1、环境准备

主机名        IP地址应用信息
k8s-master01192.168.124.251kube-apiserver、kube-controller-manager、kube-scheduler、etcd、keepalived+haproxy
k8s-master02192.168.124.252kube-apiserver、kube-controller-manager、kube-scheduler、etcd、keepalived+haproxy
k8s-node01192.168.124.253kubelet、kube-proxy、Containerd、etcd
k8s-node02192.168.124.254kubelet、kube-proxy、Containerd
LB-VIP192.168.124.250集群负载VIP

Pod网段：172.16.0.0/16

service网段：10.96.0.0/16

1.1、软件版本

这里使用的是开源Rocky Linux操作系统，该系统是继 CentOS 8停产后，继而由CentOS创始人再次延续CentOS8 而开发的系统，一系列操作命令与CentOS 8 无区别，但默认是禁用root远程登录的，需要在/etc/ssh/sshd_config打开，开源社区：Rocky Linux

软件名称版本信息
Rocky Linux 9.05.14.0-70.17.1.el9_0.x86_64 自带的
kubernetesv1.25.0
etcd3.5.4
cfssl1.6.1
containerd1.6.6

1.2、软件下载地址

下载kubernetes1.25.+的二进制包
github二进制包下载地址：https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.25.md
wget https://dl.k8s.io/v1.25.0/kubernetes-server-linux-amd64.tar.gz

下载etcd二进制包
github二进制包下载地址：https://github.com/etcd-io/etcd/releases
wget https://github.com/etcd-io/etcd/releases/download/v3.5.4/etcd-v3.5.4-linux-amd64.tar.gz

containerd下载二进制包
wget https://github.com/containerd/containerd/releases/download/v1.6.6/containerd-1.6.6-linux-amd64.tar.gz

cni网络插件下载
wget https://github.com/containernetworking/plugins/releases/download/v1.1.1/cni-plugins-linux-amd64-v1.1.1.tgz

crictl客户端工具
wget https://github.com/kubernetes-sigs/cri-tools/releases/download/v1.24.2/crictl-v1.24.2-linux-amd64.tar.gz

下载cfssl二进制包
github二进制包下载地址：https://github.com/cloudflare/cfssl/releases
wget https://github.com/cloudflare/cfssl/releases/download/v1.6.1/cfssl_1.6.1_linux_amd64
wget https://github.com/cloudflare/cfssl/releases/download/v1.6.1/cfssljson_1.6.1_linux_amd64
wget https://github.com/cloudflare/cfssl/releases/download/v1.6.1/cfssl-certinfo_1.6.1_linux_amd64

1.3、初始化系统

#  安装必要工具
yum -y install vim telnet wget curl lrzsz bash-completion net-tools ntpdate device-mapper-persistent-data lvm2

#  设置主机名称
hostnamectl set-hostname k8s-master01
hostnamectl set-hostname k8s-master02
hostnamectl set-hostname k8s-node01
hostnamectl set-hostname k8s-node02

#  添加 hosts文件
cat >> /etc/hosts <<EOF
192.168.124.251 k8s-master01
192.168.124.252 k8s-master02
192.168.124.253 k8s-node01
192.168.124.254 k8s-node02
192.168.124.250 k8s-LB-VIP
114.115.223.243 registry
EOF

#  关闭防火墙
systemctl stop firewalld
systemctl disable firewalld

#  关闭selinux
sed -i "s#SELINUX=enforcing#SELINUX=disabled#g" /etc/sysconfig/selinux

#  关闭交换分区
sed -ri 's/.*swap.*/#&/' /etc/fstab
swapoff -a && sysctl -w vm.swappiness=0

#  时间同步, 如果服务器之间时间不一致的话，会导致配置的集群失败，基本上公司都会有时间同步机器
vim /etc/chrony.conf
注释掉2.pool.ntp.org，添加一行国家科学院的ntp时间服务器地址
#pool 2.pool.ntp.org iburst
pool ntp.ntsc.ac.cn iburst
# Serve time even if not synchronized to a time source.
local stratum 10

systemctl restart chronyd

#  配置 limit
ulimit -SHn 65535
cat >> /etc/security/limits.conf <<EOF
* soft nofile 655360
* hard nofile 131072
* soft nproc 655350
* hard nproc 655350
* seft memlock unlimited
* hard memlock unlimitedd
EOF

#  调整 k8s 的内核参数
cat <<EOF > /etc/sysctl.d/k8s.conf
net.ipv4.ip_forward = 1
net.bridge.bridge-nf-call-iptables = 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
net.ipv6.conf.all.disable_ipv6 = 0
net.ipv6.conf.default.disable_ipv6 = 0
net.ipv6.conf.lo.disable_ipv6 = 0
net.ipv6.conf.all.forwarding = 0
EOF
#  生效
sysctl --system

#  安装ipvs
yum -y install ipvsadm ipset sysstat conntrack libseccomp
cat >> /etc/modules-load.d/ipvs.conf <<EOF 
ip_vs
ip_vs_rr
ip_vs_wrr
ip_vs_sh
nf_conntrack
ip_tables
ip_set
xt_set
ipt_set
ipt_rpfilter
ipt_REJECT
ipip
EOF

systemctl restart systemd-modules-load.service

lsmod | grep -e ip_vs -e nf_conntrack
ip_vs_sh               16384  0
ip_vs_wrr              16384  0
ip_vs_rr               16384  0
ip_vs                 180224  6 ip_vs_rr,ip_vs_sh,ip_vs_wrr
nf_conntrack          176128  1 ip_vs
nf_defrag_ipv6         24576  2 nf_conntrack,ip_vs
nf_defrag_ipv4         16384  1 nf_conntrack
libcrc32c              16384  3 nf_conntrack,xfs,ip_vs

