淘先锋技术网

首页 1 2 3 4 5 6 7

安装前准备

192.168.100.26 k8s-01
192.168.100.27 k8s-02
192.168.100.28 k8s-03
 
#node节点
192.168.100.29 k8s-04     #node节点只运行node,但是设置证书的时候要添加这个ip
本文档的所有etcd集群、master集群、worker节点均使用以上三台机器,并且初始化步骤需要在所有机器上执行命令。如果没有特殊命令,所有操作均在192.168.100.26上进行操作
hostnamectl set-hostname k8s-01  #所有机器按照要求修改
hostnamectl set-hostname k8s-02
hostnamectl set-hostname k8s-03
hostnamectl set-hostname k8s-04

bash        #刷新主机名
# 设置/etc/hosts
cat >> /etc/hosts <<EOF
192.168.100.26  k8s-01
192.168.100.27  k8s-02
192.168.100.28  k8s-03
192.168.100.29  k8s-04
EOF

# 只要在k8s-01 设置免密,主机密码 123456,各位自己改成自己的
wget -O /etc/yum.repos.d/epel.repo http://mirrors.aliyun.com/repo/epel-7.repo
curl -o /etc/yum.repos.d/CentOS-Base.repo http://mirrors.aliyun.com/repo/Centos-7.repo
yum install -y expect
 sed -i "s@PermitRootLogin no@PermitRootLogin yes@g" /etc/ssh/sshd_config
sed -i "s@PasswordAuthentication no@PasswordAuthentication yes@g" /etc/ssh/sshd_config
systemctl restart sshd
#分发公钥
ssh-keygen -t rsa -P "" -f /root/.ssh/id_rsa
for i in k8s-01 k8s-02 k8s-03 k8s-04;do
expect -c "
spawn ssh-copy-id -i /root/.ssh/id_rsa.pub root@$i
        expect {
                \"*yes/no*\" {send \"yes\r\"; exp_continue}
                \"*password*\" {send \"123456\r\"; exp_continue}
                \"*Password*\" {send \"123456\r\";}
        } "
done 

# 更新path ,本次路径全部在/opt 目录下
echo 'PATH=/opt/k8s/bin:$PATH' >>/etc/profile
source  /etc/profile
env|grep PATH

# 内核以及基础配置更新,内核升级步骤可以自选
yum -y install gcc gcc-c++ make autoconf libtool-ltdl-devel gd-devel freetype-devel libxml2-devel libjpeg-devel libpng-devel openssh-clients openssl-devel curl-devel bison patch libmcrypt-devel libmhash-devel ncurses-devel binutils compat-libstdc++-33 elfutils-libelf elfutils-libelf-devel glibc glibc-common glibc-devel libgcj libtiff pam-devel libicu libicu-devel gettext-devel libaio-devel libaio libgcc libstdc++ libstdc++-devel unixODBC unixODBC-devel numactl-devel glibc-headers sudo bzip2 mlocate flex lrzsz sysstat lsof setuptool system-config-network-tui system-config-firewall-tui ntsysv ntp pv lz4 dos2unix unix2dos rsync dstat iotop innotop mytop telnet iftop expect cmake nc gnuplot screen xorg-x11-utils xorg-x11-xinit rdate bc expat-devel compat-expat1 tcpdump sysstat man nmap curl lrzsz elinks finger bind-utils traceroute mtr ntpdate zip unzip vim wget net-tools
systemctl stop firewalld
systemctl disable firewalld
iptables -F && iptables -X && iptables -F -t nat && iptables -X -t nat
iptables -P FORWARD ACCEPT
swapoff -a
sed -i '/ swap / s/^\(.*\)$/#\1/g' /etc/fstab
setenforce 0
sed -i 's/^SELINUX=.*/SELINUX=disabled/' /etc/selinux/config

# reboot 后yum update -y 执行下

# 加载内核模块调优
find  /lib/modules/`uname -r`/ -name "ip_vs_rr*"
find  /lib/modules/`uname -r`/ -name "br_netfilter*"
cat > /etc/rc.local  << EOF
modprobe ip_vs_rr
modprobe br_netfilter
EOF
cat > /etc/modules-load.d/ipvs.conf << EOF
 ip_vs_rr
 br_netfilter
EOF
systemctl enable --now systemd-modules-load.service
#验证是否成功
lsmod |egrep " ip_vs_rr|br_netfilter"

cat > kubernetes.conf <<EOF
net.bridge.bridge-nf-call-iptables=1
net.bridge.bridge-nf-call-ip6tables=1
net.ipv4.ip_forward=1
net.ipv4.tcp_tw_recycle=0
vm.swappiness=0 # 禁止使用 swap 空间,只有当系统 OOM 时才允许使用它
vm.overcommit_memory=1 # 不检查物理内存是否够用
vm.panic_on_oom=0 # 开启 OOM
fs.inotify.max_user_instances=8192
fs.inotify.max_user_watches=1048576
fs.file-max=52706963
fs.nr_open=52706963
net.ipv6.conf.all.disable_ipv6=1
net.netfilter.nf_conntrack_max=2310720
EOF
cp kubernetes.conf  /etc/sysctl.d/kubernetes.conf
sysctl -p /etc/sysctl.d/kubernetes.conf
需要关闭tcp_tw_recycle,否则和NAT冲突,会导致服务不通
关闭IPV6,防止触发Docker BUG

timedatectl set-timezone Asia/Shanghai
 #将当前的 UTC 时间写入硬件时钟
timedatectl set-local-rtc 0
 #重启依赖于系统时间的服务
systemctl restart rsyslog 
systemctl restart crond
mkdir -p  /opt/k8s/{bin,work} /etc/{kubernetes,etcd}/cert
#在所有节点上执行,因为flanneld是在所有节点运行的

安装前设置分发脚本

后续所有的使用环境变量都定义在environment.sh中,需要根据个人机器及网络环境修改。并且需要拷贝到所有节点的/opt/k8s/bin目录下
cat environment.sh
#!/usr/bin/bash
# 生成 EncryptionConfig 所需的加密 key
export ENCRYPTION_KEY=$(head -c 32 /dev/urandom | base64)
# 集群各机器 IP 数组
export NODE_IPS=( 192.168.100.26 192.168.100.27 192.168.100.28 192.168.100.29 )
# 集群各 IP 对应的主机名数组
export NODE_NAMES=(k8s-01 k8s-02 k8s-03 k8s-04)
# 集群MASTER机器 IP 数组
export MASTER_IPS=(192.168.100.26 192.168.100.27 192.168.100.28 )
# 集群所有的master Ip对应的主机
export MASTER_NAMES=(k8s-01 k8s-02 k8s-03)
# etcd 集群服务地址列表
export ETCD_ENDPOINTS="https://192.168.100.26:2379,https://192.168.100.27:2379,https://192.168.100.28:2379"
# etcd 集群间通信的 IP 和端口
export ETCD_NODES="k8s-01=https://192.168.100.26:2380,k8s-02=https://192.168.100.27:2380,k8s-03=https://192.168.100.28:2380"
# etcd 集群所有node ip
export ETCD_IPS=(192.168.100.26 192.168.100.27 192.168.100.28 192.168.100.29 )
# kube-apiserver 的反向代理(kube-nginx)地址端口
export KUBE_APISERVER="https://192.168.100.199:8443"
# 节点间互联网络接口名称
export I
# etcd 数据目录
export ETCD_DATA_DIR="/data/k8s/etcd/data"
# etcd WAL 目录,建议是 SSD 磁盘分区,或者和 ETCD_DATA_DIR 不同的磁盘分区
export ETCD_WAL_DIR="/data/k8s/etcd/wal"
# k8s 各组件数据目录
export K8S_DIR="/data/k8s/k8s"
# docker 数据目录
#export DOCKER_DIR="/data/k8s/docker"
## 以下参数一般不需要修改
# TLS Bootstrapping 使用的 Token,可以使用命令 head -c 16 /dev/urandom | od -An -t x | tr -d ' ' 生成
#BOOTSTRAP_TOKEN="41f7e4ba8b7be874fcff18bf5cf41a7c"
# 最好使用 当前未用的网段 来定义服务网段和 Pod 网段
# 服务网段,部署前路由不可达,部署后集群内路由可达(kube-proxy 保证)
SERVICE_CIDR="10.254.0.0/16"
# Pod 网段,建议 /16 段地址,部署前路由不可达,部署后集群内路由可达(flanneld 保证)
CLUSTER_CIDR="172.30.0.0/16"
# 服务端口范围 (NodePort Range)
export NODE_PORT_RANGE="1024-32767"
# flanneld 网络配置前缀
export FLANNEL_ETCD_PREFIX="/kubernetes/network"
# kubernetes 服务 IP (一般是 SERVICE_CIDR 中第一个IP)
export CLUSTER_KUBERNETES_SVC_IP="10.254.0.1"
# 集群 DNS 服务 IP (从 SERVICE_CIDR 中预分配)
export CLUSTER_DNS_SVC_IP="10.254.0.2"
# 集群 DNS 域名(末尾不带点号)
export CLUSTER_DNS_DOMAIN="cluster.local"
# 将二进制目录 /opt/k8s/bin 加到 PATH 中
export PATH=/opt/k8s/bin:$PATH



#分发环境变量
source environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp environment.sh root@${node_ip}:/opt/k8s/bin/
    ssh root@${node_ip} "chmod +x /opt/k8s/bin/* "
done

开始安装k8s集群

cfssl 安装

为确保安全,kubernetes各个组件需要使用x509证书对通信进行加密和认证
CA(Certificate Authority)是自签名的根证书,用来签名后续创建的其他证书。本文章使用CloudFlare的PKI工具cfssl创建所有证书。

注意: 如果没有特殊指明,本文档的所有操作均在k8s-01节点执行,远程分发到其他节点
#安装cfssl
mkdir -p /opt/k8s/cert && cd /opt/k8s
wget https://pkg.cfssl.org/R1.2/cfssl_linux-amd64
mv cfssl_linux-amd64 /opt/k8s/bin/cfssl
wget https://pkg.cfssl.org/R1.2/cfssljson_linux-amd64
mv cfssljson_linux-amd64 /opt/k8s/bin/cfssljson
wget https://pkg.cfssl.org/R1.2/cfssl-certinfo_linux-amd64
mv cfssl-certinfo_linux-amd64 /opt/k8s/bin/cfssl-certinfo
chmod +x /opt/k8s/bin/*
export PATH=/opt/k8s/bin:$PATH

cd /opt/k8s/work
cat > ca-config.json <<EOF
{
  "signing": {
    "default": {
      "expiry": "87600h"
    },
    "profiles": {
      "kubernetes": {
        "usages": [
            "signing",
            "key encipherment",
            "server auth",
            "client auth"
        ],
        "expiry": "87600h"
      }
    }
  }
}
EOF
 
 
 
######################
signing 表示该证书可用于签名其它证书,生成的ca.pem证书找中CA=TRUE
server auth 表示client可以用该证书对server提供的证书进行验证
client auth 表示server可以用该证书对client提供的证书进行验证

cd /opt/k8s/work
cat > ca-csr.json <<EOF
{
  "CN": "kubernetes",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "BeiJing",
      "L": "BeiJing",
      "O": "k8s",
      "OU": "4Paradigm"
    }
  ],
  "ca": {
    "expiry": "876000h"
 }
}
EOF
 
 
 
#######################
CN CommonName,kube-apiserver从证书中提取该字段作为请求的用户名(User Name),浏览器使用该字段验证网站是否合法
O Organization,kube-apiserver 从证书中提取该字段作为请求用户和所属组(Group)
kube-apiserver将提取的User、Group作为RBAC授权的用户和标识



cd /opt/k8s/work
cfssl gencert -initca ca-csr.json | cfssljson -bare ca
ls ca*

#分发证书
#将生成的CA证书、秘钥文件、配置文件拷贝到所有节点的/etc/kubernetes/cert目录下
 
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "mkdir -p /etc/kubernetes/cert"
    scp ca*.pem ca-config.json root@${node_ip}:/etc/kubernetes/cert
  done
  

部署kubectl命令行工具

cd /opt/k8s/work
wget http://down.i4t.com/k8s1.14/kubernetes-client-linux-amd64.tar.gz
tar -xzvf kubernetes-client-linux-amd64.tar.gz
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp kubernetes/client/bin/kubectl root@${node_ip}:/opt/k8s/bin/
    ssh root@${node_ip} "chmod +x /opt/k8s/bin/*"
  done
  

创建admin证书和私钥

kubectl与apiserver https通信,apiserver对提供的证书进行认证和授权。kubectl作为集群的管理工具,需要被授予最高权限,这里创建具有最高权限的admin证书

创建证书签名请求
cd /opt/k8s/work
cat > admin-csr.json <<EOF
{
  "CN": "admin",
  "hosts": [],
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "BeiJing",
      "L": "BeiJing",
      "O": "system:masters",
      "OU": "4Paradigm"
    }
  ]
}
EOF
 
 
 
###################
● O 为system:masters,kube-apiserver收到该证书后将请求的Group设置为system:masters
● 预定的ClusterRoleBinding cluster-admin将Group system:masters与Role cluster-admin绑定,该Role授予API的权限
● 该证书只有被kubectl当做client证书使用,所以hosts字段为空
cd /opt/k8s/work
cfssl gencert -ca=/opt/k8s/work/ca.pem \
  -ca-key=/opt/k8s/work/ca-key.pem \
  -config=/opt/k8s/work/ca-config.json \
  -profile=kubernetes admin-csr.json | cfssljson -bare admin
ls admin*

