搜索到
115
篇与
的结果
-
rocky linux 9 安装 多主架构 一、固定IP地址#配置 sudo nmcli connection modify ens160 \ ipv4.method manual \ ipv4.addresses 192.168.30.50/24 \ ipv4.gateway 192.168.30.2 \ ipv4.dns "8.8.8.8,8.8.4.4" #更新配置 sudo nmcli connection down ens160 && sudo nmcli connection up ens160二、准备工作 2.0 修改主机名#每个节点对应一个 hostnamectl set-hostname k8s-01 hostnamectl set-hostname k8s-02 hostnamectl set-hostname k8s-03#提前配好vip ip 三个节点都要做 cat >>/etc/hosts <<'EOF' 192.168.30.50 k8s-01 192.168.30.51 k8s-02 192.168.30.52 k8s-03 192.168.30.58 k8s-vip EOF2.1 配置yum源#sudo mkdir /etc/yum.repos.d/backup #sudo mv /etc/yum.repos.d/*.repo /etc/yum.repos.d/backup/ 直接执行下面的 # 使用阿里云推荐的配置方法 sudo sed -e 's!^mirrorlist=!#mirrorlist=!g' \ -e 's!^#baseurl=http://dl.rockylinux.org/$contentdir!baseurl=https://mirrors.aliyun.com/rockylinux!g' \ -i /etc/yum.repos.d/Rocky-*.repo #清理并重建缓存 sudo dnf clean all sudo dnf makecache #测试更新 sudo dnf -y update sudo dnf -y install wget curl vim tar gzip2.2设置时区#查看当前时区设置 timedatectl #设置时区为中国时区（上海时间） sudo timedatectl set-timezone Asia/Shanghai2.3设置时间#安装并配置 Chrony（推荐） # RHEL/CentOS/Alma/Rocky sudo dnf -y install chrony || sudo yum -y install chrony sudo systemctl enable --now chronyd # 编辑配置文件 sudo vi /etc/chrony.conf #把默认的 pool/server 行注释掉（没外网也无用），然后加入（或确认存在）以下内容： # 把 30.50 作为“本地时间源”，无外部上游时自成一体 local stratum 10 # 允许本网段客户端访问 allow 192.168.30.0/24 # 绑定监听到这块网卡（可选，但建议写上） bindaddress 192.168.30.50 # 客户端第一次偏差大时允许快速步进校时 makestep 1 3 # 用系统时钟做源，且把系统时间同步到硬件时钟（断电后也较准） rtcsync #保存重启 sudo systemctl restart chronyd #防火墙放行 # firewalld（RHEL系） sudo firewall-cmd --add-service=ntp --permanent sudo firewall-cmd --reload #验证服务器状态 # 查看 chrony 源与自我状态 chronyc tracking # 查看已连接的客户端（执行一会儿后能看到） chronyc clients # 确认监听 123/udp sudo ss -lunp | grep :123# 客户端安装 # RHEL系 sudo dnf -y install chrony || sudo yum -y install chrony # Debian/Ubuntu sudo apt -y install chrony # 配置（RHEL: /etc/chrony.conf；Ubuntu/Debian: /etc/chrony/chrony.conf） # 注释掉原来的 pool/server 行，新增： server 192.168.30.50 iburst # 重启并查看 sudo systemctl restart chronyd chronyc sources -v chronyc tracking2.4关闭swap分区sudo swapoff -a sudo sed -ri '/\sswap\s/s/^#?/#/' /etc/fstab2.5关闭selinuxsudo systemctl disable --now firewalld #推荐：保持 Enforcing（Kubernetes + containerd 在 RHEL9 系已支持），同时安装策略包： sudo dnf -y install container-selinux getenforce # 看到 Enforcing 即可 #图省事（不太安全）：设为 Permissive： sudo setenforce 0 sudo sed -i 's/^SELINUX=enforcing/SELINUX=permissive/' /etc/selinux/config2.6内核模块与 sysctl（所有节点）# 加载并持久化必须内核模块 cat <<'EOF' | sudo tee /etc/modules-load.d/k8s.conf overlay br_netfilter EOF sudo modprobe overlay sudo modprobe br_netfilter # 必备内核参数（转发与桥接） cat <<'EOF' | sudo tee /etc/sysctl.d/99-kubernetes-cri.conf net.bridge.bridge-nf-call-iptables = 1 net.bridge.bridge-nf-call-ip6tables = 1 net.ipv4.ip_forward = 1 EOF sudo sysctl --system #说明：RHEL9/ Rocky9 默认 cgroup v2，Kubernetes + containerd 完全支持，无需改动。2.7文件描述符（fd/ulimit）与进程数# 系统级最大打开文件数 cat > /etc/security/limits.d/k8s.conf <<EOF * soft nofile 65535 * hard nofile 131070 EOF ulimit -Sn ulimit -Hn2.8kube-proxy 的 IPVS 模式#安装 sudo dnf -y install ipset ipvsadm cat <<'EOF' | sudo tee /etc/modules-load.d/k8s.conf overlay br_netfilter # 如启用 IPVS，取消以下行的注释： ip_vs ip_vs_rr ip_vs_wrr ip_vs_sh nf_conntrack EOF # 立即加载 sudo modprobe overlay sudo modprobe br_netfilter # 如果要用 IPVS，再执行： for m in ip_vs ip_vs_rr ip_vs_wrr ip_vs_sh nf_conntrack; do sudo modprobe $m; done #验证模块 lsmod | egrep 'br_netfilter|ip_vs|nf_conntrack'三、安装containerd（所有k8s节点都要做） 3.1 使用阿里云的源sudo dnf config-manager --set-enabled powertools # Rocky Linux 8/9需启用PowerTools仓库 sudo dnf install -y yum-utils device-mapper-persistent-data lvm2 #1、卸载之前的 dnf remove docker docker-ce containerd docker-common docker-selinux docker-engine -y #2、准备repo sudo tee /etc/yum.repos.d/docker-ce.repo <<-'EOF' [docker-ce-stable] name=Docker CE Stable - AliOS baseurl=https://mirrors.aliyun.com/docker-ce/linux/centos/$releasever/$basearch/stable enabled=1 gpgcheck=1 gpgkey=https://mirrors.aliyun.com/docker-ce/linux/centos/gpg EOF # 3、安装 sudo dnf install -y containerd.io sudo dnf install containerd* -y3.2配置# 1、配置 mkdir -pv /etc/containerd containerd config default > /etc/containerd/config.toml #为containerd生成配置文件 #2、替换默认pause镜像地址:这一步非常非常非常非常重要 grep sandbox_image /etc/containerd/config.toml sudo sed -i 's|registry.k8s.io/pause:3.8|registry.cn-guangzhou.aliyuncs.com/xingcangku/registry.k8s.io-pause:3.8|g' /etc/containerd/config.toml grep sandbox_image /etc/containerd/config.toml #请务必确认新地址是可用的: sandbox_image = "registry.cn-guangzhou.aliyuncs.com/xingcangku/registry.k8s.io-pause:3.8" #3、配置systemd作为容器的cgroup driver grep SystemdCgroup /etc/containerd/config.toml sed -i 's/SystemdCgroup \= false/SystemdCgroup \= true/' /etc/containerd/config.toml grep SystemdCgroup /etc/containerd/config.toml # 4、配置加速器(必须配置，否则后续安装cni网络插件时无法从docker.io里下载镜像) #参考:https://github.com/containerd/containerd/blob/main/docs/cri/config.md#registry-configuration #添加 config_path="/etc/containerd/certs.d" sed -i 's/config_path\ =.*/config_path = \"\/etc\/containerd\/certs.d\"/g' /etc/containerd/config.tomlmkdir -p /etc/containerd/certs.d/docker.io cat>/etc/containerd/certs.d/docker.io/hosts.toml << EOF server ="https://docker.io" [host."https ://dockerproxy.com"] capabilities = ["pull","resolve"] [host."https://docker.m.daocloud.io"] capabilities = ["pull","resolve"] [host."https://docker.chenby.cn"] capabilities = ["pull","resolve"] [host."https://registry.docker-cn.com"] capabilities = ["pull","resolve" ] [host."http://hub-mirror.c.163.com"] capabilities = ["pull","resolve" ] EOF#5、配置containerd开机自启动 #5.1 启动containerd服务并配置开机自启动 systemctl daemon-reload && systemctl restart containerd systemctl enable --now containerd #5.2 查看containerd状态 systemctl status containerd #5.3查看containerd的版本 ctr version四、安装nginx+keepalived#安装与开启 dnf install -y nginx keepalived curl dnf install -y nginx-mod-stream systemctl enable nginx keepalived #配置 Nginx（两台 Master 都要配） #目标：在本机 0.0.0.0:16443 监听，转发到两个后端的 kube-apiserver（50:16443、51:16443） #编辑 /etc/nginx/nginx.conf（保留 http 段也没关系，关键是顶层加上 stream 段；Rocky9 的 nginx 支持动态模块）： # /etc/nginx/nginx.conf user nginx; worker_processes auto; error_log /var/log/nginx/error.log; pid /run/nginx.pid; # 使用系统提供的动态模块配置（若已安装将自动加载 stream 模块） include /usr/share/nginx/modules/*.conf; events { worker_connections 10240; } # 四层转发到两台 apiserver stream { upstream k8s_apiserver { server 192.168.30.50:6443 max_fails=3 fail_timeout=10s; server 192.168.30.51:6443 max_fails=3 fail_timeout=10s; } server { listen 0.0.0.0:16443; proxy_connect_timeout 5s; proxy_timeout 30s; proxy_pass k8s_apiserver; } } http { # 这里保持nginx默认 http 配置即可，删与不删均可。 include /etc/nginx/mime.types; default_type application/octet-stream; sendfile on; keepalive_timeout 65; server { listen 81; return 200 "ok\n"; } } #配置 Keepalived（两台 Master） #创建健康检查脚本 /etc/keepalived/check_nginx_kube.sh： cat >/etc/keepalived/check_nginx_kube.sh <<'EOF' #!/usr/bin/env bash # 通过本地Nginx转发口探活K8s apiserver（无认证的 /readyz，HTTP 200 即通过） curl -fsSk --connect-timeout 2 https://127.0.0.1:16443/readyz >/dev/null EOF chmod +x /etc/keepalived/check_nginx_kube.sh #Master1（192.168.30.50） 的 /etc/keepalived/keepalived.conf： ! Configuration File for keepalived global_defs { router_id LVS_K8S_50 # vrrp_strict # 若使用部分虚拟化/容器网络会引发问题，可注释掉 } vrrp_script chk_nginx_kube { script "/etc/keepalived/check_nginx_kube.sh" interval 3 timeout 2 fall 2 rise 2 weight -20 } vrrp_instance VI_1 { state BACKUP interface ens160 # 改为你的网卡 virtual_router_id 58 # 1-255 任意一致值，这里取 58 priority 150 # Master1 高优先 advert_int 1 # 单播，避免二层组播受限环境（强烈推荐） unicast_src_ip 192.168.30.50 unicast_peer { 192.168.30.51 } authentication { auth_type PASS auth_pass 9c9c58 } virtual_ipaddress { 192.168.30.58/24 dev ens160 } track_script { chk_nginx_kube } } #Master2（192.168.30.151） 的 /etc/keepalived/keepalived.conf： ! Configuration File for keepalived global_defs { router_id LVS_K8S_51 # vrrp_strict } vrrp_script chk_nginx_kube { script "/etc/keepalived/check_nginx_kube.sh" interval 3 timeout 2 fall 2 rise 2 weight -20 } vrrp_instance VI_1 { state BACKUP interface ens160 virtual_router_id 58 priority 100 # 次优先 advert_int 1 unicast_src_ip 192.168.30.51 unicast_peer { 192.168.30.50 } authentication { auth_type PASS auth_pass 9c9c58 } virtual_ipaddress { 192.168.30.58/24 dev ens160 } track_script { chk_nginx_kube } } #启动 systemctl restart keepalived ip a | grep 192.168.30.58 #停掉 Master1 的 keepalived：systemctl stop keepalived，VIP 应在 Master2 出现，验证完再 systemctl start keepalived。五、安装k8s 5.1 准备k8s源# 创建repo文件 cat <<EOF | sudo tee /etc/yum.repos.d/kubernetes.repo [kubernetes] name=Kubernetes baseurl=https://mirrors.aliyun.com/kubernetes/yum/repos/kubernetes-el7-x86_64/ enabled=1 gpgcheck=1 repo_gpgcheck=1 gpgkey=https://mirrors.aliyun.com/kubernetes/yum/doc/yum-key.gpg https://mirrors.aliyun.com/kubernetes/yum/doc/rpm-package-key.gpg EOF sudo dnf makecache #参考:https://developer.aliyun.com/mirror/kubernetes/setenforce dnf install -y kubelet-1.27* kubeadm-1.27* kubectl-1.27* systemctl enable kubelet && systemctl start kubelet && systemctl status kubelet 安装锁定版本的插件 sudo dnf install -y dnf-plugin-versionlock 锁定版本不让后续更新sudo dnf versionlock add kubelet-1.27* kubeadm-1.27* kubectl-1.27* containerd.io [root@k8s-01 ~]# sudo dnf versionlock list Last metadata expiration check: 0:35:21 ago on Fri Aug 8 10:40:25 2025. kubelet-0:1.27.6-0.* kubeadm-0:1.27.6-0.* kubectl-0:1.27.6-0.* containerd.io-0:1.7.27-3.1.el9.* #sudo dnf update就会排除锁定的应用5.2 主节点操作（node节点不执行）[root@k8s-01 ~]# kubeadm config images list I0906 16:16:30.198629 49023 version.go:256] remote version is much newer: v1.34.0; falling back to: stable-1.27 registry.k8s.io/kube-apiserver:v1.27.16 registry.k8s.io/kube-controller-manager:v1.27.16 registry.k8s.io/kube-scheduler:v1.27.16 registry.k8s.io/kube-proxy:v1.27.16 registry.k8s.io/pause:3.9 registry.k8s.io/etcd:3.5.7-0 registry.k8s.io/coredns/coredns:v1.10.1 kubeadm config print init-defaults > kubeadm.yaml[root@k8s-01 ~]# cat kubeadm.yaml # kubeadm-config.yaml apiVersion: kubeadm.k8s.io/v1beta3 kind: InitConfiguration bootstrapTokens: - token: abcdef.0123456789abcdef ttl: 24h0m0s usages: ["signing","authentication"] groups: ["system:bootstrappers:kubeadm:default-node-token"] localAPIEndpoint: # 这里必须是你要执行 kubeadm init 的这台机器的真实IP（Master1） advertiseAddress: 192.168.30.50 bindPort: 6443 nodeRegistration: criSocket: unix:///run/containerd/containerd.sock imagePullPolicy: IfNotPresent # 不要在这里硬编码 name，默认会用主机的 hostname，避免复用此文件时出错 taints: null --- apiVersion: kubeadm.k8s.io/v1beta3 kind: ClusterConfiguration clusterName: kubernetes kubernetesVersion: v1.27.16 controlPlaneEndpoint: "192.168.30.58:16443" # 指向 Nginx+Keepalived 的 VIP:PORT certificatesDir: /etc/kubernetes/pki imageRepository: registry.cn-hangzhou.aliyuncs.com/google_containers networking: dnsDomain: cluster.local serviceSubnet: 10.96.0.0/12 podSubnet: 10.244.0.0/16 # 供 Calico 使用，此网段可保持不变 apiServer: timeoutForControlPlane: 4m0s certSANs: # 建议把 VIP、两台 Master 的 IP 和主机名都放进 SAN，避免证书不信任 - "192.168.30.58" # VIP - "192.168.30.50" - "192.168.30.51" - "k8s-01" # 如你的主机名不同，请改成实际 hostname - "k8s-02" - "127.0.0.1" - "localhost" - "kubernetes" - "kubernetes.default" - "kubernetes.default.svc" - "kubernetes.default.svc.cluster.local" controllerManager: {} scheduler: {} etcd: local: dataDir: /var/lib/etcd --- apiVersion: kubeproxy.config.k8s.io/v1alpha1 kind: KubeProxyConfiguration mode: "ipvs" --- apiVersion: kubelet.config.k8s.io/v1beta1 kind: KubeletConfiguration cgroupDriver: "systemd"root@k8s-01 ~]# kubeadm init --config kubeadm.yaml --upload-certs [init] Using Kubernetes version: v1.27.16 [preflight] Running pre-flight checks [preflight] Pulling images required for setting up a Kubernetes cluster [preflight] This might take a minute or two, depending on the speed of your internet connection [preflight] You can also perform this action in beforehand using 'kubeadm config images pull' W0906 17:26:53.821977 54526 checks.go:835] detected that the sandbox image "registry.cn-guangzhou.aliyuncs.com/xingcangku/registry.k8s.io-pause:3.8" of the container runtime is inconsistent with that used by kubeadm. It is recommended that using "registry.cn-hangzhou.aliyuncs.com/google_containers/pause:3.9" as the CRI sandbox image. [certs] Using certificateDir folder "/etc/kubernetes/pki" [certs] Generating "ca" certificate and key [certs] Generating "apiserver" certificate and key [certs] apiserver serving cert is signed for DNS names [k8s-01 k8s-02 kubernetes kubernetes.default kubernetes.default.svc kubernetes.default.svc.cluster.local localhost] and IPs [10.96.0.1 192.168.30.50 192.168.30.58 192.168.30.51 127.0.0.1] [certs] Generating "apiserver-kubelet-client" certificate and key [certs] Generating "front-proxy-ca" certificate and key [certs] Generating "front-proxy-client" certificate and key [certs] Generating "etcd/ca" certificate and key [certs] Generating "etcd/server" certificate and key [certs] etcd/server serving cert is signed for DNS names [k8s-01 