看时间同步源的状态
chronyc sourcestats -v

配置limits

cat >> /etc/security/limits.conf <<EOF
* soft nofile 655360
* hard nofile 131072
* soft nproc 655350
* hard nproc 655350
* soft memlock unlimited
* hard memlock unlimited
EOF

加载IPVS

cat > /etc/modules-load.d/ipvs.conf << EOF
ip_vs
ip_vs_rr
ip_vs_wrr
ip_vs_sh
nf_conntrack
ip_tables
ip_set
xt_set
ipt_set
ipt_rpfilter
ipt_REJECT
ipip
EOF

systemctl restart systemd-modules-load.service

检查模块是否加载成功

root@k8s-master01:~# 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                 176128  6 ip_vs_rr,ip_vs_sh,ip_vs_wrr
nf_conntrack          172032  1 ip_vs
nf_defrag_ipv6         24576  2 nf_conntrack,ip_vs
nf_defrag_ipv4         16384  1 nf_conntrack
libcrc32c              16384  5 nf_conntrack,btrfs,xfs,raid456,ip_vs

内核参数配置

cat > /etc/sysctl.d/k8s.conf << EOF
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.swappiness = 0
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 = 300
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 = 655535
net.ipv4.tcp_timestamps = 0
net.core.somaxconn = 16384
EOF

升级内核

低内核升级内核至4.18版本以上
Ubuntu 22.04.03 内核够新了可以不用升级

$ uname -r
5.15.0-88-generic

解决53端口冲突

systemd-resolved占用53端口，这个会跟coredns端口冲突，导致coredns无法运行，所以需要禁止监听53端口

备份原有文件

mv /etc/systemd/resolved.conf /etc/systemd/resolved.conf.old
cat > /etc/systemd/resolved.conf << EOF
[Resolve]
#DNS=223.5.5.5
# 关闭53端口监听
DNSStubListener=no
EOF

# 重启服务，让配置生效
systemctl restart systemd-resolved

软件下载地址

https://github.com/containerd/containerd/releases/download/v1.6.23/cri-containerd-1.6.23-linux-amd64.tar.gz

https://dl.k8s.io/v1.27.8/kubernetes-server-linux-amd64.tar.gz

https://github.com/etcd-io/etcd/releases/download/v3.5.9/etcd-v3.5.9-linux-amd64.tar.gz

安装etcd集群

下载解压etcd

这里部署在master01-03三个节点，建议单独机器部署etcd集群

wget https://github.com/etcd-io/etcd/releases/download/v3.5.9/etcd-v3.5.9-linux-amd64.tar.gz
tar -zxvf etcd-v3.5.9-linux-amd64.tar.gz --strip-components=1 -C /usr/local/bin etcd-v3.5.9-linux-amd64/etcd{,ctl}

etcd证书配置

目录说明

etcd 证书生成存放目录 /opt/pki/etcd
etcd 证书生产使用目录 /etc/etcd/ssl

etcd配置文件

创建etcd证书配置文件

mkdir -p /opt/pki/etcd /etc/etcd/ssl
cd /opt/pki/etcd

# 创建ca 配置文件
cat > /opt/pki/etcd/ca-config.json << EOF
{
  "signing": {
    "default": {
      "expiry": "876000h"
    },
    "profiles": {
      "kubernetes": {
        "usages": [
            "signing",
            "key encipherment",
            "server auth",
            "client auth"
        ],
        "expiry": "876000h"
      }
    }
  }
}
EOF

# 创建etcd-ca.json， etcd的ca文件配置
cat > /opt/pki/etcd/etcd-ca-csr.json << EOF
{
  "CN": "etcd",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Guangdong",
      "L": "Guangzhou",
      "O": "etcd",
      "OU": "Etcd Security"
    }
  ],
  "ca": {
    "expiry": "876000h"
  }
}
EOF

# 创建 etcd-csr.json，ca证书签名请求(CSR)
cat > /opt/pki/etcd/etcd-csr.json << EOF
{
  "CN": "etcd",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Guangdong",
      "L": "Guangzhou",
      "O": "etcd",
      "OU": "Etcd Security"
    }
  ]
}
EOF

生成etcd证书

安装证书生成工具

apt install -y golang-cfssl

etcd ca证书生成

cfssl gencert -initca etcd-ca-csr.json | cfssljson -bare /opt/pki/etcd/etcd-ca

etcd 证书生成, 需要etcd集群节点的IP和域名都写在hostname配置中

cfssl gencert -ca=/opt/pki/etcd/etcd-ca.pem -ca-key=/opt/pki/etcd/etcd-ca-key.pem -config=ca-config.json --hostname=127.0.0.1,k8s-master01,k8s-master02,k8s-master03,192.168.77.81,192.168.77.82,192.168.77.83 -profile=kubernetes etcd-csr.json |cfssljson -bare /opt/pki/etcd/etcd

生成的证书列表

root@sunday:/opt/pki/etcd# ls -la
total 36
drwxr-xr-x 2 root root  186 Dec 16 16:31 .
drwxr-xr-x 3 root root   18 Dec 16 16:31 ..
-rw-r--r-- 1 root root  294 Dec 16 16:30 ca-config.json
-rw-r--r-- 1 root root 1050 Dec 16 16:31 etcd-ca.csr
-rw-r--r-- 1 root root  249 Dec 16 16:30 etcd-ca-csr.json
-rw------- 1 root root 1679 Dec 16 16:31 etcd-ca-key.pem
-rw-r--r-- 1 root root 1318 Dec 16 16:31 etcd-ca.pem
-rw-r--r-- 1 root root 1131 Dec 16 16:31 etcd.csr
-rw-r--r-- 1 root root  210 Dec 16 16:30 etcd-csr.json
-rw------- 1 root root 1675 Dec 16 16:31 etcd-key.pem
-rw-r--r-- 1 root root 1464 Dec 16 16:31 etcd.pem