创建kubeconfig文件

kubeconfig为kubectl的配置文件,包含访问apiserver的所有信息,如apiserver地址、CA证书和自身使用的证书
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
# 设置集群参数
kubectl config set-cluster kubernetes \
  --certificate-authority=/opt/k8s/work/ca.pem \
  --embed-certs=true \
  --server=${KUBE_APISERVER} \
  --kubeconfig=kubectl.kubeconfig
#设置客户端认证参数
kubectl config set-credentials admin \
  --client-certificate=/opt/k8s/work/admin.pem \
  --client-key=/opt/k8s/work/admin-key.pem \
  --embed-certs=true \
  --kubeconfig=kubectl.kubeconfig
# 设置上下文参数
kubectl config set-context kubernetes \
  --cluster=kubernetes \
  --user=admin \
  --kubeconfig=kubectl.kubeconfig
# 设置默认上下文
kubectl config use-context kubernetes --kubeconfig=kubectl.kubeconfig
 
 
 
################
--certificate-authority 验证kube-apiserver证书的根证书
--client-certificate、--client-key 刚生成的admin证书和私钥,连接kube-apiserver时使用
--embed-certs=true 将ca.pem和admin.pem证书嵌入到生成的kubectl.kubeconfig文件中 (如果不加入,写入的是证书文件路径,后续拷贝kubeconfig到其它机器时,还需要单独拷贝证书)

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "mkdir -p ~/.kube"
    scp kubectl.kubeconfig root@${node_ip}:~/.kube/config
  done

部署ETCD集群

 cd /opt/k8s/work
wget http://down.i4t.com/k8s1.14/etcd-v3.3.13-linux-amd64.tar.gz
tar -xvf etcd-v3.3.13-linux-amd64.tar.gz
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${ETCD_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp etcd-v3.3.13-linux-amd64/etcd* root@${node_ip}:/opt/k8s/bin
    ssh root@${node_ip} "chmod +x /opt/k8s/bin/*"
  done
 
 # 创建etcd 证书密钥
 cd /opt/k8s/work
cat > etcd-csr.json <<EOF
{
  "CN": "etcd",
  "hosts": [
    "127.0.0.1",
    "192.168.100.26",
    "192.168.100.27",
    "192.168.100.28"
  ],
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "BeiJing",
      "L": "BeiJing",
      "O": "k8s",
      "OU": "4Paradigm"
    }
  ]
}
EOF
 
 
#host字段指定授权使用该证书的etcd节点IP或域名列表,需要将etcd集群的3个节点都添加其中

cd /opt/k8s/work
cfssl gencert -ca=/opt/k8s/work/ca.pem \
    -ca-key=/opt/k8s/work/ca-key.pem \
    -config=/opt/k8s/work/ca-config.json \
    -profile=kubernetes etcd-csr.json | cfssljson -bare etcd
ls etcd*pem

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${ETCD_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "mkdir -p /etc/etcd/cert"
    scp etcd*.pem root@${node_ip}:/etc/etcd/cert/
  done
 
 # 创建启动文件
 cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
cat > etcd.service.template <<EOF
[Unit]
Description=Etcd Server
After=network.target
After=network-online.target
Wants=network-online.target
Documentation=https://github.com/coreos
[Service]
Type=notify
WorkingDirectory=${ETCD_DATA_DIR}
ExecStart=/opt/k8s/bin/etcd \\
  --data-dir=${ETCD_DATA_DIR} \\
  --wal-dir=${ETCD_WAL_DIR} \\
  --name=##NODE_NAME## \\
  --cert-file=/etc/etcd/cert/etcd.pem \\
  --key-file=/etc/etcd/cert/etcd-key.pem \\
  --trusted-ca-file=/etc/kubernetes/cert/ca.pem \\
  --peer-cert-file=/etc/etcd/cert/etcd.pem \\
  --peer-key-file=/etc/etcd/cert/etcd-key.pem \\
  --peer-trusted-ca-file=/etc/kubernetes/cert/ca.pem \\
  --peer-client-cert-auth \\
  --client-cert-auth \\
  --listen-peer-urls=https://##NODE_IP##:2380 \\
  --initial-advertise-peer-urls=https://##NODE_IP##:2380 \\
  --listen-client-urls=https://##NODE_IP##:2379,http://127.0.0.1:2379 \\
  --advertise-client-urls=https://##NODE_IP##:2379 \\
  --initial-cluster-token=etcd-cluster-0 \\
  --initial-cluster=${ETCD_NODES} \\
  --initial-cluster-state=new \\
  --auto-compaction-mode=periodic \\
  --auto-compaction-retention=1 \\
  --max-request-bytes=33554432 \\
  --quota-backend-bytes=6442450944 \\
  --heartbeat-interval=250 \\
  --election-timeout=2000
Restart=on-failure
RestartSec=5
LimitNOFILE=65536
[Install]
WantedBy=multi-user.target
EOF

配置说明 (此处不需要修改任何配置)

WorkDirectory、--data-dir 指定etcd工作目录和数据存储为${ETCD_DATA_DIR},需要在启动前创建这个目录 (后面跟着我操作就可以,会有创建步骤)
--wal-dir 指定wal目录,为了提高性能,一般使用SSD和--data-dir不同的盘
--name 指定节点名称,当--initial-cluster-state值为new时,--name的参数值必须位于--initial-cluster列表中
--cert-file、--key-file ETCD server与client通信时使用的证书和私钥
--trusted-ca-file 签名client证书的CA证书,用于验证client证书
--peer-cert-file、--peer-key-file ETCD与peer通信使用的证书和私钥
--peer-trusted-ca-file 签名peer证书的CA证书,用于验证peer证书


#分发会将配置文件中的#替换成ip
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for (( i=0; i < 3; i++ ))
  do
    sed -e "s/##NODE_NAME##/${MASTER_NAMES[i]}/" -e "s/##NODE_IP##/${ETCD_IPS[i]}/" etcd.service.template > etcd-${ETCD_IPS[i]}.service 
  done
ls *.service
 
 
#NODE_NAMES 和 NODE_IPS 为相同长度的 bash 数组,分别为节点名称和对应的 IP;

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp etcd-${node_ip}.service root@${node_ip}:/etc/systemd/system/etcd.service
  done

重命名etcd启动文件并启动etcd服务

etcd首次进程启动会等待其他节点加入etcd集群,执行启动命令会卡顿一会,为正常现象

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "mkdir -p ${ETCD_DATA_DIR} ${ETCD_WAL_DIR}"
    ssh root@${node_ip} "systemctl daemon-reload && systemctl enable etcd && systemctl restart etcd " &
  done
 
#这里我们创建了etcd的工作目录

#检查启动结果
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "systemctl status etcd|grep Active"
  done

正常状态下为这种情况 
# for node_ip in ${MASTER_IPS[@]}
>   do
>     echo ">>> ${node_ip}"
>     ssh root@${node_ip} "systemctl status etcd|grep Active"
>   done
>>> 192.168.100.26
   Active: active (running) since Mon 2023-08-21 16:10:15 CST; 52s ago
>>> 192.168.100.27
   Active: active (running) since Mon 2023-08-21 16:10:15 CST; 52s ago
>>> 192.168.100.28
   Active: active (running) since Mon 2023-08-21 16:10:15 CST; 52s ago

可以用这个命令查看journalctl -fu etcd

验证etcd是否正常
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ETCDCTL_API=3 /opt/k8s/bin/etcdctl \
    --endpoints=https://${node_ip}:2379 \
    --cacert=/etc/kubernetes/cert/ca.pem \
    --cert=/etc/etcd/cert/etcd.pem \
    --key=/etc/etcd/cert/etcd-key.pem endpoint health
  done

正常为如下操作
# for node_ip in ${MASTER_IPS[@]}
>   do
>     echo ">>> ${node_ip}"
>     ETCDCTL_API=3 /opt/k8s/bin/etcdctl \
>     --endpoints=https://${node_ip}:2379 \
>     --cacert=/etc/kubernetes/cert/ca.pem \
>     --cert=/etc/etcd/cert/etcd.pem \
>     --key=/etc/etcd/cert/etcd-key.pem endpoint health
>   done
>>> 192.168.100.26
https://192.168.100.26:2379 is healthy: successfully committed proposal: took = 2.247021ms
>>> 192.168.100.27
https://192.168.100.27:2379 is healthy: successfully committed proposal: took = 2.080702ms
>>> 192.168.100.28
https://192.168.100.28:2379 is healthy: successfully committed proposal: took = 2.262168ms

通过etcd 查看集群的leader
source /opt/k8s/bin/environment.sh
ETCDCTL_API=3 /opt/k8s/bin/etcdctl \
  -w table --cacert=/etc/kubernetes/cert/ca.pem \
  --cert=/etc/etcd/cert/etcd.pem \
  --key=/etc/etcd/cert/etcd-key.pem \
  --endpoints=${ETCD_ENDPOINTS} endpoint status
# ETCDCTL_API=3 /opt/k8s/bin/etcdctl \
>   -w table --cacert=/etc/kubernetes/cert/ca.pem \
>   --cert=/etc/etcd/cert/etcd.pem \
>   --key=/etc/etcd/cert/etcd-key.pem \
>   --endpoints=${ETCD_ENDPOINTS} endpoint status
+-----------------------------+------------------+---------+---------+-----------+-----------+------------+
|          ENDPOINT           |        ID        | VERSION | DB SIZE | IS LEADER | RAFT TERM | RAFT INDEX |
+-----------------------------+------------------+---------+---------+-----------+-----------+------------+
| https://192.168.100.26:2379 | 4fb7383fdc28cdcb |  3.3.13 |   20 kB |      true |         2 |          8 |
| https://192.168.100.27:2379 | e69d641fa8a08905 |  3.3.13 |   20 kB |     false |         2 |          8 |
| https://192.168.100.28:2379 | 1f54d9cf6d187788 |  3.3.13 |   20 kB |     false |         2 |          8 |
+-----------------------------+------------------+---------+---------+-----------+-----------+------------+

部署Flannel网络

Kubernetes要求集群内各个节点(包括master)能通过Pod网段互联互通,Flannel使用vxlan技术为各个节点创建一个互通的Pod网络,使用的端口为8472.第一次启动时,从etcd获取配置的Pod网络,为本节点分配一个未使用的地址段,然后创建flannel.1网络接口(也可能是其它名称)flannel将分配给自己的Pod网段信息写入/run/flannel/docker文件,docker后续使用这个文件中的环境变量设置Docker0网桥,从而从这个地址段为本节点的所有Pod容器分配IP

下载分发flanneld二进制文件 (本次flanneld不使用Pod运行)
cd /opt/k8s/work
mkdir flannel
wget http://down.i4t.com/k8s1.14/flannel-v0.11.0-linux-amd64.tar.gz
tar -xzvf flannel-v0.11.0-linux-amd64.tar.gz -C flannel

flanneld从etcd集群存取网段分配信息,而etcd集群开启了双向x509证书认证,所以需要为flannel生成证书和私钥

创建证书签名请求
cd /opt/k8s/work
cat > flanneld-csr.json <<EOF
{
  "CN": "flanneld",
  "hosts": [],
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "BeiJing",
      "L": "BeiJing",
      "O": "k8s",
      "OU": "4Paradigm"
    }
  ]
}
EOF

cfssl gencert -ca=/opt/k8s/work/ca.pem \
  -ca-key=/opt/k8s/work/ca-key.pem \
  -config=/opt/k8s/work/ca-config.json \
  -profile=kubernetes flanneld-csr.json | cfssljson -bare flanneld
ls flanneld*pem

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "mkdir -p /etc/flanneld/cert"
    scp flanneld*.pem root@${node_ip}:/etc/flanneld/cert
  done
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
etcdctl \
  --endpoints=${ETCD_ENDPOINTS} \
  --ca-file=/opt/k8s/work/ca.pem \
  --cert-file=/opt/k8s/work/flanneld.pem \
  --key-file=/opt/k8s/work/flanneld-key.pem \
  mk ${FLANNEL_ETCD_PREFIX}/config '{"Network":"'${CLUSTER_CIDR}'", "SubnetLen": 21, "Backend": {"Type": "vxlan"}}'
注意:

flanneld当前版本v0.11.0不支持etcd v3,故使用etcd v2 API写入配置Key和网段数据;

写入的Pod网段${CLUSTER_CIDR}地址段(如/16)必须小于SubnetLen,必须与kube-controller-manager的--cluster-cidr参数一致

#创建flanneld的启动文件
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
cat > flanneld.service << EOF
[Unit]
Description=Flanneld overlay address etcd agent
After=network.target
After=network-online.target
Wants=network-online.target
After=etcd.service
Before=docker.service
[Service]
Type=notify
ExecStart=/opt/k8s/bin/flanneld \\
  -etcd-cafile=/etc/kubernetes/cert/ca.pem \\
  -etcd-certfile=/etc/flanneld/cert/flanneld.pem \\
  -etcd-keyfile=/etc/flanneld/cert/flanneld-key.pem \\
  -etcd-endpoints=${ETCD_ENDPOINTS} \\
  -etcd-prefix=${FLANNEL_ETCD_PREFIX} \\
  -iface=${IFACE} \\
  -ip-masq
ExecStartPost=/opt/k8s/bin/mk-docker-opts.sh -k DOCKER_NETWORK_OPTIONS -d /run/flannel/docker
Restart=always
RestartSec=5
StartLimitInterval=0
[Install]
WantedBy=multi-user.target
RequiredBy=docker.service
EOF
mk-docker-opts.sh 脚本将分配给 flanneld 的 Pod 子网段信息写入 /run/flannel/docker 文件,后续 docker 启动时使用这个文件中的环境变量配置 docker0 网桥;
flanneld 使用系统缺省路由所在的接口与其它节点通信,对于有多个网络接口(如内网和公网)的节点,可以用 -iface 参数指定通信接口;
flanneld 运行时需要 root 权限;
-ip-masq: flanneld 为访问 Pod 网络外的流量设置 SNAT 规则,同时将传递给 Docker 的变量 --ip-masq(/run/flannel/docker 文件中)设置为 false,这样 Docker 将不再创建 SNAT 规则; Docker 的 --ip-masq 为 true 时,创建的 SNAT 规则比较“暴力”:将所有本节点 Pod 发起的、访问非 docker0 接口的请求做 SNAT,这样访问其他节点 Pod 的请求来源 IP 会被设置为 flannel.1 接口的 IP,导致目的 Pod 看不到真实的来源 Pod IP。 flanneld 创建的 SNAT 规则比较温和,只对访问非 Pod 网段的请求做 SNAT。
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp flanneld.service root@${node_ip}:/etc/systemd/system/
  done
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "systemctl daemon-reload && systemctl enable flanneld && systemctl restart flanneld"
  done
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "systemctl status flanneld|grep Active"
  done

