Kubernetes 1.24 二进制高可用集群安装

生产环境中，建议使用版本大于5的Kubernetes版本，如1.24.6
系统：CentOS 7.5
K8S：1.24.6
containerd: v1.6.4
calico: 1.24

集群环境

hostname	IP/VIP	software
k8s-master01	192.168.1.171	etcd、apiserver、scheduler、controller-manager、kube-proxy、kubelet
k8s-master02	192.168.1.172	etcd、apiserver、scheduler、controller-manager、kube-proxy、kubelet
k8s-master03	192.168.1.173	etcd、apiserver、scheduler、controller-manager、kube-proxy、kubelet
k8s-node01	192.168.1.174	kube-proxy、kubelet
k8s-node02	192.168.1.175	kube-proxy、kubelet
haproxy01	192.168.1.161	haproxy、keepalived
haproxy02	192.168.1.162	haproxy、keepalived
VIP	192.168.1.111	IPVS

基本环境配置

修改hosts
所有机器添加hosts解析

cat >> /etc/hosts <<EOF
192.168.1.111 apiserver.sundayhk.com
192.168.1.171 k8s-master01
192.168.1.172 k8s-master02
192.168.1.173 k8s-master03
192.168.1.174 k8s-node01
192.168.1.175 k8s-node02
192.168.1.161 haproxy01
192.168.1.162 haproxy02
EOF

修改主机名
所有机器设置主机名

hostnamectl set-hostname k8s-master01
bash # 生效

name=(k8s-master01 k8s-master02 k8s-master03 k8s-node01 k8s-node02)
for i in ${name[@]};do ssh root@$i  hostnamectl set-hostname $i;done

关闭防火墙 selinux swap
所有节点

# CentOS7需要关闭NetworkManager，CentOS8不需要
systemctl disable --now firewalld  NetworkManager dnsmasq
iptables -F && iptables -X && iptables -F -t nat && iptables -X -t nat
iptables -P FORWARD ACCEPT
setenforce 0
sed -i 's/^SELINUX=.*/SELINUX=disabled/' /etc/selinux/config
swapoff -a
sed -i '/ swap / s/^\(.*\)$/#\1/g' /etc/fstab
#如果开启了swap分区，kubelet会启动失败(可以通过设置参数--fail-swap-on设置为false) 不建议

阿里云repo源
所有节点

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

安装基本工具

yum install wget curl ntpdate jq psmisc vim net-tools yum-utils device-mapper-persistent-data lvm2 git -y

时间同步
所有haproxy

ntpdate

timedatectl set-timezone Asia/Shanghai
timedatectl set-local-rtc 0
ntpdate ntp.aliyun.com
echo "*/30 * * * * ntpdate ntp.aliyun.com >/dev/null 2>&1" >> /var/spool/cron/root
systemctl restart crond

chronyd

yum install chrony -y
cat > /etc/chrony.conf << EOF 
pool ntp.aliyun.com iburst
driftfile /var/lib/chrony/drift
makestep 1.0 3
rtcsync
allow 192.168.1.0/24
local stratum 10
keyfile /etc/chrony.keys
leapsectz right/UTC
logdir /var/log/chrony
EOF
systemctl enable chronyd --now

所有master和node节点(除haproxy)

yum install chrony -y
cat > /etc/chrony.conf << EOF 
pool 192.168.1.111 iburst
driftfile /var/lib/chrony/drift
makestep 1.0 3
rtcsync
keyfile /etc/chrony.keys
leapsectz right/UTC
logdir /var/log/chrony
EOF
systemctl enable chronyd --now

# 使用客户端进行验证
chronyc sources -v

配置limits
所有节点

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

echo "ulimit -SHn 65535" >> /etc/profile
source /etc/profile

设置免密
Master01配置免密码登录其他节点

yum install -y sshpass
ssh-keygen -f /root/.ssh/id_rsa -P ''
export IP="k8s-master01 k8s-master02 k8s-master03 k8s-node01 k8s-node02"
export SSHPASS=sunday  # 密码
for HOST in $IP;do
     sshpass -e ssh-copy-id -o StrictHostKeyChecking=no $HOST
done

内核参数

k8s集群中必须的内核参数，所有节点配置k8s内核

cat <<EOF > /etc/sysctl.d/k8s.conf
net.ipv4.ip_forward = 1
net.bridge.bridge-nf-call-iptables = 1
net.bridge.bridge-nf-call-ip6tables = 1
fs.may_detach_mounts = 1
vm.overcommit_memory=1
vm.panic_on_oom=0
fs.inotify.max_user_watches=89100
fs.file-max=52706963
fs.nr_open=52706963
net.netfilter.nf_conntrack_max=2310720

net.ipv4.tcp_keepalive_time = 600
net.ipv4.tcp_keepalive_probes = 3
net.ipv4.tcp_keepalive_intvl =15
net.ipv4.tcp_max_tw_buckets = 36000
net.ipv4.tcp_tw_reuse = 1
net.ipv4.tcp_max_orphans = 327680
net.ipv4.tcp_orphan_retries = 3
net.ipv4.tcp_syncookies = 1
net.ipv4.tcp_max_syn_backlog = 16384
net.ipv4.ip_conntrack_max = 65536
net.ipv4.tcp_max_syn_backlog = 16384
net.ipv4.tcp_timestamps = 0
net.core.somaxconn = 16384
EOF
sysctl --system

升级内核

Docker overlay2需要使用kernel 4.x版本，所以我们需要升级内核 CentOS 7.x 系统自带的 3.10.x 内核存在一些 Bugs，导致运行的 Docker、Kubernetes 不稳定

rpm --import https://www.elrepo.org/RPM-GPG-KEY-elrepo.org
rpm -Uvh http://www.elrepo.org/elrepo-release-7.0-3.el7.elrepo.noarch.rpm
#默认安装为最新内核
yum --enablerepo=elrepo-kernel install kernel-ml
#修改内核顺序
grub2-set-default  0 && grub2-mkconfig -o /etc/grub2.cfg
#使用下面命令看看确认下是否启动默认内核指向上面安装的内核
grubby --default-kernel
#这里的输出结果应该为我们升级后的内核信息
reboot
#可以等所有初始化步骤结束进行reboot操作