同步etcd证书和etcd二进制

复制etcd证书到master节点 /etc/etcd/ssl

name=(k8s-master01 k8s-master02 k8s-master03)
user=sunday
for host in ${name[@]}; do \
    echo $host
    ssh $user@$host "sudo mkdir -p /etc/etcd/ssl"; \
    rsync --rsync-path="sudo rsync" /opt/pki/etcd/{etcd-ca.pem,etcd-key.pem,etcd.pem} $user@$host:/etc/etcd/ssl/;
    rsync --rsync-path="sudo rsync" /usr/local/bin/{etcd,etcdctl} $user@$host:/usr/local/bin/;
done

etcd 服务配置

etcd-cluster01节点配置文件

mkdir -p /data/etcd
cat > /etc/etcd/etcd.config.yml << EOF
name: 'k8s-master01'       # 更换成master01的主机名
data-dir: /data/etcd
wal-dir: /data/etcd/wal
snapshot-count: 5000
heartbeat-interval: 100
election-timeout: 1000
quota-backend-bytes: 0
listen-peer-urls: 'https://192.168.77.81:2380'    # 更换成master01的IP
listen-client-urls: 'https://192.168.77.81:2379,http://127.0.0.1:2379' # 更换成master01的IP和本地回环地址
max-snapshots: 3
max-wals: 5
cors:
initial-advertise-peer-urls: 'https://192.168.77.81:2380' # 更换成master01的IP
advertise-client-urls: 'https://192.168.77.81:2379' # 更换成master01的IP
discovery:
discovery-fallback: 'proxy'
discovery-proxy:
discovery-srv:
initial-cluster: 'k8s-master01=https://192.168.77.81:2380,k8s-master02=https://192.168.77.82:2380,k8s-master03=https://192.168.77.83:2380' # 所有集群主机名和IP地址
initial-cluster-token: 'etcd-k8s-cluster' # # 集群的token
initial-cluster-state: 'new'
strict-reconfig-check: false
enable-v2: true
enable-pprof: true
proxy: 'off'
proxy-failure-wait: 5000
proxy-refresh-interval: 30000
proxy-dial-timeout: 1000
proxy-write-timeout: 5000
proxy-read-timeout: 0
client-transport-security:
  cert-file: '/etc/etcd/ssl/etcd.pem'
  key-file: '/etc/etcd/ssl/etcd-key.pem'
  client-cert-auth: true
  trusted-ca-file: '/etc/etcd/ssl/etcd-ca.pem'
  auto-tls: true
peer-transport-security:
  cert-file: '/etc/etcd/ssl/etcd.pem'
  key-file: '/etc/etcd/ssl/etcd-key.pem'
  peer-client-cert-auth: true
  trusted-ca-file: '/etc/etcd/ssl/etcd-ca.pem'
  auto-tls: true
debug: false
log-package-levels:
log-outputs: [default]
force-new-cluster: false
EOF

etcd-cluster02节点配置文件

mkdir -p /data/etcd
cat > /etc/etcd/etcd.config.yml << EOF
name: 'k8s-master02'       # 更换成master02的主机名
data-dir: /data/etcd
wal-dir: /data/etcd/wal
snapshot-count: 5000
heartbeat-interval: 100
election-timeout: 1000
quota-backend-bytes: 0
listen-peer-urls: 'https://192.168.77.82:2380'    # 更换成master02的IP
listen-client-urls: 'https://192.168.77.82:2379,http://127.0.0.1:2379' # 更换成master02的IP和本地回环地址
max-snapshots: 3
max-wals: 5
cors:
initial-advertise-peer-urls: 'https://192.168.77.82:2380' # 更换成master02的IP
advertise-client-urls: 'https://192.168.77.82:2379' # 更换成master02的IP
discovery:
discovery-fallback: 'proxy'
discovery-proxy:
discovery-srv:
initial-cluster: 'k8s-master01=https://192.168.77.81:2380,k8s-master02=https://192.168.77.82:2380,k8s-master03=https://192.168.77.83:2380' # 所有集群主机名和IP地址
initial-cluster-token: 'etcd-k8s-cluster' # # 集群的token
initial-cluster-state: 'new'
strict-reconfig-check: false
enable-v2: true
enable-pprof: true
proxy: 'off'
proxy-failure-wait: 5000
proxy-refresh-interval: 30000
proxy-dial-timeout: 1000
proxy-write-timeout: 5000
proxy-read-timeout: 0
client-transport-security:
  cert-file: '/etc/etcd/ssl/etcd.pem'
  key-file: '/etc/etcd/ssl/etcd-key.pem'
  client-cert-auth: true
  trusted-ca-file: '/etc/etcd/ssl/etcd-ca.pem'
  auto-tls: true
peer-transport-security:
  cert-file: '/etc/etcd/ssl/etcd.pem'
  key-file: '/etc/etcd/ssl/etcd-key.pem'
  peer-client-cert-auth: true
  trusted-ca-file: '/etc/etcd/ssl/etcd-ca.pem'
  auto-tls: true
debug: false
log-package-levels:
log-outputs: [default]
force-new-cluster: false
EOF

etcd-cluster03节点配置文件

mkdir -p /data/etcd
cat > /etc/etcd/etcd.config.yml << EOF
name: 'k8s-master03'       # 更换成node01的主机名
data-dir: /data/etcd
wal-dir: /data/etcd/wal
snapshot-count: 5000
heartbeat-interval: 100
election-timeout: 1000
quota-backend-bytes: 0
listen-peer-urls: 'https://192.168.77.83:2380'    # 更换成node01的IP
listen-client-urls: 'https://192.168.77.83:2379,http://127.0.0.1:2379' # 更换成node01的IP和本地回环地址
max-snapshots: 3
max-wals: 5
cors:
initial-advertise-peer-urls: 'https://192.168.77.83:2380' # 更换成node01的IP
advertise-client-urls: 'https://192.168.77.83:2379' # 更换成node01的IP
discovery:
discovery-fallback: 'proxy'
discovery-proxy:
discovery-srv:
initial-cluster: 'k8s-master01=https://192.168.77.81:2380,k8s-master02=https://192.168.77.82:2380,k8s-master03=https://192.168.77.83:2380' # 所有集群主机名和IP地址
initial-cluster-token: 'etcd-k8s-cluster' # # 集群的token
initial-cluster-state: 'new'
strict-reconfig-check: false
enable-v2: true
enable-pprof: true
proxy: 'off'
proxy-failure-wait: 5000
proxy-refresh-interval: 30000
proxy-dial-timeout: 1000
proxy-write-timeout: 5000
proxy-read-timeout: 0
client-transport-security:
  cert-file: '/etc/etcd/ssl/etcd.pem'
  key-file: '/etc/etcd/ssl/etcd-key.pem'
  client-cert-auth: true
  trusted-ca-file: '/etc/etcd/ssl/etcd-ca.pem'
  auto-tls: true
peer-transport-security:
  cert-file: '/etc/etcd/ssl/etcd.pem'
  key-file: '/etc/etcd/ssl/etcd-key.pem'
  peer-client-cert-auth: true
  trusted-ca-file: '/etc/etcd/ssl/etcd-ca.pem'
  auto-tls: true
debug: false
log-package-levels:
log-outputs: [default]
force-new-cluster: false
EOF