# 检查分配给flanneld的Pod网段信息
source /opt/k8s/bin/environment.sh
etcdctl \
  --endpoints=${ETCD_ENDPOINTS} \
  --ca-file=/etc/kubernetes/cert/ca.pem \
  --cert-file=/etc/flanneld/cert/flanneld.pem \
  --key-file=/etc/flanneld/cert/flanneld-key.pem \
  get ${FLANNEL_ETCD_PREFIX}/config
 
 #查看已分配的Pod子网网段列表
 source /opt/k8s/bin/environment.sh
etcdctl \
  --endpoints=${ETCD_ENDPOINTS} \
  --ca-file=/etc/kubernetes/cert/ca.pem \
  --cert-file=/etc/flanneld/cert/flanneld.pem \
  --key-file=/etc/flanneld/cert/flanneld-key.pem \
  ls ${FLANNEL_ETCD_PREFIX}/subnets
#查看某Pod网段对应节点IP和flannel接口地址
source /opt/k8s/bin/environment.sh
etcdctl \
  --endpoints=${ETCD_ENDPOINTS} \
  --ca-file=/etc/kubernetes/cert/ca.pem \
  --cert-file=/etc/flanneld/cert/flanneld.pem \
  --key-file=/etc/flanneld/cert/flanneld-key.pem \
  get ${FLANNEL_ETCD_PREFIX}/subnets/172.30.104.0-21
 
#后面节点IP需要根据我们查出来的地址进行修改
# etcdctl \
>   --endpoints=${ETCD_ENDPOINTS} \
>   --ca-file=/etc/kubernetes/cert/ca.pem \
>   --cert-file=/etc/flanneld/cert/flanneld.pem \
>   --key-file=/etc/flanneld/cert/flanneld-key.pem \
>   ls ${FLANNEL_ETCD_PREFIX}/subnets
/kubernetes/network/subnets/172.30.104.0-21
/kubernetes/network/subnets/172.30.224.0-21
/kubernetes/network/subnets/172.30.24.0-21
/kubernetes/network/subnets/172.30.64.0-21
[root@k8s-01 work]# source /opt/k8s/bin/environment.sh
[root@k8s-01 work]# source /opt/k8s/bin/environment.sh
[root@k8s-01 work]# etcdctl \
>   --endpoints=${ETCD_ENDPOINTS} \
>   --ca-file=/etc/kubernetes/cert/ca.pem \
>   --cert-file=/etc/flanneld/cert/flanneld.pem \
>   --key-file=/etc/flanneld/cert/flanneld-key.pem \
>   get ${FLANNEL_ETCD_PREFIX}/subnets/172.30.104.0-21
{"PublicIP":"192.168.100.28","BackendType":"vxlan","BackendData":{"VtepMAC":"9a:aa:f4:f0:2c:e8"}}

# 查看节点flannel网络信息
ip addr show
flannel.1网卡的地址为分配的pod自网段的第一个个IP (.0),且是/32的地址
ip addr show|grep flannel.1
到其它节点 Pod 网段请求都被转发到 flannel.1 网卡;

flanneld 根据 etcd 中子网段的信息,如 ${FLANNEL_ETCD_PREFIX}/subnets/172.30.80.0-21,来决定进请求发送给哪个节点的互联 IP;

验证各节点能通过 Pod 网段互通

在各节点上部署 flannel 后,检查是否创建了 flannel 接口(名称可能为 flannel0、flannel.0、flannel.1 等):
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh ${node_ip} "/usr/sbin/ip addr show flannel.1|grep -w inet"
  done

kube-apiserver 高可用

使用Nginx 4层透明代理功能实现k8s节点(master节点和worker节点)高可用访问kube-apiserver的步骤
控制节点的kube-controller-manager、kube-scheduler是多实例部署,所以只要一个实例正常,就可以保证集群高可用
集群内的Pod使用k8s服务域名kubernetes访问kube-apiserver,kube-dns会自动解析多个kube-apiserver节点的IP,所以也是高可用的
在每个Nginx进程,后端对接多个apiserver实例,Nginx对他们做健康检查和负载均衡
kubelet、kube-proxy、controller-manager、schedule通过本地nginx (监听我们vip 192.158.0.54)访问kube-apiserver,从而实现kube-apiserver高可用
下载编译nginx (k8s-01安装就可以,后面有拷贝步骤)
cd /opt/k8s/work
wget http://down.i4t.com/k8s1.14/nginx-1.15.3.tar.gz
tar -xzvf nginx-1.15.3.tar.gz
 
#编译
cd /opt/k8s/work/nginx-1.15.3
mkdir nginx-prefix
./configure --with-stream --without-http --prefix=$(pwd)/nginx-prefix --without-http_uwsgi_module 
make && make install
 
#############
--without-http_scgi_module --without-http_fastcgi_module
--with-stream:开启 4 层透明转发(TCP Proxy)功能;
--without-xxx:关闭所有其他功能,这样生成的动态链接二进制程序依赖最小;

查看安装后的动态库
ldd ./nginx-prefix/sbin/nginx
由于只开启了 4 层透明转发功能,所以除了依赖 libc 等操作系统核心 lib 库外,没有对其它 lib 的依赖(如 libz、libssl 等),这样可以方便部署到各版本操作系统中

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    mkdir -p /opt/k8s/kube-nginx/{conf,logs,sbin}
  done

#拷贝二进制到其他文件,一次执行不成功,就多执行一次
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp /opt/k8s/work/nginx-1.15.3/nginx-prefix/sbin/nginx  root@${node_ip}:/opt/k8s/kube-nginx/sbin/kube-nginx
    ssh root@${node_ip} "chmod a+x /opt/k8s/kube-nginx/sbin/*"
    ssh root@${node_ip} "mkdir -p /opt/k8s/kube-nginx/{conf,logs,sbin}"
    sleep 3
  done

# 配置Nginx文件,开启4层透明转发

cd /opt/k8s/work
cat > kube-nginx.conf <<EOF
worker_processes 1;
events {
    worker_connections  1024;
}
stream {
    upstream backend {
        hash $remote_addr consistent;
        server 192.168.100.26:6443        max_fails=3 fail_timeout=30s;
        server 192.168.100.27:6443        max_fails=3 fail_timeout=30s;
        server 192.168.100.28:6443        max_fails=3 fail_timeout=30s;
    }
    server {
        listen *:8443;
        proxy_connect_timeout 1s;
        proxy_pass backend;
    }
}
EOF
 
#这里需要将server替换我们自己的地址


cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp kube-nginx.conf  root@${node_ip}:/opt/k8s/kube-nginx/conf/kube-nginx.conf
  done

#配置启动文件
cd /opt/k8s/work
cat > kube-nginx.service <<EOF
[Unit]
Description=kube-apiserver nginx proxy
After=network.target
After=network-online.target
Wants=network-online.target
[Service]
Type=forking
ExecStartPre=/opt/k8s/kube-nginx/sbin/kube-nginx -c /opt/k8s/kube-nginx/conf/kube-nginx.conf -p /opt/k8s/kube-nginx -t
ExecStart=/opt/k8s/kube-nginx/sbin/kube-nginx -c /opt/k8s/kube-nginx/conf/kube-nginx.conf -p /opt/k8s/kube-nginx
ExecReload=/opt/k8s/kube-nginx/sbin/kube-nginx -c /opt/k8s/kube-nginx/conf/kube-nginx.conf -p /opt/k8s/kube-nginx -s reload
PrivateTmp=true
Restart=always
RestartSec=5
StartLimitInterval=0
LimitNOFILE=65536
[Install]
WantedBy=multi-user.target
EOF

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp kube-nginx.service  root@${node_ip}:/etc/systemd/system/
  done

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "systemctl daemon-reload && systemctl enable kube-nginx && systemctl start kube-nginx"
  done

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "systemctl status kube-nginx |grep 'Active:'"
  done

KeepLived 部署

需要一个vip
在所有master节点安装keeplived
yum  install -y keepalived

在192.168.100.26 上操作
cat > /etc/keepalived/keepalived.conf <<EOF
! Configuration File for keepalived
global_defs {
   router_id 192.168.100.26
}
vrrp_script chk_nginx {
    script "/etc/keepalived/check_port.sh 8443"
    interval 2
    weight -20
}
vrrp_instance VI_1 {
    state MASTER
    interface eth0
    virtual_router_id 251
    priority 100
    advert_int 1
    mcast_src_ip 192.168.100.26
    nopreempt
    authentication {
        auth_type PASS
        auth_pass 11111111
    }
    track_script {
         chk_nginx
    }
    virtual_ipaddress {
        192.168.100.199
    }
}
EOF
 
## 192.168.100.26 为节点IP,192.168.100.199位VIP

#将配置拷贝到其他节点,并替换相关IP
for node_ip in 192.168.100.26 192.168.100.27 192.168.100.28
  do
    echo ">>> ${node_ip}"
    scp  /etc/keepalived/keepalived.conf $node_ip:/etc/keepalived/keepalived.conf
  done
 
#替换IP
ssh [email protected] sed -i 's#192.168.100.26#192.168.100.27#g'  /etc/keepalived/keepalived.conf
ssh [email protected] sed -i 's#192.168.100.26#192.168.100.28#g'  /etc/keepalived/keepalived.conf
 
#192.168.100.26不替换是因为已经修改好了

# 创建健康检查脚本
vim  /opt/check_port.sh 
CHK_PORT=$1
 if [ -n "$CHK_PORT" ];then
        PORT_PROCESS=`ss -lt|grep $CHK_PORT|wc -l`
        if [ $PORT_PROCESS -eq 0 ];then
                echo "Port $CHK_PORT Is Not Used,End."
                exit 1
        fi
 else
        echo "Check Port Cant Be Empty!"
 fi

for NODE in k8s-01 k8s-02 k8s-03; do
    echo "--- $NODE ---"
    scp -r /opt/check_port.sh  $NODE:/etc/keepalived/
    ssh $NODE 'systemctl enable --now keepalived'
done

#没有启动成功,请执行下面命令,从新启动。启动成功vip肯定就通了
systemctl start keepalived

部署master节点

kubernetes master节点运行组件如下:kube-apiserver、kube-scheduler、kube-controller-manager、kube-nginx

kube-apiserver、kube-scheduler、kube-controller-manager均以多实例模式运行
kube-scheduler和kube-controller-manager会自动选举一个leader实例,其他实例处于阻塞模式,当leader挂了后,重新选举产生的leader,从而保证服务可用性
kube-apiserver是无状态的,需要通过kube-nginx进行代理访问,从而保证服务可用性
以下操作都在K8s-01操作

下载kubernetes二进制包,并分发到所有master节点

cd /opt/k8s/work
wget http://down.i4t.com/k8s1.14/kubernetes-server-linux-amd64.tar.gz
tar -xzvf kubernetes-server-linux-amd64.tar.gz
cd kubernetes
tar -xzvf  kubernetes-src.tar.gz


cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp kubernetes/server/bin/kube-apiserver root@${node_ip}:/opt/k8s/bin/
    scp kubernetes/server/bin/{apiextensions-apiserver,cloud-controller-manager,kube-controller-manager,kube-proxy,kube-scheduler,kubeadm,kubectl,kubelet,mounter} root@${node_ip}:/opt/k8s/bin/
    ssh root@${node_ip} "chmod +x /opt/k8s/bin/*"
  done
 
#同时将kubelet kube-proxy拷贝到所有节点
 
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp kubernetes/server/bin/{kubelet,kube-proxy} root@${node_ip}:/opt/k8s/bin/
    ssh root@${node_ip} "chmod +x /opt/k8s/bin/*"
  done

#添加密钥
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
cat > kubernetes-csr.json <<EOF
{
  "CN": "kubernetes",
  "hosts": [
    "127.0.0.1",
    "192.168.100.26",
    "192.168.100.27",
    "192.168.100.28",
    "192.168.100.199",
    "10.254.0.1",
    "kubernetes",
    "kubernetes.default",
    "kubernetes.default.svc",
    "kubernetes.default.svc.cluster",
    "kubernetes.default.svc.cluster.local."
  ],
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "BeiJing",
      "L": "BeiJing",
      "O": "k8s",
      "OU": "4Paradigm"
    }
  ]
}
EOF
 