基础组件

主要安装的是集群中用到的各种组件，比如IPVS、Docker-ce、Kubernetes各组件等

安装IPVS

所有节点安装ipvsadm

yum install -y ipvsadm ipset sysstat conntrack libseccomp

所有节点配置ipvs模块，在内核4.19+版本nf_conntrack_ipv4已经改为nf_conntrack， 4.18以下使用nf_conntrack_ipv4即可

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 enable --now systemd-modules-load.service

检查是否加载

lsmod | grep -E "ip_vs | nf_conntrack"

安装Containerd

使用Containerd作为Runtime(推荐)

配置containerd及cni插件

wget https://github.com/containerd/containerd/releases/download/v1.6.4/cri-containerd-cni-1.6.4-linux-amd64.tar.gz

mkdir -p /etc/cni/net.d /opt/cni/bin 
tar -C / -xvzf cri-containerd-cni-1.6.4-linux-amd64.tar.gz

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

配置Containerd所需的内核

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

mkdir /etc/containerd -p
containerd config default > /etc/containerd/config.toml
sed -i 's/k8s.gcr.io/registry.aliyuncs.com\/google_containers/' /etc/containerd/config.toml
sed -i 's/SystemdCgroup \= false/SystemdCgroup \= true/' /etc/containerd/config.toml
sed -i 's/snapshotter = "overlayfs"/snapshotter = "native"/' /etc/containerd/config.toml

Containerd service

cat > /etc/systemd/system/containerd.service <<EOF
[Unit]
Description=containerd container runtime
Documentation=https://containerd.io
After=network.target local-fs.target

[Service]
ExecStartPre=-/sbin/modprobe overlay
ExecStart=/usr/local/bin/containerd
Type=notify
Delegate=yes
KillMode=process
Restart=always
RestartSec=5
LimitNPROC=infinity
LimitCORE=infinity
LimitNOFILE=infinity
TasksMax=infinity
OOMScoreAdjust=-999

[Install]
WantedBy=multi-user.target
EOF

systemctl daemon-reload
systemctl enable --now containerd
systemctl status containerd

分发二进制包

https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md

下载etcd、kubernetes二进制包

wget https://github.com/etcd-io/etcd/releases/download/v3.5.4/etcd-v3.5.4-linux-amd64.tar.gz
wget https://storage.googleapis.com/kubernetes-release/release/v1.24.6/kubernetes-server-linux-amd64.tar.gz

解压安装到/usr/local/bin/目录

tar -xf etcd-v3.5.4-linux-amd64.tar.gz --strip-components=1 -C /usr/local/bin etcd-v3.5.4-linux-amd64/etcd{,ctl}
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}

分发组件

Masters='k8s-master02 k8s-master03'
Nodes='k8s-node01 k8s-node02'
for i in $Masters; do 
  echo $i; 
  scp /usr/local/bin/kube{let,ctl,-apiserver,-controller-manager,-scheduler,-proxy} $i:/usr/local/bin/; 
  scp /usr/local/bin/etcd* $NODE:/usr/local/bin/; 
done
for i in $Nodes; do scp /usr/local/bin/kube{let,-proxy} $i:/usr/local/bin/; done

所有节点创建/opt/cni/bin目录

mkdir -p /opt/cni/bin

检查版本及是否正常

ls -l /usr/local/bin
kubelet --version
etcdctl version

cfssl工具

wget "https://pkg.cfssl.org/R1.2/cfssl_linux-amd64" -O /usr/local/bin/cfssl
wget "https://pkg.cfssl.org/R1.2/cfssljson_linux-amd64" -O /usr/local/bin/cfssljson
wget https://pkg.cfssl.org/R1.2/cfssl-certinfo_linux-amd64 -O /usr/local/bin/cfssl-certinfo
chmod +x /usr/local/bin/bin/cfssl*

生成证书

所有Master节点创建etcd证书目录

mkdir /etc/etcd/ssl -p

master01节点创建kubernetes相关目录

mkdir -p /etc/kubernetes/pki
mkdir /opt/pki

ca证书

只需创建一个CA证书，后续创建的所有证书(kubernetes+etcd)都是由它签名

cd /opt/pki

cat > ca-config.json << EOF 
{
  "signing": {
    "default": {
      "expiry": "876000h"
    },
    "profiles": {
      "kubernetes": {
        "usages": [
            "signing",
            "key encipherment",
            "server auth",
            "client auth"
        ],
        "expiry": "876000h"
      }
    }
  }
}
EOF

cat > ca-csr.json  << EOF 
{
  "CN": "kubernetes",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Beijing",
      "L": "Beijing",
      "O": "Kubernetes",
      "OU": "Kubernetes-manual"
    }
  ],
  "ca": {
    "expiry": "876000h"
  }
}
EOF

cfssl gencert -initca ca-csr.json | cfssljson -bare /etc/kubernetes/pki/ca

etcd证书

Master01节点生成etcd证书
生成证书的CSR文件：证书签名请求文件，配置了一些域名、公司、单位

cat > etcd-ca-csr.json  << EOF 
{
  "CN": "etcd",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Beijing",
      "L": "Beijing",
      "O": "etcd",
      "OU": "Etcd Security"
    }
  ],
  "ca": {
    "expiry": "876000h"
  }
}
EOF

cat > etcd-csr.json << EOF 
{
  "CN": "etcd",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Beijing",
      "L": "Beijing",
      "O": "etcd",
      "OU": "Etcd Security"
    }
  ]
}
EOF

cd /opt/pki
# 生成etcd证书和key
cfssl gencert -initca etcd-ca-csr.json | cfssljson -bare /etc/etcd/ssl/etcd-ca

cfssl gencert \
   -ca=/etc/etcd/ssl/etcd-ca.pem \
   -ca-key=/etc/etcd/ssl/etcd-ca-key.pem \
   -config=ca-config.json \
   -hostname=k8s-master01,k8s-master02,k8s-master03,192.168.1.171,192.168.1.172,192.168.1.173 \
   -profile=kubernetes etcd-csr.json | cfssljson -bare /etc/etcd/ssl/etcd