配置Services文件

cat > /usr/lib/systemd/system/etcd.service << EOF
[Unit]
Description=Etcd Service
Documentation=https://coreos.com/etcd/docs/latest/
After=network.target

[Service]
Type=notify
ExecStart=/usr/local/bin/etcd --config-file=/etc/etcd/etcd.config.yml
Restart=on-failure
RestartSec=10
LimitNOFILE=65536

[Install]
WantedBy=multi-user.target
Alias=etcd3.service
EOF

启动服务并且加入开机启动

systemctl daemon-reload 
systemctl enable --now etcd
systemctl status etcd

测试etcd集群状态

root@k8s-master01:~# etcdctl --endpoints="192.168.77.81:2379,192.168.77.82:2379,192.168.77.83:2379" --cacert=/etc/etcd/ssl/etcd-ca.pem --cert=/etc/etcd/ssl/etcd.pem --key=/etc/etcd/ssl/etcd-key.pem  endpoint status --write-out=table
+--------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+
|      ENDPOINT      |        ID        | VERSION | DB SIZE | IS LEADER | IS LEARNER | RAFT TERM | RAFT INDEX | RAFT APPLIED INDEX | ERRORS |
+--------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+
| 192.168.77.81:2379 | 4f618a57e2e4f983 |   3.5.9 |   20 kB |      true |      false |         5 |         15 |                 15 |        |
| 192.168.77.82:2379 | c74a110d8f902a2a |   3.5.9 |   20 kB |     false |      false |         5 |         15 |                 15 |        |
| 192.168.77.83:2379 | 53179a9063ddf0cc |   3.5.9 |   20 kB |     false |      false |         5 |         15 |                 15 |        |
+--------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+

高可用服务安装

haproxy

安装keepalived和haproxy

apt install -y keepalived haproxy

两台haproxy一样

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

listen monitor
  bind 0.0.0.0:8100
  mode http
  stats enable
  stats uri / 
  stats refresh 5s

frontend k8s-master
  bind 0.0.0.0:8443
  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 192.168.77.81:6443  check
  server k8s-master02 192.168.77.82:6443  check
  server k8s-master03 192.168.77.83:6443  check
EOF

keepalived

keepalived配置文件不一样，注意每个节点的IP和interface
keepalived01

cat > /etc/keepalived/keepalived.conf << EOF
! Configuration File for keepalived
global_defs {
    router_id LVS_DEVEL
}
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 ens192
    mcast_src_ip 192.168.77.101
    virtual_router_id 61
    priority 100
    nopreempt
    advert_int 2
    authentication {
        auth_type PASS
        auth_pass K8SHA_KA_AUTH
    }
    virtual_ipaddress {
        192.168.77.100
    }
    track_script {
      chk_apiserver 
  }
}
EOF

keepalived02

cat > /etc/keepalived/keepalived.conf << EOF
! Configuration File for keepalived
global_defs {
    router_id LVS_DEVEL
}
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 ens192
    mcast_src_ip 192.168.77.102
    virtual_router_id 61
    priority 90
    nopreempt
    advert_int 2
    authentication {
        auth_type PASS
        auth_pass K8SHA_KA_AUTH
    }
    virtual_ipaddress {
        192.168.77.100
    }
    track_script {
      chk_apiserver 
  } 
}
EOF

健康检查配置

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

启动haproxy和keepalived

systemctl daemon-reload
systemctl enable --now haproxy
systemctl enable --now keepalived
systemctl restart haproxy keepalived

测试高可用

ping 192.168.77.100

关闭主节点, vip是否漂移到备节点
注：现在apiserver还未部署，所以不能telnet 8443端口，因为负载不到6443端口。

安装containerd

这里master也充当node，所以也要安装
配置containerd 内核参数

cat > /etc/sysctl.d/99-kubernetes-cri.conf << EOF
net.bridge.bridge-nf-call-iptables  = 1
net.ipv4.ip_forward                 = 1
net.bridge.bridge-nf-call-ip6tables = 1
EOF

sysctl --system

配置containerd所需的模块

cat > /etc/modules-load.d/containerd.conf <<EOF
overlay
br_netfilter
EOF
systemctl restart systemd-modules-load.service

下载解压

wget https://github.com/containerd/containerd/releases/download/v1.6.23/cri-containerd-1.6.23-linux-amd64.tar.gz

tar zxf cri-containerd-1.6.23-linux-amd64.tar.gz -C /

mkdir -p /etc/containerd
containerd config default > /etc/containerd/config.toml

修改/etc/containerd/config.toml文件

vim /etc/containerd/config.toml
sed -i 's/SystemdCgroup = false/SystemdCgroup = true/g' /etc/containerd/config.toml

.....
sandbox_image = "registry.aliyuncs.com/google_containers/pause:3.6"
.....
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc.options]
    ...
    SystemdCgroup = true # 重点 没设置的话 pod会不断自动重启
....
      [plugins."io.containerd.grpc.v1.cri".registry.mirrors]
        [plugins."io.containerd.grpc.v1.cri".registry.mirrors."docker.io"]
          endpoint = ["https://xxxxx.mirror.aliyuncs.com"]
        [plugins."io.containerd.grpc.v1.cri".registry.mirrors."gcr.io"]
          endpoint = ["gcr.m.daocloud.io"]
        [plugins."io.containerd.grpc.v1.cri".registry.mirrors."k8s.gcr.io"]
          endpoint = ["k8s-gcr.m.daocloud.io"]
        [plugins."io.containerd.grpc.v1.cri".registry.mirrors."quay.io"]
          endpoint = ["quay.m.daocloud.io"]
        [plugins."io.containerd.grpc.v1.cri".registry.mirrors."registry.k8s.io"]
          endpoint = ["k8s.m.daocloud.io"]