#需要将集群的所有IP及VIP添加进去
#如果要添加注意最后的逗号,不要忘记添加,否则下一步报错
hosts 字段指定授权使用该证书的IP和域名列表,这里列出了master节点IP、kubernetes服务的IP和域名

kubernetes serviceIP是apiserver自动创建的,一般是--service-cluster-ip-range参数指定的网段的第一个IP
$ kubectl get svc kubernetes
NAME         TYPE        CLUSTER-IP   EXTERNAL-IP   PORT(S)   AGE
kubernetes   ClusterIP   10.254.0.1           443/TCP   31d
 
#目前我们是看不到

   cfssl gencert -ca=/opt/k8s/work/ca.pem \
      -ca-key=/opt/k8s/work/ca-key.pem \
      -config=/opt/k8s/work/ca-config.json \
      -profile=kubernetes kubernetes-csr.json | cfssljson -bare kubernetes
    ls kubernetes*pem
    cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "mkdir -p /etc/kubernetes/cert"
    scp kubernetes*.pem root@${node_ip}:/etc/kubernetes/cert/
  done

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
cat > encryption-config.yaml <<EOF
kind: EncryptionConfig
apiVersion: v1
resources:
  - resources:
      - secrets
    providers:
      - aescbc:
          keys:
            - name: key1
              secret: ${ENCRYPTION_KEY}
      - identity: {}
EOF

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp encryption-config.yaml root@${node_ip}:/etc/kubernetes/
  done

#创建审核文件
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
cat > audit-policy.yaml <<EOF
apiVersion: audit.k8s.io/v1beta1
kind: Policy
rules:
  # The following requests were manually identified as high-volume and low-risk, so drop them.
  - level: None
    resources:
      - group: ""
        resources:
          - endpoints
          - services
          - services/status
    users:
      - 'system:kube-proxy'
    verbs:
      - watch
  - level: None
    resources:
      - group: ""
        resources:
          - nodes
          - nodes/status
    userGroups:
      - 'system:nodes'
    verbs:
      - get
  - level: None
    namespaces:
      - kube-system
    resources:
      - group: ""
        resources:
          - endpoints
    users:
      - 'system:kube-controller-manager'
      - 'system:kube-scheduler'
      - 'system:serviceaccount:kube-system:endpoint-controller'
    verbs:
      - get
      - update
  - level: None
    resources:
      - group: ""
        resources:
          - namespaces
          - namespaces/status
          - namespaces/finalize
    users:
      - 'system:apiserver'
    verbs:
      - get
  # Don't log HPA fetching metrics.
  - level: None
    resources:
      - group: metrics.k8s.io
    users:
      - 'system:kube-controller-manager'
    verbs:
      - get
      - list
  # Don't log these read-only URLs.
  - level: None
    nonResourceURLs:
      - '/healthz*'
      - /version
      - '/swagger*'
  # Don't log events requests.
  - level: None
    resources:
      - group: ""
        resources:
          - events
  # node and pod status calls from nodes are high-volume and can be large, don't log responses for expected updates from nodes
  - level: Request
    omitStages:
      - RequestReceived
    resources:
      - group: ""
        resources:
          - nodes/status
          - pods/status
    users:
      - kubelet
      - 'system:node-problem-detector'
      - 'system:serviceaccount:kube-system:node-problem-detector'
    verbs:
      - update
      - patch
  - level: Request
    omitStages:
      - RequestReceived
    resources:
      - group: ""
        resources:
          - nodes/status
          - pods/status
    userGroups:
      - 'system:nodes'
    verbs:
      - update
      - patch
  # deletecollection calls can be large, don't log responses for expected namespace deletions
  - level: Request
    omitStages:
      - RequestReceived
    users:
      - 'system:serviceaccount:kube-system:namespace-controller'
    verbs:
      - deletecollection
  # Secrets, ConfigMaps, and TokenReviews can contain sensitive & binary data,
  # so only log at the Metadata level.
  - level: Metadata
    omitStages:
      - RequestReceived
    resources:
      - group: ""
        resources:
          - secrets
          - configmaps
      - group: authentication.k8s.io
        resources:
          - tokenreviews
  # Get repsonses can be large; skip them.
  - level: Request
    omitStages:
      - RequestReceived
    resources:
      - group: ""
      - group: admissionregistration.k8s.io
      - group: apiextensions.k8s.io
      - group: apiregistration.k8s.io
      - group: apps
      - group: authentication.k8s.io
      - group: authorization.k8s.io
      - group: autoscaling
      - group: batch
      - group: certificates.k8s.io
      - group: extensions
      - group: metrics.k8s.io
      - group: networking.k8s.io
      - group: policy
      - group: rbac.authorization.k8s.io
      - group: scheduling.k8s.io
      - group: settings.k8s.io
      - group: storage.k8s.io
    verbs:
      - get
      - list
      - watch
  # Default level for known APIs
  - level: RequestResponse
    omitStages:
      - RequestReceived
    resources:
      - group: ""
      - group: admissionregistration.k8s.io
      - group: apiextensions.k8s.io
      - group: apiregistration.k8s.io
      - group: apps
      - group: authentication.k8s.io
      - group: authorization.k8s.io
      - group: autoscaling
      - group: batch
      - group: certificates.k8s.io
      - group: extensions
      - group: metrics.k8s.io
      - group: networking.k8s.io
      - group: policy
      - group: rbac.authorization.k8s.io
      - group: scheduling.k8s.io
      - group: settings.k8s.io
      - group: storage.k8s.io
  # Default level for all other requests.
  - level: Metadata
    omitStages:
      - RequestReceived
EOF

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp audit-policy.yaml root@${node_ip}:/etc/kubernetes/audit-policy.yaml
  done
cat > proxy-client-csr.json <<EOF
{
  "CN": "aggregator",
  "hosts": [],
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "BeiJing",
      "L": "BeiJing",
      "O": "k8s",
      "OU": "4Paradigm"
    }
  ]
}
EOF

CN名称需要位于kube-apiserver的--requestherader-allowed-names参数中,否则后续访问metrics时会提示权限不足
生成证书和私钥

source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp proxy-client*.pem root@${node_ip}:/etc/kubernetes/cert/
  done

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
cat > kube-apiserver.service.template <<EOF
[Unit]
Description=Kubernetes API Server
Documentation=https://github.com/GoogleCloudPlatform/kubernetes
After=network.target
[Service]
WorkingDirectory=${K8S_DIR}/kube-apiserver
ExecStart=/opt/k8s/bin/kube-apiserver \\
  --advertise-address=##NODE_IP## \\
  --default-not-ready-toleration-seconds=360 \\
  --default-unreachable-toleration-seconds=360 \\
  --feature-gates=DynamicAuditing=true \\
  --max-mutating-requests-inflight=2000 \\
  --max-requests-inflight=4000 \\
  --default-watch-cache-size=200 \\
  --delete-collection-workers=2 \\
  --encryption-provider-config=/etc/kubernetes/encryption-config.yaml \\
  --etcd-cafile=/etc/kubernetes/cert/ca.pem \\
  --etcd-certfile=/etc/kubernetes/cert/kubernetes.pem \\
  --etcd-keyfile=/etc/kubernetes/cert/kubernetes-key.pem \\
  --etcd-servers=${ETCD_ENDPOINTS} \\
  --bind-address=##NODE_IP## \\
  --secure-port=6443 \\
  --tls-cert-file=/etc/kubernetes/cert/kubernetes.pem \\
  --tls-private-key-file=/etc/kubernetes/cert/kubernetes-key.pem \\
  --insecure-port=0 \\
  --audit-dynamic-configuration \\
  --audit-log-maxage=15 \\
  --audit-log-maxbackup=3 \\
  --audit-log-maxsize=100 \\
  --audit-log-truncate-enabled \\
  --audit-log-path=${K8S_DIR}/kube-apiserver/audit.log \\
  --audit-policy-file=/etc/kubernetes/audit-policy.yaml \\
  --profiling \\
  --anonymous-auth=false \\
  --client-ca-file=/etc/kubernetes/cert/ca.pem \\
  --enable-bootstrap-token-auth \\
  --requestheader-allowed-names="aggregator" \\
  --requestheader-client-ca-file=/etc/kubernetes/cert/ca.pem \\
  --requestheader-extra-headers-prefix="X-Remote-Extra-" \\
  --requestheader-group-headers=X-Remote-Group \\
  --requestheader-username-headers=X-Remote-User \\
  --service-account-key-file=/etc/kubernetes/cert/ca.pem \\
  --authorization-mode=Node,RBAC \\
  --runtime-config=api/all=true \\
  --enable-admission-plugins=NodeRestriction \\
  --allow-privileged=true \\
  --apiserver-count=3 \\
  --event-ttl=168h \\
  --kubelet-certificate-authority=/etc/kubernetes/cert/ca.pem \\
  --kubelet-client-certificate=/etc/kubernetes/cert/kubernetes.pem \\
  --kubelet-client-key=/etc/kubernetes/cert/kubernetes-key.pem \\
  --kubelet-https=true \\
  --kubelet-timeout=10s \\
  --proxy-client-cert-file=/etc/kubernetes/cert/proxy-client.pem \\
  --proxy-client-key-file=/etc/kubernetes/cert/proxy-client-key.pem \\
  --service-cluster-ip-range=${SERVICE_CIDR} \\
  --service-node-port-range=${NODE_PORT_RANGE} \\
  --logtostderr=true \\
  --v=2
Restart=on-failure
RestartSec=10
Type=notify
LimitNOFILE=65536
[Install]
WantedBy=multi-user.target
EOF

--advertise-address:apiserver 对外通告的 IP(kubernetes 服务后端节点 IP);
--default-*-toleration-seconds:设置节点异常相关的阈值;
--max-*-requests-inflight:请求相关的最大阈值;
--etcd-*:访问 etcd 的证书和 etcd 服务器地址;
--experimental-encryption-provider-config:指定用于加密 etcd 中 secret 的配置;
--bind-address: https 监听的 IP,不能为 127.0.0.1,否则外界不能访问它的安全端口 6443;
--secret-port:https 监听端口;
--insecure-port=0:关闭监听 http 非安全端口(8080);
--tls-*-file:指定 apiserver 使用的证书、私钥和 CA 文件;
--audit-*:配置审计策略和审计日志文件相关的参数;
--client-ca-file:验证 client (kue-controller-manager、kube-scheduler、kubelet、kube-proxy 等)请求所带的证书;
--enable-bootstrap-token-auth:启用 kubelet bootstrap 的 token 认证;
--requestheader-*:kube-apiserver 的 aggregator layer 相关的配置参数,proxy-client & HPA 需要使用;
--requestheader-client-ca-file:用于签名 --proxy-client-cert-file 和 --proxy-client-key-file 指定的证书;在启用了 metric aggregator 时使用;
--requestheader-allowed-names:不能为空,值为逗号分割的 --proxy-client-cert-file 证书的 CN 名称,这里设置为 "aggregator";
--service-account-key-file:签名 ServiceAccount Token 的公钥文件,kube-controller-manager 的 --service-account-private-key-file 定私钥文件,两者配对使用;
--runtime-config=api/all=true: 启用所有版本的 APIs,如 autoscaling/v2alpha1;
--authorization-mode=Node,RBAC、--anonymous-auth=false: 开启 Node 和 RBAC 授权模式,拒绝未授权的请求;
--enable-admission-plugins:启用一些默认关闭的 plugins;
--allow-privileged:运行执行 privileged 权限的容器;
--apiserver-count=3:指定 apiserver 实例的数量;
--event-ttl:指定 events 的保存时间;
--kubelet-:如果指定,则使用 https 访问 kubelet APIs;需要为证书对应的用户(上面 kubernetes.pem 证书的用户为 kubernetes) 用户定义 RBAC 规则,否则访问 kubelet API 时提示未授权;
--proxy-client-*:apiserver 访问 metrics-server 使用的证书;
--service-cluster-ip-range: 指定 Service Cluster IP 地址段;
--service-node-port-range: 指定 NodePort 的端口范围;
如果 kube-apiserver 机器没有运行 kube-proxy,则还需要添加 --enable-aggregator-routing=true 参数;
 关于 --requestheader-XXX 相关参数,参考:
https://github.com/kubernetes-incubator/apiserver-builder/blob/master/docs/concepts/auth.md
https://docs.bitnami.com/kubernetes/how-to/configure-autoscaling-custom-metrics/
注意: requestheader-client-ca-file指定的CA证书,必须具有client auth and server auth

如果--requestheader-allowed-names为空,或者--proxy-client-cert-file证书的CN名称不在allowed-names中,则后续查看node或者Pods的metrics失败

为各个节点创建和分发kube-apiserver启动文件

替换模板文件的变量,为各个节点生成启动文件
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for (( i=0; i < 3; i++ ))  #这里是三个节点所以为3,请根据实际情况修改,后边不在提示,同理
  do
    sed -e "s/##NODE_NAME##/${MASTER_NAMES[i]}/" -e "s/##NODE_IP##/${MASTER_IPS[i]}/" kube-apiserver.service.template > kube-apiserver-${MASTER_IPS[i]}.service 
  done
ls kube-apiserver*.service

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp kube-apiserver-${node_ip}.service root@${node_ip}:/etc/systemd/system/kube-apiserver.service
  done

source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "mkdir -p ${K8S_DIR}/kube-apiserver"
    ssh root@${node_ip} "systemctl daemon-reload && systemctl enable kube-apiserver && systemctl restart kube-apiserver"
  done
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "systemctl status kube-apiserver |grep 'Active:'"
  done
#如果开启不了,查看日志 journalctl -u kube-apiserver

#打印kube-apiserver写入etcd数据
source /opt/k8s/bin/environment.sh
ETCDCTL_API=3 etcdctl \
    --endpoints=${ETCD_ENDPOINTS} \
    --cacert=/opt/k8s/work/ca.pem \
    --cert=/opt/k8s/work/etcd.pem \
    --key=/opt/k8s/work/etcd-key.pem \
    get /registry/ --prefix --keys-only