同步证书到其他master节点

for i in k8s-master02 k8s-master03;do
    ssh $i "mkdir -p /etc/etcd/ssl"
    scp /etc/etcd/ssl/*.pem $i:/etc/etcd/ssl/
done

apiserver证书

cat > apiserver-csr.json << EOF 
{
  "CN": "kube-apiserver",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Beijing",
      "L": "Beijing",
      "O": "Kubernetes",
      "OU": "Kubernetes-manual"
    }
  ]
}
EOF

# 生成一个根证书 ，多写了一些IP作为预留IP，为将来添加node做准备
# 10.96.0.1是service网段的第一个地址，需要计算，192.168.1.111为高可用vip地址

cfssl gencert \
-ca=/etc/kubernetes/pki/ca.pem \
-ca-key=/etc/kubernetes/pki/ca-key.pem \
-config=ca-config.json \
-hostname=10.96.0.1,127.0.0.1,kubernetes,kubernetes.default,kubernetes.default.svc,kubernetes.default.svc.cluster,kubernetes.default.svc.cluster.local,apiserver.sundayhk.com,k8s-master01,k8s-master02,k8s-master03,k8s-node01,k8s-node02,192.168.1.111,192.168.1.171,192.168.1.172,192.168.1.173,192.168.1.174,192.168.1.175  \
-profile=kubernetes   apiserver-csr.json | cfssljson -bare /etc/kubernetes/pki/apiserver

apiserver聚合证书

cat > front-proxy-ca-csr.json  << EOF 
{
  "CN": "kubernetes",
  "key": {
     "algo": "rsa",
     "size": 2048
  },
  "ca": {
    "expiry": "876000h"
  }
}
EOF

cat > front-proxy-client-csr.json  << EOF 
{
  "CN": "front-proxy-client",
  "key": {
     "algo": "rsa",
     "size": 2048
  }
}
EOF

cfssl gencert -initca front-proxy-ca-csr.json | cfssljson -bare /etc/kubernetes/pki/front-proxy-ca

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

###controller-manager证书

cat > controller-manager-csr.json << EOF 
{
  "CN": "system:kube-controller-manager",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Beijing",
      "L": "Beijing",
      "O": "system:kube-controller-manager",
      "OU": "Kubernetes-manual"
    }
  ]
}
EOF

cfssl gencert \
   -ca=/etc/kubernetes/pki/ca.pem \
   -ca-key=/etc/kubernetes/pki/ca-key.pem \
   -config=ca-config.json \
   -profile=kubernetes \
   controller-manager-csr.json | cfssljson -bare /etc/kubernetes/pki/controller-manager

# 设置一个集群项 
# 注意，如果不是高可用集群,将192.168.1.111改为master01的地址或域名

kubectl config set-cluster kubernetes \
    --certificate-authority=/etc/kubernetes/pki/ca.pem \
    --embed-certs=true \
    --server=https://192.168.1.111:8443 \
    --kubeconfig=/etc/kubernetes/controller-manager.kubeconfig
     
# 设置一个环境项，一个上下文
kubectl config set-context system:kube-controller-manager@kubernetes \
    --cluster=kubernetes \
    --user=system:kube-controller-manager \
    --kubeconfig=/etc/kubernetes/controller-manager.kubeconfig

#  set-credentials 设置一个用户项
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
     
# 设置默认环境
kubectl config use-context system:kube-controller-manager@kubernetes \
    --kubeconfig=/etc/kubernetes/controller-manager.kubeconfig

scheduler证书

cat > scheduler-csr.json << EOF 
{
  "CN": "system:kube-scheduler",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Beijing",
      "L": "Beijing",
      "O": "system:kube-scheduler",
      "OU": "Kubernetes-manual"
    }
  ]
}
EOF

cfssl gencert \
   -ca=/etc/kubernetes/pki/ca.pem \
   -ca-key=/etc/kubernetes/pki/ca-key.pem \
   -config=ca-config.json \
   -profile=kubernetes \
   scheduler-csr.json | cfssljson -bare /etc/kubernetes/pki/scheduler

# 注意，如果不是高可用集群, 将192.168.1.111改为master01的地址或域名  
kubectl config set-cluster kubernetes \
    --certificate-authority=/etc/kubernetes/pki/ca.pem \
    --embed-certs=true \
    --server=https://192.168.1.111:8443 \
  --kubeconfig=/etc/kubernetes/scheduler.kubeconfig

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
     
kubectl config set-context system:kube-scheduler@kubernetes \
    --cluster=kubernetes \
    --user=system:kube-scheduler \
    --kubeconfig=/etc/kubernetes/scheduler.kubeconfig
     
kubectl config use-context system:kube-scheduler@kubernetes \
    --kubeconfig=/etc/kubernetes/scheduler.kubeconfig

kube-proxy证书

cat > kube-proxy-csr.json  << EOF 
{
  "CN": "system:kube-proxy",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Beijing",
      "L": "Beijing",
      "O": "system:kube-proxy",
      "OU": "Kubernetes-manual"
    }
  ]
}
EOF

cfssl gencert \
   -ca=/etc/kubernetes/pki/ca.pem \
   -ca-key=/etc/kubernetes/pki/ca-key.pem \
   -config=ca-config.json \
   -profile=kubernetes \
   kube-proxy-csr.json | cfssljson -bare /etc/kubernetes/pki/kube-proxy
   
kubectl config set-cluster kubernetes \
  --certificate-authority=/etc/kubernetes/pki/ca.pem \
  --embed-certs=true \
  --server=https://192.168.1.111:8443 \
 --kubeconfig=/etc/kubernetes/kube-proxy.kubeconfig
  
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
  
kubectl config set-context kube-proxy@kubernetes \
  --cluster=kubernetes \
  --user=kube-proxy \
 --kubeconfig=/etc/kubernetes/kube-proxy.kubeconfig
  
kubectl config use-context kube-proxy@kubernetes --kubeconfig=/etc/kubernetes/kube-proxy.kubeconfig

ServiceAccount Key secret

openssl genrsa -out /etc/kubernetes/pki/sa.key 2048
openssl rsa -in /etc/kubernetes/pki/sa.key -pubout -out /etc/kubernetes/pki/sa.pub

admin证书

cat > admin-csr.json << EOF 
{
  "CN": "admin",
  "key": {
    "algo": "rsa",
    "size": 2048
  },
  "names": [
    {
      "C": "CN",
      "ST": "Beijing",
      "L": "Beijing",
      "O": "system:masters",
      "OU": "Kubernetes-manual"
    }
  ]
}
EOF

cfssl gencert \
   -ca=/etc/kubernetes/pki/ca.pem \
   -ca-key=/etc/kubernetes/pki/ca-key.pem \
   -config=ca-config.json \
   -profile=kubernetes \
   admin-csr.json | cfssljson -bare /etc/kubernetes/pki/admin