localhost] and IPs [192.168.30.50 127.0.0.1 ::1] [certs] Generating "etcd/peer" certificate and key [certs] etcd/peer serving cert is signed for DNS names [k8s-01 localhost] and IPs [192.168.30.50 127.0.0.1 ::1] [certs] Generating "etcd/healthcheck-client" certificate and key [certs] Generating "apiserver-etcd-client" certificate and key [certs] Generating "sa" key and public key [kubeconfig] Using kubeconfig folder "/etc/kubernetes" [kubeconfig] Writing "admin.conf" kubeconfig file [kubeconfig] Writing "kubelet.conf" kubeconfig file [kubeconfig] Writing "controller-manager.conf" kubeconfig file [kubeconfig] Writing "scheduler.conf" kubeconfig file [kubelet-start] Writing kubelet environment file with flags to file "/var/lib/kubelet/kubeadm-flags.env" [kubelet-start] Writing kubelet configuration to file "/var/lib/kubelet/config.yaml" [kubelet-start] Starting the kubelet [control-plane] Using manifest folder "/etc/kubernetes/manifests" [control-plane] Creating static Pod manifest for "kube-apiserver" [control-plane] Creating static Pod manifest for "kube-controller-manager" [control-plane] Creating static Pod manifest for "kube-scheduler" [etcd] Creating static Pod manifest for local etcd in "/etc/kubernetes/manifests" [wait-control-plane] Waiting for the kubelet to boot up the control plane as static Pods from directory "/etc/kubernetes/manifests". This can take up to 4m0s [apiclient] All control plane components are healthy after 12.002658 seconds [upload-config] Storing the configuration used in ConfigMap "kubeadm-config" in the "kube-system" Namespace [kubelet] Creating a ConfigMap "kubelet-config" in namespace kube-system with the configuration for the kubelets in the cluster [upload-certs] Storing the certificates in Secret "kubeadm-certs" in the "kube-system" Namespace [upload-certs] Using certificate key: 0574b43d75ac9722533a3a5042cb86b97441b855371cb34e5fdd3c8733a39d8d [mark-control-plane] Marking the node k8s-01 as control-plane by adding the labels: [node-role.kubernetes.io/control-plane node.kubernetes.io/exclude-from-external-load-balancers] [mark-control-plane] Marking the node k8s-01 as control-plane by adding the taints [node-role.kubernetes.io/control-plane:NoSchedule] [bootstrap-token] Using token: abcdef.0123456789abcdef [bootstrap-token] Configuring bootstrap tokens, cluster-info ConfigMap, RBAC Roles [bootstrap-token] Configured RBAC rules to allow Node Bootstrap tokens to get nodes [bootstrap-token] Configured RBAC rules to allow Node Bootstrap tokens to post CSRs in order for nodes to get long term certificate credentials [bootstrap-token] Configured RBAC rules to allow the csrapprover controller automatically approve CSRs from a Node Bootstrap Token [bootstrap-token] Configured RBAC rules to allow certificate rotation for all node client certificates in the cluster [bootstrap-token] Creating the "cluster-info" ConfigMap in the "kube-public" namespace [kubelet-finalize] Updating "/etc/kubernetes/kubelet.conf" to point to a rotatable kubelet client certificate and key [addons] Applied essential addon: CoreDNS [addons] Applied essential addon: kube-proxy Your Kubernetes control-plane has initialized successfully! To start using your cluster, you need to run the following as a regular user: mkdir -p $HOME/.kube sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config sudo chown $(id -u):$(id -g) $HOME/.kube/config Alternatively, if you are the root user, you can run: export KUBECONFIG=/etc/kubernetes/admin.conf You should now deploy a pod network to the cluster. Run "kubectl apply -f [podnetwork].yaml" with one of the options listed at: https://kubernetes.io/docs/concepts/cluster-administration/addons/ You can now join any number of the control-plane node running the following command on each as root: kubeadm join 192.168.30.58:6443 --token abcdef.0123456789abcdef \ --discovery-token-ca-cert-hash sha256:26d30a8cbfabc6d8a5b3965b9577a3ce33b01c4958a3e19fd001f06a0f3cb019 \ --control-plane --certificate-key 0574b43d75ac9722533a3a5042cb86b97441b855371cb34e5fdd3c8733a39d8d Please note that the certificate-key gives access to cluster sensitive data, keep it secret! As a safeguard, uploaded-certs will be deleted in two hours; If necessary, you can use "kubeadm init phase upload-certs --upload-certs" to reload certs afterward. Then you can join any number of worker nodes by running the following on each as root: kubeadm join 192.168.30.58:6443 --token abcdef.0123456789abcdef \ --discovery-token-ca-cert-hash sha256:26d30a8cbfabc6d8a5b3965b9577a3ce33b01c4958a3e19fd001f06a0f3cb019 #如果出现失败的情况 kubeadm reset -f [root@k8s-01 ~]# kubeadm reset -f [preflight] Running pre-flight checks W0906 17:08:03.892290 53705 removeetcdmember.go:106] [reset] No kubeadm config, using etcd pod spec to get data directory [reset] Deleted contents of the etcd data directory: /var/lib/etcd [reset] Stopping the kubelet service [reset] Unmounting mounted directories in "/var/lib/kubelet" W0906 17:08:03.899240 53705 cleanupnode.go:134] [reset] Failed to evaluate the "/var/lib/kubelet" directory. Skipping its unmount and cleanup: lstat /var/lib/kubelet: no such file or directory [reset] Deleting contents of directories: [/etc/kubernetes/manifests /etc/kubernetes/pki] [reset] Deleting files: [/etc/kubernetes/admin.conf /etc/kubernetes/kubelet.conf /etc/kubernetes/bootstrap-kubelet.conf /etc/kubernetes/controller-manager.conf /etc/kubernetes/scheduler.conf] The reset process does not clean CNI configuration. To do so, you must remove /etc/cni/net.d The reset process does not reset or clean up iptables rules or IPVS tables. If you wish to reset iptables, you must do so manually by using the "iptables" command. If your cluster was setup to utilize IPVS, run ipvsadm --clear (or similar) to reset your systems IPVS tables. The reset process does not clean your kubeconfig files and you must remove them manually. Please, check the contents of the $HOME/.kube/config file. #还需要手动删除 rm -rf /$HOME/.kube/config systemctl restart containerd rm -rf ~/.kube /etc/kubernetes/pki/* /etc/kubernetes/manifests/*#安装 CNI #Flannel（简单） kubectl apply -f https://raw.githubusercontent.com/flannel-io/flannel/v0.25.5/Documentation/kube-flannel.yml #Calico（功能更全） kubectl apply -f https://raw.githubusercontent.com/projectcalico/calico/v3.27.3/manifests/calico.yaml [root@k8s-02 ~]# kubectl get pod -A NAMESPACE NAME READY STATUS RESTARTS AGE kube-system calico-kube-controllers-59765c79db-rvqm5 1/1 Running 0 8m3s kube-system calico-node-4jlgw 1/1 Running 0 8m3s kube-system calico-node-lvzgx 1/1 Running 0 8m3s kube-system calico-node-qdrmn 1/1 Running 0 8m3s kube-system coredns-65dcc469f7-gktmx 1/1 Running 0 51m kube-system coredns-65dcc469f7-wmppd 1/1 Running 0 51m kube-system etcd-k8s-01 1/1 Running 0 51m kube-system etcd-k8s-02 1/1 Running 0 20m kube-system kube-apiserver-k8s-01 1/1 Running 0 51m kube-system kube-apiserver-k8s-02 1/1 Running 0 19m kube-system kube-controller-manager-k8s-01 1/1 Running 1 (20m ago) 51m kube-system kube-controller-manager-k8s-02 1/1 Running 0 19m kube-system kube-proxy-k7z9v 1/1 Running 0 22m kube-system kube-proxy-sgrln 1/1 Running 0 51m kube-system kube-proxy-wpkjb 1/1 Running 0 20m kube-system kube-scheduler-k8s-01 1/1 Running 1 (19m ago) 51m kube-system kube-scheduler-k8s-02 1/1 Running 0 19m #测试切换 #在当前 VIP 所在主机执行： systemctl stop keepalived #观察另外一台是否接管 VIP： ip a | grep 192.168.30.58 #再次访问： 正常会返回ok curl -k https://192.168.30.58:6443/readyz #恢复 vip会自动漂移回来 systemctl start keepalived#kubectl 正常 [root@k8s-01 ~]# kubectl get cs 2>/dev/null || \ kubectl get --raw='/readyz?verbose' | head NAME STATUS MESSAGE ERROR scheduler Healthy ok controller-manager Healthy ok etcd-0 Healthy -
容器化 + 上线到 K8s + 被 Prom 抓取 容器化 + 上线到 K8s + 被 Prom 抓取 目标：Exporter 以容器形式部署到集群，并被 Prometheus 抓取。 任务 构建镜像并 push：make docker IMG=…。 应用 k8s/deployment.yaml + Service；为你的命名空间调好 selector。 如果你集群用 Prometheus Operator，创建 ServiceMonitor 让它自动发现 scrape 目标。 Prometheus target 变为 Up，图表能看到你的新指标。 若用 Operator，ServiceMonitor 生效（label 选择器正确）。一、准备条件你有 Docker、kubectl 权限，能访问集群。 Harbor 私有仓库可用（如果是私有，需要在 K8s 里创建 imagePullSecret，步骤见第 4 步）。 Exporter 监听 0.0.0.0:9090 且有 /metrics（若没有，见“可选：最小 main.go”）。二、（可选）最小 main.go（若你项目还没暴露 /metrics）在你的可执行入口里加入（或新建 main.go）：package main import ( "log" "net/http" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus/collectors" "github.com/prometheus/client_golang/prometheus/promhttp" ) func main() { reg := prometheus.NewRegistry() reg.MustRegister(collectors.NewGoCollector(), collectors.NewProcessCollector(collectors.ProcessCollectorOpts{})) // TODO: 在这里注册你自己的指标 reg.MustRegister(yourMetric) mux := http.NewServeMux() mux.Handle("/metrics", promhttp.HandlerFor(reg, promhttp.HandlerOpts{})) //（若你有 /live、/ready 就更好） mux.HandleFunc("/live", func(w http.ResponseWriter, r *http.Request) { w.WriteHeader(200) }) mux.HandleFunc("/ready", func(w http.ResponseWriter, r *http.Request) { w.WriteHeader(200) }) log.Println("listening on :9090") log.Fatal(http.ListenAndServe(":9090", mux)) } 三、Dockerfile（多阶段构建，体积小、非 root 运行） 在项目根目录新建 Dockerfile：root@k8s-03:/woke/go-password-validator-main# cat Dockerfile # ---- build ---- FROM golang:1.23-alpine AS build WORKDIR /src COPY go.mod go.sum ./ RUN go mod download COPY . . # 如果入口在仓库根目录的 main.go： RUN CGO_ENABLED=0 GOOS=linux GOARCH=amd64 \ go build -ldflags="-s -w" -o /out/exporter . # ---- runtime ---- FROM gcr.io/distroless/static:nonroot USER nonroot:nonroot COPY --from=build /out/exporter /exporter EXPOSE 9090 ENTRYPOINT ["/exporter"] 四、Makefile 目标 在项目根目录的 Makefile 增加：root@k8s-03:/woke/go-password-validator-main# cat Makefile # ---------- 现有的目标，保留 ---------- test: go test ./... fmt: go fmt ./... vet: go vet ./... install-lint: # 建议用 go install（Go 1.16+） go install golang.org/x/lint/golint@latest @go env GOPATH >/dev/null lint: go list ./... | grep -v /vendor/ | xargs -L1 golint -set_exit_status install-staticcheck: go install honnef.co/go/tools/cmd/staticcheck@latest staticcheck: staticcheck -f stylish ./... # ---------- Docker 相关，新增 ---------- REGISTRY ?= 192.168.30.180:30003 REPO ?= test/go TAG ?= $(shell date +%Y%m%d-%H%M%S) IMG := $(REGISTRY)/$(REPO):$(TAG) .PHONY: docker docker-build docker-push docker: docker-build docker-push docker-build: docker build -t $(IMG) . docker-push: docker push $(IMG) 使用：# 登录你的 Harbor docker login harbor.example.com # 构建并 push（替换成你自己的 Harbor 项目/镜像名） make docker IMG=harbor.example.com/ops/go-password-exporter:v0.1.0 #如果配置好了Makefile文件 可以直接执行 make docker 也可以像上面这样定制五、Harbor 私有仓库拉取凭据（K8s imagePullSecret）注意：imagePullSecret 是命名空间级的，需要在哪个 ns 拉镜像，就在哪个 ns 创建；要全局通用只能在每个 ns 都创建（或用准入控制器自动注入）。#示例，在 monitoring 命名空间创建： kubectl -n monitoring create secret docker-registry harbor-cred \ --docker-server=192.168.30.180:30003 \ --docker-username='admin' \ --docker-password='Harbor12345' \ --docker-email='ops@example.com' 六、部署到 K8s（Deployment + Service）#deployment.yaml apiVersion: apps/v1 kind: Deployment metadata: name: pass-validator-exporter namespace: monitoring labels: app.kubernetes.io/name: pass-validator-exporter spec: replicas: 1 selector: matchLabels: app.kubernetes.io/name: pass-validator-exporter template: metadata: labels: app.kubernetes.io/name: pass-validator-exporter spec: imagePullSecrets: - name: harbor-cred containers: - name: exporter image: 192.168.30.180:30003/test/go:20250905-154053 imagePullPolicy: IfNotPresent ports: - name: http containerPort: 9090 readinessProbe: httpGet: { path: /ready, port: http } initialDelaySeconds: 3 periodSeconds: 5 livenessProbe: httpGet: { path: /live, port: http } initialDelaySeconds: 10 periodSeconds: 10 resources: requests: { cpu: "50m", memory: "64Mi" } limits: { cpu: "200m", memory: "128Mi" } securityContext: allowPrivilegeEscalation: false readOnlyRootFilesystem: true runAsNonRoot: true runAsUser: 65532#service.yaml apiVersion: v1 kind: Service metadata: name: pass-validator-exporter namespace: monitoring labels: app.kubernetes.io/name: pass-validator-exporter # 若你是“裸 Prometheus + 注解发现”，可打开以下注解： # annotations: # prometheus.io/scrape: "true" # prometheus.io/path: "/metrics" # prometheus.io/port: "9090" spec: type: ClusterIP selector: app.kubernetes.io/name: pass-validator-exporter ports: - name: http port: 9090 targetPort: http kubectl apply -f k8s/deployment.yaml kubectl apply -f k8s/service.yaml # 验证： kubectl -n monitoring get pods -l app.kubernetes.io/name=pass-validator-exporter -w kubectl -n monitoring get svc pass-validator-exporter # 本地看指标（可选）： kubectl -n monitoring port-forward svc/pass-validator-exporter 19090:9090 curl http://127.0.0.1:19090/metrics | head七、让 Prometheus 抓取方案 A：你在用 Prometheus Operator / kube-prometheus-stack（推荐） 关键点：ServiceMonitor 的 selector 要能匹配到 Service 的 label；同时 ServiceMonitor 自己的 label 要匹配到 Prometheus 实例的 serviceMonitorSelector。大多数 Helm 安装用的 label 是 release: kube-prometheus-stack（按你的集群实际为准）。