1.4、配置免密登录

在master01配置免密登录其他机器

ssh-keygen -t rsa     # 一直回车即可
ssh-copy-id 192.168.124.252
ssh-copy-id 192.168.124.253
ssh-copy-id 192.168.124.254

# 验证免密登录
ssh root@192.168.124.254
Last login: Fri Oct 28 10:28:42 2022 from 192.168.124.5
[root@k8s-node02 ~]#

2、Node节点安装Containerd

在两台Node节点安装

# 解压containerd包
tar -zxf containerd-1.6.6-linux-amd64.tar.gz -C /opt/
cp /opt/bin/* /usr/bin/

# 创建 cni 目录
mkdir -p /etc/cni/net.d /opt/cni/bin 
#解压cni二进制包
tar -zxf cni-plugins-linux-amd64-v1.1.1.tgz -C /opt/cni/bin/

#  解压 crictl工具
tar -zxf crictl-v1.24.2-linux-amd64.tar.gz -C /usr/bin/

2.1、创建启动文件

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

[Service]
#uncomment to enable the experimental sbservice (sandboxed) version of containerd/cri integration
#Environment="ENABLE_CRI_SANDBOXES=sandboxed"
ExecStartPre=-/sbin/modprobe overlay
ExecStart=/usr/bin/containerd

Type=notify
Delegate=yes
KillMode=process
Restart=always
RestartSec=5
# Having non-zero Limit*s causes performance problems due to accounting overhead
# in the kernel. We recommend using cgroups to do container-local accounting.
LimitNPROC=infinity
LimitCORE=infinity
LimitNOFILE=infinity
# Comment TasksMax if your systemd version does not supports it.
# Only systemd 226 and above support this version.
TasksMax=infinity
OOMScoreAdjust=-999

[Install]
WantedBy=multi-user.target
EOF

2.2、创建配置文件

mkdir /etc/containerd
containerd config default | tee /etc/containerd/config.toml

# 修改Containerd运行时使用systemd作为启动
sed -i "s#SystemdCgroup\ \=\ false#SystemdCgroup\ \=\ true#g" /etc/containerd/config.toml
cat /etc/containerd/config.toml | grep SystemdCgroup

# 修改Containerd的镜像仓库文件，这里使用的是registry.cn-hangzhou.aliyuncs.com/chenby作为镜像仓库
sed -i "s#k8s.gcr.io#registry.cn-hangzhou.aliyuncs.com/chenby#g" /etc/containerd/config.toml
cat /etc/containerd/config.toml | grep sandbox_image

# 补充一句
在config.toml 文件中最上面 大概第4左右行的位置 是修改containerd数据存储目录，默认和docker一样的，在/var/log/containerd下，有需要可以自行修改

2.3、配置crictl 客户端工具

cat > /etc/crictl.yaml <<EOF
runtime-endpoint: unix:///run/containerd/containerd.sock
image-endpoint: unix:///run/containerd/containerd.sock
timeout: 10
debug: false
EOF

2.4、启动Containerd

wget https://github.com/opencontainers/runc/releases/download/v1.1.4/runc.amd64 -O /usr/bin/runc
chmod +x /usr/bin/runc

#  systemctl daemon-reload
#  systemctl start containerd

3、解压二进制包

在Master01操作

tar -zxf kubernetes-server-linux-amd64.tar.gz
tar -zxf etcd-v3.5.4-linux-amd64.tar.gz

3.1、拷贝文件到其他节点

cd kubernetes/server/bin
cp -r kube-apiserver kube-controller-manager kube-scheduler kubectl /usr/local/bin
scp -r kube-apiserver kube-controller-manager kube-scheduler kubectl root@192.168.124.252:/usr/local/bin
scp -r kubelet kube-proxy root@192.168.124.253:/usr/local/bin
scp -r kubelet kube-proxy root@192.168.124.254:/usr/local/bin

cd etcd-v3.5.4-linux-amd64
cp -r etcd etcdctl /usr/local/bin
scp -r etcd etcdctl root@192.168.124.252:/usr/local/bin
scp -r etcd etcdctl root@192.168.124.253:/usr/local/bin

4、生成k8s组件证书

4.1、生成etcd证书

在master01上操作

#  在部署etcd 的机器上 创建目录
mkdir -p /etc/etcd/ssl

#  把下载后的证书工具重命名
chmod +x cfssl*
mv cfssl_1.6.1_linux_amd64  /usr/local/bin/cfssl
mv cfssljson_1.6.1_linux_amd64  /usr/local/bin/cfssljson
mv cfssl-certinfo_1.6.1_linux_amd64 /usr/local/bin/cfssl-certinfo

#  进入提前准备好的证书目录中
cd /root/k8s-pki-yaml/pki

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=127.0.0.1,k8s-etcd01,k8s-etcd02,k8s-etcd03,192.168.124.251,192.168.124.252,192.168.124.253 \
-profile=kubernetes \
etcd-csr.json | cfssljson -bare /etc/etcd/ssl/etcd

4.2、拷贝证书到其他etcd节点

scp -r /etc/etcd/ssl/*  root@192.168.124.252:/etc/etcd/ssl
scp -r /etc/etcd/ssl/*  root@192.168.124.253:/etc/etcd/ssl