#检查集群信息
netstat -lntup|grep kube

[root@k8s-01 work]# kubectl cluster-info
Kubernetes master is running at https://192.168.100.199:8443

To further debug and diagnose cluster problems, use 'kubectl cluster-info dump'.
[root@k8s-01 work]# kubectl get all --all-namespaces
NAMESPACE   NAME                 TYPE        CLUSTER-IP   EXTERNAL-IP   PORT(S)   AGE
default     service/kubernetes   ClusterIP   10.254.0.1   <none>        443/TCP   2m26s
[root@k8s-01 work]# kubectl get componentstatuses
NAME                 STATUS      MESSAGE                                                                                     ERROR
controller-manager   Unhealthy   Get http://127.0.0.1:10252/healthz: dial tcp 127.0.0.1:10252: connect: connection refused   
scheduler            Unhealthy   Get http://127.0.0.1:10251/healthz: dial tcp 127.0.0.1:10251: connect: connection refused   
etcd-2               Healthy     {"health":"true"}                                                                           
etcd-1               Healthy     {"health":"true"}                                                                           
etcd-0               Healthy     {"health":"true"}                                                                           

如果提示有报错,请检查~/.kube/config以及配置证书是否有问题

授权kube-apiserver访问kubelet API的权限

在执行kubectl命令时,apiserver会将请求转发到kubelet的https端口。这里定义的RBAC规则,授权apiserver使用的证书(kubernetes.pem)用户名(CN:kubernetes)访问kubelet API的权限


kubectl create clusterrolebinding kube-apiserver:kubelet-apis --clusterrole=system:kubelet-api-admin --user kubernetes

部署高可用kube-controller-manager集群

该集群包含三个节点,启动后通过竞争选举机制产生一个leader节点,其他节点为阻塞状态。当leader节点不可用时,阻塞节点将会在此选举产生新的leader,从而保证服务的高可用。为保证通信安全,这里采用x509证书和私钥,kube-controller-manager在与apiserver的安全端口(http 10252)通信使用;

创建kube-controller-manager证书和私钥

创建证书签名请求
cd /opt/k8s/work
cat > kube-controller-manager-csr.json <<EOF
{
    "CN": "system:kube-controller-manager",
    "key": {
        "algo": "rsa",
        "size": 2048
    },
    "hosts": [
      "127.0.0.1",
      "192.168.100.26",
      "192.168.100.27",
      "192.168.100.28"
    ],
    "names": [
      {
        "C": "CN",
        "ST": "BeiJing",
        "L": "BeiJing",
        "O": "system:kube-controller-manager",
        "OU": "4Paradigm"
      }
    ]
}
EOF
 
 
#这里的IP地址为master ip

host列表包含所有的kube-controller-manager节点IP(VIP不需要输入)
CN和O均为system:kube-controller-manager,kubernetes内置的ClusterRoleBindings system:kube-controller-manager赋予kube-controller-manager工作所需权限
生成证书和私钥

cd /opt/k8s/work
cfssl gencert -ca=/opt/k8s/work/ca.pem \
  -ca-key=/opt/k8s/work/ca-key.pem \
  -config=/opt/k8s/work/ca-config.json \
  -profile=kubernetes kube-controller-manager-csr.json | cfssljson -bare kube-controller-manager
ls kube-controller-manager*pem

将生成的证书和私钥分发到所有master节点
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp kube-controller-manager*.pem root@${node_ip}:/etc/kubernetes/cert/
  done

# 创建和分发kubeconfig文件
#kube-controller-manager使用kubeconfig文件访问apiserver
#该文件提供了apiserver地址、嵌入的CA证书和kube-controller-manager证书
 
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
kubectl config set-cluster kubernetes \
  --certificate-authority=/opt/k8s/work/ca.pem \
  --embed-certs=true \
  --server=${KUBE_APISERVER} \
  --kubeconfig=kube-controller-manager.kubeconfig
kubectl config set-credentials system:kube-controller-manager \
  --client-certificate=kube-controller-manager.pem \
  --client-key=kube-controller-manager-key.pem \
  --embed-certs=true \
  --kubeconfig=kube-controller-manager.kubeconfig
kubectl config set-context system:kube-controller-manager \
  --cluster=kubernetes \
  --user=system:kube-controller-manager \
  --kubeconfig=kube-controller-manager.kubeconfig
kubectl config use-context system:kube-controller-manager --kubeconfig=kube-controller-manager.kubeconfig

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp kube-controller-manager.kubeconfig root@${node_ip}:/etc/kubernetes/
  done


创建kube-controller-manager启动文件

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
cat > kube-controller-manager.service.template <<EOF
[Unit]
Description=Kubernetes Controller Manager
Documentation=https://github.com/GoogleCloudPlatform/kubernetes
[Service]
WorkingDirectory=${K8S_DIR}/kube-controller-manager
ExecStart=/opt/k8s/bin/kube-controller-manager \\
  --profiling \\
  --cluster-name=kubernetes \\
  --controllers=*,bootstrapsigner,tokencleaner \\
  --kube-api-qps=1000 \\
  --kube-api-burst=2000 \\
  --leader-elect \\
  --use-service-account-credentials\\
  --concurrent-service-syncs=2 \\
  --bind-address=0.0.0.0 \\
  #--secure-port=10252 \\
  --tls-cert-file=/etc/kubernetes/cert/kube-controller-manager.pem \\
  --tls-private-key-file=/etc/kubernetes/cert/kube-controller-manager-key.pem \\
  #--port=0 \\
  --authentication-kubeconfig=/etc/kubernetes/kube-controller-manager.kubeconfig \\
  --client-ca-file=/etc/kubernetes/cert/ca.pem \\
  --requestheader-allowed-names="" \\
  --requestheader-client-ca-file=/etc/kubernetes/cert/ca.pem \\
  --requestheader-extra-headers-prefix="X-Remote-Extra-" \\
  --requestheader-group-headers=X-Remote-Group \\
  --requestheader-username-headers=X-Remote-User \\
  --authorization-kubeconfig=/etc/kubernetes/kube-controller-manager.kubeconfig \\
  --cluster-signing-cert-file=/etc/kubernetes/cert/ca.pem \\
  --cluster-signing-key-file=/etc/kubernetes/cert/ca-key.pem \\
  --experimental-cluster-signing-duration=876000h \\
  --horizontal-pod-autoscaler-sync-period=10s \\
  --concurrent-deployment-syncs=10 \\
  --concurrent-gc-syncs=30 \\
  --node-cidr-mask-size=24 \\
  --service-cluster-ip-range=${SERVICE_CIDR} \\
  --pod-eviction-timeout=6m \\
  --terminated-pod-gc-threshold=10000 \\
  --root-ca-file=/etc/kubernetes/cert/ca.pem \\
  --service-account-private-key-file=/etc/kubernetes/cert/ca-key.pem \\
  --kubeconfig=/etc/kubernetes/kube-controller-manager.kubeconfig \\
  --logtostderr=true \\
  --v=2
Restart=on-failure
RestartSec=5
[Install]
WantedBy=multi-user.target
EOF

参数解释

--port=0:关闭监听非安全端口(http),同时 --address 参数无效,--bind-address 参数有效;
--secure-port=10252、--bind-address=0.0.0.0: 在所有网络接口监听 10252 端口的 https /metrics 请求;
--kubeconfig:指定 kubeconfig 文件路径,kube-controller-manager 使用它连接和验证 kube-apiserver;
--authentication-kubeconfig 和 --authorization-kubeconfig:kube-controller-manager 使用它连接 apiserver,对 client 的请求进行认证和授权。kube-controller-manager 不再使用 --tls-ca-file 对请求 https metrics 的 Client 证书进行校验。如果没有配置这两个 kubeconfig 参数,则 client 连接 kube-controller-manager https 端口的请求会被拒绝(提示权限不足)。
--cluster-signing-*-file:签名 TLS Bootstrap 创建的证书;
--experimental-cluster-signing-duration:指定 TLS Bootstrap 证书的有效期;
--root-ca-file:放置到容器 ServiceAccount 中的 CA 证书,用来对 kube-apiserver 的证书进行校验;
--service-account-private-key-file:签名 ServiceAccount 中 Token 的私钥文件,必须和 kube-apiserver 的 --service-account-key-file 指定的公钥文件配对使用;
--service-cluster-ip-range :指定 Service Cluster IP 网段,必须和 kube-apiserver 中的同名参数一致;
--leader-elect=true:集群运行模式,启用选举功能;被选为 leader 的节点负责处理工作,其它节点为阻塞状态;
--controllers=*,bootstrapsigner,tokencleaner:启用的控制器列表,tokencleaner 用于自动清理过期的 Bootstrap token;
--horizontal-pod-autoscaler-*:custom metrics 相关参数,支持 autoscaling/v2alpha1;
--tls-cert-file、--tls-private-key-file:使用 https 输出 metrics 时使用的 Server 证书和秘钥;
--use-service-account-credentials=true: kube-controller-manager 中各 controller 使用 serviceaccount 访问 kube-apiserver;


 cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for (( i=0; i < 3; i++ ))
  do
    sed -e "s/##NODE_NAME##/${MASTER_NAMES[i]}/" -e "s/##NODE_IP##/${MASTER_IPS[i]}/" kube-controller-manager.service.template > kube-controller-manager-${MASTER_IPS[i]}.service 
  done
ls kube-controller-manager*.service


cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp kube-controller-manager-${node_ip}.service root@${node_ip}:/etc/systemd/system/kube-controller-manager.service
  done

source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "mkdir -p ${K8S_DIR}/kube-controller-manager"
    ssh root@${node_ip} "systemctl daemon-reload && systemctl enable kube-controller-manager && systemctl restart kube-controller-manager"
  done
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "systemctl status kube-controller-manager|grep Active"
  done

#检查服务状态
[root@k8s-01 work]# netstat -lnpt | grep kube-cont
tcp6       0      0 :::10257                :::*                    LISTEN      9664/kube-controlle 
tcp6       0      0 :::10252                :::*                    LISTEN      9664/kube-controlle 

 

kube-controller-manager 创建权限

ClusteRole system:kube-controller-manager的权限太小,只能创建secret、serviceaccount等资源,将controller的权限分散到ClusterRole system:controller:xxx中

[root@k8s-01 work]# kubectl describe clusterrole system:kube-controller-manager
Name:         system:kube-controller-manager
Labels:       kubernetes.io/bootstrapping=rbac-defaults
Annotations:  rbac.authorization.kubernetes.io/autoupdate: true
PolicyRule:
  Resources                                  Non-Resource URLs  Resource Names  Verbs
  ---------                                  -----------------  --------------  -----
  secrets                                    []                 []              [create delete get update]
  endpoints                                  []                 []              [create get update]
  serviceaccounts                            []                 []              [create get update]
  events                                     []                 []              [create patch update]
  tokenreviews.authentication.k8s.io         []                 []              [create]
  subjectaccessreviews.authorization.k8s.io  []                 []              [create]
  configmaps                                 []                 []              [get]
  namespaces                                 []                 []              [get]
  *.*                                        []                 []              [list watch]
需要在 kube-controller-manager 的启动参数中添加 --use-service-account-credentials=true 参数,这样 main controller 会为各 controller 创建对应的 ServiceAccount XXX-controller。内置的 ClusterRoleBinding system:controller:XXX 将赋予各 XXX-controller ServiceAccount 对应的 ClusterRole system:controller:XXX 权限。
[root@k8s-01 work]# kubectl get clusterrole|grep controller
system:controller:attachdetach-controller                              12m
system:controller:certificate-controller                               12m
system:controller:clusterrole-aggregation-controller                   12m
system:controller:cronjob-controller                                   12m
system:controller:daemon-set-controller                                12m
system:controller:deployment-controller                                12m
system:controller:disruption-controller                                12m
system:controller:endpoint-controller                                  12m
system:controller:expand-controller                                    12m
system:controller:generic-garbage-collector                            12m
system:controller:horizontal-pod-autoscaler                            12m
system:controller:job-controller                                       12m
system:controller:namespace-controller                                 12m
system:controller:node-controller                                      12m
system:controller:persistent-volume-binder                             12m
system:controller:pod-garbage-collector                                12m
system:controller:pv-protection-controller                             12m
system:controller:pvc-protection-controller                            12m
system:controller:replicaset-controller                                12m
system:controller:replication-controller                               12m
system:controller:resourcequota-controller                             12m
system:controller:route-controller                                     12m
system:controller:service-account-controller                           12m
system:controller:service-controller                                   12m
system:controller:statefulset-controller                               12m
system:controller:ttl-controller                                       12m
system:kube-controller-manager                                         12m