# 注意，如果不是高可用集群,将192.168.1.111改为master01的地址或域名   
kubectl config set-cluster kubernetes \
  --certificate-authority=/etc/kubernetes/pki/ca.pem \
  --embed-certs=true \
  --server=https://192.168.1.111:8443 \
  --kubeconfig=/etc/kubernetes/admin.kubeconfig
  
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
  
kubectl config set-context kubernetes-admin@kubernetes \
  --cluster=kubernetes \
  --user=kubernetes-admin \
  --kubeconfig=/etc/kubernetes/admin.kubeconfig
 
kubectl config use-context kubernetes-admin@kubernetes \
  --kubeconfig=/etc/kubernetes/admin.kubeconfig

同步至其他master

for i in k8s-master02 k8s-master03;do
    scp -r /etc/kubernetes/pki $i:/etc/kubernetes/
    scp /etc/kubernetes/*.kubeconfig $i:/etc/kubernetes/
done

[root@k8s-master01 ~]# ls -l /etc/kubernetes/
total 36
-rw------- 1 root root 6456 Oct 18 03:06 admin.kubeconfig
-rw------- 1 root root 6594 Oct 18 20:45 controller-manager.kubeconfig
-rw------- 1 root root 6458 Oct 18 03:17 kube-proxy.kubeconfig
drwxr-xr-x 2 root root 4096 Oct 18 20:57 pki
-rw------- 1 root root 6522 Oct 18 20:45 scheduler.kubeconfig
[root@k8s-master01 ~]# ls -l /etc/kubernetes/pki/
total 92
-rw-r--r-- 1 root root 1025 Oct 18 03:06 admin.csr
-rw------- 1 root root 1679 Oct 18 03:06 admin-key.pem
-rw-r--r-- 1 root root 1444 Oct 18 03:06 admin.pem
-rw-r--r-- 1 root root 1029 Oct 18 02:23 apiserver.csr
-rw------- 1 root root 1679 Oct 18 02:23 apiserver-key.pem
-rw-r--r-- 1 root root 1834 Oct 18 02:23 apiserver.pem
-rw-r--r-- 1 root root 1025 Oct 18 02:23 ca.csr
-rw------- 1 root root 1675 Oct 18 02:23 ca-key.pem
-rw-r--r-- 1 root root 1411 Oct 18 02:23 ca.pem
-rw-r--r-- 1 root root 1082 Oct 18 02:38 controller-manager.csr
-rw------- 1 root root 1679 Oct 18 02:38 controller-manager-key.pem
-rw-r--r-- 1 root root 1501 Oct 18 02:38 controller-manager.pem
-rw-r--r-- 1 root root  891 Oct 18 03:17 front-proxy-ca.csr
-rw------- 1 root root 1675 Oct 18 03:17 front-proxy-ca-key.pem
-rw-r--r-- 1 root root 1143 Oct 18 03:17 front-proxy-ca.pem
-rw-r--r-- 1 root root  903 Oct 18 03:17 front-proxy-client.csr
-rw------- 1 root root 1679 Oct 18 03:17 front-proxy-client-key.pem
-rw-r--r-- 1 root root 1188 Oct 18 03:17 front-proxy-client.pem
-rw-r--r-- 1 root root 1675 Oct 18 03:14 sa.key
-rw-r--r-- 1 root root  451 Oct 18 03:14 sa.pub
-rw-r--r-- 1 root root 1058 Oct 18 03:02 scheduler.csr
-rw------- 1 root root 1679 Oct 18 03:02 scheduler-key.pem
-rw-r--r-- 1 root root 1476 Oct 18 03:02 scheduler.pem
[root@k8s-master01 ~]# ls -l /etc/kubernetes/pki/ | wc -l
24

Ectd配置

etcd配置大致相同，注意修改每个Master节点的etcd配置的主机名和IP地址

master01

cat > /etc/etcd/etcd.config.yaml << EOF 
name: 'k8s-master01'
data-dir: /var/lib/etcd
wal-dir: /var/lib/etcd/wal
snapshot-count: 5000
heartbeat-interval: 100
election-timeout: 1000
quota-backend-bytes: 0
listen-peer-urls: 'https://192.168.1.171:2380'
listen-client-urls: 'https://192.168.1.171:2379,http://127.0.0.1:2379'
max-snapshots: 3
max-wals: 5
cors:
initial-advertise-peer-urls: 'https://192.168.1.171:2380'
advertise-client-urls: 'https://192.168.1.171:2379'
discovery:
discovery-fallback: 'proxy'
discovery-proxy:
discovery-srv:
initial-cluster: 'k8s-master01=https://192.168.1.171:2380,k8s-master02=https://192.168.1.172:2380,k8s-master03=https://192.168.1.173:2380'
initial-cluster-token: 'etcd-k8s-cluster'
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

master02

cat > /etc/etcd/etcd.config.yaml << EOF 
name: 'k8s-master02'
data-dir: /var/lib/etcd
wal-dir: /var/lib/etcd/wal
snapshot-count: 5000
heartbeat-interval: 100
election-timeout: 1000
quota-backend-bytes: 0
listen-peer-urls: 'https://192.168.1.172:2380'
listen-client-urls: 'https://192.168.1.172:2379,http://127.0.0.1:2379'
max-snapshots: 3
max-wals: 5
cors:
initial-advertise-peer-urls: 'https://192.168.1.172:2380'
advertise-client-urls: 'https://192.168.1.172:2379'
discovery:
discovery-fallback: 'proxy'
discovery-proxy:
discovery-srv:
initial-cluster: 'k8s-master01=https://192.168.1.171:2380,k8s-master02=https://192.168.1.172:2380,k8s-master03=https://192.168.1.173:2380'
initial-cluster-token: 'etcd-k8s-cluster'
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

master03

cat > /etc/etcd/etcd.config.yaml << EOF 
name: 'k8s-master03'
data-dir: /var/lib/etcd
wal-dir: /var/lib/etcd/wal
snapshot-count: 5000
heartbeat-interval: 100
election-timeout: 1000
quota-backend-bytes: 0
listen-peer-urls: 'https://192.168.1.173:2380'
listen-client-urls: 'https://192.168.1.173:2379,http://127.0.0.1:2379'
max-snapshots: 3
max-wals: 5
cors:
initial-advertise-peer-urls: 'https://192.168.1.173:2380'
advertise-client-urls: 'https://192.168.1.173:2379'
discovery:
discovery-fallback: 'proxy'
discovery-proxy:
discovery-srv:
initial-cluster: 'k8s-master01=https://192.168.1.171:2380,k8s-master02=https://192.168.1.172:2380,k8s-master03=https://192.168.1.173:2380'
initial-cluster-token: 'etcd-k8s-cluster'
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