4.3、生成apiserver证书

# 所有节点 创建此目录
mkdir -p /etc/kubernetes/pki

# 进入证书存放目录
cd /root/k8s-pki-yaml/pki

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

cfssl gencert   \
-ca=/etc/kubernetes/pki/ca.pem   \
-ca-key=/etc/kubernetes/pki/ca-key.pem   \
-config=ca-config.json   \
-hostname=10.96.0.1,192.168.124.250,127.0.0.1,kubernetes,kubernetes.default,kubernetes.default.svc,kubernetes.default.svc.cluster,kubernetes.default.svc.cluster.local,x.oiox.cn,k.oiox.cn,l.oiox.cn,o.oiox.cn,192.168.124.251,192.168.124.252 \
-profile=kubernetes  apiserver-csr.json | cfssljson -bare /etc/kubernetes/pki/apiserver

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

4.4、生成controller-manager证书

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

kubectl config set-cluster kubernetes \
--certificate-authority=/etc/kubernetes/pki/ca.pem \
--embed-certs=true \
--server=https://192.168.124.250:8443 \
--kubeconfig=/etc/kubernetes/controller-manager.kubeconfig

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

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

kubectl config use-context system:kube-controller-manager@kubernetes \
 --kubeconfig=/etc/kubernetes/controller-manager.kubeconfig

4.5、生成scheduler证书

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

kubectl config set-cluster kubernetes \
--certificate-authority=/etc/kubernetes/pki/ca.pem \
--embed-certs=true \
--server=https://192.168.124.250:8443 \
--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

4.6、生成admin证书

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

kubectl config set-cluster kubernetes \
--certificate-authority=/etc/kubernetes/pki/ca.pem \
--embed-certs=true \
--server=https://192.168.124.250:8443  \
--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

4.7、生成kube-proxy证书

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://192.168.124.250:8443 \
--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

4.8、创建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

4.9、拷贝证书到其他节点

scp -r  /etc/kubernetes/*  root@192.168.124.252:/etc/kubernetes
scp -r /etc/kubernetes/*   root@192.168.124.253:/etc/kubernetes
scp -r /etc/kubernetes/*   root@192.168.124.254:/etc/kubernetes

5、部署etcd

5.1、master01上配置etcd01

cat > /etc/etcd/etcd.config.yml << EOF 
name: 'k8s-etcd01'
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://192.168.124.251:2380'
listen-client-urls: 'https://192.168.124.251:2379,http://127.0.0.1:2379'
max-snapshots: 3
max-wals: 5
cors:
initial-advertise-peer-urls: 'https://192.168.124.251:2380'
advertise-client-urls: 'https://192.168.124.251:2379'
discovery:
discovery-fallback: 'proxy'
discovery-proxy:
discovery-srv:
initial-cluster: 'k8s-etcd01=https://192.168.124.251:2380,k8s-etcd02=https://192.168.124.252:2380,k8s-etcd03=https://192.168.124.253:2380'
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/kubernetes/pki/etcd/etcd.pem'
  key-file: '/etc/kubernetes/pki/etcd/etcd-key.pem'
  client-cert-auth: true
  trusted-ca-file: '/etc/kubernetes/pki/etcd/etcd-ca.pem'
  auto-tls: true
peer-transport-security:
  cert-file: '/etc/kubernetes/pki/etcd/etcd.pem'
  key-file: '/etc/kubernetes/pki/etcd/etcd-key.pem'
  peer-client-cert-auth: true
  trusted-ca-file: '/etc/kubernetes/pki/etcd/etcd-ca.pem'
  auto-tls: true
debug: false
log-package-levels:
log-outputs: [default]
force-new-cluster: false
EOF

5.2、master01上配置etcd02

cat > /etc/etcd/etcd.config.yml << EOF 
name: 'k8s-etcd02'
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://192.168.124.252:2380'
listen-client-urls: 'https://192.168.124.252:2379,http://127.0.0.1:2379'
max-snapshots: 3
max-wals: 5
cors:
initial-advertise-peer-urls: 'https://192.168.124.252:2380'
advertise-client-urls: 'https://192.168.124.252:2379'
discovery:
discovery-fallback: 'proxy'
discovery-proxy:
discovery-srv:
initial-cluster: 'k8s-etcd01=https://192.168.124.251:2380,k8s-etcd02=https://192.168.124.252:2380,k8s-etcd03=https://192.168.124.253:2380'
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/kubernetes/pki/etcd/etcd.pem'
  key-file: '/etc/kubernetes/pki/etcd/etcd-key.pem'
  client-cert-auth: true
  trusted-ca-file: '/etc/kubernetes/pki/etcd/etcd-ca.pem'
  auto-tls: true
peer-transport-security:
  cert-file: '/etc/kubernetes/pki/etcd/etcd.pem'
  key-file: '/etc/kubernetes/pki/etcd/etcd-key.pem'
  peer-client-cert-auth: true
  trusted-ca-file: '/etc/kubernetes/pki/etcd/etcd-ca.pem'
  auto-tls: true
debug: false
log-package-levels:
log-outputs: [default]
force-new-cluster: false
EOF