#以 deployment controller 为例:
[root@k8s-01 work]# kubectl describe clusterrole system:controller:deployment-controller
Name:         system:controller:deployment-controller
Labels:       kubernetes.io/bootstrapping=rbac-defaults
Annotations:  rbac.authorization.kubernetes.io/autoupdate: true
PolicyRule:
  Resources                          Non-Resource URLs  Resource Names  Verbs
  ---------                          -----------------  --------------  -----
  replicasets.apps                   []                 []              [create delete get list patch update watch]
  replicasets.extensions             []                 []              [create delete get list patch update watch]
  events                             []                 []              [create patch update]
  pods                               []                 []              [get list update watch]
  deployments.apps                   []                 []              [get list update watch]
  deployments.extensions             []                 []              [get list update watch]
  deployments.apps/finalizers        []                 []              [update]
  deployments.apps/status            []                 []              [update]
  deployments.extensions/finalizers  []                 []              [update]
  deployments.extensions/status      []                 []              [update]
 #查看当前的 leader
[root@k8s-01 work]# kubectl get endpoints kube-controller-manager --namespace=kube-system  -o yaml
apiVersion: v1
kind: Endpoints
metadata:
  annotations:
    control-plane.alpha.kubernetes.io/leader: '{"holderIdentity":"k8s-01_ede3a742-4001-11ee-b717-4201c0a8641a","leaseDurationSeconds":15,"acquireTime":"2023-08-21T09:05:52Z","renewTime":"2023-08-21T09:09:23Z","leaderTransitions":0}'
  creationTimestamp: "2023-08-21T09:05:52Z"
  name: kube-controller-manager
  namespace: kube-system
  resourceVersion: "604"
  selfLink: /api/v1/namespaces/kube-system/endpoints/kube-controller-manager
  uid: ede66bf9-4001-11ee-b6ee-4201c0a8641a

部署高可用kube-scheduler

cd /opt/k8s/work
cat > kube-scheduler-csr.json <<EOF
{
    "CN": "system:kube-scheduler",
    "hosts": [
      "127.0.0.1",
      "192.168.100.26",
      "192.168.100.27",
      "192.168.100.28"
    ],
    "key": {
        "algo": "rsa",
        "size": 2048
    },
    "names": [
      {
        "C": "CN",
        "ST": "BeiJing",
        "L": "BeiJing",
        "O": "system:kube-scheduler",
        "OU": "4Paradigm"
      }
    ]
}
EOF
hosts 列表包含所有 kube-scheduler 节点 IP;
CN 和 O 均为 system:kube-scheduler,kubernetes 内置的 ClusterRoleBindings system:kube-scheduler 将赋予 kube-scheduler 工作所需的权限;
生成证书和私钥:

cd /opt/k8s/work
cfssl gencert -ca=/opt/k8s/work/ca.pem \
  -ca-key=/opt/k8s/work/ca-key.pem \
  -config=/opt/k8s/work/ca-config.json \
  -profile=kubernetes kube-scheduler-csr.json | cfssljson -bare kube-scheduler
ls kube-scheduler*pem

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp kube-scheduler*.pem root@${node_ip}:/etc/kubernetes/cert/
  done
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
kubectl config set-cluster kubernetes \
  --certificate-authority=/opt/k8s/work/ca.pem \
  --embed-certs=true \
  --server=${KUBE_APISERVER} \
  --kubeconfig=kube-scheduler.kubeconfig
kubectl config set-credentials system:kube-scheduler \
  --client-certificate=kube-scheduler.pem \
  --client-key=kube-scheduler-key.pem \
  --embed-certs=true \
  --kubeconfig=kube-scheduler.kubeconfig
kubectl config set-context system:kube-scheduler \
  --cluster=kubernetes \
  --user=system:kube-scheduler \
  --kubeconfig=kube-scheduler.kubeconfig
kubectl config use-context system:kube-scheduler --kubeconfig=kube-scheduler.kubeconfig
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp kube-scheduler.kubeconfig root@${node_ip}:/etc/kubernetes/
  done
 #创建 kube-scheduler 配置文件
 cd /opt/k8s/work
cat >kube-scheduler.yaml.template <<EOF
apiVersion: kubescheduler.config.k8s.io/v1alpha1
kind: KubeSchedulerConfiguration
bindTimeoutSeconds: 600
clientConnection:
  burst: 200
  kubeconfig: "/etc/kubernetes/kube-scheduler.kubeconfig"
  qps: 100
enableContentionProfiling: false
enableProfiling: true
hardPodAffinitySymmetricWeight: 1
healthzBindAddress: 127.0.0.1:10251
leaderElection:
  leaderElect: true
metricsBindAddress: ##NODE_IP##:10251
EOF

--kubeconfig:指定 kubeconfig 文件路径,kube-scheduler 使用它连接和验证 kube-apiserver;
--leader-elect=true:集群运行模式,启用选举功能;被选为 leader 的节点负责处理工作,其它节点为阻塞状态;
替换模板文件中的变量:


cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for (( i=0; i < 3; i++ ))
  do
    sed -e "s/##NODE_NAME##/${NODE_NAMES[i]}/" -e "s/##NODE_IP##/${NODE_IPS[i]}/" kube-scheduler.yaml.template > kube-scheduler-${NODE_IPS[i]}.yaml
  done
ls kube-scheduler*.yaml


cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp kube-scheduler-${node_ip}.yaml root@${node_ip}:/etc/kubernetes/kube-scheduler.yaml
  done


cd /opt/k8s/work
cat > kube-scheduler.service.template <<EOF
[Unit]
Description=Kubernetes Scheduler
Documentation=https://github.com/GoogleCloudPlatform/kubernetes
[Service]
WorkingDirectory=${K8S_DIR}/kube-scheduler
ExecStart=/opt/k8s/bin/kube-scheduler \\
  --config=/etc/kubernetes/kube-scheduler.yaml \\
  --bind-address=##NODE_IP## \\
  --secure-port=10259 \\
  --port=0 \\
  --tls-cert-file=/etc/kubernetes/cert/kube-scheduler.pem \\
  --tls-private-key-file=/etc/kubernetes/cert/kube-scheduler-key.pem \\
  --authentication-kubeconfig=/etc/kubernetes/kube-scheduler.kubeconfig \\
  --client-ca-file=/etc/kubernetes/cert/ca.pem \\
  --requestheader-allowed-names="" \\
  --requestheader-client-ca-file=/etc/kubernetes/cert/ca.pem \\
  --requestheader-extra-headers-prefix="X-Remote-Extra-" \\
  --requestheader-group-headers=X-Remote-Group \\
  --requestheader-username-headers=X-Remote-User \\
  --authorization-kubeconfig=/etc/kubernetes/kube-scheduler.kubeconfig \\
  --logtostderr=true \\
  --v=2
Restart=always
RestartSec=5
StartLimitInterval=0
[Install]
WantedBy=multi-user.target
EOF
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for (( i=0; i < 3; i++ ))
  do
    sed -e "s/##NODE_NAME##/${NODE_NAMES[i]}/" -e "s/##NODE_IP##/${NODE_IPS[i]}/" kube-scheduler.service.template > kube-scheduler-${NODE_IPS[i]}.service 
  done
ls kube-scheduler*.service
 
 
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    scp kube-scheduler-${node_ip}.service root@${node_ip}:/etc/systemd/system/kube-scheduler.service
  done

source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "mkdir -p ${K8S_DIR}/kube-scheduler"
    ssh root@${node_ip} "systemctl daemon-reload && systemctl enable kube-scheduler && systemctl restart kube-scheduler"
done
#检查服务运行状态
source /opt/k8s/bin/environment.sh
for node_ip in ${MASTER_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "systemctl status kube-scheduler|grep Active"
  done
查看输出的 metrics

注意:以下命令在 kube-scheduler 节点上执行。

kube-scheduler 监听 10251 和 10251 端口:

10251:接收 http 请求,非安全端口,不需要认证授权;

10259:接收 https 请求,安全端口,需要认证授权;

两个接口都对外提供 /metrics 和 /healthz 的访问。

[root@k8s-01 work]# curl -s http://192.168.100.26:10251/metrics|head
# HELP apiserver_audit_event_total Counter of audit events generated and sent to the audit backend.
# TYPE apiserver_audit_event_total counter
apiserver_audit_event_total 0
# HELP apiserver_audit_requests_rejected_total Counter of apiserver requests rejected due to an error in audit logging backend.
# TYPE apiserver_audit_requests_rejected_total counter
apiserver_audit_requests_rejected_total 0
# HELP apiserver_client_certificate_expiration_seconds Distribution of the remaining lifetime on the certificate used to authenticate a request.
# TYPE apiserver_client_certificate_expiration_seconds histogram
apiserver_client_certificate_expiration_seconds_bucket{le="0"} 0
apiserver_client_certificate_expiration_seconds_bucket{le="1800"} 0


#查看当前leader
kubectl get endpoints kube-scheduler --namespace=kube-system  -o yaml


work节点安装

kubernetes work节点运行如下组件: >docker、kubelet、kube-proxy、flanneld、kube-nginx

前面已经安装flanneld这就不在安装了
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "yum install -y epel-release"
    ssh root@${node_ip} "yum install -y conntrack ipvsadm ntp ntpdate ipset jq iptables curl sysstat libseccomp && modprobe ip_vs "
  done

部署Docker组件

yum install -y yum-utils device-mapper-persistent-data lvm2
yum-config-manager --add-repo http://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo
yum makecache fast
yum -y install docker-ce

mkdir -p /etc/docker/
cat > /etc/docker/daemon.json <<EOF
{
  "exec-opts": ["native.cgroupdriver=systemd"],
  "registry-mirrors": ["https://hjvrgh7a.mirror.aliyuncs.com"],
  "log-driver": "json-file",
  "log-opts": {
    "max-size": "100m"
  },
  "storage-driver": "overlay2"
}
EOF

另一个版本
 mkdir -p /etc/docker/
cat > /etc/docker/daemon.json <<EOF
{
  "exec-opts": ["native.cgroupdriver=systemd"],
  "registry-mirrors": [
    "https://hub-mirror.c.163.com",
    "https://mirror.baidubce.com"
  ],
  "log-driver": "json-file",
  "log-opts": {
    "max-size": "100m"
  },
  "storage-driver": "overlay2"
}
EOF
 
#这里配置当时镜像加速器,可以不进行配置,但是建议配置
要添加我们harbor仓库需要在添加下面一行
  "insecure-registries": ["harbor.xxx.com"],
默认docker hub需要https协议,使用上面配置不需要配置https

# 以下操作 每一台都要执行
>/usr/lib/systemd/system/docker.service
cat /usr/lib/systemd/system/docker.service
[Unit]
Description=Docker Application Container Engine
Documentation=https://docs.docker.com
BindsTo=containerd.service
After=network-online.target firewalld.service containerd.service
Wants=network-online.target
Requires=docker.socket
 
[Service]
Type=notify
# the default is not to use systemd for cgroups because the delegate issues still
# exists and systemd currently does not support the cgroup feature set required
# for containers run by docker
ExecStart=/usr/bin/dockerd  $DOCKER_NETWORK_OPTIONS -H fd:// --containerd=/run/containerd/containerd.sock
EnvironmentFile=-/run/flannel/docker
ExecReload=/bin/kill -s HUP $MAINPID
TimeoutSec=0
RestartSec=2
Restart=always
 
# Note that StartLimit* options were moved from "Service" to "Unit" in systemd 229.
# Both the old, and new location are accepted by systemd 229 and up, so using the old location
# to make them work for either version of systemd.
StartLimitBurst=3
 
# Note that StartLimitInterval was renamed to StartLimitIntervalSec in systemd 230.
# Both the old, and new name are accepted by systemd 230 and up, so using the old name to make
# this option work for either version of systemd.
StartLimitInterval=60s
 
# Having non-zero Limit*s causes performance problems due to accounting overhead
# in the kernel. We recommend using cgroups to do container-local accounting.
LimitNOFILE=infinity
LimitNPROC=infinity
LimitCORE=infinity
 
# Comment TasksMax if your systemd version does not support it.
# Only systemd 226 and above support this option.
TasksMax=infinity
 
# set delegate yes so that systemd does not reset the cgroups of docker containers
Delegate=yes
 
# kill only the docker process, not all processes in the cgroup
KillMode=process
 
[Install]
WantedBy=multi-user.target


source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "systemctl daemon-reload && systemctl enable docker && systemctl restart docker"
  done
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "systemctl status docker|grep Active"
  done

# 检查docker网桥
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "/usr/sbin/ip addr show flannel.1 && /usr/sbin/ip addr show docker0"
  done

部署kubelet组件

kubelet运行在每个worker节点上,接收kube-apiserver发送的请求,管理Pod容器,执行交互命令

kubelet启动时自动向kube-apiserver注册节点信息,内置的cAdivsor统计和监控节点的资源使用资源情况。为确保安全,部署时关闭了kubelet的非安全http端口,对请求进行认证和授权,拒绝未授权的访问

创建kubelet bootstrap kubeconfig文件
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_name in ${NODE_NAMES[@]}
  do
    echo ">>> ${node_name}"
    # 创建 token
    export BOOTSTRAP_TOKEN=$(kubeadm token create \
      --description kubelet-bootstrap-token \
      --groups system:bootstrappers:${node_name} \
      --kubeconfig ~/.kube/config)
    # 设置集群参数
    kubectl config set-cluster kubernetes \
      --certificate-authority=/etc/kubernetes/cert/ca.pem \
      --embed-certs=true \
      --server=${KUBE_APISERVER} \
      --kubeconfig=kubelet-bootstrap-${node_name}.kubeconfig
    # 设置客户端认证参数
    kubectl config set-credentials kubelet-bootstrap \
      --token=${BOOTSTRAP_TOKEN} \
      --kubeconfig=kubelet-bootstrap-${node_name}.kubeconfig
    # 设置上下文参数
    kubectl config set-context default \
      --cluster=kubernetes \
      --user=kubelet-bootstrap \
      --kubeconfig=kubelet-bootstrap-${node_name}.kubeconfig
    # 设置默认上下文
    kubectl config use-context default --kubeconfig=kubelet-bootstrap-${node_name}.kubeconfig
  done
向kubeconfig写入的是token,bootstrap结束后kube-controller-manager为kubelet创建client和server证书
查看kubeadm为各个节点创建的token