启动服务并加入开机启动项

systemctl  enable --now containerd
systemctl  status  containerd

分发containerd 到其他服务器

name=(k8s-master02 k8s-master03 k8s-node01 k8s-node02)
user=sunday
for host in ${name[@]}; do \
    echo $host;
    ssh $user@$host "sudo mkdir -p /etc/containerd /opt/cni/bin /opt/containerd /etc/cni/net.d"; \
    rsync --rsync-path="sudo rsync" /usr/local/sbin/runc $user@$host:/usr/local/sbin/; \
    rsync --rsync-path="sudo rsync" /usr/local/bin/* $user@$host:/usr/local/bin/; \
    rsync --rsync-path="sudo rsync" /etc/systemd/system/containerd.service $user@$host:/etc/systemd/system/; \
    rsync --rsync-path="sudo rsync" /etc/containerd/config.toml $user@$host:/etc/containerd/; \
    rsync --rsync-path="sudo rsync" /etc/sysctl.d/99-kubernetes-cri.conf $user@$host:/etc/sysctl.d/;
done

kubernetes master组件

下载安装

wget https://dl.k8s.io/v1.27.8/kubernetes-server-linux-amd64.tar.gz

tar xf kubernetes-server-linux-amd64.tar.gz --strip-components=3 -C /usr/local/bin kubernetes/server/bin/kube{let,ctl,-apiserver,-controller-manager,-scheduler,-proxy}

分发master组件

masters='k8s-master02 k8s-master03'
user=sunday
for i in $masters; do 
  echo $i; 
  rsync --rsync-path="sudo rsync" /usr/local/bin/kube{ctl,-apiserver,-controller-manager,-scheduler} $user@$i:/usr/local/bin/; 
done

分发node组件

nodes='k8s-master02 k8s-master03 k8s-node01 k8s-node02'
user=sunday
for i in $nodes; do 
    rsync --rsync-path="sudo rsync" /usr/local/bin/kube{let,-proxy} $user@$i:/usr/local/bin/;
done

kubernetes证书配置

目录说明

k8s 证书生成存放目录 /opt/pki/k8s
k8s 证书生产使用目录 /etc/kubernetes/pki

证书配置文件
```
mkdir -p /opt/pki/k8s /etc/kubernetes/pki
```

# 创建ca 配置文件
cat > /opt/pki/k8s/ca-config.json << EOF
{
  "signing": {
    "default": {
      "expiry": "876000h"
    },
    "profiles": {
      "kubernetes": {
        "usages": [
            "signing",
            "key encipherment",
            "server auth",
            "client auth"
        ],
        "expiry": "876000h"
      }
    }
  }
}
EOF

# ca 证书配置
cat >  /opt/pki/k8s/ca-csr.json << EOF
{
  "CN": "kubernetes",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Guangdong",
      "L": "Guangzhou",
      "O": "Kubernetes",
      "OU": "Kubernetes-manual"
    }
  ],
  "ca": {
    "expiry": "876000h"
  }
}
EOF

# apiserver服务证书配置
cat > /opt/pki/k8s/apiserver-csr.json << EOF
{
  "CN": "kube-apiserver",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Guangdong",
      "L": "Guangzhou",
      "O": "Kubernetes",
      "OU": "Kubernetes-manual"
    }
  ]
}
EOF

# kube-controller-manager服务证书配置
cat > /opt/pki/k8s/kube-controller-manager-csr.json << EOF
{
  "CN": "system:kube-controller-manager",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Guangdong",
      "L": "Guangzhou",
      "O": "system:kube-controller-manager",
      "OU": "Kubernetes-manual"
    }
  ]
}
EOF

# kube-scheduler服务证书配置
cat > /opt/pki/k8s/kube-scheduler-csr.json << EOF
{
  "CN": "system:kube-scheduler",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Guangdong",
      "L": "Guangzhou",
      "O": "system:kube-scheduler",
      "OU": "Kubernetes-manual"
    }
  ]
}
EOF

# 集群管理员证书配置
cat > /opt/pki/k8s/admin-csr.json << EOF
{
  "CN": "admin",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Guangdong",
      "L": "Guangzhou",
      "O": "system:masters",
      "OU": "Kubernetes-manual"
    }
  ]
}
EOF

# 最小权限证书配置
cat > /opt/pki/k8s/front-proxy-ca-csr.json << EOF
{
  "CN": "kubernetes",
  "key": {
     "algo": "rsa",
     "size": 2048
  },
  "ca": {
    "expiry": "876000h"
  }
}
EOF

# 最小权限客户端证书配置
cat > /opt/pki/k8s/front-proxy-client-csr.json << EOF
{
  "CN": "front-proxy-client",
  "key": {
     "algo": "rsa",
     "size": 2048
  }
}
EOF

证书生成

apiserver证书hostname 说明

证书hostname 需要把所有master的IP和VIP地址包含在证书里面，所以在部署的时候需要规划好master节点和vip，多写几个IP，预留扩容节点
证书还需要包含service的IP，以及集群内部默认的service名称，否则需要重新生成证书
包含的IP和主机名如下
10.96.0.1 是service的第一个IP地址

# ca证书生成
cfssl gencert -initca /opt/pki/k8s/ca-csr.json | cfssljson -bare /opt/pki/k8s/ca

# api server 服务证书生成
cfssl gencert -ca=/opt/pki/k8s/ca.pem -ca-key=/opt/pki/k8s/ca-key.pem -config=/opt/pki/k8s/ca-config.json -hostname=k8s-master01,k8s-master02,k8s-master03,k8s-master04,k8s-master05,kubernetes,kubernetes.default,kubernetes.default.svc,kubernetes.default.svc.cluster,kubernetes.default.svc.cluster.local,127.0.0.1,10.96.0.1,192.168.77.81,192.168.77.82,192.168.77.83,192.168.77.84,192.168.77.85,192.168.77.100 -profile=kubernetes /opt/pki/k8s/apiserver-csr.json | cfssljson -bare /opt/pki/k8s/apiserver

# api server 聚合证书，第三服务使用的最小权限证书
cfssl gencert -initca /opt/pki/k8s/front-proxy-ca-csr.json | cfssljson -bare /opt/pki/k8s/front-proxy-ca

cfssl gencert -ca=/opt/pki/k8s/front-proxy-ca.pem -ca-key=/opt/pki/k8s/front-proxy-ca-key.pem -config=/opt/pki/k8s/ca-config.json -profile=kubernetes front-proxy-client-csr.json | cfssljson -bare /opt/pki/k8s/front-proxy-client