# 看 Prometheus 实例的 selector 要求（取第一个 Prometheus 资源） kubectl -n monitoring get prometheus -o jsonpath='{.items[0].spec.serviceMonitorSelector.matchLabels}{"\n"}' # 一般会看到 {"release":"<你的 Helm release 名>"}#创建 servicemonitor.yaml 如果上面没有查到直接删除 labels: # release: kube-prometheus-stack # ←改成你 Prometheus 实例在选的那个 label apiVersion: monitoring.coreos.com/v1 kind: ServiceMonitor metadata: name: pass-validator-exporter namespace: monitoring labels: release: kube-prometheus-stack # ←改成你 Prometheus 实例在选的那个 label spec: namespaceSelector: matchNames: ["monitoring"] selector: matchLabels: app.kubernetes.io/name: pass-validator-exporter # 要和 Service 的 label 完全一致 endpoints: - port: http # 要和 Service 端口名一致 path: /metrics interval: 15s scrapeTimeout: 10s#应用并验证： kubectl apply -f servicemonitor.yaml # 在 Prometheus UI -> Status -> Targets 里应该出现你的 target，并且是 UP。 #启动pod测试集群内获取是否正常 kubectl -n monitoring run tmp-curl --rm -it --image=curlimages/curl --restart=Never \ -- http://pass-validator-exporter.monitoring.svc:9090/metrics | head #可以在浏览器IP+端口访问 kubectl -n monitoring port-forward --address 0.0.0.0 svc/prometheus-k8s 9090:9090方案 B：裸 Prometheus（没装 Operator）你需要在 Prometheus 的 prometheus.yml 里启用 kubernetes_sd_configs，并用注解过滤（上面 Service 已给注解示例）。典型片段如下（放到你的 scrape_configs 里）：- job_name: 'kubernetes-services' kubernetes_sd_configs: - role: endpoints relabel_configs: - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape] action: keep regex: "true" - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path] action: replace target: __metrics_path__ regex: "(.+)" - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port] action: replace target: __address__ regex: (.+?)(?::\d+)?;(\d+) replacement: $1:$2 #改好配置后重启 Prometheus，去 Targets 看是否 UP。八、迭代上线（改代码后快速发版）# 1) 构建并推送新镜像 make docker IMG=harbor.example.com/ops/go-password-exporter:v0.1.1 # 2) 滚动更新 Deployment（或直接改 yaml） kubectl -n monitoring set image deploy/pass-validator-exporter exporter=harbor.example.com/ops/go-password-exporter:v0.1.1 kubectl -n monitoring rollout status deploy/pass-validator-exporter 九、验收清单Prometheus Targets 里看到 pass-validator-exporter → UP。 在 Prometheus 或 Grafana 中能查询到你的新指标（例如：your_metric_name）。 如果是 Operator：ServiceMonitor 的 labels.release 与 Prometheus 实例选择器 匹配；ServiceMonitor.spec.selector.matchLabels 与 Service 的 labels 匹配；endpoints.port 与 Service 端口名 一致。十、常见坑速查镜像拉不下来：Deployment 没配置 imagePullSecrets，或 secret 在错的命名空间。 Target 一直 DOWN：容器没监听 0.0.0.0；端口/路径不一致；Service 选择器写错；endpoints.port 名字不对。 Operator 抓不到：ServiceMonitor 的 labels 与 Prometheus 的 serviceMonitorSelector 不匹配。 /metrics 超时：指标收集阻塞（锁/IO）；建议拆分收集逻辑并设置 scrapeTimeout。 权限：Exporter 是 HTTP 只读，不需要额外 RBAC。
-
rocky-linux-9离线安装k8s 1.27 一、阶段 A：在「有网打包机」制作离线包打包机推荐同为 Rocky 9；也可用任意 x86_64 Linux。以下默认使用 dnf 和 ctr/docker 二选一抓镜像。1.1 目录与变量export K8S_VER="1.27.16" export K8S_MINOR="v1.27" export WORK="/opt/k8s-offline-${K8S_VER}" sudo mkdir -p $WORK/{rpms,images,cni,calico,tools}1.2 配置 Kubernetes 1.27 专属 RPM 仓库（仅打包机临时用）#/etc/yum.repos.d/kubernetes-1.27.repo [kubernetes-1.27] name=Kubernetes 1.27 baseurl=https://pkgs.k8s.io/core:/stable:/v1.27/rpm/ enabled=1 gpgcheck=1 gpgkey=https://pkgs.k8s.io/core:/stable:/v1.27/rpm/repodata/repomd.xml.keyKubernetes 从 2023 起使用 pkgs.k8s.io 的分小版本仓库，上面这个是 1.27 专用源。1.3 下载 RPM（含依赖，供离线节点安装）sudo dnf -y install dnf-plugins-core # containerd / runc / 常用依赖 sudo dnf -y download --resolve --destdir=$WORK/rpms \ containerd runc conntrack-tools iptables iproute-tc ethtool socat \ tar openssl curl bash-completion #Rocky 默认仓库里没有叫 containerd 的包，所以 dnf download 在严格模式下直接退出了 所以要加下面这步 # 安装 dnf 插件并添加 Docker CE 源（RHEL/EL9 适用） sudo dnf -y install dnf-plugins-core sudo dnf config-manager --add-repo https://download.docker.com/linux/rhel/docker-ce.repo # 更新元数据 sudo dnf clean all && sudo dnf makecache # kube 组件（固定 1.27.16） #sudo dnf -y download --resolve --destdir=$WORK/rpms \ #kubelet-${K8S_VER} kubeadm-${K8S_VER} kubectl-${K8S_VER} \ #kubernetes-cni cri-tools #上面别用 # 仅下载，不解析依赖 sudo dnf -y download --destdir="$WORK/rpms" \ kubelet-${K8S_VER} kubeadm-${K8S_VER} kubectl-${K8S_VER} \ kubernetes-cni cri-tools1.4 下载 CNI 插件与 crictl 工具# CNI plugins（官方二进制包，放到 /opt/cni/bin） curl -L -o $WORK/cni/cni-plugins-linux-amd64-v1.3.0.tgz \ https://github.com/containernetworking/plugins/releases/download/v1.3.0/cni-plugins-linux-amd64-v1.3.0.tgz # crictl（来自 cri-tools） CRICTL_VER="v1.27.0" # 与集群兼容即可 curl -L -o $WORK/tools/crictl-${CRICTL_VER}-linux-amd64.tar.gz \ https://github.com/kubernetes-sigs/cri-tools/releases/download/${CRICTL_VER}/crictl-${CRICTL_VER}-linux-amd64.tar.gz1.5 下载 Calico 清单与镜像curl -L -o $WORK/calico/calico-v3.26.4.yaml \ https://raw.githubusercontent.com/projectcalico/calico/v3.26.4/manifests/calico.yaml # 提取镜像名（也可手工列出） grep -E "image: .*calico" $WORK/calico/calico-v3.26.4.yaml | awk '{print $2}' | sort -u > $WORK/images/calico-images.txt [root@localhost ~]# cat $WORK/images/calico-images.txt docker.io/calico/cni:v3.26.4 docker.io/calico/kube-controllers:v3.26.4 docker.io/calico/node:v3.26.4 1.6 生成 kubeadm 所需镜像清单（精确到 v1.27.16）# 本机先临时装 kubeadm（或用容器）来打印镜像列表 sudo dnf -y install kubeadm-${K8S_VER} kubeadm config images list --kubernetes-version v${K8S_VER} > $WORK/images/k8s-images.txt #kubeadm config images list 是官方推荐获取离线镜像列表的方式；也支持 --config 指定自定义仓库。1.7 拉取并打包镜像（二选一：有 Docker 或有 containerd）# 方式 A：Docker while read -r img; do docker pull "$img"; done < $WORK/images/k8s-images.txt while read -r img; do docker pull "$img"; done < $WORK/images/calico-images.txt docker save $(cat $WORK/images/k8s-images.txt $WORK/images/calico-images.txt) \ -o $WORK/images/k8s-${K8S_VER}-and-calico-v3.26.4.tar # 方式 B：containerd（ctr） sudo systemctl enable --now containerd || true while read -r img; do sudo ctr -n k8s.io i pull "$img"; done < $WORK/images/k8s-images.txt while read -r img; do sudo ctr -n k8s.io i pull "$img"; done < $WORK/images/calico-images.txt sudo ctr -n k8s.io i export $WORK/images/k8s-${K8S_VER}-and-calico-v3.26.4.tar $(cat $WORK/images/k8s-images.txt $WORK/images/calico-images.txt) 1.8 打总包cd $(dirname $WORK) sudo tar czf k8s-offline-${K8S_VER}-rocky9.tar.gz $(basename $WORK) # 把这个 tar.gz 拷贝到所有离线节点（控制面/工作节点） 二、docker安装离线包 2.1在线机器上打离线包# 0) 变量 export WORK="/opt/docker-offline-$(date +%F)" sudo mkdir -p "$WORK"/{rpms,images,scripts} ARCH=$(uname -m) # 一般是 x86_64；如是 ARM64 则为 aarch64 # 1) 加 Docker 官方仓库（RHEL/EL 系列通用，Rocky 9 适用） sudo dnf -y install dnf-plugins-core sudo dnf config-manager --add-repo https://download.docker.com/linux/rhel/docker-ce.repo sudo dnf clean all && sudo dnf makecache # 2) 下载“完整功能”所需 RPM（含依赖） PKGS="docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin docker-ce-rootless-extras" # 用 --resolve 拉全依赖；若个别包临时不可用，strict=0 可跳过不中断 sudo dnf -y download --resolve --setopt=strict=0 \ --destdir="$WORK/rpms" --arch="$ARCH" $PKGS # 同时把 Rootless 相关常见依赖也一并打包（如尚未被上面带下） sudo dnf -y download --resolve --setopt=strict=0 \ --destdir="$WORK/rpms" --arch="$ARCH" \ slirp4netns fuse-overlayfs container-selinux # 3)（可选）打基础测试镜像离线包 docker pull hello-world:latest docker pull alpine:latest docker pull busybox:stable docker save hello-world:latest alpine:latest busybox:stable -o "$WORK/images/docker-base-images.tar" # 4) 生成本地仓库元数据 + 安装脚本 sudo dnf -y install createrepo_c createrepo_c "$WORK/rpms" cat > "$WORK/scripts/install-offline.sh" <<"EOF" #!/usr/bin/env bash set -euo pipefail DIR="$(cd "$(dirname "$0")"/.. && pwd)" # 临时本地仓库安装方法（更稳妥） sudo dnf -y install createrepo_c || true sudo createrepo_c "$DIR/rpms" sudo tee /etc/yum.repos.d/docker-offline.repo >/dev/null <<REPO [docker-offline] name=Docker Offline baseurl=file://$DIR/rpms enabled=1 gpgcheck=0 REPO # 安装 sudo dnf -y install docker-ce docker-ce-cli containerd.io \ docker-buildx-plugin docker-compose-plugin docker-ce-rootless-extras # 启动并开机自启 sudo systemctl enable --now docker # 可选：把当前用户加入 docker 组（需要重新登录生效） if id -u "$SUDO_USER" &>/dev/null; then sudo usermod -aG docker "$SUDO_USER" || true fi # 导入基础镜像（如存在） if [ -f "$DIR/images/docker-base-images.tar" ]; then sudo docker load -i "$DIR/images/docker-base-images.tar" fi echo "Done. Check: docker version && docker compose version && docker buildx version" EOF chmod +x "$WORK/scripts/install-offline.sh" # 5) 打一个总包 sudo tar -C "$(dirname "$WORK")" -czf "${WORK}.tar.gz" "$(basename "$WORK")" echo "离线包已生成：${WORK}.tar.gz" 2.2 离线机器上安装#把 ${WORK}.tar.gz 拷贝到离线主机，解压并执行脚本： sudo tar -C /opt -xzf /path/to/docker-offline-*.tar.gz cd /opt/docker-offline-*/scripts #sudo ./install-offline.sh sudo dnf -y --disablerepo='*' --nogpgcheck install \ /opt/docker-offline-2025-09-01/rpms/*.rpm # 重新登录后验证 docker version [root@localhost opt]# docker version Client: Docker Engine - Community Version: 28.3.3 API version: 1.51 Go version: go1.24.5 Git commit: 980b856 Built: Fri Jul 25 11:36:28 2025 OS/Arch: linux/amd64 Context: default Server: Docker Engine - Community Engine: Version: 28.3.3 API version: 1.51 (minimum version 1.24) Go version: go1.24.5 Git commit: bea959c Built: Fri Jul 25 11:33:28 2025 OS/Arch: linux/amd64 Experimental: false containerd: Version: 1.7.27 GitCommit: 05044ec0a9a75232cad458027ca83437aae3f4da runc: Version: 1.2.5 GitCommit: v1.2.5-0-g59923ef docker-init: Version: 0.19.0 GitCommit: de40ad0 docker compose version # 注意：是 docker compose（v2 插件），不是老的 docker-compose docker run --rm hello-world三、阶段 B：在「离线节点」安装与初始化 3.1 系统准备（所有节点）sudo tar xzf k8s-offline-1.27.16-rocky9.tar.gz -C / OFF="/opt/k8s-offline-1.27.16" hostnamectl set-hostname k8s-01 echo "192.168.30.150 k8s-01" >> /etc/hosts ping -c1 k8s-01swapoff -a sed -ri 's/^\s*([^#].*\sswap\s)/#\1/' /etc/fstab cat >/etc/sysctl.d/k8s.conf <<'EOF' net.ipv4.ip_forward=1 net.bridge.bridge-nf-call-iptables=1 net.bridge.bridge-nf-call-ip6tables=1 EOF sysctl --system #先加载 IPVS 内核模块 cat >/etc/modules-load.d/ipvs.conf <<'EOF' ip_vs ip_vs_rr ip_vs_wrr ip_vs_sh nf_conntrack EOF for m in ip_vs ip_vs_rr ip_vs_wrr ip_vs_sh nf_conntrack; do modprobe $m; done 3.1.1 关闭 swap（含 zram）#Rocky 9 默认启用 zram，kubelet 需要禁用 swap： sudo swapoff -a # 永久：卸载 zram 生成器或禁用其单元 sudo dnf -y remove zram-generator-defaults || true # 如有 /etc/fstab 的 swap 条目，注释掉；并确认: lsblk | grep -E 'SWAP|zram' || true #RHEL9/基于 systemd 的发行版一般通过 zram-generator 提供 swap；禁用/移除是官方建议之一。 3.1.2 内核模块与 sysctl（bridge/overlay/IP 转发）# /etc/modules-load.d/k8s.conf echo -e "overlay\nbr_netfilter" | sudo tee /etc/modules-load.d/k8s.conf sudo modprobe overlay && sudo modprobe br_netfilter # /etc/sysctl.d/k8s.conf cat <<'EOF' | sudo tee /etc/sysctl.d/k8s.conf net.bridge.bridge-nf-call-iptables = 1 net.bridge.bridge-nf-call-ip6tables = 1 net.ipv4.ip_forward = 1 EOF sudo sysctl --system #（这些设置是 Kubernetes 官方与 Fedora/Rocky 指南里明确要求的） 3.1.3 SELinux 与防火墙1. 建议保留 SELinux Enforcing（若遇容器标记问题可先设为 Permissive 再排障）。 2. 防火墙可开放必要端口或临时停用；端口清单见官方“Ports and Protocols”。至少： 控制面：6443/TCP（API）、2379-2380/TCP（etcd）、10250/10257/10259/TCP 所有节点：10250/TCP；CNI 端口（如 Calico VXLAN 默认 4789/UDP）等按 CNI 文档配置。3.2 安装 RPM（离线目录直接安装）cd $OFF/rpms sudo dnf -y --disablerepo='*' install ./*.rpm sudo systemctl enable --now containerd #（--disablerepo='*' 可避免 dnf 去查线上元数据，离线时很有用）3.2.1 安装 CNI 与 crictlsudo mkdir -p /opt/cni/bin sudo tar -xzf $OFF/cni/cni-plugins-linux-amd64-v1.3.0.tgz -C /opt/cni/bin sudo tar -xzf $OFF/tools/crictl-v1.27.0-linux-amd64.tar.gz -C /usr/local/bin3.3配置 containerd（systemd cgroup & pause 镜像）# 生成默认配置后修改 mkdir -p /etc/containerd containerd config default > /etc/containerd/config.toml # 关键点：设置 SystemdCgroup=true，并确保 sandbox_image 使用我们已导入的 pause:3.9 sudo sed -i 's/SystemdCgroup = false/SystemdCgroup = true/' /etc/containerd/config.toml sudo sed -i 's@sandbox_image = .*@sandbox_image = "registry.k8s.io/pause:3.9"@' /etc/containerd/config.toml #打开 /etc/containerd/config.toml，确保这几处： disabled_plugins = [] #如果看到 io.containerd.grpc.v1.cri 出现在 disabled_plugins 里，删掉它。 #存在并启用 CRI 插件段落（一般默认就有）： [plugins."io.containerd.grpc.v1.cri"] # 这里还有一堆子配置，保持默认即可 #kubelet 要求 systemd cgroup，改成： [plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc.options] SystemdCgroup = true #建议把 pause 镜像固定为 3.9（1.27.x 对应）： [plugins."io.containerd.grpc.v1.cri"] sandbox_image = "registry.k8s.io/pause:3.9" # 离线或私有仓库环境就改成你的地址，比如： # sandbox_image = "192.168.30.150:5000/pause:3.9" #打开 /etc/containerd/config.toml，确认/修改以下几处（都在同一文件里）： # 顶部：不要禁用 CRI disabled_plugins = [] # ← 把 ["cri"] 改成 []，或直接删掉此行 version = 2 # 如果模板没有这一行，建议加上 [plugins."io.containerd.grpc.v1.cri"] sandbox_image = "registry.k8s.io/pause:3.9" # 你已离线导入了这个镜像，正好保持一致 # 如用私有仓库，写成 "你的仓库/pause:3.9" [plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc] runtime_type = "io.containerd.runc.v2" [plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc.options] SystemdCgroup = true # kubelet 要求 systemd cgroup #重启并自检 systemctl daemon-reload systemctl enable --now containerd #kubectl暂时不用启动 等kubeadm启动 systemctl status containerd --no-pager -l #确认 CRI 插件已加载（任一条有结果即可）： ctr plugins ls | grep cri # 期望看到 io.containerd.grpc.v1.cri <OK> # 或者 crictl --runtime-endpoint unix:///run/containerd/containerd.sock info # 能输出 runtimeName 等信息即 OK；若没装 crictl 可跳过 sudo systemctl restart containerd #（K8s 在 RHEL9/cgroup v2 上推荐 systemd cgroup 驱动；containerd 侧需显式开启3.4 预载镜像（离线导入）sudo ctr -n k8s.io images import $OFF/images/k8s-1.27.16-and-calico-v3.26.4.tar sudo ctr -n k8s.io images ls | grep -E 'kube-|coredns|etcd|pause|calico' 3.5 kubeadm 初始化（控制面节点）创建 kubeadm-config.yaml（按需改 advertiseAddress、Pod/Service 网段；Calico 习惯 192.168.0.0/16）：# kubeadm-config.yaml [root@k8s-01 ~]# cat kubeadm.yaml # kubeadm-config.yaml apiVersion: kubeadm.k8s.io/v1beta3 kind: InitConfiguration localAPIEndpoint: advertiseAddress: 192.168.30.150 bindPort: 6443 nodeRegistration: criSocket: unix:///run/containerd/containerd.sock imagePullPolicy: IfNotPresent --- apiVersion: kubeadm.k8s.io/v1beta3 kind: ClusterConfiguration clusterName: kubernetes kubernetesVersion: v1.27.16 imageRepository: registry.k8s.io networking: serviceSubnet: 10.96.0.0/12 podSubnet: 172.20.0.0/16 --- apiVersion: kubeproxy.config.k8s.io/v1alpha1 kind: KubeProxyConfiguration mode: ipvs --- apiVersion: kubelet.config.k8s.io/v1beta1 kind: KubeletConfiguration cgroupDriver: systemd 下面是开启ipvs apiVersion: kubeadm.k8s.io/v1beta3 kind: InitConfiguration localAPIEndpoint: advertiseAddress: 192.168.30.151 # ← 改成本机控制面IP bindPort: 6443 nodeRegistration: criSocket: unix:///run/containerd/containerd.sock imagePullPolicy: IfNotPresent --- apiVersion: kubeadm.k8s.io/v1beta3 kind: ClusterConfiguration clusterName: kubernetes kubernetesVersion: v1.27.16 imageRepository: registry.k8s.io # 离线/内网镜像时改成你的私仓 networking: serviceSubnet: 10.96.0.0/12 podSubnet: 172.20.0.0/16 # 要与 Calico 使用的网段一致（你现在就是用这个） dns: type: CoreDNS --- apiVersion: kubeproxy.config.k8s.io/v1alpha1 kind: KubeProxyConfiguration mode: ipvs ipvs: scheduler: rr # 可选：rr / wrr / wlc / sh / mh 等 # strictARP: true # 以后用 MetalLB L2 时再打开 --- apiVersion: kubelet.config.k8s.io/v1beta1 kind: KubeletConfiguration cgroupDriver: systemd# 0) 主机名解析（避免之前的 hostname 警告） hostnamectl set-hostname k8s-01 grep -q '192.168.30.150 k8s-01' /etc/hosts || echo '192.168.30.150 k8s-01' >> /etc/hosts # 1) 关闭 swap（若未关） swapoff -a sed -ri 's/^\s*([^#].*\sswap\s)/#\1/' /etc/fstab # 2) 必要内核 & sysctl（kubelet 常见阻塞点） modprobe br_netfilter || true cat >/etc/modules-load.d/k8s.conf <<'EOF' br_netfilter EOF cat >/etc/sysctl.d/k8s.conf <<'EOF' net.bridge.bridge-nf-call-iptables=1 net.bridge.bridge-nf-call-ip6tables=1 net.ipv4.ip_forward=1 EOF sysctl --system # 3) （可选）避免策略阻塞：SELinux/防火墙（离线/内网先松） setenforce 0 2>/dev/null || true sed -i 's/^SELINUX=enforcing/SELINUX=permissive/' /etc/selinux/config 2>/dev/null || true systemctl disable --now firewalld 2>/dev/null || true # 4) 重启关键服务 systemctl restart containerd systemctl restart kubelet # 5) 再次观察 crictl --runtime-endpoint /run/containerd/containerd.sock ps -a | egrep 'kube-(apiserver|controller-manager|scheduler)|etcd' journalctl -u kubelet -e --no-pager | tail -n 200 #执行初始化： sudo kubeadm init --config kubeadm-config.yaml #初始化离线 不联网 kubeadm init --config kubeadm.yaml --upload-certs -v=5 # 成功后配置 kubectl mkdir -p $HOME/.kube sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config sudo chown $(id -u):$(id -g) $HOME/.kube/configsudo systemctl disable --now firewalld || true # 立刻加载模块 sudo modprobe overlay && sudo modprobe br_netfilter # 持久化 echo -e "overlay\nbr_netfilter" | sudo tee /etc/modules-load.d/k8s.conf # 必要 sysctl sudo tee /etc/sysctl.d/k8s.conf >/dev/null <<'EOF' net.ipv4.ip_forward = 1 net.bridge.bridge-nf-call-iptables = 1 net.bridge.bridge-nf-call-ip6tables = 1 EOF sudo sysctl --system # 快速确认三项都为 1 sysctl net.ipv4.ip_forward sysctl net.bridge.bridge-nf-call-iptables sysctl net.bridge.bridge-nf-call-ip6tables 安装 Calico（离线文件）： kubectl apply -f $OFF/calico/calico-v3.26.4.yaml kubectl -n kube-system get pods -w mkdir -p $HOME/.kube cp -i /etc/kubernetes/admin.conf $HOME/.kube/config chown $(id -u):$(id -g) $HOME/.kube/config kubectl get pods -n kube-system -o wide kubectl get nodes -o wide #kubelet 开机自启（kubeadm 已临时启动，设为自启更规范） systemctl enable --now kubelet #配好 kubectl，并验证控制面 # 生成过 admin.conf 的话（kubeadm 已经写过） [ -f /etc/kubernetes/admin.conf ] && { mkdir -p $HOME/.kube cp -i /etc/kubernetes/admin.conf $HOME/.kube/config chown $(id -u):$(id -g) $HOME/.kube/config } kubectl cluster-info kubectl get pods -n kube-system -o wide kubectl get nodes -o wide # 现在控制面起来了，但在装 CNI 前 Node 可能是 NotReady #如果意外没有 /etc/kubernetes/admin.conf（极少数情况），可补一条： kubeadm init phase kubeconfig admin #加载 IPVS 内核模块（你 kube-proxy 设了 ipvs） modprobe ip_vs ip_vs_rr ip_vs_wrr ip_vs_sh nf_conntrack cat >/etc/modules-load.d/ipvs.conf <<'EOF' ip_vs ip_vs_rr ip_vs_wrr ip_vs_sh nf_conntrack EOF #安装你的 CNI（Calico 离线） 确保清单里 CALICO_IPV4POOL_CIDR 与你 kubeadm 的 podSubnet: 172.20.0.0/16 一致。 你本地已导入镜像 calico/node|cni|kube-controllers:v3.26.4，直接套用离线 calico.yaml 即可： kubectl apply -f /path/to/calico.yaml kubectl -n kube-system get pods -w # 等 calico-*、coredns、kube-proxy 全部 Running kubectl get nodes # 状态应变为 Ready 3.6 加入工作节点#在每个工作节点重复 系统准备/安装 RPM/导入镜像 的步骤，然后在控制面上生成 join 命令： [root@k8s-01 ~]# kubeadm token create --print-join-command kubeadm join 192.168.30.150:6443 --token fnturx.ph8jg99zgdmze81w --discovery-token-ca-cert-hash sha256:1ef5e1f3558c8f9336dd4785c0207cb837cceb37c253179e9988f03dc0c00146 #把输出的 kubeadm join ... 在各工作节点执行即可。 #拿到的命令在每个 worker 上执行即可加入集群。 #若以后要加 额外控制面节点，再执行： kubeadm init phase upload-certs --skip-certificate-key-print kubeadm token create --print-join-command --certificate-key <上一步输出的key> #持久化服务 systemctl enable --now kubelet systemctl enable --now containerd
-
利用公有云访问内网k8s集群 一、准备条件和安装wireguard1.需要一台有公网IP的机器 公有云也行 2.k8s集群有traefik或者inginx 3.两边都要安装wireguard 4.准备一个域名解析到公有云IP root@k8s-01:~# dnf install -y wireguard #dnf install -y wireguard-tools二、创建公钥秘钥#两个秘钥privatekey(私钥)publickey(公钥) wg genkey | tee /etc/wireguard/privatekey | wg pubkey > /etc/wireguard/publickey三、配置root@VM-12-5-ubuntu:~# wg show wg0 interface: wg0 public key: 4GSWTJJq5zv6yd0pa4apypDSxxE+J7HckZ0OJOdfNlg= private key: (hidden) listening port: 51820 peer: dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= endpoint: 113.108.37.18:2103 allowed ips: 10.88.0.2/32 latest handshake: 44 seconds ago transfer: 279.00 KiB received, 137.54 KiB sent persistent keepalive: every 25 seconds [root@k8s-01 ~]# wg show wg0 interface: wg0 public key: dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= private key: (hidden) listening port: 46509 peer: 4GSWTJJq5zv6yd0pa4apypDSxxE+J7HckZ0OJOdfNlg= endpoint: 43.138.186.171:51820 allowed ips: 10.88.0.1/32 latest handshake: 37 seconds ago transfer: 130.80 KiB received, 259.68 KiB sent persistent keepalive: every 25 seconds公有云 wg0 的 interface 公钥是 4GSWTJ...，它的 peer 公钥是 dF92nK... K8s 侧 wg0 的 interface 公钥是 dF92nK...，它的 peer 公钥是 4GSWTJ... 也就是“本机 interface 公钥 == 对端 peer 公钥”，两边互为一对，没问题。#公有云（43.138.186.171）上的 wg0.conf [Interface] Address = 10.88.0.1/24 ListenPort = 51820 PrivateKey = (你的云主机私钥) PostUp = sysctl -w net.ipv4.ip_forward=1 ; iptables -A FORWARD -i wg0 -j ACCEPT ; iptables -A FORWARD -o wg0 -j ACCEPT PostDown = iptables -D FORWARD -i wg0 -j ACCEPT ; iptables -D FORWARD -o wg0 -j ACCEPT [Interface]：本机（云主机）这个 WireGuard 网卡 wg0 的本地配置。 Address = 10.88.0.1/24：给 wg0 配的“隧道内网 IP”。 10.88.0.1 就是云主机在隧道里的地址。 /24 代表这个隧道网段是 10.88.0.0/24，以后可以再加别的 peer（10.88.0.x）。 ListenPort = 51820：云主机监听的 UDP 端口，等着别的 peer 来连它（常用默认就是 51820/udp）。 PrivateKey：云主机的私钥（保密）。公钥是用它导出的，发给对端使用。 PostUp/PostDown：wg-quick up/down 时要执行的钩子。 sysctl -w net.ipv4.ip_forward=1：开启三层转发（允许这台机子在不同网卡间转发 IP 包）。 两条 iptables FORWARD ACCEPT：允许数据包通过 wg0 转发。 注意这里没有做 SNAT/MASQUERADE，因为你现在只在 10.88 网段里互通，不需要 NAT。如果以后要让云主机访问 K8s 后面的 其它网段（比如 192.168.173.0/24），可能需要再加路由或 SNAT，这个在文末扩展里说。 [Peer] PublicKey = (k8s-01 的公钥) AllowedIPs = 10.88.0.2/32 PersistentKeepalive = 25 [Peer]：描述一个对端（这里就是 K8s 节点）的配置。 PublicKey：K8s 节点的公钥（用来验证/加密，不能拿私钥填）。 AllowedIPs = 10.88.0.2/32：两层含义（这是 WireGuard 的“妙处”） 路由：告诉本机“发往 10.88.0.2 的包，从这个 peer 走”。 ACL：只接受对端发来的、源地址是 10.88.0.2 的流量（更安全）。 /32 表示只这一个 IP。如果以后你想通过这个 peer 转更多网段（比如 192.168.173.0/24），就把它们加进 AllowedIPs。 PersistentKeepalive = 25：每 25 秒发一个空包“打洞/保活”。 对 NAT/防火墙后的 peer 很重要，防止 UDP 映射过期。放在云主机这边不是必须，但也无害。#K8s 节点（192.168.173.101）上的 wg0.conf [Interface] ListenPort = 46509 Address = 10.88.0.2/24 PrivateKey = (k8s-01 的私钥) ListenPort = 46509：K8s 节点也在本地开了一个 UDP 监听端口。 实践里 客户端可不必监听（可以省略），只要它主动连云主机就行；但保留也没问题。 Address = 10.88.0.2/24：K8s 在隧道里的地址。 PrivateKey：K8s 的私钥（保密）。 [Peer] PublicKey = (云主机的公钥) Endpoint = 43.138.186.171:51820 AllowedIPs = 10.88.0.1/32 PersistentKeepalive = 25 PublicKey：云主机的公钥。 Endpoint = 43.138.186.171:51820：要去连接的对端外网地址+端口（云主机的公网IP+ListenPort）。 客户端必须写 Endpoint 才知道从哪拨号。 服务器端（云主机）通常不写 Endpoint，它会从对端第一个包学到真实来源地址。 AllowedIPs = 10.88.0.1/32： 路由：发往 10.88.0.1 的包走这个 peer； ACL：只接受源地址是 10.88.0.1 的流量。 PersistentKeepalive = 25：这个放在客户端非常关键（多数客户端在 NAT 后）。这两份配置整体在做什么？ 建立了一个点对点的三层隧道： 云主机（10.88.0.1） ↔ K8s 节点（10.88.0.2） 两边 AllowedIPs 互指对方的 /32 地址，因此： 发往 10.88.0.1 的流量从 K8s → 隧道走； 发往 10.88.0.2 的流量从云主机 → 隧道走； 因为 Interface Address 都是 /24，你将来可以很自然地再加更多 peer（10.88.0.3、10.88.0.4…），形成一个小型“星型/网状” VPN。常见问题 / 最佳实践 1./24 vs /32 有啥区别？ Address 的 /24 只是本机网卡的掩码（影响本机“直连子网”的认知），不直接决定能不能通谁。真正决定“隧道里允许/路由哪些网段”的是 各个 peer 的 AllowedIPs。 你现在 AllowedIPs 都是 /32，所以只有两个 IP 会走这条隧道，干净且安全。 2.为什么服务器端不需要写 Endpoint？ 因为它“被拨号”，从首包能自动学到对端外网地址（NAT 环境下也能工作）。 3.防火墙要开啥？ 云主机：放行 UDP 51820（外网入站）。 两端：放行 wg0 的 FORWARD（你已加），如果还要访问 K8s 的 NodePort，记得在 K8s 节点上放行对应端口来自 wg0 的入站（例如 iptables -I INPUT -i wg0 -p tcp --dport 32150 -j ACCEPT）。 4.密钥怎么生成？ umask 077 wg genkey | tee privatekey | wg pubkey > publickey 本机 PrivateKey 用在 [Interface]；对端的 PublicKey 用在本机的 [Peer]。 5.开机自启 systemctl enable --now wg-quick@wg0 如果出现下面这种报错大概率是wg0已经存在了 可能手动 wg-quick up wg0 过，结果现在 systemctl enable --now 在“启用的同时再次启动”，启动阶段发现 wg0 已经在运行，于是报错。 root@k8s-01:~# systemctl enable --now wg-quick@wg0 Created symlink /etc/systemd/system/multi-user.target.wants/wg-quick@wg0.service → /lib/systemd/system/wg-quick@.service. Job for wg-quick@wg0.service failed because the control process exited with error code. See "systemctl status wg-quick@wg0.service" and "journalctl -xeu wg-quick@wg0.service" for details. root@k8s-01:~# systemctl status wg-quick@wg0.service × wg-quick@wg0.service - WireGuard via wg-quick(8) for wg0 Loaded: loaded (/lib/systemd/system/wg-quick@.service; enabled; vendor preset: enabled) Active: failed (Result: exit-code) since Thu 2025-08-28 03:01:09 UTC; 58s ago Docs: man:wg-quick(8) man:wg(8) https://www.wireguard.com/ https://www.wireguard.com/quickstart/ https://git.zx2c4.com/wireguard-tools/about/src/man/wg-quick.8 https://git.zx2c4.com/wireguard-tools/about/src/man/wg.8 Process: 66728 ExecStart=/usr/bin/wg-quick up wg0 (code=exited, status=1/FAILURE) Main PID: 66728 (code=exited, status=1/FAILURE) CPU: 11ms Aug 28 03:01:09 k8s-01 systemd[1]: Starting WireGuard via wg-quick(8) for wg0... Aug 28 03:01:09 k8s-01 wg-quick[66728]: wg-quick: `wg0' already exists Aug 28 03:01:09 k8s-01 systemd[1]: wg-quick@wg0.service: Main process exited, code=exited, status=1/FAILURE Aug 28 03:01:09 k8s-01 systemd[1]: wg-quick@wg0.service: Failed with result 'exit-code'. Aug 28 03:01:09 k8s-01 systemd[1]: Failed to start WireGuard via wg-quick(8) for wg0. # 1) 看看当前是否已 up（可选） wg show ip a show dev wg0 # 2) 先优雅下线（会执行 PostDown，清理 iptables） wg-quick down wg0 || true 重载秘钥 wg set wg0 private-key /etc/wireguard/privatekey # 3) 重新用 systemd 启动（让开机自启 + 由 systemd 接管） systemctl start wg-quick@wg0 systemctl enable wg-quick@wg0 # 4) 确认状态与连通性 systemctl status wg-quick@wg0 --no-pager wg show ping -c 3 10.88.0.1 # 在 k8s-01 上测试到云主机 6.排错检查 wg show ip a show wg0 ip r | grep 10.88. ping 10.88.0.1 # 从 k8s ping 10.88.0.2 # 从云主机 加载秘钥命令 root@VM-12-5-ubuntu:~# wg set wg0 private-key /etc/wireguard/privatekey四、连接测试root@VM-12-5-ubuntu:~# wg show wg0 interface: wg0 public key: 4GSWTJJq5zv6yd0pa4apypDSxxE+J7HckZ0OJOdfNlg= private key: (hidden) listening port: 51820 peer: dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= endpoint: 113.108.37.18:2103 allowed ips: 10.88.0.2/32 latest handshake: 44 seconds ago transfer: 279.00 KiB received, 137.54 KiB sent persistent keepalive: every 25 seconds [root@k8s-01 ~]# wg show wg0 interface: wg0 public key: dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= private key: (hidden) listening port: 46509 peer: 4GSWTJJq5zv6yd0pa4apypDSxxE+J7HckZ0OJOdfNlg= endpoint: 43.138.186.171:51820 allowed ips: 10.88.0.1/32 latest handshake: 37 seconds ago transfer: 130.80 KiB received, 259.68 KiB sent persistent keepalive: every 25 seconds 握手正常 两边都显示 latest handshake 为几十秒前，且 transfer 有收发字节在增加——说明隧道已联通。 Endpoint 显示解释 公有云上看到的对端 endpoint: 113.108.37.18:2103 是 K8s 侧出网的公网/NAT 地址与端口（被动学习到的）。 K8s 侧配置中的 Endpoint = 43.138.186.171:51820 是 主动连向公有云的固定地址。这种一主一从（NAT 穿透）是正常现象。