[root@k8s-01 work]# kubeadm token list --kubeconfig ~/.kube/config
TOKEN                     TTL       EXPIRES                     USAGES                   DESCRIPTION               EXTRA GROUPS
1r8xjv.oypmp64rmji9r4d1   23h       2023-08-22T17:28:35+08:00   authentication,signing   kubelet-bootstrap-token   system:bootstrappers:k8s-01
7a6n62.yzd0y8rb2vnufqlc   23h       2023-08-22T17:28:36+08:00   authentication,signing   kubelet-bootstrap-token   system:bootstrappers:k8s-04
fyw4n9.3wwgsgwgjyhxxw11   23h       2023-08-22T17:28:35+08:00   authentication,signing   kubelet-bootstrap-token   system:bootstrappers:k8s-02
i3cd24.fbvpytiu9rliclke   23h       2023-08-22T17:28:36+08:00   authentication,signing   kubelet-bootstrap-token   system:bootstrappers:k8s-03


token有效期为1天,超期后将不能被用来bootstrap kubelet,且会被kube-controller-manager的token cleaner清理
kube-apiserver接收kubelet的bootstrap token后,将请求的user设置为system:bootstrap; group设置为system:bootstrappers,后续将为这个group设置ClusterRoleBinding
#查看各token关联的Secret
[root@k8s-01 work]# kubectl get secrets  -n kube-system|grep bootstrap-token
bootstrap-token-1r8xjv                           bootstrap.kubernetes.io/token         7      73s
bootstrap-token-7a6n62                           bootstrap.kubernetes.io/token         7      72s
bootstrap-token-fyw4n9                           bootstrap.kubernetes.io/token         7      73s
bootstrap-token-i3cd24                           bootstrap.kubernetes.io/token         7      72s

#分发 bootstrap kubeconfig 文件到所有 worker 节点
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_name in ${NODE_NAMES[@]}
  do
    echo ">>> ${node_name}"
    scp kubelet-bootstrap-${node_name}.kubeconfig root@${node_name}:/etc/kubernetes/kubelet-bootstrap.kubeconfig
  done

#创建和分发kubelet
cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
cat > kubelet-config.yaml.template <<EOF
kind: KubeletConfiguration
apiVersion: kubelet.config.k8s.io/v1beta1
address: "##NODE_IP##"
staticPodPath: ""
syncFrequency: 1m
fileCheckFrequency: 20s
httpCheckFrequency: 20s
staticPodURL: ""
port: 10250
readOnlyPort: 0
rotateCertificates: true
serverTLSBootstrap: true
authentication:
  anonymous:
    enabled: false
  webhook:
    enabled: true
  x509:
    clientCAFile: "/etc/kubernetes/cert/ca.pem"
authorization:
  mode: Webhook
registryPullQPS: 0
registryBurst: 20
eventRecordQPS: 0
eventBurst: 20
enableDebuggingHandlers: true
enableContentionProfiling: true
healthzPort: 10248
healthzBindAddress: "##NODE_IP##"
clusterDomain: "${CLUSTER_DNS_DOMAIN}"
clusterDNS:
  - "${CLUSTER_DNS_SVC_IP}"
nodeStatusUpdateFrequency: 10s
nodeStatusReportFrequency: 1m
imageMinimumGCAge: 2m
imageGCHighThresholdPercent: 85
imageGCLowThresholdPercent: 80
volumeStatsAggPeriod: 1m
kubeletCgroups: ""
systemCgroups: ""
cgroupRoot: ""
cgroupsPerQOS: true
cgroupDriver: systemd
runtimeRequestTimeout: 10m
hairpinMode: promiscuous-bridge
maxPods: 220
podCIDR: "${CLUSTER_CIDR}"
podPidsLimit: -1
resolvConf: /etc/resolv.conf
maxOpenFiles: 1000000
kubeAPIQPS: 1000
kubeAPIBurst: 2000
serializeImagePulls: false
evictionHard:
  memory.available:  "100Mi"
nodefs.available:  "10%"
nodefs.inodesFree: "5%"
imagefs.available: "15%"
evictionSoft: {}
enableControllerAttachDetach: true
failSwapOn: true
containerLogMaxSize: 20Mi
containerLogMaxFiles: 10
systemReserved: {}
kubeReserved: {}
systemReservedCgroup: ""
kubeReservedCgroup: ""
enforceNodeAllocatable: ["pods"]
EOF




address:kubelet 安全端口(https,10250)监听的地址,不能为 127.0.0.1,否则 kube-apiserver、heapster 等不能调用 kubelet 的 API;
readOnlyPort=0:关闭只读端口(默认 10255),等效为未指定;
authentication.anonymous.enabled:设置为 false,不允许匿名访问 10250 端口;
authentication.x509.clientCAFile:指定签名客户端证书的 CA 证书,开启 HTTP 证书认证;
authentication.webhook.enabled=true:开启 HTTPs bearer token 认证;
对于未通过 x509 证书和 webhook 认证的请求(kube-apiserver 或其他客户端),将被拒绝,提示 Unauthorized;
authroization.mode=Webhook:kubelet 使用 SubjectAccessReview API 查询 kube-apiserver 某 user、group 是否具有操作资源的权限(RBAC);
featureGates.RotateKubeletClientCertificate、featureGates.RotateKubeletServerCertificate:自动 rotate 证书,证书的有效期取决于 kube-controller-manager 的 --experimental-cluster-signing-duration 参数;
需要 root 账户运行;
为各个节点创建和分发kubelet配置文件


cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do 
    echo ">>> ${node_ip}"
    sed -e "s/##NODE_IP##/${node_ip}/" kubelet-config.yaml.template > kubelet-config-${node_ip}.yaml.template
    scp kubelet-config-${node_ip}.yaml.template root@${node_ip}:/etc/kubernetes/kubelet-config.yaml
  done


cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
cat > kubelet.service.template <<EOF
[Unit]
Description=Kubernetes Kubelet
Documentation=https://github.com/GoogleCloudPlatform/kubernetes
After=docker.service
Requires=docker.service
[Service]
WorkingDirectory=${K8S_DIR}/kubelet
ExecStart=/opt/k8s/bin/kubelet \\
  --allow-privileged=true \\
  --bootstrap-kubeconfig=/etc/kubernetes/kubelet-bootstrap.kubeconfig \\
  --cert-dir=/etc/kubernetes/cert \\
  --cni-conf-dir=/etc/cni/net.d \\
  --container-runtime=docker \\
  --container-runtime-endpoint=unix:///var/run/dockershim.sock \\
  --root-dir=${K8S_DIR}/kubelet \\
  --kubeconfig=/etc/kubernetes/kubelet.kubeconfig \\
  --config=/etc/kubernetes/kubelet-config.yaml \\
  --hostname-override=##NODE_NAME## \\
  --pod-infra-container-image=registry.aliyuncs.com/google_containers/pause:3.2  \\
  --image-pull-progress-deadline=15m \\
  --volume-plugin-dir=${K8S_DIR}/kubelet/kubelet-plugins/volume/exec/ \\
  --logtostderr=true \\
  --v=2
Restart=always
RestartSec=5
StartLimitInterval=0
[Install]
WantedBy=multi-user.target
EOF

如果设置了 --hostname-override 选项,则 kube-proxy 也需要设置该选项,否则会出现找不到 Node 的情况;
--bootstrap-kubeconfig:指向 bootstrap kubeconfig 文件,kubelet 使用该文件中的用户名和 token 向 kube-apiserver 发送 TLS Bootstrapping 请求;
K8S approve kubelet 的 csr 请求后,在 --cert-dir 目录创建证书和私钥文件,然后写入 --kubeconfig 文件;
--pod-infra-container-image 不使用 redhat 的 pod-infrastructure:latest 镜像,它不能回收容器的僵尸;
分发启动文件


cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_name in ${NODE_NAMES[@]}
  do 
    echo ">>> ${node_name}"
    sed -e "s/##NODE_NAME##/${node_name}/" kubelet.service.template > kubelet-${node_name}.service
    scp kubelet-${node_name}.service root@${node_name}:/etc/systemd/system/kubelet.service
  done
 
 
Bootstrap Token Auth 和授予权限 kubelet 启动时查找 --kubeletconfig
参数对应的文件是否存在,如果不存在则使用 --bootstrap-kubeconfig 指定的 kubeconfig 文件向
kube-apiserver 发送证书签名请求 (CSR)。 kube-apiserver 收到 CSR 请求后,对其中的 Token
进行认证,认证通过后将请求的 user 设置为 system:bootstrap:,group 设置为
system:bootstrappers,这一过程称为 Bootstrap Token Auth。




创建user和group的CSR权限,不创建kubelet会启动失败
kubectl create clusterrolebinding kubelet-bootstrap --clusterrole=system:node-bootstrapper --group=system:bootstrappers

#启动kubelet
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "mkdir -p ${K8S_DIR}/kubelet/kubelet-plugins/volume/exec/"
    ssh root@${node_ip} "/usr/sbin/swapoff -a"
    ssh root@${node_ip} "systemctl daemon-reload && systemctl enable kubelet && systemctl restart kubelet"
  done

关闭 swap 分区,否则 kubelet 会启动失败;
kubelet 启动后使用 --bootstrap-kubeconfig 向 kube-apiserver 发送 CSR 请求,当这个

CSR 被 approve 后,kube-controller-manager 为 kubelet 创建 TLS 客户端证书、私钥和

--kubeletconfig 文件。 注意:kube-controller-manager 需要配置 --cluster-signing-cert-file 和 --cluster-signing-key-file 参数,才会为 TLS Bootstrap 创建证书和私钥。


[root@k8s-01 work]# kubectl get csr
NAME        AGE   REQUESTOR                 CONDITION
csr-4fhqr   25s   system:bootstrap:i3cd24   Pending
csr-85jzl   20s   system:bootstrap:fyw4n9   Pending
csr-9lwfj   9s    system:bootstrap:fyw4n9   Pending
csr-bzhvt   20s   system:bootstrap:i3cd24   Pending
csr-gw4w4   4s    system:bootstrap:fyw4n9   Pending
csr-j42zv   15s   system:bootstrap:fyw4n9   Pending
csr-jc7mx   5s    system:bootstrap:1r8xjv   Pending
csr-lns5s   3s    system:bootstrap:i3cd24   Pending
csr-pjczh   14s   system:bootstrap:i3cd24   Pending
csr-qztj9   27s   system:bootstrap:1r8xjv   Pending
csr-s9c2x   16s   system:bootstrap:1r8xjv   Pending
csr-th5pc   9s    system:bootstrap:i3cd24   Pending
csr-vvsdv   10s   system:bootstrap:1r8xjv   Pending
csr-wgj7x   26s   system:bootstrap:fyw4n9   Pending
csr-xd8gb   21s   system:bootstrap:1r8xjv   Pending

这里节点均处于pending(等待)状态

自动approve CSR请求

创建三个ClusterRoleBinding,分别用于自动approve client、renew client、renew server证

cd /opt/k8s/work
cat > csr-crb.yaml <<EOF
 # Approve all CSRs for the group "system:bootstrappers"
 kind: ClusterRoleBinding
 apiVersion: rbac.authorization.k8s.io/v1
 metadata:
   name: auto-approve-csrs-for-group
 subjects:
 - kind: Group
   name: system:bootstrappers
   apiGroup: rbac.authorization.k8s.io
 roleRef:
   kind: ClusterRole
   name: system:certificates.k8s.io:certificatesigningrequests:nodeclient
   apiGroup: rbac.authorization.k8s.io
---
 # To let a node of the group "system:nodes" renew its own credentials
 kind: ClusterRoleBinding
 apiVersion: rbac.authorization.k8s.io/v1
 metadata:
   name: node-client-cert-renewal
 subjects:
 - kind: Group
   name: system:nodes
   apiGroup: rbac.authorization.k8s.io
 roleRef:
   kind: ClusterRole
   name: system:certificates.k8s.io:certificatesigningrequests:selfnodeclient
   apiGroup: rbac.authorization.k8s.io
---
# A ClusterRole which instructs the CSR approver to approve a node requesting a
# serving cert matching its client cert.
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: approve-node-server-renewal-csr
rules:
- apiGroups: ["certificates.k8s.io"]
  resources: ["certificatesigningrequests/selfnodeserver"]
  verbs: ["create"]
---
 # To let a node of the group "system:nodes" renew its own server credentials
 kind: ClusterRoleBinding
 apiVersion: rbac.authorization.k8s.io/v1
 metadata:
   name: node-server-cert-renewal
 subjects:
 - kind: Group
   name: system:nodes
   apiGroup: rbac.authorization.k8s.io
 roleRef:
   kind: ClusterRole
   name: approve-node-server-renewal-csr
   apiGroup: rbac.authorization.k8s.io
EOF
kubectl apply -f csr-crb.yaml



auto-approve-csrs-for-group 自动approve node的第一次CSR,注意第一次CSR时,请求的Group为system:bootstrappers
node-client-cert-renewal 自动approve node后续过期的client证书,自动生成的证书Group为system:nodes
node-server-cert-renewal 自动approve node后续过期的server证书,自动生成的证书Group

查看kubelet

等待1-10分钟,3个节点的CSR都会自动approved

Pending的CSR用于创建kubelet serve证书,需要手动approve (后面步骤)