5.3、k8s-node01上配置etcd03

cat > /etc/etcd/etcd.config.yml << EOF 
name: 'k8s-etcd03'
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://192.168.124.253:2380'
listen-client-urls: 'https://192.168.124.253:2379,http://127.0.0.1:2379'
max-snapshots: 3
max-wals: 5
cors:
initial-advertise-peer-urls: 'https://192.168.124.253:2380'
advertise-client-urls: 'https://192.168.124.253:2379'
discovery:
discovery-fallback: 'proxy'
discovery-proxy:
discovery-srv:
initial-cluster: 'k8s-etcd01=https://192.168.124.251:2380,k8s-etcd02=https://192.168.124.252:2380,k8s-etcd03=https://192.168.124.253:2380'
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/kubernetes/pki/etcd/etcd.pem'
  key-file: '/etc/kubernetes/pki/etcd/etcd-key.pem'
  client-cert-auth: true
  trusted-ca-file: '/etc/kubernetes/pki/etcd/etcd-ca.pem'
  auto-tls: true
peer-transport-security:
  cert-file: '/etc/kubernetes/pki/etcd/etcd.pem'
  key-file: '/etc/kubernetes/pki/etcd/etcd-key.pem'
  peer-client-cert-auth: true
  trusted-ca-file: '/etc/kubernetes/pki/etcd/etcd-ca.pem'
  auto-tls: true
debug: false
log-package-levels:
log-outputs: [default]
force-new-cluster: false
EOF

5.4、创建etcd启动文件

cat > /usr/lib/systemd/system/etcd.service << EOF

[Unit]
Description=Etcd Service
Documentation=https://coreos.com/etcd/docs/latest/
After=network.target

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

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

EOF

5.5、启动etcd

mkdir /etc/kubernetes/pki/etcd
ln -s /etc/etcd/ssl/* /etc/kubernetes/pki/etcd/
systemctl daemon-reload && systemctl start etcd   #需要三台一同启动
systemctl enable etcd

5.6、查看etcd集群状态

export ETCDCTL_API=3
etcdctl --endpoints="192.168.124.251:2379,192.168.124.252:2379,192.168.124.253:2379" --cacert=/etc/kubernetes/pki/etcd/etcd-ca.pem --cert=/etc/kubernetes/pki/etcd/etcd.pem --key=/etc/kubernetes/pki/etcd/etcd-key.pem  endpoint status --write-out=table

# 输出如下，一主两从
+----------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+
|       ENDPOINT       |        ID        | VERSION | DB SIZE | IS LEADER | IS LEARNER | RAFT TERM | RAFT INDEX | RAFT APPLIED INDEX | ERRORS |
+----------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+
| 192.168.124.251:2379 | 1026c1ebe076125d |   3.5.4 |   20 kB |      true |      false |         2 |          9 |                  9 |        |
| 192.168.124.252:2379 | 8c7539173eea4911 |   3.5.4 |   20 kB |     false |      false |         2 |          9 |                  9 |        |
| 192.168.124.253:2379 | 1b8b842ad30ff6a0 |   3.5.4 |   20 kB |     false |      false |         2 |          9 |                  9 |        |
+----------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+

6、keepalived+haproxy

在两台master上安装

yum -y install keepalived haproxy

6.1、配置haproxy

两台master节点的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 monitor-in
 bind *:33305
 mode http
 option httplog
 monitor-uri /monitor

frontend k8s-master
 bind 0.0.0.0:8443
 bind 127.0.0.1:8443
 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  192.168.124.251:6443 check
 server  k8s-master02  192.168.124.252:6443 check
EOF

6.2、配置keepalived

master01上的keepalived

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
    # 注意网卡名
    interface ens160 
    mcast_src_ip 192.168.124.251
    virtual_router_id 51
    priority 100
    nopreempt
    advert_int 2
    authentication {
        auth_type PASS
        auth_pass K8SHA_KA_AUTH
    }
    virtual_ipaddress {
        192.168.124.250
    }
    track_script {
      chk_apiserver 
} }

EOF

6.3、master02的keepalived配置

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
    # 注意网卡名
    interface ens160
    mcast_src_ip 192.168.124.252
    virtual_router_id 51
    priority 50
    nopreempt
    advert_int 2
    authentication {
        auth_type PASS
        auth_pass K8SHA_KA_AUTH
    }
    virtual_ipaddress {
        192.168.124.250
    }
    track_script {
      chk_apiserver 
} }

EOF

6.4、健康检查配置

两台节点都要有健康检查配置

cat >  /etc/keepalived/check_apiserver.sh << EOF
#!/bin/bash

err=0
for k in \$(seq 1 3)
do
    check_code=\$(pgrep haproxy)
    if [[ \$check_code == "" ]]; then
        err=\$(expr \$err + 1)
        sleep 1
        continue
    else
        err=0
        break
    fi
done

if [[ \$err != "0" ]]; then
    echo "systemctl stop keepalived"
    /usr/bin/systemctl stop keepalived
    exit 1
else
    exit 0
fi
EOF

# 添加执行权限
chmod +x /etc/keepalived/check_apiserver.sh

6.5、启动并测试

systemctl daemon-reload
systemctl enable --now haproxy
systemctl enable --now keepalived
#  测试ping 
ping 192.168.124.250
telnet 192.168.124.250 8443

7、部署apiserver

# 在 Master  节点上创建目录
mkdir -p /etc/kubernetes/manifests /var/log/kubernetes

7.1、master01的配置

cat > /usr/lib/systemd/system/kube-apiserver.service << EOF

[Unit]
Description=Kubernetes API Server
Documentation=https://github.com/kubernetes/kubernetes
After=network.target

[Service]
ExecStart=/usr/local/bin/kube-apiserver \\
      --v=2  \\
      --logtostderr=true  \\
      --allow-privileged=true  \\
      --bind-address=0.0.0.0  \\
      --secure-port=6443  \\
      --advertise-address=192.168.124.251 \\
      --service-cluster-ip-range=10.96.0.0/16 \\
      --service-node-port-range=30000-32767  \\
      --etcd-servers=https://192.168.124.251:2379,https://192.168.124.252:2379,https://192.168.124.253:2379 \\
      --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
      # --feature-gates=IPv6DualStack=true
      # --token-auth-file=/etc/kubernetes/token.csv