互ping测试 root@VM-12-5-ubuntu:~# ping -c 3 10.88.0.2 PING 10.88.0.2 (10.88.0.2) 56(84) bytes of data. 64 bytes from 10.88.0.2: icmp_seq=1 ttl=64 time=913 ms 64 bytes from 10.88.0.2: icmp_seq=2 ttl=64 time=1112 ms 64 bytes from 10.88.0.2: icmp_seq=3 ttl=64 time=1083 ms --- 10.88.0.2 ping statistics --- 3 packets transmitted, 3 received, 0% packet loss, time 2002ms rtt min/avg/max/mdev = 913.232/1036.088/1112.054/87.679 ms, pipe 2 root@k8s-01:~# ping -c 3 10.88.0.1 PING 10.88.0.1 (10.88.0.1) 56(84) bytes of data. 64 bytes from 10.88.0.1: icmp_seq=1 ttl=64 time=1090 ms 64 bytes from 10.88.0.1: icmp_seq=2 ttl=64 time=1110 ms 64 bytes from 10.88.0.1: icmp_seq=3 ttl=64 time=1094 ms --- 10.88.0.1 ping statistics --- 3 packets transmitted, 3 received, 0% packet loss, time 2016ms rtt min/avg/max/mdev = 1089.897/1098.075/1110.163/8.722 ms, pipe 2如果你要从公有云访问 K8s 集群内部 把 公有云侧指向 K8s 侧的 [Peer] 的 AllowedIPs 扩到需要的网段，例如： AllowedIPs = 10.88.0.2/32, 10.244.0.0/16, 10.96.0.0/12, 192.168.30.0/24 并在 K8s 出口网关（运行 wireguard 的那台） 开启转发和 SNAT（若需要）： sysctl -w net.ipv4.ip_forward=1 iptables -t nat -A POSTROUTING -s 10.244.0.0/16 -o <外网网卡> -j MASQUERADE # 视需要把 10.96.0.0/12、192.168.30.0/24 也做 MASQUERADE 注：如果你在 K8s 里用了 CNI 的内置 MASQ 或有专用出口网关，按实际网络结构调整。五、域名测试 5.1 方案 A（简单入门）：在公有云 Nginx 终止 TLS，回源走 HTTP 到 Traefik（NodePort 32150） 5.1.1 K8s 侧：放一个测试应用 + Ingress#用 Traefik 当 IngressClass，域名就用 zhuanfa.axzys.cn（跟外网一致，方便验证“相同”）。 # demo-whoami.yaml apiVersion: apps/v1 kind: Deployment metadata: name: whoami namespace: demo spec: replicas: 1 selector: matchLabels: { app: whoami } template: metadata: labels: { app: whoami } spec: containers: - name: whoami image: traefik/whoami:v1.10 ports: - containerPort: 80 --- apiVersion: v1 kind: Service metadata: name: whoami namespace: demo spec: selector: { app: whoami } ports: - port: 80 targetPort: 80 protocol: TCP --- apiVersion: networking.k8s.io/v1 kind: Ingress metadata: name: whoami namespace: demo annotations: kubernetes.io/ingress.class: traefik traefik.ingress.kubernetes.io/router.entrypoints: web spec: rules: - host: zhuanfa.axzys.cn http: paths: - path: / pathType: Prefix backend: service: name: whoami port: number: 80 kubectl create ns demo kubectl apply -f demo-whoami.yaml kubectl -n demo get ingressroot@k8s-01:~# kubectl get svc -n traefik NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE traefik NodePort 10.100.109.7 <none> 80:30080/TCP,443:30443/TCP 27d 小检查：从公有云主机上（10.88.0.1）直连 Traefik 的 NodePort 看看有没有返回： root@VM-12-5-ubuntu:~# curl -H 'Host: zhuanfa.axzys.cn' http://10.88.0.2:30080 Hostname: whoami-678b958ccd-mqx5f IP: 127.0.0.1 IP: ::1 IP: 10.244.2.74 IP: fe80::f097:a9ff:fe0e:b981 RemoteAddr: 10.244.2.25:35632 GET / HTTP/1.1 Host: zhuanfa.axzys.cn User-Agent: curl/7.81.0 Accept: */* Accept-Encoding: gzip X-Forwarded-For: 10.244.0.0 X-Forwarded-Host: zhuanfa.axzys.cn X-Forwarded-Port: 80 X-Forwarded-Proto: http X-Forwarded-Server: traefik-release-589c7ff647-2668z X-Real-Ip: 10.244.0.0 #能看到 whoami 的 JSON/文本就 OK。如果服务器有防火墙，请在 K8s 节点上放行来自 wg0 的 NodePort： iptables -I INPUT -i wg0 -p tcp --dport 30080 -j ACCEPT # （如开启 https 回源，再放 30080）5.1.2 公有云 Nginx：终止 TLS，并通过 WireGuard 走 HTTP 回源HTTP 先通（测试用） /etc/nginx/sites-available/zhuanfa.axzys.cnupstream traefik_via_wg_http { server 10.88.0.2:30080; # Traefik web (NodePort) keepalive 32; } server { listen 80; server_name zhuanfa.axzys.cn; # 如需把所有 80 跳 443，等签好证书后再加： # return 301 https://$host$request_uri; location / { proxy_set_header Host $host; proxy_set_header X-Real-IP $remote_addr; proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; proxy_set_header X-Forwarded-Proto $scheme; proxy_http_version 1.1; proxy_set_header Connection ""; proxy_read_timeout 120s; proxy_send_timeout 120s; proxy_pass http://traefik_via_wg_http; } } #启用站点并重载 ln -s /etc/nginx/sites-available/zhuanfa.axzys.cn /etc/nginx/sites-enabled/ nginx -t && systemctl reload nginxhttp://zhuanfa.axzys.cn/#再加 HTTPS（证书放在公有云） 最方便的是用 certbot 自动签： apt-get update && apt-get install -y certbot python3-certbot-nginx certbot --nginx -d zhuanfa.axzys.cnroot@VM-12-5-ubuntu:~# apt-get install -y certbot python3-certbot-nginx Reading package lists... Done Building dependency tree... Done Reading state information... Done The following additional packages will be installed: python3-acme python3-certbot python3-certifi python3-configargparse python3-icu python3-josepy python3-parsedatetime python3-requests python3-requests-toolbelt python3-rfc3339 python3-tz python3-urllib3 python3-zope.component python3-zope.event python3-zope.hookable Suggested packages: python-certbot-doc python3-certbot-apache python-acme-doc python-certbot-nginx-doc python3-socks python-requests-doc The following NEW packages will be installed: certbot python3-acme python3-certbot python3-certbot-nginx python3-certifi python3-configargparse python3-icu python3-josepy python3-parsedatetime python3-requests python3-requests-toolbelt python3-rfc3339 python3-tz python3-urllib3 python3-zope.component python3-zope.event python3-zope.hookable 0 upgraded, 17 newly installed, 0 to remove and 202 not upgraded. Need to get 1,322 kB of archives. After this operation, 6,211 kB of additional disk space will be used. Get:1 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-josepy all 1.10.0-1 [22.0 kB] Get:2 http://mirrors.tencentyun.com/ubuntu jammy/main amd64 python3-certifi all 2020.6.20-1 [150 kB] Get:3 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 python3-urllib3 all 1.26.5-1~exp1ubuntu0.3 [98.6 kB] Get:4 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 python3-requests all 2.25.1+dfsg-2ubuntu0.3 [48.8 kB] Get:5 http://mirrors.tencentyun.com/ubuntu jammy/main amd64 python3-requests-toolbelt all 0.9.1-1 [38.0 kB] Get:6 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 python3-tz all 2022.1-1ubuntu0.22.04.1 [30.7 kB] Get:7 http://mirrors.tencentyun.com/ubuntu jammy/main amd64 python3-rfc3339 all 1.1-3 [7,110 B] Get:8 http://mirrors.tencentyun.com/ubuntu jammy-updates/universe amd64 python3-acme all 1.21.0-1ubuntu0.1 [36.4 kB] Get:9 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-configargparse all 1.5.3-1 [26.9 kB] Get:10 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-parsedatetime all 2.6-2 [32.9 kB] Get:11 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-zope.hookable amd64 5.1.0-1build1 [11.6 kB] Get:12 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-zope.event all 4.4-3 [8,180 B] Get:13 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-zope.component all 4.3.0-3 [38.3 kB] Get:14 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-certbot all 1.21.0-1build1 [175 kB] Get:15 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 certbot all 1.21.0-1build1 [21.3 kB] Get:16 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-certbot-nginx all 1.21.0-1 [35.4 kB] Get:17 http://mirrors.tencentyun.com/ubuntu jammy/main amd64 python3-icu amd64 2.8.1-0ubuntu2 [540 kB] Fetched 1,322 kB in 2s (759 kB/s) Preconfiguring packages ... Selecting previously unselected package python3-josepy. (Reading database ... 88845 files and directories currently installed.) Preparing to unpack .../00-python3-josepy_1.10.0-1_all.deb ... Unpacking python3-josepy (1.10.0-1) ... Selecting previously unselected package python3-certifi. Preparing to unpack .../01-python3-certifi_2020.6.20-1_all.deb ... Unpacking python3-certifi (2020.6.20-1) ... Selecting previously unselected package python3-urllib3. Preparing to unpack .../02-python3-urllib3_1.26.5-1~exp1ubuntu0.3_all.deb ... Unpacking python3-urllib3 (1.26.5-1~exp1ubuntu0.3) ... Selecting previously unselected package python3-requests. Preparing to unpack .../03-python3-requests_2.25.1+dfsg-2ubuntu0.3_all.deb ... Unpacking python3-requests (2.25.1+dfsg-2ubuntu0.3) ... Selecting previously unselected package python3-requests-toolbelt. Preparing to unpack .../04-python3-requests-toolbelt_0.9.1-1_all.deb ... Unpacking python3-requests-toolbelt (0.9.1-1) ... Selecting previously unselected package python3-tz. Preparing to unpack .../05-python3-tz_2022.1-1ubuntu0.22.04.1_all.deb ... Unpacking python3-tz (2022.1-1ubuntu0.22.04.1) ... Selecting previously unselected package python3-rfc3339. Preparing to unpack .../06-python3-rfc3339_1.1-3_all.deb ... Unpacking python3-rfc3339 (1.1-3) ... Selecting previously unselected package python3-acme. Preparing to unpack .../07-python3-acme_1.21.0-1ubuntu0.1_all.deb ... Unpacking python3-acme (1.21.0-1ubuntu0.1) ... Selecting previously unselected package python3-configargparse. Preparing to unpack .../08-python3-configargparse_1.5.3-1_all.deb ... Unpacking python3-configargparse (1.5.3-1) ... Selecting previously unselected package python3-parsedatetime. Preparing to unpack .../09-python3-parsedatetime_2.6-2_all.deb ... Unpacking python3-parsedatetime (2.6-2) ... Selecting previously unselected package python3-zope.hookable. Preparing to unpack .../10-python3-zope.hookable_5.1.0-1build1_amd64.deb ... Unpacking python3-zope.hookable (5.1.0-1build1) ... Selecting previously unselected package python3-zope.event. Preparing to unpack .../11-python3-zope.event_4.4-3_all.deb ... Unpacking python3-zope.event (4.4-3) ... Selecting previously unselected package python3-zope.component. Preparing to unpack .../12-python3-zope.component_4.3.0-3_all.deb ... Unpacking python3-zope.component (4.3.0-3) ... Selecting previously unselected package python3-certbot. Preparing to unpack .../13-python3-certbot_1.21.0-1build1_all.deb ... Unpacking python3-certbot (1.21.0-1build1) ... Selecting previously unselected package certbot. Preparing to unpack .../14-certbot_1.21.0-1build1_all.deb ... Unpacking certbot (1.21.0-1build1) ... Selecting previously unselected package python3-certbot-nginx. Preparing to unpack .../15-python3-certbot-nginx_1.21.0-1_all.deb ... Unpacking python3-certbot-nginx (1.21.0-1) ... Selecting previously unselected package python3-icu. Preparing to unpack .../16-python3-icu_2.8.1-0ubuntu2_amd64.deb ... Unpacking python3-icu (2.8.1-0ubuntu2) ... Setting up python3-configargparse (1.5.3-1) ... Setting up python3-parsedatetime (2.6-2) ... Setting up python3-icu (2.8.1-0ubuntu2) ... Setting up python3-zope.event (4.4-3) ... Setting up python3-tz (2022.1-1ubuntu0.22.04.1) ... Setting up python3-zope.hookable (5.1.0-1build1) ... Setting up python3-certifi (2020.6.20-1) ... Setting up python3-urllib3 (1.26.5-1~exp1ubuntu0.3) ... Setting up python3-josepy (1.10.0-1) ... Setting up python3-rfc3339 (1.1-3) ... Setting up python3-zope.component (4.3.0-3) ... Setting up python3-requests (2.25.1+dfsg-2ubuntu0.3) ... Setting up python3-requests-toolbelt (0.9.1-1) ... Setting up python3-acme (1.21.0-1ubuntu0.1) ... Setting up python3-certbot (1.21.0-1build1) ... Setting up certbot (1.21.0-1build1) ... Created symlink /etc/systemd/system/timers.target.wants/certbot.timer → /lib/systemd/system/certbot.timer. Setting up python3-certbot-nginx (1.21.0-1) ... Processing triggers for man-db (2.10.2-1) ... Scanning processes... Scanning linux images... Running kernel seems to be up-to-date. No services need to be restarted. No containers need to be restarted. No user sessions are running outdated binaries. No VM guests are running outdated hypervisor (qemu) binaries on this host. root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# certbot --nginx -d zhuanfa.axzys.cn Saving debug log to /var/log/letsencrypt/letsencrypt.log Enter email address (used for urgent renewal and security notices) (Enter 'c' to cancel): 7902731@qq.com - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Please read the Terms of Service at https://letsencrypt.org/documents/LE-SA-v1.5-February-24-2025.pdf. You must agree in order to register with the ACME server. Do you agree? - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - (Y)es/(N)o: Y - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Would you be willing, once your first certificate is successfully issued, to share your email address with the Electronic Frontier Foundation, a founding partner of the Let's Encrypt project and the non-profit organization that develops Certbot? We'd like to send you email about our work encrypting the web, EFF news, campaigns, and ways to support digital freedom. - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - (Y)es/(N)o: Y Account registered. Requesting a certificate for zhuanfa.axzys.cn Successfully received certificate. Certificate is saved at: /etc/letsencrypt/live/zhuanfa.axzys.cn/fullchain.pem Key is saved at: /etc/letsencrypt/live/zhuanfa.axzys.cn/privkey.pem This certificate expires on 2025-11-25. These files will be updated when the certificate renews. Certbot has set up a scheduled task to automatically renew this certificate in the background. Deploying certificate Successfully deployed certificate for zhuanfa.axzys.cn to /etc/nginx/sites-enabled/zhuanfa.axzys.cn Congratulations! You have successfully enabled HTTPS on https://zhuanfa.axzys.cn - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - If you like Certbot, please consider supporting our work by: * Donating to ISRG / Let's Encrypt: https://letsencrypt.org/donate * Donating to EFF: https://eff.org/donate-le - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -certbot 会把 Nginx 配置自动改成 80→443 跳转 + SSL 证书挂载。之后再访问： https://zhuanfa.axzys.cn/#链路 说明：TLS 在公有云 Nginx 终止，Nginx → Traefik 用 HTTP（wg 隧道里，安全性没问题）。