# controller-manage证书生成
cfssl gencert -ca=/opt/pki/k8s/ca.pem -ca-key=/opt/pki/k8s/ca-key.pem -config=/opt/pki/k8s/ca-config.json -profile=kubernetes kube-controller-manager-csr.json | cfssljson -bare /opt/pki/k8s/controller-manager

# scheduler证书生成
cfssl gencert -ca=/opt/pki/k8s/ca.pem -ca-key=/opt/pki/k8s/ca-key.pem -config=/opt/pki/k8s/ca-config.json -profile=kubernetes kube-scheduler-csr.json | cfssljson -bare /opt/pki/k8s/scheduler

# 集群管理员证书生成
cfssl gencert -ca=/opt/pki/k8s/ca.pem -ca-key=/opt/pki/k8s/ca-key.pem -config=/opt/pki/k8s/ca-config.json -profile=kubernetes admin-csr.json | cfssljson -bare /opt/pki/k8s/admin

cp -r /opt/pki/k8s/*.pem /etc/kubernetes/pki/

配置文件

controller-manager用户配置文件

这里使用haproxy高可用负载apiserver，apiserver 填写的是vip:port(192.168.77.100:8443), 如没有配置高可用，则直接填写一台apiserver的ip和端口(默认6443)

# 配置集群访问相关配置
kubectl config set-cluster kubernetes --certificate-authority=/etc/kubernetes/pki/ca.pem --embed-certs=true --server=https://192.168.77.100:8443 --kubeconfig=/etc/kubernetes/controller-manager.kubeconfig

# 配置用户上下文
kubectl config set-context system:kube-controller-manager@kubernetes --cluster=kubernetes --user=system:kube-controller-manager --kubeconfig=/etc/kubernetes/controller-manager.kubeconfig

# 设置用户 credentials
kubectl config set-credentials system:kube-controller-manager --client-certificate=/etc/kubernetes/pki/controller-manager.pem --client-key=/etc/kubernetes/pki/controller-manager-key.pem --embed-certs=true --kubeconfig=/etc/kubernetes/controller-manager.kubeconfig

# 设置默认使用的用户上下文
kubectl config use-context system:kube-controller-manager@kubernetes --kubeconfig=/etc/kubernetes/controller-manager.kubeconfig

Scheduler用户配置文件

# 配置集群访问相关配置
kubectl config set-cluster kubernetes --certificate-authority=/etc/kubernetes/pki/ca.pem --embed-certs=true --server=https://192.168.77.100:8443 --kubeconfig=/etc/kubernetes/scheduler.kubeconfig

# 配置用户上下文
kubectl config set-context system:kube-scheduler@kubernetes --cluster=kubernetes --user=system:kube-scheduler --kubeconfig=/etc/kubernetes/scheduler.kubeconfig

# 设置用户 credentials
kubectl config set-credentials system:kube-scheduler --client-certificate=/etc/kubernetes/pki/scheduler.pem --client-key=/etc/kubernetes/pki/scheduler-key.pem --embed-certs=true --kubeconfig=/etc/kubernetes/scheduler.kubeconfig

# 设置默认使用的用户上下文
kubectl config use-context system:kube-scheduler@kubernetes --kubeconfig=/etc/kubernetes/scheduler.kubeconfig

集群管理员配置文件

# 配置集群访问相关配置
kubectl config set-cluster kubernetes --certificate-authority=/etc/kubernetes/pki/ca.pem --embed-certs=true --server=https://192.168.77.100:8443 --kubeconfig=/etc/kubernetes/admin.kubeconfig

# 配置用户上下文
kubectl config set-context kubernetes-admin@kubernetes --cluster=kubernetes --user=kubernetes-admin --kubeconfig=/etc/kubernetes/admin.kubeconfig

# 设置用户 credentials
kubectl config set-credentials kubernetes-admin --client-certificate=/etc/kubernetes/pki/admin.pem --client-key=/etc/kubernetes/pki/admin-key.pem --embed-certs=true --kubeconfig=/etc/kubernetes/admin.kubeconfig

# 设置默认使用的用户上下文
kubectl config use-context kubernetes-admin@kubernetes --kubeconfig=/etc/kubernetes/admin.kubeconfig

用于配置servcieAccount和secret证书

# sa证书
openssl genrsa -out /opt/pki/k8s/sa.key 2048
openssl rsa -in /opt/pki/k8s/sa.key -pubout -out /opt/pki/k8s/sa.pub
cp /opt/pki/k8s/{sa.key,sa.pub} /etc/kubernetes/pki/

同步证书和配置文件

mkdir -p /etc/kubernetes/pki/
cp -r /opt/pki/k8s/*.pem /etc/kubernetes/pki/
user=sunday
for i in k8s-master02 k8s-master03;do
    ssh $user@$i "sudo mkdir -p /etc/kubernetes/pki/";
    rsync --rsync-path="sudo rsync" /etc/kubernetes/pki/*.{pem,key,pub} $user@$i:/etc/kubernetes/pki/;
    rsync --rsync-path="sudo rsync" /etc/kubernetes/*.kubeconfig $user@$i:/etc/kubernetes/;
done

创建集群所需的目录（所有节点都需要创建）

mkdir -p /etc/kubernetes/manifests/ /etc/systemd/system/kubelet.service.d /var/lib/kubelet /var/log/kubernetes

kube-apiserver 服务配置

cat > /usr/lib/systemd/system/kube-apiserver.service << \EOF
[Unit]
Description=Kubernetes API Server
Documentation=https://github.com/kubernetes/kubernetes
After=network.target