启动ETCD
所有Master节点创建etcd service并启动

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.yaml
Restart=on-failure
RestartSec=10
LimitNOFILE=65536
[Install]
WantedBy=multi-user.target
Alias=etcd3.service
EOF

所有haproxy节点创建etcd的证书目录

systemctl daemon-reload
systemctl enable --now etcd

查看etcd状态

export ETCDCTL_API=3
etcdctl --endpoints="192.168.1.171:2379,192.168.1.172:2379,192.168.1.173:2379" --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

高可用配置

haproxy

所有haproxy节点安装keepalived和haproxy·

yum install keepalived haproxy -y

所有haproxy配置HAProxy，配置一样

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

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 192.168.1.171:6443  check
  server k8s-master02 192.168.1.172:6443  check
  server k8s-master03 192.168.1.173:6443  check
EOF

keepalived

keepalived01

所有Haproxy节点配置KeepAlived 配置不一样，注意每个节点的IP和interface

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 eth0
    mcast_src_ip 192.168.1.161
    virtual_router_id 61
    priority 100
    nopreempt
    advert_int 2
    authentication {
        auth_type PASS
        auth_pass K8SHA_KA_AUTH
    }
    virtual_ipaddress {
        192.168.1.111
    }
    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 eth0
    mcast_src_ip 192.168.1.162
    virtual_router_id 61
    priority 90
    nopreempt
    advert_int 2
    authentication {
        auth_type PASS
        auth_pass K8SHA_KA_AUTH
    }
    virtual_ipaddress {
        192.168.1.111
    }
    track_script {
      chk_apiserver 
  } 
}
EOF

健康检查配置
所有haproxy节点

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

所有master节点启动haproxy和keepalived

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

Kubernetes组件配置

所有节点创建相关目录

mkdir -p /etc/kubernetes/manifests/ /var/lib/kubelet /var/log/kubernetes

apiserver

注意k8s service网段为10.96.0.0/12,该网段不能和宿主机的网段、Pod网段的重复
请按需修改

所有master节点配置kube-apiserver service

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  \
      --logtostderr=true  \
      --allow-privileged=true  \
      --bind-address=0.0.0.0  \
      --secure-port=6443  \
      --advertise-address=192.168.1.111 \
      --service-cluster-ip-range=10.96.0.0/12  \
      --service-node-port-range=30000-32767  \
      --etcd-servers=https://192.168.1.171:2379,https://192.168.1.172:2379,https://192.168.1.173:2379 \
      --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  \
      --enable-aggregator-routing=true
      # --token-auth-file=/etc/kubernetes/token.csv

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

[Install]
WantedBy=multi-user.target
EOF

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

controller-manager

所有Master节点配置kube-controller-manager service

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 \
      --logtostderr=true \
      --bind-address=127.0.0.1 \
      --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 \
      --pod-eviction-timeout=2m0s \
      --controllers=*,bootstrapsigner,tokencleaner \
      --allocate-node-cidrs=true \
      --service-cluster-ip-range=10.96.0.0/12 \
      --cluster-cidr=172.16.0.0/12 \
      --node-cidr-mask-size-ipv4=24 \
      --requestheader-client-ca-file=/etc/kubernetes/pki/front-proxy-ca.pem 

Restart=always
RestartSec=10s

[Install]
WantedBy=multi-user.target
EOF

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

scheduler

所有Master节点配置kube-scheduler service

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 \
      --logtostderr=true \
      --bind-address=127.0.0.1 \
      --leader-elect=true \
      --kubeconfig=/etc/kubernetes/scheduler.kubeconfig

Restart=always
RestartSec=10s

[Install]
WantedBy=multi-user.target
EOF

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

TLS Bootstrapping配置

在master01创建bootstrap

kubectl config set-cluster kubernetes \
  --certificate-authority=/etc/kubernetes/pki/ca.pem \
  --embed-certs=true --server=https://192.168.1.111:8443 \
  --kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig

# token 需与下面的bootstrap.secret.yaml的token-id、token-secret 保持一致
kubectl config set-credentials tls-bootstrap-token-user \
  --token=c8ad9c.2e4d610cf3e7426e \
  --kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig
  
kubectl config set-context tls-bootstrap-token-user@kubernetes \
  --cluster=kubernetes  --user=tls-bootstrap-token-user \
  --kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig
  
kubectl config use-context tls-bootstrap-token-user@kubernetes \
  --kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig

# token的位置在bootstrap.secret.yaml，如果修改的话到这个文件修改
mkdir -p /root/.kube 
cp /etc/kubernetes/admin.kubeconfig /root/.kube/config

注意：bootstrap.secret.yaml的token-id、token-secret，需与上命令token即c8ad9c.2e4d610cf3e7426e保持一致

mkdir ~/bootstrap
cd ~/bootstrap

cat > bootstrap.secret.yaml  << EOF
apiVersion: v1
kind: Secret
metadata:
  name: bootstrap-token-c8ad9c
  namespace: kube-system
type: bootstrap.kubernetes.io/token
stringData:
  description: "The default bootstrap token generated by 'kubelet '."
  token-id: c8ad9c
  token-secret: 2e4d610cf3e7426e
  usage-bootstrap-authentication: "true"
  usage-bootstrap-signing: "true"
  auth-extra-groups:  system:bootstrappers:default-node-token,system:bootstrappers:worker,system:bootstrappers:ingress
 