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

[Install]
WantedBy=multi-user.target

EOF

7.2、Master02的配置

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

[Service]
ExecStart=/usr/local/bin/kube-apiserver \\
      --v=2  \\
      --logtostderr=true  \\
      --allow-privileged=true  \\
      --bind-address=0.0.0.0  \\
      --secure-port=6443  \\
      --advertise-address=192.168.124.252 \\
      --service-cluster-ip-range=10.96.0.0/16 \\
      --service-node-port-range=30000-32767  \\
      --etcd-servers=https://192.168.124.251:2379,https://192.168.124.252:2379,https://192.168.124.253:2379 \\
      --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
      # --feature-gates=IPv6DualStack=true
      # --token-auth-file=/etc/kubernetes/token.csv

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

[Install]
WantedBy=multi-user.target

EOF

7.3、启动apiserver

systemctl daemon-reload && systemctl start kube-apiserver
systemctl status kube-apiserver

8、部署controller-manager

两台master节点配置相同

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=10.96.0.0/16 \\
      --cluster-cidr=172.16.0.0/16 \\
      --node-cidr-mask-size-ipv4=24 \\
      --requestheader-client-ca-file=/etc/kubernetes/pki/front-proxy-ca.pem 
      # --feature-gates=IPv6DualStack=true

Restart=always
RestartSec=10s

[Install]
WantedBy=multi-user.target

EOF

8.1、启动controller-manager

systemctl daemon-reload && systemctl start  kube-controller-manager
systemctl status kube-controller-manager

9、部署scheduler

两台master节点配置一致

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

9.1、启动scheduler

systemctl daemon-reload && systemctl start kube-scheduler
systemctl status kube-scheduler

10、TLS Bootstrapping配置

在master01上操作，进入提前准备好的目录中执行

cd /root/k8s-pki-yaml/bootstrap

kubectl config set-cluster kubernetes \
--certificate-authority=/etc/kubernetes/pki/ca.pem \
--embed-certs=true --server=https://192.168.124.250:8443 \
--kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig

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

#  此操作 在 master02也执行
mkdir -p /root/.kube ; cp /etc/kubernetes/admin.kubeconfig /root/.kube/config

# 创建bootstrap
kubectl create -f bootstrap.secret.yaml

# 把 bootstrap-kubelet.kubeconfig 拷贝到 master02 节点和 node节点
scp -r /etc/kubernetes/bootstrap-kubelet.kubeconfig  root@192.168.124.252:/etc/kubernetes
scp -r /etc/kubernetes/bootstrap-kubelet.kubeconfig  root@192.168.124.253:/etc/kubernetes
scp -r /etc/kubernetes/bootstrap-kubelet.kubeconfig  root@192.168.124.254:/etc/kubernetes

10.1、查看集群

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

11、部署Kubelet

11.1、配置kubelet启动文件

两台node节点配置都一致


mkdir -p /var/lib/kubelet  /etc/kubernetes/manifests/  /etc/cni/net.d/

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.yml \\
    --container-runtime-endpoint=unix:///run/containerd/containerd.sock  \\
    --node-labels=node.kubernetes.io/node=
    # --feature-gates=IPv6DualStack=true
    # --container-runtime=remote
    # --runtime-request-timeout=15m
    # --cgroup-driver=systemd

[Install]
WantedBy=multi-user.target
EOF

11.2、配置kubelet.yaml文件

两台Node节点配置一致

cat > /etc/kubernetes/kubelet-conf.yml <<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

11.3、启动kubelet

systemctl daemon-reload && systemctl start kubelet
systemctl enable kubelet
systemctl status kubelet

12、部署Kube-proxy

12.1、创建启动文件

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

12.2、创建配置文件

两台节点配置一致

cat > /etc/kubernetes/kube-proxy.yaml << EOF
apiVersion: kubeproxy.config.k8s.io/v1alpha1
bindAddress: 0.0.0.0
clientConnection:
  acceptContentTypes: ""
  burst: 10
  contentType: application/vnd.kubernetes.protobuf
  kubeconfig: /etc/kubernetes/kube-proxy.kubeconfig
  qps: 5
clusterCIDR: 172.16.0.0/16 
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

12.3、启动kube-proxy

systemctl daemon-reload && systemctl start kube-proxy
systemctl enable kube-proxy
systemctl status kube-proxy

12.4、查看Node状态

kubectl get nodes
NAME         STATUS     ROLES    AGE   VERSION
k8s-node01   NotReady   <none>   15s   v1.25.0
k8s-node02   NotReady   <none>   70m   v1.25.0

13、安装calico网络

cd /root/k8s-pki-yaml/calico/

#  更改网段
vim calico.yaml
在 第 4588行 改成如下
4588             - name: CALICO_IPV4POOL_CIDR
4589               value: "172.16.0.0/16"

#  创建
kubectl create -f calico.yaml

13.1、查看节点状态

kubectl get pods -A
NAMESPACE     NAME                                       READY   STATUS    RESTARTS   AGE
kube-system   calico-kube-controllers-86d8c4fb68-wrm7s   1/1     Running   0          2m14s
kube-system   calico-node-cg2cl                          1/1     Running   0          2m14s
kube-system   calico-node-fb52n                          1/1     Running   0          2m14s
kube-system   calico-typha-768795f74d-c7fmf              1/1     Running   0          2m14s