5.2 公有云 Nginx（使用 stream 透传 TCP）在 /etc/nginx/nginx.conf 里添加 stream {} 段（与 http {} 同级），并把 80/443 都透传到 Traefik 的 NodePort：stream { upstream traefik_http { server 10.88.0.2:30080; # Traefik web (HTTP) } upstream traefik_https { server 10.88.0.2:30443; # Traefik websecure (HTTPS) } server { listen 80; proxy_pass traefik_http; proxy_timeout 120s; proxy_connect_timeout 5s; } server { listen 443; proxy_pass traefik_https; proxy_timeout 120s; proxy_connect_timeout 5s; } } #重载 nginx -t && systemctl reload nginx现在访问 http://zhuanfa.axzys.cn 会被 Traefik 处理（你可以在 Traefik 里做 80→443 跳转），https://zhuanfa.axzys.cn 证书也由 Traefik 下发与续期。 注意：Nginx 必须是带 stream 模块的（Ubuntu/Debian 默认包一般已带）。六、常见陷阱 & 排错清单NodePort 只在内网开放： 若你担心 NodePort 泄露到其他网卡，可以把 kube-proxy 配成只监听 WireGuard 网段： 在 kube-proxy 的 ConfigMap 里设置 nodePortAddresses: ["10.88.0.0/24"]，然后滚动重启 kube-proxy。 或临时用 iptables 只允许 -i wg0 的 32150/31948。 请求头： 方案 A 用 HTTP 反代时，务必保留 Host 和 X-Forwarded-* 头（上面 Nginx 配置已加），否则基于 Host 的 Ingress 匹配会失败。 Traefik Dashboard 405： 你之前用 curl -I 访问 /dashboard/ 出现 405，这是正常的（Dashboard 不回应 HEAD）。用 curl -v http://.../dashboard/ 或浏览器 GET 即可。 隧道路由： 你已经能互 ping（10.88.0.1 ↔ 10.88.0.2），说明 AllowedIPs/防火墙没问题；如果 Nginx 回源连不上，优先 curl 10.88.0.2:32150/31948 验证链路。你可以这样快速验证 选 方案 A： 1）应用上面 demo YAML（web 入口）。 2）公有云 Nginx 配好 HTTP 反代。 3）本地打开 http://zhuanfa.axzys.cn/ → 看到 whoami。 4）再跑 certbot → 用 https://zhuanfa.axzys.cn/ 访问。 选 方案 B： 1）Ingress 切到 websecure（或同时配置 web 做 80→443 跳转）。 2）公有云 Nginx 加 stream 透传 80/443 到 32150/31948。 3）浏览器直接 https://zhuanfa.axzys.cn/，证书由 Traefik 管。七、扩展 7.1 想让云主机直接访问 K8s 后面的内网（比如 192.168.173.0/24）怎么办？#在现在的点对点配置里，只通了 10.88.0.1 ↔ 10.88.0.2。如果还想从云主机访问 K8s 节点所在内网（或 Pod/Service 网段），有两种常见做法： {dotted startColor="#ff6c6c" endColor="#1989fa"/}{dotted startColor="#ff6c6c" endColor="#1989fa"/}{dotted startColor="#ff6c6c" endColor="#1989fa"/}{dotted startColor="#ff6c6c" endColor="#1989fa"/}{dotted startColor="#ff6c6c" endColor="#1989fa"/}{dotted startColor="#ff6c6c" endColor="#1989fa"/}{dotted startColor="#ff6c6c" endColor="#1989fa"/}{dotted startColor="#ff6c6c" endColor="#1989fa"/}{dotted startColor="#ff6c6c" endColor="#1989fa"/}{dotted startColor="#ff6c6c" endColor="#1989fa"/}{dotted startColor="#ff6c6c" endColor="#1989fa"/}{dotted startColor="#ff6c6c" endColor="#1989fa"/}Last login: Wed Aug 27 13:32:47 2025 from 183.14.30.81 root@VM-12-5-ubuntu:~# apt-get update Hit:1 http://mirrors.tencentyun.com/ubuntu jammy InRelease Get:2 http://mirrors.tencentyun.com/ubuntu jammy-updates InRelease [128 kB] Get:3 http://mirrors.tencentyun.com/ubuntu jammy-security InRelease [129 kB] Get:4 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 Packages [2,843 kB] Get:5 http://mirrors.tencentyun.com/ubuntu jammy-updates/main Translation-en [447 kB] Get:6 http://mirrors.tencentyun.com/ubuntu jammy-updates/restricted amd64 Packages [4,269 kB] Get:7 http://mirrors.tencentyun.com/ubuntu jammy-updates/restricted Translation-en [778 kB] Get:8 http://mirrors.tencentyun.com/ubuntu jammy-updates/universe amd64 Packages [1,227 kB] Get:9 http://mirrors.tencentyun.com/ubuntu jammy-updates/universe Translation-en [304 kB] Get:10 http://mirrors.tencentyun.com/ubuntu jammy-updates/multiverse amd64 Packages [59.5 kB] Get:11 http://mirrors.tencentyun.com/ubuntu jammy-updates/multiverse Translation-en [14.2 kB] Get:12 http://mirrors.tencentyun.com/ubuntu jammy-security/main amd64 Packages [2,595 kB] Get:13 http://mirrors.tencentyun.com/ubuntu jammy-security/main Translation-en [383 kB] Get:14 http://mirrors.tencentyun.com/ubuntu jammy-security/restricted amd64 Packages [4,118 kB] Get:15 http://mirrors.tencentyun.com/ubuntu jammy-security/restricted Translation-en [751 kB] Get:16 http://mirrors.tencentyun.com/ubuntu jammy-security/universe amd64 Packages [994 kB] Get:17 http://mirrors.tencentyun.com/ubuntu jammy-security/universe Translation-en [217 kB] Get:18 http://mirrors.tencentyun.com/ubuntu jammy-security/multiverse amd64 Packages [40.3 kB] Get:19 http://mirrors.tencentyun.com/ubuntu jammy-security/multiverse Translation-en [8,908 B] Fetched 19.3 MB in 4s (4,695 kB/s) Reading package lists... Done root@VM-12-5-ubuntu:~# apt-get install -y wireguard Reading package lists... Done Building dependency tree... Done Reading state information... Done The following additional packages will be installed: wireguard-tools Suggested packages: openresolv | resolvconf The following NEW packages will be installed: wireguard wireguard-tools 0 upgraded, 2 newly installed, 0 to remove and 202 not upgraded. Need to get 90.0 kB of archives. After this operation, 345 kB of additional disk space will be used. Get:1 http://mirrors.tencentyun.com/ubuntu jammy/main amd64 wireguard-tools amd64 1.0.20210914-1ubuntu2 [86.9 kB] Get:2 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 wireguard all 1.0.20210914-1ubuntu2 [3,114 B] Fetched 90.0 kB in 0s (505 kB/s) Selecting previously unselected package wireguard-tools. (Reading database ... 88675 files and directories currently installed.) Preparing to unpack .../wireguard-tools_1.0.20210914-1ubuntu2_amd64.deb ... Unpacking wireguard-tools (1.0.20210914-1ubuntu2) ... Selecting previously unselected package wireguard. Preparing to unpack .../wireguard_1.0.20210914-1ubuntu2_all.deb ... Unpacking wireguard (1.0.20210914-1ubuntu2) ... Setting up wireguard-tools (1.0.20210914-1ubuntu2) ... wg-quick.target is a disabled or a static unit not running, not starting it. Setting up wireguard (1.0.20210914-1ubuntu2) ... Processing triggers for man-db (2.10.2-1) ... Scanning processes... Scanning linux images... Running kernel seems to be up-to-date. No services need to be restarted. No containers need to be restarted. No user sessions are running outdated binaries. No VM guests are running outdated hypervisor (qemu) binaries on this host. root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# ls snap root@VM-12-5-ubuntu:~# vi /etc/wireguard/wg0.conf root@VM-12-5-ubuntu:~# wg genkey | tee /etc/wireguard/privatekey | wg pubkey > /etc/wireguard/publickey root@VM-12-5-ubuntu:~# sudo ufw status Status: inactive root@VM-12-5-ubuntu:~# vi /etc/wireguard/wg0.conf root@VM-12-5-ubuntu:~# systemctl enable --now wg-quick@wg0 Created symlink /etc/systemd/system/multi-user.target.wants/wg-quick@wg0.service → /lib/systemd/system/wg-quick@.service. root@VM-12-5-ubuntu:~# wg show interface: wg0 public key: Vl13ICrsWW4tODYv94bNV2Es9FPY4/6MoJ0hO1YXG3I= private key: (hidden) listening port: 51820 peer: n7/nzuiBYLFm+ijhBR8d0G/JcNPu+eKg1V//vX5yuBU= allowed ips: 10.88.0.2/32 persistent keepalive: every 25 seconds root@VM-12-5-ubuntu:~# ping -c 3 10.88.0.2 PING 10.88.0.2 (10.88.0.2) 56(84) bytes of data. From 10.88.0.1 icmp_seq=1 Destination Host Unreachable ping: sendmsg: Destination address required From 10.88.0.1 icmp_seq=2 Destination Host Unreachable ping: sendmsg: Destination address required From 10.88.0.1 icmp_seq=3 Destination Host Unreachable ping: sendmsg: Destination address required --- 10.88.0.2 ping statistics --- 3 packets transmitted, 0 received, +3 errors, 100% packet loss, time 2028ms root@VM-12-5-ubuntu:~# curl -I -H 'Host: zhuanfa.axzys.cn' http://10.88.0.2:30080 curl: (7) Failed to connect to 10.88.0.2 port 30080 after 0 ms: No route to host root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# # 检查是否有任何阻止规则 sudo iptables -L -n -v Chain INPUT (policy ACCEPT 0 packets, 0 bytes) pkts bytes target prot opt in out source destination 56282 49M YJ-FIREWALL-INPUT all -- * * 0.0.0.0/0 0.0.0.0/0 Chain FORWARD (policy ACCEPT 0 packets, 0 bytes) pkts bytes target prot opt in out source destination 0 0 ACCEPT all -- wg0 * 0.0.0.0/0 0.0.0.0/0 0 0 ACCEPT all -- * wg0 0.0.0.0/0 0.0.0.0/0 Chain OUTPUT (policy ACCEPT 0 packets, 0 bytes) pkts bytes target prot opt in out source destination Chain YJ-FIREWALL-INPUT (1 references) pkts bytes target prot opt in out source destination 0 0 REJECT all -- * * 94.181.229.254 0.0.0.0/0 reject-with icmp-port-unreachable root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# sudo tcpdump -i any -n port 51820 tcpdump: data link type LINUX_SLL2 tcpdump: verbose output suppressed, use -v[v]... for full protocol decode listening on any, link-type LINUX_SLL2 (Linux cooked v2), snapshot length 262144 bytes 14:06:35.051827 eth0 In IP 113.108.37.18.2102 > 10.1.12.5.51820: UDP, length 148 14:06:40.683575 eth0 In IP 113.108.37.18.2102 > 10.1.12.5.51820: UDP, length 148 14:06:45.803948 eth0 In IP 113.108.37.18.2102 > 10.1.12.5.51820: UDP, length 148 14:06:51.435594 eth0 In IP 113.108.37.18.2102 > 10.1.12.5.51820: UDP, length 148 14:06:57.067465 eth0 In IP 113.108.37.18.2102 > 10.1.12.5.51820: UDP, length 148 ^C 5 packets captured 6 packets received by filter 0 packets dropped by kernel root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# sudo iptables -t nat -A POSTROUTING -o eth33 -j MASQUERADE root@VM-12-5-ubuntu:~# sudo sysctl -w net.ipv4.ip_forward=1 net.ipv4.ip_forward = 1 root@VM-12-5-ubuntu:~# vi /etc/wireguard/wg0.conf root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# sudo ss -lunp | grep 51820 UNCONN 0 0 0.0.0.0:51820 0.0.0.0:* UNCONN 0 0 [::]:51820 [::]:* root@VM-12-5-ubuntu:~# sudo wg show interface: wg0 public key: Vl13ICrsWW4tODYv94bNV2Es9FPY4/6MoJ0hO1YXG3I= private key: (hidden) listening port: 51820 peer: n7/nzuiBYLFm+ijhBR8d0G/JcNPu+eKg1V//vX5yuBU= allowed ips: 10.88.0.2/32 persistent keepalive: every 25 seconds root@VM-12-5-ubuntu:~# cat /etc/wireguard/wg0.conf [Interface] Address = 10.88.0.1/24 ListenPort = 51820 PrivateKey = BgxjDizUdEATpdh0iZ7Y+zQo2iVyqRBgp70CemeZ30A= # 允许转发 PostUp = sysctl -w net.ipv4.ip_forward=1 ; iptables -A FORWARD -i wg0 -j ACCEPT ; iptables -A FORWARD -o wg0 -j ACCEPT PostDown = iptables -D FORWARD -i wg0 -j ACCEPT ; iptables -D FORWARD -o wg0 -j ACCEPT [Peer] PublicKey = n7/nzuiBYLFm+ijhBR8d0G/JcNPu+eKg1V//vX5yuBU= AllowedIPs = 10.88.0.2/32 PersistentKeepalive = 25 root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# umask 077 wg genkey | tee /etc/wireguard/server.priv | wg pubkey > /etc/wireguard/server.pub cat /etc/wireguard/server.pub 4GSWTJJq5zv6yd0pa4apypDSxxE+J7HckZ0OJOdfNlg= root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# cat /etc/wireguard/server.priv qFvMNYv27vwcIfJuu6fXLcxYNscOTvlDxmd9JzN8fV8= root@VM-12-5-ubuntu:~# vi /etc/wireguard/wg0.conf root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# systemctl restart wg-quick@wg0 root@VM-12-5-ubuntu:~# wg show interface: wg0 public key: 4GSWTJJq5zv6yd0pa4apypDSxxE+J7HckZ0OJOdfNlg= private key: (hidden) listening port: 51820 peer: n7/nzuiBYLFm+ijhBR8d0G/JcNPu+eKg1V//vX5yuBU= allowed ips: 10.88.0.2/32 persistent keepalive: every 25 seconds root@VM-12-5-ubuntu:~# ping -c 3 10.88.0.2 PING 10.88.0.2 (10.88.0.2) 56(84) bytes of data. From 10.88.0.1 icmp_seq=1 Destination Host Unreachable ping: sendmsg: Destination address required From 10.88.0.1 icmp_seq=2 Destination Host Unreachable ping: sendmsg: Destination address required From 10.88.0.1 icmp_seq=3 Destination Host Unreachable ping: sendmsg: Destination address required --- 10.88.0.2 ping statistics --- 3 packets transmitted, 0 received, +3 errors, 100% packet loss, time 2042ms root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# ping -c 3 10.88.0.2 PING 10.88.0.2 (10.88.0.2) 56(84) bytes of data. From 10.88.0.1 icmp_seq=1 Destination Host Unreachable ping: sendmsg: Destination address required From 10.88.0.1 icmp_seq=2 Destination Host Unreachable ping: sendmsg: Destination address required From 10.88.0.1 icmp_seq=3 Destination Host Unreachable ping: sendmsg: Destination address required --- 10.88.0.2 ping statistics --- 3 packets transmitted, 0 received, +3 errors, 100% packet loss, time 2038ms root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# ip -c a show dev wg0 4: wg0: <POINTOPOINT,NOARP,UP,LOWER_UP> mtu 1420 qdisc noqueue state UNKNOWN group default qlen 1000 link/none inet 10.88.0.1/24 scope global wg0 valid_lft forever preferred_lft forever root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# sudo ufw allow 51820/udp Rules updated Rules updated (v6) root@VM-12-5-ubuntu:~# sudo ufw status Status: inactive root@VM-12-5-ubuntu:~# sudo tcpdump -ni any udp port 51820 tcpdump: data link type LINUX_SLL2 tcpdump: verbose output suppressed, use -v[v]... for full protocol decode listening on any, link-type LINUX_SLL2 (Linux cooked v2), snapshot length 262144 bytes 14:41:19.914736 eth0 In IP 113.108.37.18.2103 > 10.1.12.5.51820: 14:41:25.547105 eth0 In IP 113.108.37.18.2103 > 10.1.12.5.51820: 14:41:31.178873 eth0 In IP 113.108.37.18.2103 > 10.1.12.5.51820: 14:41:36.811278 eth0 In IP 113.108.37.18.2103 > 10.1.12.5.51820: 14:41:41.931850 eth0 In IP 113.108.37.18.2103 > 10.1.12.5.51820: 14:41:47.563886 eth0 In IP 113.108.37.18.2103 > 10.1.12.5.51820: 14:41:52.682762 eth0 In IP 113.108.37.18.2103 > 10.1.12.5.51820: 14:41:58.314897 eth0 In IP 113.108.37.18.2103 > 10.1.12.5.51820: 14:42:03.947282 eth0 In IP 113.108.37.18.2103 > 10.1.12.5.51820: ^C 9 packets captured 10 packets received by filter 0 packets dropped by kernel root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# watch -n1 wg show root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# sudo wg showconf wg0 [Interface] ListenPort = 51820 PrivateKey = qFvMNYv27vwcIfJuu6fXLcxYNscOTvlDxmd9JzN8fV8= [Peer] PublicKey = n7/nzuiBYLFm+ijhBR8d0G/JcNPu+eKg1V//vX5yuBU= AllowedIPs = 10.88.0.2/32 PersistentKeepalive = 25 root@VM-12-5-ubuntu:~# sudo cat /etc/wireguard/wg0.conf [Interface] Address = 10.88.0.1/24 ListenPort = 51820 PrivateKey = qFvMNYv27vwcIfJuu6fXLcxYNscOTvlDxmd9JzN8fV8= PostUp = sysctl -w net.ipv4.ip_forward=1 ; iptables -A FORWARD -i wg0 -j ACCEPT ; iptables -A FORWARD -o wg0 -j ACCEPT PostDown = iptables -D FORWARD -i wg0 -j ACCEPT ; iptables -D FORWARD -o wg0 -j ACCEPT [Peer] PublicKey = n7/nzuiBYLFm+ijhBR8d0G/JcNPu+eKg1V//vX5yuBU= AllowedIPs = 10.88.0.2/32 PersistentKeepalive = 25 root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# sudo sed -i 's|^PublicKey = .