---
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 bootstrap.secret.yaml

查看集群状态

[root@k8s-master01 system]# kubectl get cs
Warning: v1 ComponentStatus is deprecated in v1.19+
NAME                 STATUS    MESSAGE                         ERROR
scheduler            Healthy   ok                              
controller-manager   Healthy   ok                              
etcd-0               Healthy   {"health":"true","reason":""}   
etcd-1               Healthy   {"health":"true","reason":""}   
etcd-2               Healthy   {"health":"true","reason":""}

Node节点配置

分发证书

Master01节点分发证书至Node节点

for i in k8s-master02 k8s-master03 k8s-node01 k8s-node02; do
  scp /etc/kubernetes/{bootstrap-kubelet,kube-proxy}.kubeconfig $i:/etc/kubernetes/
  scp /etc/kubernetes/pki/{ca.pem,ca-key.pem,front-proxy-ca.pem} $i:/etc/kubernetes/pki/
done

kubelet配置

所有节点创建相关目录

mkdir -p /var/lib/kubelet /var/log/kubernetes /etc/kubernetes/manifests/

所有节点配置kubelet service

cat > /usr/lib/systemd/system/kubelet.service << \EOF
[Unit]
Description=Kubernetes Kubelet
Documentation=https://github.com/kubernetes/kubernetes
After=containerd.service
Requires=containerd.service

[Service]
ExecStart=/usr/local/bin/kubelet \
    --bootstrap-kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig \
    --kubeconfig=/etc/kubernetes/kubelet.kubeconfig \
    --config=/etc/kubernetes/kubelet-conf.yaml \
    --container-runtime=remote  \
    --runtime-request-timeout=15m  \
    --container-runtime-endpoint=unix:///run/containerd/containerd.sock  \
    --cgroup-driver=systemd \
    --node-labels=node.kubernetes.io/node=

Restart=always
StartLimitInterval=0
RestartSec=10

[Install]
WantedBy=multi-user.target
EOF

注意node-labels=node.kubernetes.io/node='' ubuntu为'' centos为空

创建kubelet的配置文件

注意：如果更改了k8s的service网段，需要更改kubelet-conf.yaml的clusterDNS配置，改成service网段的第十个地址，如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

启动所有节点kubelet

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

此时系统日志/var/log/messages
Unable to update cni config: no networks found in /etc/cni/net.d 显示只有如下信息为正常

[root@k8s-master01 ~]# kubectl get node
NAME           STATUS   ROLES    AGE     VERSION
k8s-master01   Ready    <none>   7m     v1.24.6
k8s-master02   Ready    <none>   3m36s   v1.24.6
k8s-master03   Ready    <none>   3m48s   v1.24.6
k8s-node01     Ready    <none>   3m31s   v1.24.6
k8s-node02     Ready    <none>   3m30s   v1.24.6

kube-proxy的配置

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: 172.16.0.0/12
configSyncPeriod: 15m0s
conntrack:
  max: null
  maxPerCore: 32768
  min: 131072
  tcpCloseWaitTimeout: 1h0m0s
  tcpEstablishedTimeout: 24h0m0s
enableProfiling: false
healthzBindAddress: 0.0.0.0:10256
hostnameOverride: ""
iptables:
  masqueradeAll: false
  masqueradeBit: 14
  minSyncPeriod: 0s
  syncPeriod: 30s
ipvs:
  masqueradeAll: true
  minSyncPeriod: 5s
  scheduler: "rr"
  syncPeriod: 30s
kind: KubeProxyConfiguration
metricsBindAddress: 127.0.0.1:10249
mode: "ipvs"
nodePortAddresses: null
oomScoreAdj: -999
portRange: ""
udpIdleTimeout: 250ms
EOF

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

启动kube-proxy

systemctl daemon-reload
systemctl enable --now kube-proxy
systemctl status kube-proxy

安装Calico

以下步骤只在master01执行

CNI插件问题：注释掉默认containerd cni插件，避免冲突，若此目录中有多个cni配置文件，kubelet 将会使用按文件名的字典顺序排列的第一个作为配置文件，所以前面默认选择使用的是 containerd-net 这个插件。

mv /etc/cni/net.d/10-containerd-net.conflist /etc/cni/net.d/10-containerd-net.conflist.bak
ifconfig cni0 down && ip link delete cni0
systemctl daemon-reload
systemctl restart containerd kubelet

# 直接etcd认证更高性能
curl https://raw.githubusercontent.com/projectcalico/calico/v3.24.5/manifests/calico-etcd.yaml -O
# https://docs.projectcalico.org/getting-started/kubernetes/installation/config-options

这里以apiserver认证方式安装

wget https://docs.projectcalico.org/manifests/calico.yaml --no-check-certificate

修改pod网段

vim calico.yaml

POD_CIDR="172.16.0.0/12"
sed -i 's@# - name: CALICO_IPV4POOL_CIDR@- name: CALICO_IPV4POOL_CIDR@' calico.yaml
sed -i 's@#   value: "192.168.0.0/16"@  value: '"$POD_CIDR"'@' calico.yaml

kubectl apply -f calico.yaml

查看calico状态

[root@k8s-master01 ~]# kubectl get pod -n kube-system
NAME                                       READY   STATUS    RESTARTS   AGE
calico-kube-controllers-6bb4597c4f-smvmr   1/1     Running   0          2m16s
calico-node-2bmx4                          1/1     Running   0          2m16s
calico-node-4jpvn                          1/1     Running   0          2m16s
calico-node-7bh4b                          1/1     Running   0          2m16s
calico-node-l5wch                          1/1     Running   0          2m16s
calico-node-r896n                          1/1     Running   0          2m16s

calicoctl (可选)

wget https://github.com/projectcalico/calico/releases/download/v3.24.2/calicoctl-linux-amd64 -O /usr/local/bin/calicoctl
chmod +x /usr/local/bin/calicoctl

# 已经配置~/.kube/config，则不用配置以下两个
export KUBECONFIG=/etc/kubernetes/admin.kubeconfig 
export DATASTORE_TYPE=kubernetes

[root@k8s-master01 ~]# calicoctl get nodes
NAME           
k8s-master01   
k8s-master02   
k8s-master03   
k8s-node01     
k8s-node02 

[root@k8s-master01 ~]# calicoctl get ippool -o wide
NAME                  CIDR            NAT    IPIPMODE   VXLANMODE   DISABLED   DISABLEBGPEXPORT   SELECTOR   
default-ipv4-ippool   172.16.0.0/12   true   Always     Never       false      false              all()  

[root@k8s-master01 ~]# calicoctl node status
Calico process is running.