#  查看node状态
kubectl get nodes
NAME         STATUS     ROLES    AGE   VERSION
k8s-node01   Ready      <none>   29m   v1.25.0
k8s-node02   Ready      <none>   99m   v1.25.0

14、安装CoreDns

cd /root/k8s-pki-yaml/CoreDNS/

vim coredns.yaml
在 186 行 改成如下 IP
clusterIP: 10.96.0.10

#  创建
kubectl create -f coredns.yaml

#  查看状态
kubectl get pods -n kube-system          
NAME                                       READY   STATUS    RESTARTS   AGE
calico-kube-controllers-86d8c4fb68-ldhx2   1/1     Running   0          13m
calico-node-5jx6t                          1/1     Running   0          13m
calico-node-j29c8                          1/1     Running   0          13m
calico-typha-768795f74d-6dc59              1/1     Running   0          13m
coredns-5bc764d4f4-m7xwh                   1/1     Running   0          3m7s

15、配置命令补齐

命令补齐可以在输入kubectl 等一系列命令时 tab 自动补齐

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

16、验证集群可用性

# 部署 测试的 pod 资源
cat > busybox.yaml <<EOF
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

#启动buxybox
kubectl create -f busybox.yaml

# 查看是否成功启动
kubectl  get pods
NAME      READY   STATUS    RESTARTS   AGE
busybox   1/1     Running   0          17s

16.1、pod解析默认命名空间

#用pod 解析默认命名空间中的kubernetes
kubectl get svc
NAME         TYPE        CLUSTER-IP   EXTERNAL-IP   PORT(S)   AGE
kubernetes   ClusterIP   10.96.0.1    <none>        443/TCP   17h

kubectl exec busybox -n default -- 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

16.2、跨域是否可以通信

kubectl exec  busybox -n default -- nslookup kube-dns.kube-system
Server:    10.96.0.10
Address 1: 10.96.0.10 kube-dns.kube-system.svc.cluster.local

Name:      kube-dns.kube-system
Address 1: 10.96.0.10 kube-dns.kube-system.svc.cluster.local

16.3、访问端口

telnet 10.96.0.1 443
Trying 10.96.0.1...
Connected to 10.96.0.1.
Escape character is '^]'.

 telnet 10.96.0.10 53
Trying 10.96.0.10...
Connected to 10.96.0.10.
Escape character is '^]'.

curl 10.96.0.10:53
curl: (52) Empty reply from server

16.4、pod之间是否可以互通

kubectl get pods -o wide
NAME      READY   STATUS    RESTARTS   AGE     IP              NODE         NOMINATED NODE   READINESS GATES
busybox   1/1     Running   0          4m12s   10.244.58.199   k8s-node02   <none>           <none>

kubectl get pods -n kube-system -o wide
NAME                                       READY   STATUS    RESTARTS   AGE   IP                NODE         NOMINATED NODE   READINESS GATES
calico-kube-controllers-86d8c4fb68-mbr6b   1/1     Running   0          35m   172.16.85.193     k8s-node01   <none>           <none>
calico-node-pz4jw                          1/1     Running   0          35m   192.168.124.253   k8s-node01   <none>           <none>
calico-node-x726v                          1/1     Running   0          35m   192.168.124.254   k8s-node02   <none>           <none>
calico-typha-768795f74d-gc22c              1/1     Running   0          35m   192.168.124.253   k8s-node01   <none>           <none>
coredns-5bc764d4f4-9rxxf                   1/1     Running   0          31m   172.16.58.193     k8s-node02   <none>           <none>

# 进入busybox ping其他节点上的pod
kubectl exec -ti busybox -- sh

/ # ping 192.168.124.254
PING 192.168.124.254 (192.168.124.254): 56 data bytes
64 bytes from 192.168.124.254: seq=0 ttl=63 time=2.039 ms
64 bytes from 192.168.124.254: seq=1 ttl=63 time=0.648 ms
^C
--- 192.168.124.254 ping statistics ---
2 packets transmitted, 2 packets received, 0% packet loss
round-trip min/avg/max = 0.648/1.343/2.039 ms
/ # 
/ # ping 192.168.124.253
PING 192.168.124.253 (192.168.124.253): 56 data bytes
64 bytes from 192.168.124.253: seq=0 ttl=64 time=0.545 ms
64 bytes from 192.168.124.253: seq=1 ttl=64 time=0.071 ms
^C
--- 192.168.124.253 ping statistics ---
2 packets transmitted, 2 packets received, 0% packet loss
round-trip min/avg/max = 0.071/0.308/0.545 ms
/ # 
/ # ping 172.16.85.193
PING 172.16.85.193 (172.16.85.193): 56 data bytes
64 bytes from 172.16.85.193: seq=0 ttl=63 time=0.528 ms
64 bytes from 172.16.85.193: seq=1 ttl=63 time=0.162 ms
64 bytes from 172.16.85.193: seq=2 ttl=63 time=0.165 ms
^C
--- 172.16.85.193 ping statistics ---
3 packets transmitted, 3 packets received, 0% packet loss
round-trip min/avg/max = 0.162/0.285/0.528 ms