目前所有节点均为ready状态

NAME     STATUS   ROLES    AGE     VERSION
k8s-01   Ready       2m29s   v1.14.2
k8s-02   Ready       2m28s   v1.14.2
k8s-03   Ready       2m28s   v1.14.2
k8s-04   Ready       2m27s   v1.14.2

kube-controller-manager为各node生成了kubeconfig文件和公钥
[root@k8s-01 work]# ls -l /etc/kubernetes/kubelet.kubeconfig
-rw------- 1 root root 2316 Aug 21 17:34 /etc/kubernetes/kubelet.kubeconfig
[root@k8s-01 work]# ls -l /etc/kubernetes/cert/|grep kubelet
-rw------- 1 root root 1273 Aug 21 17:34 kubelet-client-2023-08-21-17-34-58.pem
lrwxrwxrwx 1 root root   59 Aug 21 17:34 kubelet-client-current.pem -> /etc/kubernetes/cert/kubelet-client-2023-08-21-17-34-58.pem


手动approve server cert csr

基于安全考虑,CSR approving controllers不会自动approve kubelet server证书签名请求,需要手动approve
kubectl get csr | grep Pending | awk '{print $1}' | xargs kubectl certificate approve

kubelet API接口

kubelet启动后监听多个端口,用于接受kube-apiserver或其他客户端发送的请求

[root@k8s-02 work]# netstat -lntup|grep kubelet
tcp        0      0 127.0.0.1:40605         0.0.0.0:*               LISTEN      27600/kubelet       
tcp        0      0 192.168.100.27:10248    0.0.0.0:*               LISTEN      27600/kubelet       
tcp        0      0 192.168.100.27:10250    0.0.0.0:*               LISTEN      27600/kubelet  

10248: healthz http 服务;
10250: https 服务,访问该端口时需要认证和授权(即使访问 /healthz 也需要);
未开启只读端口 10255;
从 K8S v1.10 开始,去除了 --cadvisor-port 参数(默认 4194 端口),不支持访问 cAdvisor UI & API
bear token认证和授权

创建一个ServiceAccount,将它和ClusterRole system:kubelet-api-admin绑定,从而具有调用kubelet API的权限

kubectl create sa kubelet-api-test
kubectl create clusterrolebinding kubelet-api-test --clusterrole=system:kubelet-api-admin --serviceaccount=default:kubelet-api-test
SECRET=$(kubectl get secrets | grep kubelet-api-test | awk '{print $1}')
TOKEN=$(kubectl describe secret ${SECRET} | grep -E '^token' | awk '{print $2}')
echo ${TOKEN}


[root@k8s-01 work]# kubectl create clusterrolebinding kubelet-api-test --clusterrole=system:kubelet-api-admin --serviceaccount=default:kubelet-api-test
clusterrolebinding.rbac.authorization.k8s.io/kubelet-api-test created
[root@k8s-01 work]# SECRET=$(kubectl get secrets | grep kubelet-api-test | awk '{print $1}')
[root@k8s-01 work]# TOKEN=$(kubectl describe secret ${SECRET} | grep -E '^token' | awk '{print $2}')
[root@k8s-01 work]# echo ${TOKEN}
eyJhbGciOiJSUzI1NiIsImtpZCI6IiJ9.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.nvB9YjjVclFqrMMmAVF2dMD5hHJ6UzW6ujNO-i1ijFTEoG1cD1FQTAmdYS-hdbY_1heB5O3sFNRO6hF-E-s_yKF3aEcaxtiyJX95WE2Wt52VxA4750WV9Gqyz5HxGpsluEwlkz7eLh8jPwQHJqAE__sO1zo4-68hVGjbuEm8vFh5Bz1iQUfWFPK6RXaIzqcnkMe3T4SlZrtzHvd5ttmA2s4fsIZTvM6T157NUem7POF0MwWMIhtO1F49bMTxf2fe90dGSqZFx0gtWKoe671sbAcf6emcRkWz93GCumBrxZw5bLsm3dX_NWFj8kkVAB9WG-RGGGyK7iRg-oizXrumiA



部署kube-proxy组件

kube-proxy运行在所有worker节点上,它监听apiserver中service和endpoint的变化情况,创建路由规则提供服务IP和负载均衡功能。这里使用ipvs模式的kube-proxy进行部署

在各个节点需要安装ipvsadm和ipset命令,加载ip_vs内核模块

cd /opt/k8s/work
cat > kube-proxy-csr.json <<EOF
{
  "CN": "system:kube-proxy",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "BeiJing",
      "L": "BeiJing",
      "O": "k8s",
      "OU": "4Paradigm"
    }
  ]
}
EOF


CN:指定该证书的 User 为 system:kube-proxy;
预定义的 RoleBinding system:node-proxier 将User system:kube-proxy 与 Role system:node-proxier 绑定,该 Role 授予了调用 kube-apiserver Proxy 相关 API 的权限;
该证书只会被 kube-proxy 当做 client 证书使用,所以 hosts 字段为空;
生成证书和私钥:

cd /opt/k8s/work
cfssl gencert -ca=/opt/k8s/work/ca.pem \
  -ca-key=/opt/k8s/work/ca-key.pem \
  -config=/opt/k8s/work/ca-config.json \
  -profile=kubernetes  kube-proxy-csr.json | cfssljson -bare kube-proxy
ls kube-proxy*


cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
kubectl config set-cluster kubernetes \
  --certificate-authority=/opt/k8s/work/ca.pem \
  --embed-certs=true \
  --server=${KUBE_APISERVER} \
  --kubeconfig=kube-proxy.kubeconfig
kubectl config set-credentials kube-proxy \
  --client-certificate=kube-proxy.pem \
  --client-key=kube-proxy-key.pem \
  --embed-certs=true \
  --kubeconfig=kube-proxy.kubeconfig
kubectl config set-context default \
  --cluster=kubernetes \
  --user=kube-proxy \
  --kubeconfig=kube-proxy.kubeconfig
kubectl config use-context default --kubeconfig=kube-proxy.kubeconfig


--embed-certs=true:将 ca.pem 和 admin.pem 证书内容嵌入到生成的kubectl-proxy.kubeconfig文件中(不加时,写入的是证书文件路径);
分发 kubeconfig 文件:


cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_name in ${NODE_NAMES[@]}
  do
    echo ">>> ${node_name}"
    scp kube-proxy.kubeconfig root@${node_name}:/etc/kubernetes/
  done


创建kube-proxy配置文件

从v1.10开始,kube-proxy部分参数可以配置在文件中,可以使用--write-config-to选项生成该配置文件

cd /opt/k8s/work
cat > kube-proxy-config.yaml.template <<EOF
kind: KubeProxyConfiguration
apiVersion: kubeproxy.config.k8s.io/v1alpha1
clientConnection:
  burst: 200
  kubeconfig: "/etc/kubernetes/kube-proxy.kubeconfig"
  qps: 100
bindAddress: ##NODE_IP##
healthzBindAddress: ##NODE_IP##:10256
metricsBindAddress: ##NODE_IP##:10249
enableProfiling: true
clusterCIDR: ${CLUSTER_CIDR}
hostnameOverride: ##NODE_NAME##
mode: "ipvs"
portRange: ""
kubeProxyIPTablesConfiguration:
  masqueradeAll: false
kubeProxyIPVSConfiguration:
  scheduler: rr
  excludeCIDRs: []
EOF


bindAddress: 监听地址;
clientConnection.kubeconfig: 连接 apiserver 的 kubeconfig 文件;
-clusterCIDR: kube-proxy 根据 --cluster-cidr判断集群内部和外部流量,指定 --cluster-cidr 或 --masquerade-all 选项后 kube-proxy 才会对访问 Service IP 的请求做 SNAT;
hostnameOverride: 参数值必须与 kubelet 的值一致,否则 kube-proxy 启动后会找不到该 Node,从而不会创建任何 ipvs 规则;
mode: 使用 ipvs 模式;
分发和创建kube-proxy配置文件

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for (( i=0; i < 4; i++ ))
  do 
    echo ">>> ${NODE_NAMES[i]}"
    sed -e "s/##NODE_NAME##/${NODE_NAMES[i]}/" -e "s/##NODE_IP##/${NODE_IPS[i]}/" kube-proxy-config.yaml.template > kube-proxy-config-${NODE_NAMES[i]}.yaml.template
    scp kube-proxy-config-${NODE_NAMES[i]}.yaml.template root@${NODE_NAMES[i]}:/etc/kubernetes/kube-proxy-config.yaml
  done
 
 #我这里一共有4个节点要运行,所以这里写4,这是整个集群的node节点的数量! 这里一定要注意修改!!

#创建和分发 kube-proxy systemd unit 文件

cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
cat > kube-proxy.service <<EOF
[Unit]
Description=Kubernetes Kube-Proxy Server
Documentation=https://github.com/GoogleCloudPlatform/kubernetes
After=network.target
[Service]
WorkingDirectory=${K8S_DIR}/kube-proxy
ExecStart=/opt/k8s/bin/kube-proxy \\
  --config=/etc/kubernetes/kube-proxy-config.yaml \\
  --logtostderr=true \\
  --v=2
Restart=on-failure
RestartSec=5
LimitNOFILE=65536
[Install]
WantedBy=multi-user.target
EOF



cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_name in ${NODE_NAMES[@]}
  do 
    echo ">>> ${node_name}"
    scp kube-proxy.service root@${node_name}:/etc/systemd/system/
  done

启动 kube-proxy 服务


cd /opt/k8s/work
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "mkdir -p ${K8S_DIR}/kube-proxy"
    ssh root@${node_ip} "modprobe ip_vs_rr"
    ssh root@${node_ip} "systemctl daemon-reload && systemctl enable kube-proxy && systemctl restart kube-proxy"
  done


source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "systemctl status kube-proxy|grep Active"
  done

 
[root@k8s-01 work]# netstat -lnpt|grep kube-prox
tcp        0      0 192.168.100.26:10249    0.0.0.0:*               LISTEN      32089/kube-proxy    
tcp        0      0 192.168.100.26:10256    0.0.0.0:*               LISTEN      32089/kube-proxy 



source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh root@${node_ip} "/usr/sbin/ipvsadm -ln"
  done

[root@k8s-01 work]# for node_ip in ${NODE_IPS[@]}
>   do
>     echo ">>> ${node_ip}"
>     ssh root@${node_ip} "/usr/sbin/ipvsadm -ln"
>   done
>>> 192.168.100.26
IP Virtual Server version 1.2.1 (size=4096)
Prot LocalAddress:Port Scheduler Flags
  -> RemoteAddress:Port           Forward Weight ActiveConn InActConn
TCP  10.254.0.1:443 rr
  -> 192.168.100.26:6443          Masq    1      0          0         
  -> 192.168.100.27:6443          Masq    1      0          0         
  -> 192.168.100.28:6443          Masq    1      0          0         
>>> 192.168.100.27
IP Virtual Server version 1.2.1 (size=4096)
Prot LocalAddress:Port Scheduler Flags
  -> RemoteAddress:Port           Forward Weight ActiveConn InActConn
TCP  10.254.0.1:443 rr
  -> 192.168.100.26:6443          Masq    1      0          0         
  -> 192.168.100.27:6443          Masq    1      0          0         
  -> 192.168.100.28:6443          Masq    1      0          0         
>>> 192.168.100.28
IP Virtual Server version 1.2.1 (size=4096)
Prot LocalAddress:Port Scheduler Flags
  -> RemoteAddress:Port           Forward Weight ActiveConn InActConn
TCP  10.254.0.1:443 rr
  -> 192.168.100.26:6443          Masq    1      0          0         
  -> 192.168.100.27:6443          Masq    1      0          0         
  -> 192.168.100.28:6443          Masq    1      0          0         
>>> 192.168.100.29
IP Virtual Server version 1.2.1 (size=4096)
Prot LocalAddress:Port Scheduler Flags
  -> RemoteAddress:Port           Forward Weight ActiveConn InActConn

可见所有通过 https 访问 K8S SVC kubernetes 的请求都转发到 kube-apiserver 节点的 6443 端口;



验证集群功能

cd /opt/k8s/work
cat > nginx-ds.yml <<EOF
apiVersion: v1
kind: Service
metadata:
  name: nginx-ds
  labels:
    app: nginx-ds
spec:
  type: NodePort
  selector:
    app: nginx-ds
  ports:
  - name: http
    port: 80
    targetPort: 80
---
apiVersion: extensions/v1beta1
kind: DaemonSet
metadata:
  name: nginx-ds
  labels:
    addonmanager.kubernetes.io/mode: Reconcile
spec:
  template:
    metadata:
      labels:
        app: nginx-ds
    spec:
      containers:
      - name: my-nginx
        image: nginx
        ports:
        - containerPort: 80
EOF

kubectl create -f nginx-ds.yml

# kubectl get pod  -o wide
NAME             READY   STATUS    RESTARTS   AGE    IP            NODE     NOMINATED NODE   READINESS GATES
nginx-ds-29n8p   1/1     Running   0          116s   172.17.0.2    k8s-02              

source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh ${node_ip} "ping -c 1 172.17.0.2"
    ssh ${node_ip} "ping -c 1 172.30.96.2"
    ssh ${node_ip} "ping -c 1 172.17.0.2"
  done

#检查服务IP和端口可达性
kubectl get svc |grep nginx-ds
source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo ">>> ${node_ip}"
    ssh ${node_ip} "curl -s 10.254.248.73"
  done
 


CoreDNS安装

source /opt/k8s/bin/environment.sh
for node_ip in ${NODE_IPS[@]}
  do
    echo "$node_ip"
    ssh $node_ip "wget -P /opt/ http://down.i4t.com/coredns_v1.4.tar"
    ssh $node_ip "docker load -i /opt/coredns_v1.4.tar"
  done
 
wget -P /opt/ http://down.i4t.com/k8s1.14/coredns.yaml

kubectl create -f /opt/coredns.yaml
 kubectl get pod -n kube-system  -l k8s-app=kube-dns


参考文章

https://i4t.com/4253.html