IPv4 BGP status
+---------------+-------------------+-------+----------+-------------+
| PEER ADDRESS  |     PEER TYPE     | STATE |  SINCE   |    INFO     |
+---------------+-------------------+-------+----------+-------------+
| 192.168.1.172 | node-to-node mesh | up    | 11:10:04 | Established |
| 192.168.1.173 | node-to-node mesh | up    | 11:10:04 | Established |
| 192.168.1.174 | node-to-node mesh | up    | 13:00:34 | Established |
| 192.168.1.175 | node-to-node mesh | up    | 11:10:05 | Established |
+---------------+-------------------+-------+----------+-------------+

安装CoreDNS

git clone https://github.com/coredns/deployment.git
cd deployment/kubernetes
./deploy.sh -s -i 10.96.0.10 | kubectl apply -f -

[root@k8s-master01 kubernetes]# kubectl get po -n kube-system -l k8s-app=kube-dns
NAME                       READY   STATUS    RESTARTS   AGE
coredns-6f4b4bd8fb-v26qh   1/1     Running   0          47s

安装Metrics-server

同步证书到所有node节点

for i in k8s-node01 k8s-node02;do
  scp /etc/kubernetes/pki/front-proxy-ca.pem $i:/etc/kubernetes/pki/
done

mkdir ~/metrics-server && cd ~/metrics-server

cat > metrics-server.yaml << EOF 
apiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    k8s-app: metrics-server
  name: metrics-server
  namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    k8s-app: metrics-server
    rbac.authorization.k8s.io/aggregate-to-admin: "true"
    rbac.authorization.k8s.io/aggregate-to-edit: "true"
    rbac.authorization.k8s.io/aggregate-to-view: "true"
  name: system:aggregated-metrics-reader
rules:
- apiGroups:
  - metrics.k8s.io
  resources:
  - pods
  - nodes
  verbs:
  - get
  - list
  - watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    k8s-app: metrics-server
  name: system:metrics-server
rules:
- apiGroups:
  - ""
  resources:
  - pods
  - nodes
  - nodes/stats
  - namespaces
  - configmaps
  verbs:
  - get
  - list
  - watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
  labels:
    k8s-app: metrics-server
  name: metrics-server-auth-reader
  namespace: kube-system
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: Role
  name: extension-apiserver-authentication-reader
subjects:
- kind: ServiceAccount
  name: metrics-server
  namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  labels:
    k8s-app: metrics-server
  name: metrics-server:system:auth-delegator
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: system:auth-delegator
subjects:
- kind: ServiceAccount
  name: metrics-server
  namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  labels:
    k8s-app: metrics-server
  name: system:metrics-server
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: system:metrics-server
subjects:
- kind: ServiceAccount
  name: metrics-server
  namespace: kube-system
---
apiVersion: v1
kind: Service
metadata:
  labels:
    k8s-app: metrics-server
  name: metrics-server
  namespace: kube-system
spec:
  ports:
  - name: https
    port: 443
    protocol: TCP
    targetPort: https
  selector:
    k8s-app: metrics-server
---
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    k8s-app: metrics-server
  name: metrics-server
  namespace: kube-system
spec:
  selector:
    matchLabels:
      k8s-app: metrics-server
  strategy:
    rollingUpdate:
      maxUnavailable: 0
  template:
    metadata:
      labels:
        k8s-app: metrics-server
    spec:
      containers:
      - args:
        - --cert-dir=/tmp
        - --secure-port=4443
        - --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
        - --kubelet-use-node-status-port
        - --metric-resolution=15s
        - --kubelet-insecure-tls
        - --requestheader-client-ca-file=/etc/kubernetes/pki/front-proxy-ca.pem # change to front-proxy-ca.crt for kubeadm
        - --requestheader-username-headers=X-Remote-User
        - --requestheader-group-headers=X-Remote-Group
        - --requestheader-extra-headers-prefix=X-Remote-Extra-
        image: registry.aliyuncs.com/google_containers/metrics-server:v0.5.0
        imagePullPolicy: IfNotPresent
        livenessProbe:
          failureThreshold: 3
          httpGet:
            path: /livez
            port: https
            scheme: HTTPS
          periodSeconds: 10
        name: metrics-server
        ports:
        - containerPort: 4443
          name: https
          protocol: TCP
        readinessProbe:
          failureThreshold: 3
          httpGet:
            path: /readyz
            port: https
            scheme: HTTPS
          initialDelaySeconds: 20
          periodSeconds: 10
        resources:
          requests:
            cpu: 100m
            memory: 200Mi
        securityContext:
          readOnlyRootFilesystem: true
          runAsNonRoot: true
          runAsUser: 1000
        volumeMounts:
        - mountPath: /tmp
          name: tmp-dir
        - name: ca-ssl
          mountPath: /etc/kubernetes/pki
      nodeSelector:
        kubernetes.io/os: linux
      priorityClassName: system-cluster-critical
      serviceAccountName: metrics-server
      volumes:
      - emptyDir: {}
        name: tmp-dir
      - name: ca-ssl
        hostPath:
          path: /etc/kubernetes/pki
---
apiVersion: apiregistration.k8s.io/v1
kind: APIService
metadata:
  labels:
    k8s-app: metrics-server
  name: v1beta1.metrics.k8s.io
spec:
  group: metrics.k8s.io
  groupPriorityMinimum: 100
  insecureSkipTLSVerify: true
  service:
    name: metrics-server
    namespace: kube-system
  version: v1beta1
  versionPriority: 100
EOF

kubectl apply -f metrics-server.yaml

[root@k8s-master01 ~]# kubectl top node
NAME           CPU(cores)   CPU%   MEMORY(bytes)   MEMORY%   
k8s-master01   164m         8%     1232Mi          65%       
k8s-master02   149m         7%     1210Mi          64%       
k8s-master03   161m         8%     1197Mi          63%       
k8s-node01     64m          6%     867Mi           46%       
k8s-node02     63m          6%     1230Mi          65%