*|PublicKey = dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik=|' /etc/wireguard/wg0.conf root@VM-12-5-ubuntu:~# sudo systemctl restart wg-quick@wg0 root@VM-12-5-ubuntu:~# wg show interface: wg0 public key: 4GSWTJJq5zv6yd0pa4apypDSxxE+J7HckZ0OJOdfNlg= private key: (hidden) listening port: 51820 peer: dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= allowed ips: 10.88.0.2/32 persistent keepalive: every 25 seconds root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# wg show interface: wg0 public key: 4GSWTJJq5zv6yd0pa4apypDSxxE+J7HckZ0OJOdfNlg= private key: (hidden) listening port: 51820 peer: dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= endpoint: 113.108.37.18:2103 allowed ips: 10.88.0.2/32 latest handshake: 19 seconds ago transfer: 180 B received, 124 B sent persistent keepalive: every 25 seconds root@VM-12-5-ubuntu:~# ping -c 3 10.88.0.2 PING 10.88.0.2 (10.88.0.2) 56(84) bytes of data. 64 bytes from 10.88.0.2: icmp_seq=1 ttl=64 time=6.01 ms 64 bytes from 10.88.0.2: icmp_seq=2 ttl=64 time=5.91 ms 64 bytes from 10.88.0.2: icmp_seq=3 ttl=64 time=5.88 ms --- 10.88.0.2 ping statistics --- 3 packets transmitted, 3 received, 0% packet loss, time 2003ms rtt min/avg/max/mdev = 5.879/5.932/6.006/0.053 ms root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# S_PRIV=$(sudo wg showconf wg0 | awk '/^PrivateKey/ {print $3; exit}') sudo sed -i "s|^PrivateKey = .*|PrivateKey = $S_PRIV|" /etc/wireguard/wg0.conf root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# ping -c 3 10.88.0.2 PING 10.88.0.2 (10.88.0.2) 56(84) bytes of data. 64 bytes from 10.88.0.2: icmp_seq=1 ttl=64 time=6.23 ms 64 bytes from 10.88.0.2: icmp_seq=2 ttl=64 time=6.17 ms 64 bytes from 10.88.0.2: icmp_seq=3 ttl=64 time=5.91 ms --- 10.88.0.2 ping statistics --- 3 packets transmitted, 3 received, 0% packet loss, time 2003ms rtt min/avg/max/mdev = 5.906/6.101/6.229/0.140 ms root@VM-12-5-ubuntu:~# sudo tcpdump -ni any udp port 51820 tcpdump: data link type LINUX_SLL2 tcpdump: verbose output suppressed, use -v[v]... for full protocol decode listening on any, link-type LINUX_SLL2 (Linux cooked v2), snapshot length 262144 bytes ^C 0 packets captured 1 packet received by filter 0 packets dropped by kernel root@VM-12-5-ubuntu:~# ^C root@VM-12-5-ubuntu:~# ping -c 3 10.88.0.2 PING 10.88.0.2 (10.88.0.2) 56(84) bytes of data. 64 bytes from 10.88.0.2: icmp_seq=1 ttl=64 time=6.36 ms 64 bytes from 10.88.0.2: icmp_seq=2 ttl=64 time=5.91 ms 64 bytes from 10.88.0.2: icmp_seq=3 ttl=64 time=5.89 ms --- 10.88.0.2 ping statistics --- 3 packets transmitted, 3 received, 0% packet loss, time 2003ms rtt min/avg/max/mdev = 5.886/6.053/6.362/0.218 ms root@VM-12-5-ubuntu:~# sudo cat /etc/wireguard/wg0.conf [Interface] Address = 10.88.0.1/24 ListenPort = 51820 PrivateKey = qFvMNYv27vwcIfJuu6fXLcxYNscOTvlDxmd9JzN8fV8= PostUp = sysctl -w net.ipv4.ip_forward=1 ; iptables -A FORWARD -i wg0 -j ACCEPT ; iptables -A FORWARD -o wg0 -j ACCEPT PostDown = iptables -D FORWARD -i wg0 -j ACCEPT ; iptables -D FORWARD -o wg0 -j ACCEPT [Peer] PublicKey = dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= AllowedIPs = 10.88.0.2/32 PersistentKeepalive = 25 root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# sudo cat /etc/wireguard/wg0.conf [Interface] Address = 10.88.0.1/24 ListenPort = 51820 PrivateKey = qFvMNYv27vwcIfJuu6fXLcxYNscOTvlDxmd9JzN8fV8= PostUp = sysctl -w net.ipv4.ip_forward=1 ; iptables -A FORWARD -i wg0 -j ACCEPT ; iptables -A FORWARD -o wg0 -j ACCEPT PostDown = iptables -D FORWARD -i wg0 -j ACCEPT ; iptables -D FORWARD -o wg0 -j ACCEPT [Peer] PublicKey = dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= AllowedIPs = 10.88.0.2/32 PersistentKeepalive = 25 root@VM-12-5-ubuntu:~# curl -H 'Host: zhuanfa.axzys.cn' http://10.88.0.2:32150/ Hostname: whoami-678b958ccd-5x2gj IP: 127.0.0.1 IP: ::1 IP: 10.244.2.60 IP: fe80::6498:49ff:fe98:6d1 RemoteAddr: 10.244.2.47:48502 GET / HTTP/1.1 Host: zhuanfa.axzys.cn User-Agent: curl/7.81.0 Accept: */* Accept-Encoding: gzip X-Forwarded-For: 10.244.0.0 X-Forwarded-Host: zhuanfa.axzys.cn X-Forwarded-Port: 80 X-Forwarded-Proto: http X-Forwarded-Server: traefik-release-589c7ff647-r2txc X-Real-Ip: 10.244.0.0 root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# curl -H 'Host: zhuanfa.axzys.cn' http://10.88.0.2:32150/ ^C root@VM-12-5-ubuntu:~# yum install nginx -y Command 'yum' not found, did you mean: command 'gum' from snap gum (0.13.0) command 'uum' from deb freewnn-jserver (1.1.1~a021+cvs20130302-7build1) command 'sum' from deb coreutils (8.32-4.1ubuntu1.2) command 'zum' from deb perforate (1.2-5.1) command 'yum4' from deb nextgen-yum4 (4.5.2-6) command 'num' from deb quickcal (2.4-1) See 'snap info <snapname>' for additional versions. root@VM-12-5-ubuntu:~# atp install nginx -y Command 'atp' not found, but there are 18 similar ones. root@VM-12-5-ubuntu:~# apt install nginx Reading package lists... Done Building dependency tree... Done Reading state information... Done The following additional packages will be installed: libnginx-mod-http-geoip2 libnginx-mod-http-image-filter libnginx-mod-http-xslt-filter libnginx-mod-mail libnginx-mod-stream libnginx-mod-stream-geoip2 nginx-common nginx-core Suggested packages: fcgiwrap nginx-doc ssl-cert The following NEW packages will be installed: libnginx-mod-http-geoip2 libnginx-mod-http-image-filter libnginx-mod-http-xslt-filter libnginx-mod-mail libnginx-mod-stream libnginx-mod-stream-geoip2 nginx nginx-common nginx-core 0 upgraded, 9 newly installed, 0 to remove and 202 not upgraded. Need to get 698 kB of archives. After this operation, 2,391 kB of additional disk space will be used. Do you want to continue? [Y/n] Y Get:1 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 nginx-common all 1.18.0-6ubuntu14.7 [40.1 kB] Get:2 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 libnginx-mod-http-geoip2 amd64 1.18.0-6ubuntu14.7 [12.0 kB] Get:3 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 libnginx-mod-http-image-filter amd64 1.18.0-6ubuntu14.7 [15.5 kB] Get:4 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 libnginx-mod-http-xslt-filter amd64 1.18.0-6ubuntu14.7 [13.8 kB] Get:5 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 libnginx-mod-mail amd64 1.18.0-6ubuntu14.7 [45.8 kB] Get:6 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 libnginx-mod-stream amd64 1.18.0-6ubuntu14.7 [73.0 kB] Get:7 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 libnginx-mod-stream-geoip2 amd64 1.18.0-6ubuntu14.7 [10.1 kB] Get:8 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 nginx-core amd64 1.18.0-6ubuntu14.7 [483 kB] Get:9 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 nginx amd64 1.18.0-6ubuntu14.7 [3,878 B] Fetched 698 kB in 1s (745 kB/s) Preconfiguring packages ... Selecting previously unselected package nginx-common. (Reading database ... 88755 files and directories currently installed.) Preparing to unpack .../0-nginx-common_1.18.0-6ubuntu14.7_all.deb ... Unpacking nginx-common (1.18.0-6ubuntu14.7) ... Selecting previously unselected package libnginx-mod-http-geoip2. Preparing to unpack .../1-libnginx-mod-http-geoip2_1.18.0-6ubuntu14.7_amd64.deb ... Unpacking libnginx-mod-http-geoip2 (1.18.0-6ubuntu14.7) ... Selecting previously unselected package libnginx-mod-http-image-filter. Preparing to unpack .../2-libnginx-mod-http-image-filter_1.18.0-6ubuntu14.7_amd64.deb ... Unpacking libnginx-mod-http-image-filter (1.18.0-6ubuntu14.7) ... Selecting previously unselected package libnginx-mod-http-xslt-filter. Preparing to unpack .../3-libnginx-mod-http-xslt-filter_1.18.0-6ubuntu14.7_amd64.deb ... Unpacking libnginx-mod-http-xslt-filter (1.18.0-6ubuntu14.7) ... Selecting previously unselected package libnginx-mod-mail. Preparing to unpack .../4-libnginx-mod-mail_1.18.0-6ubuntu14.7_amd64.deb ... Unpacking libnginx-mod-mail (1.18.0-6ubuntu14.7) ... Selecting previously unselected package libnginx-mod-stream. Preparing to unpack .../5-libnginx-mod-stream_1.18.0-6ubuntu14.7_amd64.deb ... Unpacking libnginx-mod-stream (1.18.0-6ubuntu14.7) ... Selecting previously unselected package libnginx-mod-stream-geoip2. Preparing to unpack .../6-libnginx-mod-stream-geoip2_1.18.0-6ubuntu14.7_amd64.deb ... Unpacking libnginx-mod-stream-geoip2 (1.18.0-6ubuntu14.7) ... Selecting previously unselected package nginx-core. Preparing to unpack .../7-nginx-core_1.18.0-6ubuntu14.7_amd64.deb ... Unpacking nginx-core (1.18.0-6ubuntu14.7) ... Selecting previously unselected package nginx. Preparing to unpack .../8-nginx_1.18.0-6ubuntu14.7_amd64.deb ... Unpacking nginx (1.18.0-6ubuntu14.7) ... Setting up nginx-common (1.18.0-6ubuntu14.7) ... Created symlink /etc/systemd/system/multi-user.target.wants/nginx.service → /lib/systemd/system/nginx.service. Setting up libnginx-mod-http-xslt-filter (1.18.0-6ubuntu14.7) ... Setting up libnginx-mod-http-geoip2 (1.18.0-6ubuntu14.7) ... Setting up libnginx-mod-mail (1.18.0-6ubuntu14.7) ... Setting up libnginx-mod-http-image-filter (1.18.0-6ubuntu14.7) ... Setting up libnginx-mod-stream (1.18.0-6ubuntu14.7) ... Setting up libnginx-mod-stream-geoip2 (1.18.0-6ubuntu14.7) ... Setting up nginx-core (1.18.0-6ubuntu14.7) ... * Upgrading binary nginx [ OK ] Setting up nginx (1.18.0-6ubuntu14.7) ... Processing triggers for man-db (2.10.2-1) ... Processing triggers for ufw (0.36.1-4build1) ... Scanning processes... Scanning linux images... Running kernel seems to be up-to-date. No services need to be restarted. No containers need to be restarted. No user sessions are running outdated binaries. No VM guests are running outdated hypervisor (qemu) binaries on this host. root@VM-12-5-ubuntu:~# vi /etc/nginx/sites-available/zhuanfa.axzys.cn root@VM-12-5-ubuntu:~# ln -s /etc/nginx/sites-available/zhuanfa.axzys.cn /etc/nginx/sites-enabled/ root@VM-12-5-ubuntu:~# nginx -t && systemctl reload nginx nginx: the configuration file /etc/nginx/nginx.conf syntax is ok nginx: configuration file /etc/nginx/nginx.conf test is successful root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# apt-get install -y certbot python3-certbot-nginx Reading package lists... Done Building dependency tree... Done Reading state information... Done The following additional packages will be installed: python3-acme python3-certbot python3-certifi python3-configargparse python3-icu python3-josepy python3-parsedatetime python3-requests python3-requests-toolbelt python3-rfc3339 python3-tz python3-urllib3 python3-zope.component python3-zope.event python3-zope.hookable Suggested packages: python-certbot-doc python3-certbot-apache python-acme-doc python-certbot-nginx-doc python3-socks python-requests-doc The following NEW packages will be installed: certbot python3-acme python3-certbot python3-certbot-nginx python3-certifi python3-configargparse python3-icu python3-josepy python3-parsedatetime python3-requests python3-requests-toolbelt python3-rfc3339 python3-tz python3-urllib3 python3-zope.component python3-zope.event python3-zope.hookable 0 upgraded, 17 newly installed, 0 to remove and 202 not upgraded. Need to get 1,322 kB of archives. After this operation, 6,211 kB of additional disk space will be used. Get:1 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-josepy all 1.10.0-1 [22.0 kB] Get:2 http://mirrors.tencentyun.com/ubuntu jammy/main amd64 python3-certifi all 2020.6.20-1 [150 kB] Get:3 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 python3-urllib3 all 1.26.5-1~exp1ubuntu0.3 [98.6 kB] Get:4 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 python3-requests all 2.25.1+dfsg-2ubuntu0.3 [48.8 kB] Get:5 http://mirrors.tencentyun.com/ubuntu jammy/main amd64 python3-requests-toolbelt all 0.9.1-1 [38.0 kB] Get:6 http://mirrors.tencentyun.com/ubuntu jammy-updates/main amd64 python3-tz all 2022.1-1ubuntu0.22.04.1 [30.7 kB] Get:7 http://mirrors.tencentyun.com/ubuntu jammy/main amd64 python3-rfc3339 all 1.1-3 [7,110 B] Get:8 http://mirrors.tencentyun.com/ubuntu jammy-updates/universe amd64 python3-acme all 1.21.0-1ubuntu0.1 [36.4 kB] Get:9 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-configargparse all 1.5.3-1 [26.9 kB] Get:10 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-parsedatetime all 2.6-2 [32.9 kB] Get:11 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-zope.hookable amd64 5.1.0-1build1 [11.6 kB] Get:12 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-zope.event all 4.4-3 [8,180 B] Get:13 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-zope.component all 4.3.0-3 [38.3 kB] Get:14 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-certbot all 1.21.0-1build1 [175 kB] Get:15 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 certbot all 1.21.0-1build1 [21.3 kB] Get:16 http://mirrors.tencentyun.com/ubuntu jammy/universe amd64 python3-certbot-nginx all 1.21.0-1 [35.4 kB] Get:17 http://mirrors.tencentyun.com/ubuntu jammy/main amd64 python3-icu amd64 2.8.1-0ubuntu2 [540 kB] Fetched 1,322 kB in 2s (759 kB/s) Preconfiguring packages ... Selecting previously unselected package python3-josepy. (Reading database ... 