[Service]
ExecStart=/usr/local/bin/kube-apiserver \
      --v=2  \
      --allow-privileged=true  \
      --bind-address=0.0.0.0  \
      --secure-port=6443 \
      --advertise-address=192.168.77.81 \
      --service-cluster-ip-range=10.96.0.0/16  \
      --service-node-port-range=30000-32767  \
      --etcd-servers=https://192.168.77.81:2379,https://192.168.77.82:2379,https://192.168.77.83:2379 \
      --etcd-cafile=/etc/etcd/ssl/etcd-ca.pem  \
      --etcd-certfile=/etc/etcd/ssl/etcd.pem  \
      --etcd-keyfile=/etc/etcd/ssl/etcd-key.pem  \
      --client-ca-file=/etc/kubernetes/pki/ca.pem  \
      --tls-cert-file=/etc/kubernetes/pki/apiserver.pem  \
      --tls-private-key-file=/etc/kubernetes/pki/apiserver-key.pem  \
      --kubelet-client-certificate=/etc/kubernetes/pki/apiserver.pem  \
      --kubelet-client-key=/etc/kubernetes/pki/apiserver-key.pem  \
      --service-account-key-file=/etc/kubernetes/pki/sa.pub  \
      --service-account-signing-key-file=/etc/kubernetes/pki/sa.key  \
      --service-account-issuer=https://kubernetes.default.svc.cluster.local \
      --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname  \
      --enable-admission-plugins=NamespaceLifecycle,LimitRanger,ServiceAccount,DefaultStorageClass,DefaultTolerationSeconds,NodeRestriction,ResourceQuota  \
      --authorization-mode=Node,RBAC  \
      --enable-bootstrap-token-auth=true  \
      --requestheader-client-ca-file=/etc/kubernetes/pki/front-proxy-ca.pem  \
      --proxy-client-cert-file=/etc/kubernetes/pki/front-proxy-client.pem  \
      --proxy-client-key-file=/etc/kubernetes/pki/front-proxy-client-key.pem  \
      --requestheader-allowed-names=aggregator  \
      --requestheader-group-headers=X-Remote-Group  \
      --requestheader-extra-headers-prefix=X-Remote-Extra-  \
      --requestheader-username-headers=X-Remote-User

Restart=on-failure
RestartSec=10s
LimitNOFILE=65535

[Install]
WantedBy=multi-user.target
EOF

启动 api server服务并加入开机启动

systemctl daemon-reload
systemctl enable --now kube-apiserver.service
systemctl status kube-apiserver.service

kube-controller-manager 服务配置

cat > /usr/lib/systemd/system/kube-controller-manager.service << \EOF
[Unit]
Description=Kubernetes Controller Manager
Documentation=https://github.com/kubernetes/kubernetes
After=network.target
[Service]
ExecStart=/usr/local/bin/kube-controller-manager \
      --v=2 \
      --root-ca-file=/etc/kubernetes/pki/ca.pem \
      --cluster-signing-cert-file=/etc/kubernetes/pki/ca.pem \
      --cluster-signing-key-file=/etc/kubernetes/pki/ca-key.pem \
      --service-account-private-key-file=/etc/kubernetes/pki/sa.key \
      --kubeconfig=/etc/kubernetes/controller-manager.kubeconfig \
      --leader-elect=true \
      --use-service-account-credentials=true \
      --node-monitor-grace-period=40s \
      --node-monitor-period=5s \
      --controllers=*,bootstrapsigner,tokencleaner \
      --allocate-node-cidrs=true \
      --cluster-cidr=10.244.0.0/16 \
      --requestheader-client-ca-file=/etc/kubernetes/pki/front-proxy-ca.pem \
      --node-cidr-mask-size=24
Restart=always
RestartSec=10s
[Install]
WantedBy=multi-user.target
EOF

启动kube-controller-manager服务

systemctl daemon-reload 
systemctl enable --now kube-controller-manager
systemctl status kube-controller-manager

kube-Scheduler服务配置

cat > /usr/lib/systemd/system/kube-scheduler.service << \EOF
[Unit]
Description=Kubernetes Scheduler
Documentation=https://github.com/kubernetes/kubernetes
After=network.target
[Service]
ExecStart=/usr/local/bin/kube-scheduler \
      --v=2 \
      --leader-elect=true \
      --kubeconfig=/etc/kubernetes/scheduler.kubeconfig

Restart=always
RestartSec=10s
[Install]
WantedBy=multi-user.target
EOF

启动kube-scheduler服务

systemctl daemon-reload
systemctl enable kube-scheduler
systemctl restart kube-scheduler
systemctl status kube-scheduler

配置admin配置文件

mkdir -p ~/.kube
cp /etc/kubernetes/admin.kubeconfig ~/.kube/config

检查当前集群状态

root@k8s-master01:~# kubectl get cs
Warning: v1 ComponentStatus is deprecated in v1.19+
NAME                 STATUS    MESSAGE   ERROR
controller-manager   Healthy   ok        
etcd-0               Healthy             
scheduler            Healthy   ok        
etcd-2               Healthy             
etcd-1               Healthy 

root@k8s-master01:~# kubectl get --raw='/readyz?verbose'
[+]ping ok
[+]log ok
[+]etcd ok
[+]etcd-readiness ok
[+]informer-sync ok
[+]poststarthook/start-kube-apiserver-admission-initializer ok
[+]poststarthook/generic-apiserver-start-informers ok
[+]poststarthook/priority-and-fairness-config-consumer ok
[+]poststarthook/priority-and-fairness-filter ok
[+]poststarthook/storage-object-count-tracker-hook ok
[+]poststarthook/start-apiextensions-informers ok
[+]poststarthook/start-apiextensions-controllers ok
[+]poststarthook/crd-informer-synced ok
[+]poststarthook/start-system-namespaces-controller ok
[+]poststarthook/bootstrap-controller ok
[+]poststarthook/rbac/bootstrap-roles ok
[+]poststarthook/scheduling/bootstrap-system-priority-classes ok
[+]poststarthook/priority-and-fairness-config-producer ok
[+]poststarthook/start-cluster-authentication-info-controller ok
[+]poststarthook/start-kube-apiserver-identity-lease-controller ok
[+]poststarthook/start-deprecated-kube-apiserver-identity-lease-garbage-collector ok
[+]poststarthook/start-kube-apiserver-identity-lease-garbage-collector ok
[+]poststarthook/start-legacy-token-tracking-controller ok
[+]poststarthook/aggregator-reload-proxy-client-cert ok
[+]poststarthook/start-kube-aggregator-informers ok
[+]poststarthook/apiservice-registration-controller ok
[+]poststarthook/apiservice-status-available-controller ok
[+]poststarthook/kube-apiserver-autoregistration ok
[+]autoregister-completion ok
[+]poststarthook/apiservice-openapi-controller ok
[+]poststarthook/apiservice-openapiv3-controller ok
[+]poststarthook/apiservice-discovery-controller ok
[+]shutdown ok
readyz check passed

kubernetes node组件

kube-proxy证书

# 生成证书
cat > /opt/pki/k8s/kube-proxy-csr.json << EOF
{
  "CN": "system:kube-proxy",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Guangdong",
      "L": "Guangzhou",
      "O": "system:kube-proxy",
      "OU": "Kubernetes-manual"
    }
  ]
}
EOF

cfssl gencert -ca=/opt/pki/k8s/ca.pem -ca-key=/opt/pki/k8s/ca-key.pem -config=/opt/pki/k8s/ca-config.json -profile=kubernetes /opt/pki/k8s/kube-proxy-csr.json | cfssljson -bare /opt/pki/k8s/kube-proxy

cp -r /opt/pki/k8s/kube-proxy*.pem /etc/kubernetes/pki/

kube-proxy配置文件

# 配置集群访问相关配置
kubectl config set-cluster kubernetes --certificate-authority=/etc/kubernetes/pki/ca.pem --embed-certs=true --server=https://192.168.77.100:8443 --kubeconfig=/etc/kubernetes/kube-proxy.kubeconfig