# 到这里都可以连通，证明这个pod是可以跨命名空间和跨主机通信的

16.5、验证负载均衡

#  在 任意 一台 node节点上 curl vip地址加端口 只要能获得版本信息，说明集群负载成功，请求数据流程是 curl > vip(haproxy) > apiserver

[root@k8s-node02 ~]# curl -k https://192.168.124.250:8443/version
{
  "major": "1",
  "minor": "25",
  "gitVersion": "v1.25.0",
  "gitCommit": "a866cbe2e5bbaa01cfd5e969aa3e033f3282a8a2",
  "gitTreeState": "clean",
  "buildDate": "2022-08-23T17:38:15Z",
  "goVersion": "go1.19",
  "compiler": "gc",
  "platform": "linux/amd64"
}

[root@k8s-node02 ~]# curl -k https://192.168.124.250:6443/version
{
  "major": "1",
  "minor": "25",
  "gitVersion": "v1.25.0",
  "gitCommit": "a866cbe2e5bbaa01cfd5e969aa3e033f3282a8a2",
  "gitTreeState": "clean",
  "buildDate": "2022-08-23T17:38:15Z",
  "goVersion": "go1.19",
  "compiler": "gc",
  "platform": "linux/amd64"
}

17、Prometheus监控k8s集群

# 在可以访问外网的机器上 ，下载该包，打包上传到内网机器或自己的虚机中
git clone -b release-0.10 https://github.com/prometheus-operator/kube-prometheus.git

#  需要提前把 镜像导入到本地，需要的镜像如下
docker pull registry.cn-wulanchabu.aliyuncs.com/moge1/kube-state-metrics:v2.3.0
docker pull quay.io/prometheus/node-exporter:v1.3.1
docker pull quay.io/prometheus/prometheus:v2.32.1
docker pull grafana/grafana:8.3.3
docker pull quay.io/prometheus/blackbox-exporter:v0.19.0
docker pull selina5288/prometheus-adapter:v0.9.1

在公网机器 提前把 镜像pull 下来重新打标签，生产环境中，打标签请根据自己镜像仓库来标记，我这里如下
registry.cn-beijing.aliyuncs.com/dotbalo/prometheus-adapter:v0.9.1
registry.cn-beijing.aliyuncs.com/dotbalo/node-exporter:v1.3.1
registry.cn-beijing.aliyuncs.com/dotbalo/prometheus:v2.32.1
registry.cn-beijing.aliyuncs.com/dotbalo/kube-state-metrics:v2.3.0
registry.cn-beijing.aliyuncs.com/dotbalo/grafana:8.3.3
registry.cn-beijing.aliyuncs.com/dotbalo/blackbox-exporter:v0.19.0

#  把镜像导入到本地 node 节点中
ctr -n=k8s.io image import registry.cn-beijing.aliyuncs.com/dotbalo/prometheus-adapter:v0.9.1
ctr -n=k8s.io image import registry.cn-beijing.aliyuncs.com/dotbalo/node-exporter:v1.3.1
ctr -n=k8s.io image import registry.cn-beijing.aliyuncs.com/dotbalo/prometheus:v2.32.1
ctr -n=k8s.io image import registry.cn-beijing.aliyuncs.com/dotbalo/kube-state-metrics:v2.3.0
ctr -n=k8s.io image import registry.cn-beijing.aliyuncs.com/dotbalo/grafana:8.3.3
ctr -n=k8s.io image import registry.cn-beijing.aliyuncs.com/dotbalo/blackbox-exporter:v0.19.0

17.1、创建命名空间

# 进入指定目录
cd /root/kube-prometheus/manifests
#  创建
kubectl create -f setup/

# 查看命名空间
kubectl get namespaces |grep monitoring   
NAME              STATUS   AGE
monitoring        Active   13m

17.2、修改指定配置文件

cd /root/kube-prometheus/manifests
 
# 生产环境下，需要调整alertmanager文件启动的副本数
vim alertmanager-alertmanager.yaml

 podMetadata:
    labels:
      app.kubernetes.io/component: alert-router
      app.kubernetes.io/instance: main
      app.kubernetes.io/name: alertmanager
      app.kubernetes.io/part-of: kube-prometheus
      app.kubernetes.io/version: 0.23.0
  replicas: 3                # 把这里的副本数改成3，就会自动组成高可用
  resources:
    limits:
      cpu: 100m
      memory: 100Mi

# 调整 prometheus-prometheus文件
vim prometheus-prometheus.yaml

 probeNamespaceSelector: {}
  probeSelector: {}
  replicas: 3                #  这里也改成3个副本数
  resources:
    requests:
      memory: 400Mi
  ruleNamespaceSelector: {}
  
 # 这里涉及修改镜像名称的文件一共有6个
prometheusAdapter-deployment.yaml
prometheus-prometheus.yaml
grafana-deployment.yaml
blackboxExporter-deployment.yaml
nodeExporter-daemonset.yaml
kubeStateMetrics-deployment.yaml
# 需要把原有yaml文件里的镜像名称 替换成你导入到本地node节点上的镜像名称，否则会加载不到镜像，这里不再演示

17.3、创建prometheus+grafana

#  在当前目录下 /root/kube-prometheus/manifests  创建所有
kubectl create -f .

#  查看pod 状态
kubectl get pods -n monitoring
NAME                                   READY   STATUS    RESTARTS   AGE
alertmanager-main-0                    2/2     Running   0          34m
alertmanager-main-1                    2/2     Running   0          34m
alertmanager-main-2                    2/2     Running   0          34m
blackbox-exporter-57c5ddc9f8-jpkm7     3/3     Running   0          35m
grafana-54db89877f-55hwc               1/1     Running   0          35m
kube-state-metrics-847d98796f-5kpss    3/3     Running   0          35m
node-exporter-8ds8k                    2/2     Running   0          35m
node-exporter-dg25g                    2/2     Running   0          35m
prometheus-adapter-58f76d4596-j2szt    1/1     Running   0          12m
prometheus-adapter-58f76d4596-wcdxq    1/1     Running   0          12m
prometheus-k8s-0                       2/2     Running   0          34m
prometheus-k8s-1                       2/2     Running   0          34m
prometheus-operator-5967d47854-82cx8   2/2     Running   0          35m