88845 files and directories currently installed.) Preparing to unpack .../00-python3-josepy_1.10.0-1_all.deb ... Unpacking python3-josepy (1.10.0-1) ... Selecting previously unselected package python3-certifi. Preparing to unpack .../01-python3-certifi_2020.6.20-1_all.deb ... Unpacking python3-certifi (2020.6.20-1) ... Selecting previously unselected package python3-urllib3. Preparing to unpack .../02-python3-urllib3_1.26.5-1~exp1ubuntu0.3_all.deb ... Unpacking python3-urllib3 (1.26.5-1~exp1ubuntu0.3) ... Selecting previously unselected package python3-requests. Preparing to unpack .../03-python3-requests_2.25.1+dfsg-2ubuntu0.3_all.deb ... Unpacking python3-requests (2.25.1+dfsg-2ubuntu0.3) ... Selecting previously unselected package python3-requests-toolbelt. Preparing to unpack .../04-python3-requests-toolbelt_0.9.1-1_all.deb ... Unpacking python3-requests-toolbelt (0.9.1-1) ... Selecting previously unselected package python3-tz. Preparing to unpack .../05-python3-tz_2022.1-1ubuntu0.22.04.1_all.deb ... Unpacking python3-tz (2022.1-1ubuntu0.22.04.1) ... Selecting previously unselected package python3-rfc3339. Preparing to unpack .../06-python3-rfc3339_1.1-3_all.deb ... Unpacking python3-rfc3339 (1.1-3) ... Selecting previously unselected package python3-acme. Preparing to unpack .../07-python3-acme_1.21.0-1ubuntu0.1_all.deb ... Unpacking python3-acme (1.21.0-1ubuntu0.1) ... Selecting previously unselected package python3-configargparse. Preparing to unpack .../08-python3-configargparse_1.5.3-1_all.deb ... Unpacking python3-configargparse (1.5.3-1) ... Selecting previously unselected package python3-parsedatetime. Preparing to unpack .../09-python3-parsedatetime_2.6-2_all.deb ... Unpacking python3-parsedatetime (2.6-2) ... Selecting previously unselected package python3-zope.hookable. Preparing to unpack .../10-python3-zope.hookable_5.1.0-1build1_amd64.deb ... Unpacking python3-zope.hookable (5.1.0-1build1) ... Selecting previously unselected package python3-zope.event. Preparing to unpack .../11-python3-zope.event_4.4-3_all.deb ... Unpacking python3-zope.event (4.4-3) ... Selecting previously unselected package python3-zope.component. Preparing to unpack .../12-python3-zope.component_4.3.0-3_all.deb ... Unpacking python3-zope.component (4.3.0-3) ... Selecting previously unselected package python3-certbot. Preparing to unpack .../13-python3-certbot_1.21.0-1build1_all.deb ... Unpacking python3-certbot (1.21.0-1build1) ... Selecting previously unselected package certbot. Preparing to unpack .../14-certbot_1.21.0-1build1_all.deb ... Unpacking certbot (1.21.0-1build1) ... Selecting previously unselected package python3-certbot-nginx. Preparing to unpack .../15-python3-certbot-nginx_1.21.0-1_all.deb ... Unpacking python3-certbot-nginx (1.21.0-1) ... Selecting previously unselected package python3-icu. Preparing to unpack .../16-python3-icu_2.8.1-0ubuntu2_amd64.deb ... Unpacking python3-icu (2.8.1-0ubuntu2) ... Setting up python3-configargparse (1.5.3-1) ... Setting up python3-parsedatetime (2.6-2) ... Setting up python3-icu (2.8.1-0ubuntu2) ... Setting up python3-zope.event (4.4-3) ... Setting up python3-tz (2022.1-1ubuntu0.22.04.1) ... Setting up python3-zope.hookable (5.1.0-1build1) ... Setting up python3-certifi (2020.6.20-1) ... Setting up python3-urllib3 (1.26.5-1~exp1ubuntu0.3) ... Setting up python3-josepy (1.10.0-1) ... Setting up python3-rfc3339 (1.1-3) ... Setting up python3-zope.component (4.3.0-3) ... Setting up python3-requests (2.25.1+dfsg-2ubuntu0.3) ... Setting up python3-requests-toolbelt (0.9.1-1) ... Setting up python3-acme (1.21.0-1ubuntu0.1) ... Setting up python3-certbot (1.21.0-1build1) ... Setting up certbot (1.21.0-1build1) ... Created symlink /etc/systemd/system/timers.target.wants/certbot.timer → /lib/systemd/system/certbot.timer. Setting up python3-certbot-nginx (1.21.0-1) ... Processing triggers for man-db (2.10.2-1) ... Scanning processes... Scanning linux images... Running kernel seems to be up-to-date. No services need to be restarted. No containers need to be restarted. No user sessions are running outdated binaries. No VM guests are running outdated hypervisor (qemu) binaries on this host. root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# certbot --nginx -d zhuanfa.axzys.cn Saving debug log to /var/log/letsencrypt/letsencrypt.log Enter email address (used for urgent renewal and security notices) (Enter 'c' to cancel): 7902731@qq.com - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Please read the Terms of Service at https://letsencrypt.org/documents/LE-SA-v1.5-February-24-2025.pdf. You must agree in order to register with the ACME server. Do you agree? - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - (Y)es/(N)o: Y - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Would you be willing, once your first certificate is successfully issued, to share your email address with the Electronic Frontier Foundation, a founding partner of the Let's Encrypt project and the non-profit organization that develops Certbot? We'd like to send you email about our work encrypting the web, EFF news, campaigns, and ways to support digital freedom. - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - (Y)es/(N)o: Y Account registered. Requesting a certificate for zhuanfa.axzys.cn Successfully received certificate. Certificate is saved at: /etc/letsencrypt/live/zhuanfa.axzys.cn/fullchain.pem Key is saved at: /etc/letsencrypt/live/zhuanfa.axzys.cn/privkey.pem This certificate expires on 2025-11-25. These files will be updated when the certificate renews. Certbot has set up a scheduled task to automatically renew this certificate in the background. Deploying certificate Successfully deployed certificate for zhuanfa.axzys.cn to /etc/nginx/sites-enabled/zhuanfa.axzys.cn Congratulations! You have successfully enabled HTTPS on https://zhuanfa.axzys.cn - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - If you like Certbot, please consider supporting our work by: * Donating to ISRG / Let's Encrypt: https://letsencrypt.org/donate * Donating to EFF: https://eff.org/donate-le - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - root@VM-12-5-ubuntu:~# root@VM-12-5-ubuntu:~# [root@k8s-01 ~]# sudo dnf install -y wireguard-tools Last metadata expiration check: 0:00:43 ago on Wed Aug 27 13:52:47 2025. Dependencies resolved. ===================================================================================================================================================================================================================================== Package Architecture Version Repository Size ===================================================================================================================================================================================================================================== Installing: wireguard-tools x86_64 1.0.20210914-3.el9 appstream 114 k Installing dependencies: systemd-resolved x86_64 252-51.el9_6.1 baseos 380 k Transaction Summary ===================================================================================================================================================================================================================================== Install 2 Packages Total download size: 494 k Installed size: 1.0 M Downloading Packages: (1/2): wireguard-tools-1.0.20210914-3.el9.x86_64.rpm 598 kB/s | 114 kB 00:00 (2/2): systemd-resolved-252-51.el9_6.1.x86_64.rpm 1.5 MB/s | 380 kB 00:00 ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- Total 293 kB/s | 494 kB 00:01 Running transaction check Transaction check succeeded. Running transaction test Transaction test succeeded. Running transaction Preparing : 1/1 Running scriptlet: systemd-resolved-252-51.el9_6.1.x86_64 1/2 Installing : systemd-resolved-252-51.el9_6.1.x86_64 1/2 Running scriptlet: systemd-resolved-252-51.el9_6.1.x86_64 1/2 Installing : wireguard-tools-1.0.20210914-3.el9.x86_64 2/2 Running scriptlet: wireguard-tools-1.0.20210914-3.el9.x86_64 2/2 Verifying : systemd-resolved-252-51.el9_6.1.x86_64 1/2 Verifying : wireguard-tools-1.0.20210914-3.el9.x86_64 2/2 Installed: systemd-resolved-252-51.el9_6.1.x86_64 wireguard-tools-1.0.20210914-3.el9.x86_64 Complete! [root@k8s-01 ~]# wg genkey | tee /etc/wireguard/privatekey | wg pubkey > /etc/wireguard/publickey [root@k8s-01 ~]# vi cat /etc/wireguard/publickey 2 files to edit [root@k8s-01 ~]# cat /etc/wireguard/publickey n7/nzuiBYLFm+ijhBR8d0G/JcNPu+eKg1V//vX5yuBU= [root@k8s-01 ~]# sudo systemctl stop firewalld [root@k8s-01 ~]# vi /etc/wireguard/wg0.conf [root@k8s-01 ~]# systemctl enable --now wg-quick@wg0 Created symlink /etc/systemd/system/multi-user.target.wants/wg-quick@wg0.service → /usr/lib/systemd/system/wg-quick@.service. [root@k8s-01 ~]# wg show interface: wg0 public key: dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= private key: (hidden) listening port: 42179 peer: BgxjDizUdEATpdh0iZ7Y+zQo2iVyqRBgp70CemeZ30A= endpoint: 43.138.186.171:51820 allowed ips: 10.88.0.1/32 transfer: 0 B received, 148 B sent persistent keepalive: every 25 seconds [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# ip a 1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000 link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00 inet 127.0.0.1/8 scope host lo valid_lft forever preferred_lft forever inet6 ::1/128 scope host valid_lft forever preferred_lft forever 2: ens33: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel state UP group default qlen 1000 link/ether 00:0c:29:d4:4f:e7 brd ff:ff:ff:ff:ff:ff altname enp2s1 inet 192.168.173.101/24 brd 192.168.173.255 scope global noprefixroute ens33 valid_lft forever preferred_lft forever inet6 fe80::20c:29ff:fed4:4fe7/64 scope link noprefixroute valid_lft forever preferred_lft forever 3: docker0: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc noqueue state DOWN group default link/ether b6:ee:bd:b4:cf:87 brd ff:ff:ff:ff:ff:ff inet 172.17.0.1/16 brd 172.17.255.255 scope global docker0 valid_lft forever preferred_lft forever 4: kube-ipvs0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default link/ether c2:cd:7c:86:14:bd brd ff:ff:ff:ff:ff:ff inet 10.106.48.170/32 scope global kube-ipvs0 valid_lft forever preferred_lft forever inet 10.100.101.161/32 scope global kube-ipvs0 valid_lft forever preferred_lft forever inet 10.96.0.10/32 scope global kube-ipvs0 valid_lft forever preferred_lft forever inet 10.98.232.237/32 scope global kube-ipvs0 valid_lft forever preferred_lft forever inet 10.100.223.32/32 scope global kube-ipvs0 valid_lft forever preferred_lft forever inet 10.96.0.1/32 scope global kube-ipvs0 valid_lft forever preferred_lft forever inet 10.100.147.23/32 scope global kube-ipvs0 valid_lft forever preferred_lft forever inet 10.101.189.236/32 scope global kube-ipvs0 valid_lft forever preferred_lft forever inet 10.97.132.101/32 scope global kube-ipvs0 valid_lft forever preferred_lft forever 5: flannel.1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1450 qdisc noqueue state UNKNOWN group default link/ether 5e:9d:fa:96:af:2b brd ff:ff:ff:ff:ff:ff inet 10.244.0.0/32 scope global flannel.1 valid_lft forever preferred_lft forever inet6 fe80::5c9d:faff:fe96:af2b/64 scope link valid_lft forever preferred_lft forever 6: cni0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1450 qdisc noqueue state UP group default qlen 1000 link/ether 72:66:f6:85:8e:aa brd ff:ff:ff:ff:ff:ff inet 10.244.0.1/24 brd 10.244.0.255 scope global cni0 valid_lft forever preferred_lft forever inet6 fe80::7066:f6ff:fe85:8eaa/64 scope link valid_lft forever preferred_lft forever 160: veth26c6ffcc@if2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1450 qdisc noqueue master cni0 state UP group default link/ether de:52:a9:34:79:f6 brd ff:ff:ff:ff:