# 设置用户 credentials
kubectl config set-credentials kube-proxy --client-certificate=/etc/kubernetes/pki/kube-proxy.pem --client-key=/etc/kubernetes/pki/kube-proxy-key.pem --embed-certs=true --kubeconfig=/etc/kubernetes/kube-proxy.kubeconfig

# 配置用户上下文
kubectl config set-context kube-proxy@kubernetes --cluster=kubernetes --user=kube-proxy --kubeconfig=/etc/kubernetes/kube-proxy.kubeconfig

# 设置默认使用的用户上下文
kubectl config use-context kube-proxy@kubernetes --kubeconfig=/etc/kubernetes/kube-proxy.kubeconfig

tls bootstrap 用户相关权限配置

在master01创建bootstrap
生成bootstrap的token

TOKEN_ID=$(openssl rand -hex 3)
TOKEN_SECRET=$(openssl rand -hex 8)
BOOTSTRAP_TOKEN=${TOKEN_ID}.${TOKEN_SECRET}
echo $BOOTSTRAP_TOKEN # 例: 9afe5c.07be6c9e50a9dd5

tls bootstrap 配置，用于node节点自动颁发证书

# 配置集群访问相关配置
kubectl config set-cluster kubernetes --certificate-authority=/etc/kubernetes/pki/ca.pem --embed-certs=true --server=https://192.168.77.100:8443 --kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig

# 设置用户 credentials
kubectl config set-credentials tls-bootstrap-token-user --token=${BOOTSTRAP_TOKEN} --kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig

# 配置用户上下文
kubectl config set-context tls-bootstrap-token-user@kubernetes --cluster=kubernetes --user=tls-bootstrap-token-user --kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig

# 设置默认使用的用户上下文
kubectl config use-context tls-bootstrap-token-user@kubernetes --kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig

注意：bootstrap-secret.yaml的token-id、token-secret，需与上命令token保持一致(即9afe5c.07be6c9e50a9dd5)

mkdir -p /etc/kubernetes/yaml
cat > /etc/kubernetes/yaml/bootstrap-secret.yaml  << EOF
apiVersion: v1
kind: Secret
metadata:
  name: bootstrap-token-${TOKEN_ID}
  namespace: kube-system
type: bootstrap.kubernetes.io/token
stringData:
  description: "The default bootstrap token generated by 'kubelet '."
  token-id: ${TOKEN_ID}
  token-secret: ${TOKEN_SECRET}
  usage-bootstrap-authentication: "true"
  usage-bootstrap-signing: "true"
  auth-extra-groups:  system:bootstrappers:default-node-token,system:bootstrappers:worker,system:bootstrappers:ingress
EOF

cat > /etc/kubernetes/yaml/kubelet-bootstrap-rbac.yaml  << EOF
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: kubelet-bootstrap
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: system:node-bootstrapper
subjects:
- apiGroup: rbac.authorization.k8s.io
  kind: Group
  name: system:bootstrappers:default-node-token
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: node-autoapprove-bootstrap
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: system:certificates.k8s.io:certificatesigningrequests:nodeclient
subjects:
- apiGroup: rbac.authorization.k8s.io
  kind: Group
  name: system:bootstrappers:default-node-token
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: node-autoapprove-certificate-rotation
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: system:certificates.k8s.io:certificatesigningrequests:selfnodeclient
subjects:
- apiGroup: rbac.authorization.k8s.io
  kind: Group
  name: system:nodes
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  annotations:
    rbac.authorization.kubernetes.io/autoupdate: "true"
  labels:
    kubernetes.io/bootstrapping: rbac-defaults
  name: system:kube-apiserver-to-kubelet
rules:
  - apiGroups:
      - ""
    resources:
      - nodes/proxy
      - nodes/stats
      - nodes/log
      - nodes/spec
      - nodes/metrics
    verbs:
      - "*"
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: system:kube-apiserver
  namespace: ""
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: system:kube-apiserver-to-kubelet
subjects:
  - apiGroup: rbac.authorization.k8s.io
    kind: User
    name: kube-apiserver
EOF

kubectl create -f /etc/kubernetes/yaml/bootstrap-secret.yaml
kubectl create -f /etc/kubernetes/yaml/kubelet-bootstrap-rbac.yaml

kubelet 服务配置

cat > /usr/lib/systemd/system/kubelet.service << \EOF
[Unit]
Description=Kubernetes Kubelet
Documentation=https://github.com/kubernetes/kubernetes
[Service]
ExecStart=/usr/local/bin/kubelet
Restart=always
StartLimitInterval=0
RestartSec=10
[Install]
WantedBy=multi-user.target
EOF

mkdir -p /etc/systemd/system/kubelet.service.d
cat > /etc/systemd/system/kubelet.service.d/10-kubelet.conf << \EOF
[Service]
Environment="KUBELET_KUBECONFIG_ARGS=--bootstrap-kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig --kubeconfig=/etc/kubernetes/kubelet.kubeconfig"
Environment="KUBELET_SYSTEM_ARGS=--container-runtime-endpoint=unix:///run/containerd/containerd.sock"
Environment="KUBELET_CONFIG_ARGS=--config=/etc/kubernetes/kubelet-conf.yaml"
Environment="KUBELET_EXTRA_ARGS=--node-labels=node.kubernetes.io/node='' "
ExecStart=
ExecStart=/usr/local/bin/kubelet $KUBELET_KUBECONFIG_ARGS $KUBELET_CONFIG_ARGS $KUBELET_SYSTEM_ARGS $KUBELET_EXTRA_ARGS
EOF