#  查看 grafana 端口
kubectl get svc grafana -n monitoring
NAME      TYPE        CLUSTER-IP      EXTERNAL-IP   PORT(S)    AGE
grafana   ClusterIP   10.96.250.180   <none>        3000/TCP   39m

#  修改grafana暴漏端口给外部
kubectl edit svc grafana -n monitoring

 sessionAffinity: None
  type: NodePort            #在最下面把clusterIP  改为 NodePort，保存退出即可
status:
  loadBalancer: {}

# 修改 prometheus暴漏端口
kubectl edit svc  prometheus-k8s -n monitoring

 clientIP:
      timeoutSeconds: 10800
  type: NodePort           #在最下面把clusterIP 改成 NodePort，保存退出
status:


#  查看暴漏外部的端口号，根据暴漏外部的端口号 在浏览器中访问
kubectl get svc   -n monitoring
NAME                    TYPE        CLUSTER-IP      EXTERNAL-IP   PORT(S)                         AGE
alertmanager-main       ClusterIP   10.96.247.73    <none>        9093/TCP,8080/TCP               67m
alertmanager-operated   ClusterIP   None            <none>        9093/TCP,9094/TCP,9094/UDP      66m
blackbox-exporter       ClusterIP   10.96.76.121    <none>        9115/TCP,19115/TCP              67m
grafana                 NodePort    10.96.250.180   <none>        3000:30763/TCP                  67m
kube-state-metrics      ClusterIP   None            <none>        8443/TCP,9443/TCP               67m
node-exporter           ClusterIP   None            <none>        9100/TCP                        67m
prometheus-adapter      ClusterIP   10.96.104.31    <none>        443/TCP                         67m
prometheus-k8s          NodePort    10.96.67.42     <none>        9090:32313/TCP,8080:30392/TCP   67m
prometheus-operated     ClusterIP   None            <none>        9090/TCP                        66m
prometheus-operator     ClusterIP   None            <none>        8443/TCP                        67m

17.4、访问grafana

在浏览器中，通过任意 一台 node 节点+端口 访问

http://192.168.124.253:30763/login

在界面依次点击General---Default 会出现各种自带的监控模板，当你选择NodeExporter/Nodes模板时 就会看到
由于我是Typora文档，这里上传的文章也没有截图，所以需要自己部署成功后去熟悉grafana

17.5、访问prometheus

http://192.168.124.254:32313/

通过暴漏的端口 访问prometheus自带的web ui界面

17.6、下载监控模板

由于自带的模板监控的信息有限，可以自己到下面地址去下载一些模板，这里下载模板ID为：8919

https://grafana.com/grafana/dashboards

在这个界面中 ，Data source 选择prometheus，在搜索node 就可以看到很多模板

具体的连接是：https://grafana.com/grafana/dashboards/8919-1-node-exporter-for-prometheus-dashboard-cn-0413-consulmanager/
点击 Download JSON 下载后，把json文件导入到grafana就可以，这里不再演示导入步骤，需要的可以自己去学习怎么导入创建

以上是整体部署成功过程，请你在部署前仔细过一遍文章或文档在去部署，因为很多刚学习k8s伙计直接上手就来，导致看文档部署还会出错，请注意细节，细节！

如果不想自己去下载安装包等镜像，下面是部署时用到的镜像以及安装包，百度网盘下载连接，总共大小1.3G，链接有效期30天

链接：https://pan.baidu.com/s/1xV4V_eGj3-KJN48gnySa8g 
提取码：8s2v 
 

# kubernetes # 容器 # 云原生
Logo
K8S/Kubernetes

K8S/Kubernetes社区为您提供最前沿的新闻资讯和知识内容

更多推荐

【深度】阿里巴巴万级规模 K8s 集群全局高可用体系之美

作者 |  韩堂、柘远、沉醉来源 | 阿里巴巴云原生公众号​前言台湾作家林清玄在接受记者采访的时候，如此评价自己 30 多年写作生涯：“第一个十年我才华横溢，‘贼光闪现’，令周边黯然失色；第二个十年，我终于‘宝光现形’，不再去抢风头，反而与身边的美丽相得益彰；进入第三个十年，繁华落尽见真醇，我进入了‘醇光初现’的阶段，真正体味到了境界之美”。​长夜有穷，真水无香。领略过了 K8s“身在江

avatar K8S/Kubernetes

如何基于 K8s 构建下一代 DevOps 平台？

作者 | 孙健波（天元）导读：当前云原生 DevOps 体系现状如何？面临哪些挑战？如何通过 OAM 解决云原生 DevOps 场景下的诸多问题？云原生开发应用模型 OAM(Open Application Model) 社区核心成员孙健波将为大家一一解答，并分享如何基于 OAM 和 Kubernetes 打造无限能力的下一代 DevOps 平台。什么是 DevOps？为什么基于 Kub

avatar K8S/Kubernetes

k8s 火了！

2020，上云之年，产品云端化成为一种趋势。在一线城市，很多公司都已经构建了自己的私有云环境，比如阿里云、网易云、华为云等。而Kubernetes 作为基于容器编排领域的王者，具备扩展...

avatar K8S/Kubernetes