安装Dashboard

wget https://raw.githubusercontent.com/kubernetes/dashboard/v2.7.0/aio/deploy/recommended.yaml

# 默认镜像在docker.io/ubernetesui/dashboard 默认国内加速即可
# registry.aliyuncs.com/google_containers:v2.7.0 有问题报错exec /dashboard: exec format error，应该是拉错架构了

kubectl apply -f recommended.yaml

cat > dashboard-user.yaml << EOF
apiVersion: v1
kind: ServiceAccount
metadata:
  name: admin-user
  namespace: kubernetes-dashboard
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: admin-user
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: cluster-admin
subjects:
- kind: ServiceAccount
  name: admin-user
  namespace: kubernetes-dashboard
EOF

kubectl apply -f dashboard-user.yaml

更改dashboard的svc为NodePort

[root@k8s-master01 ~]# kubectl edit svc kubernetes-dashboard -n kubernetes-dashboard
...
  sessionAffinity: None
  type: NodePort # 将Cluster为NodePort
status:
  loadBalancer: {}

[root@k8s-master01 ~]# kubectl get svc kubernetes-dashboard -n kubernetes-dashboard

NAME                   TYPE       CLUSTER-IP      EXTERNAL-IP   PORT(S)         AGE
kubernetes-dashboard   NodePort   10.101.102.61   <none>        443:32220/TCP   2m54s

创建token访问

kubectl -n kubernetes-dashboard create token admin-user

复制生成的token: yJhbGciOiJSUzI1NiIsImtpZCI6ImVvQzxxx…

使用火狐浏览器访问 https://vip:NodePort (谷歌浏览器不能登陆，需修改dashboard证书)

https://192.168.1.111:32220

集群验证

[root@k8s-master01 ~]# kubectl get cs
Warning: v1 ComponentStatus is deprecated in v1.19+
NAME                 STATUS    MESSAGE                         ERROR
scheduler            Healthy   ok                              
etcd-2               Healthy   {"health":"true","reason":""}   
controller-manager   Healthy   ok                              
etcd-1               Healthy   {"health":"true","reason":""}   
etcd-0               Healthy   {"health":"true","reason":""} 

[root@k8s-master01 ~]# kubectl get nodes
NAME           STATUS   ROLES    AGE   VERSION
k8s-master01   Ready    <none>   19h   v1.24.6
k8s-master02   Ready    <none>   17h   v1.24.6
k8s-master03   Ready    <none>   17h   v1.24.6
k8s-node01     Ready    <none>   17h   v1.24.6
k8s-node02     Ready    <none>   17h   v1.24.6

busybox测试dns

cat <<EOF | kubectl apply -f -
apiVersion: v1
kind: Pod
metadata:
  name: busybox
  namespace: default
spec:
  containers:
  - name: busybox
    image: busybox:1.28
    command:
      - sleep
      - "3600"
    imagePullPolicy: IfNotPresent
  restartPolicy: Always
EOF

[root@k8s-master01 ~]# kubectl exec -it busybox -- nslookup kubernetes
Server:    10.96.0.10
Address 1: 10.96.0.10 kube-dns.kube-system.svc.cluster.local

Name:      kubernetes
Address 1: 10.96.0.1 kubernetes.default.svc.cluster.local

[root@k8s-master01 ~]# kubectl exec -it busybox -- ping -c2 www.baidu.com
PING www.baidu.com (14.215.177.38): 56 data bytes
64 bytes from 14.215.177.38: seq=0 ttl=49 time=9.445 ms
64 bytes from 14.215.177.38: seq=1 ttl=49 time=9.524 ms

测试nginx svc以及Pod内部网络通信是否正常

cat  > nginx_deploy.yaml << EOF 
apiVersion: apps/v1
kind: Deployment
metadata:
  name: nginx
spec:
  selector:
    matchLabels:
      app: nginx
  template:
    metadata:
      labels:
        app: nginx
    spec:
      containers:
      - image: nginx:alpine
        name: nginx
        ports:
        - containerPort: 80
---
apiVersion: v1
kind: Service
metadata:
  name: nginx
spec:
  selector:
    app: nginx
  type: NodePort
  ports:
    - protocol: TCP
      port: 80
      targetPort: 80
      nodePort: 30001
EOF

kubectl apply -f nginx_deploy.yaml

[root@k8s-master01 ~]# kubectl get svc,pod -owide
NAME                 TYPE        CLUSTER-IP       EXTERNAL-IP   PORT(S)        AGE   SELECTOR
service/kubernetes   ClusterIP   10.96.0.1        <none>        443/TCP        45h   <none>
service/nginx        NodePort    10.102.100.128   <none>        80:30001/TCP   16m   app=nginx

NAME                         READY   STATUS    RESTARTS   AGE   IP             NODE           NOMINATED NODE   READINESS GATES
pod/busybox                  1/1     Running   0          24m   172.18.195.3   k8s-master03   <none>           <none>
pod/nginx-6fb79bc456-s84wf   1/1     Running   0          16m   172.25.92.66   k8s-master02   <none>           <none>

for i in k8s-master01 k8s-master02 k8s-master03 k8s-node01 k8s-node01; do
   echo $i
   ssh root@$i curl -s 10.102.100.128 | grep "using nginx" # nginx svc ip
   ssh root@$i curl -s 172.25.92.66 | grep "using nginx"  # pod ip
done

访问宿主机vip:nodePort

[root@k8s-master01 ~]# curl -I 192.168.1.111:30001
HTTP/1.1 200 OK
Server: nginx/1.23.2
Date: Thu, 20 Oct 2022 12:22:07 GMT
Content-Type: text/html
Content-Length: 615
Last-Modified: Wed, 19 Oct 2022 10:28:53 GMT
Connection: keep-alive
ETag: "634fd165-267"
Accept-Ranges: bytes

安装命令行补全

yum install bash-completion -y
source /usr/share/bash-completion/bash_completion
source <(kubectl completion bash)
echo "source <(kubectl completion bash)" >> ~/.bashrc

参考

腾讯云Ubuntu二进制搭建高可用(k8s)Kubernetes v1.24.3集群
 企业级高可用Kubernetes1.20.x集群(二进制)