clusterDNS: 10.96.0.10

cat > /etc/kubernetes/kubelet-conf.yaml << \EOF
apiVersion: kubelet.config.k8s.io/v1beta1
kind: KubeletConfiguration
address: 0.0.0.0
port: 10250
readOnlyPort: 10255
authentication:
  anonymous:
    enabled: false
  webhook:
    cacheTTL: 2m0s
    enabled: true
  x509:
    clientCAFile: /etc/kubernetes/pki/ca.pem
authorization:
  mode: Webhook
  webhook:
    cacheAuthorizedTTL: 5m0s
    cacheUnauthorizedTTL: 30s
cgroupDriver: systemd
cgroupsPerQOS: true
clusterDNS:
- 10.96.0.10
clusterDomain: cluster.local
containerLogMaxFiles: 5
containerLogMaxSize: 10Mi
contentType: application/vnd.kubernetes.protobuf
cpuCFSQuota: true
cpuManagerPolicy: none
cpuManagerReconcilePeriod: 10s
enableControllerAttachDetach: true
enableDebuggingHandlers: true
enforceNodeAllocatable:
- pods
eventBurst: 10
eventRecordQPS: 5
evictionHard:
  imagefs.available: 15%
  memory.available: 100Mi
  nodefs.available: 10%
  nodefs.inodesFree: 5%
evictionPressureTransitionPeriod: 5m0s
failSwapOn: true
fileCheckFrequency: 20s
hairpinMode: promiscuous-bridge
healthzBindAddress: 127.0.0.1
healthzPort: 10248
httpCheckFrequency: 20s
imageGCHighThresholdPercent: 85
imageGCLowThresholdPercent: 80
imageMinimumGCAge: 2m0s
iptablesDropBit: 15
iptablesMasqueradeBit: 14
kubeAPIBurst: 10
kubeAPIQPS: 5
makeIPTablesUtilChains: true
maxOpenFiles: 1000000
maxPods: 110
nodeStatusUpdateFrequency: 10s
oomScoreAdj: -999
podPidsLimit: -1
registryBurst: 10
registryPullQPS: 5
resolvConf: /etc/resolv.conf
rotateCertificates: true
runtimeRequestTimeout: 2m0s
serializeImagePulls: true
staticPodPath: /etc/kubernetes/manifests
streamingConnectionIdleTimeout: 4h0m0s
syncFrequency: 1m0s
volumeStatsAggPeriod: 1m0s
EOF

同步证书及配置

user=sunday
for i in k8s-master02 k8s-master03 k8s-node01 k8s-node02; do
    ssh $user@$i "sudo mkdir -p /etc/kubernetes /etc/systemd/system/kubelet.service.d";
    rsync --rsync-path="sudo rsync" /opt/pki/k8s/{ca.pem,ca-key.pem,front-proxy-ca.pem,kube-proxy.pem,kube-proxy-key.pem} $user@$i:/etc/kubernetes/pki/;
    rsync --rsync-path="sudo rsync" /etc/kubernetes/{kubelet.kubeconfig,kube-proxy.kubeconfig} $user@$i:/etc/kubernetes/;
    rsync --rsync-path="sudo rsync" /etc/kubernetes/kubelet-conf.yaml $user@$i:/etc/kubernetes/kubelet-conf.yaml;
    rsync --rsync-path="sudo rsync" /etc/systemd/system/kubelet.service.d/10-kubelet.conf $user@$i:/etc/systemd/system/kubelet.service.d/10-kubelet.conf;
    rsync --rsync-path="sudo rsync" /usr/lib/systemd/system/kubelet.service $user@$i:/usr/lib/systemd/system/kubelet.service;
done

启动服务并加入开机启动

systemctl daemon-reload
systemctl enable --now kubelet
systemctl status kubelet

kube-proxy 服务配置

# 服务启动文件配置(搜有节点)
cat > /usr/lib/systemd/system/kube-proxy.service << \EOF
[Unit]
Description=Kubernetes Kube Proxy
Documentation=https://github.com/kubernetes/kubernetes
After=network.target

[Service]
ExecStart=/usr/local/bin/kube-proxy \
  --config=/etc/kubernetes/kube-proxy.yaml \
  --v=2

Restart=always
RestartSec=10s

[Install]
WantedBy=multi-user.target
EOF

clusterCIDR: 10.244.0.0/16 集群网络地址段, 与pod网段保持一致

cat > /etc/kubernetes/kube-proxy.yaml << \EOF
apiVersion: kubeproxy.config.k8s.io/v1alpha1
bindAddress: 0.0.0.0
clientConnection:
  acceptContentTypes: ""
  burst: 10
  contentType: application/vnd.kubernetes.protobuf
  kubeconfig: /etc/kubernetes/kube-proxy.kubeconfig
  qps: 5
clusterCIDR: 10.244.0.0/16
configSyncPeriod: 15m0s
conntrack:
  maxPerCore: 32768
  min: 131072
  tcpCloseWaitTimeout: 1h0m0s
  tcpEstablishedTimeout: 24h0m0s
enableProfiling: false
healthzBindAddress: 0.0.0.0:10256
hostnameOverride: ""
iptables:
  masqueradeBit: 14
  minSyncPeriod: 0s
  syncPeriod: 30s
ipvs:
  minSyncPeriod: 5s
  scheduler: "rr"
  syncPeriod: 30s
kind: KubeProxyConfiguration
metricsBindAddress: 127.0.0.1:10249
mode: "ipvs"
nodePortAddresses: null
oomScoreAdj: -999
portRange: ""
EOF

同步配置文件

user=sunday
for i in k8s-master02 k8s-master03 k8s-node01 k8s-node02; do
    ssh $user@$i "sudo mkdir -p /etc/kubernetes";
    rsync --rsync-path="sudo rsync" /etc/kubernetes/{bootstrap-kubelet.kubeconfig,kubelet-conf.yaml} $user@$i:/etc/kubernetes/;
    rsync --rsync-path="sudo rsync" /etc/kubernetes/kube-proxy.yaml $user@$i:/etc/kubernetes/kube-proxy.yaml;
    rsync --rsync-path="sudo rsync" /usr/lib/systemd/system/kube-proxy.service $user@$i:/usr/lib/systemd/system/kube-proxy.service;
done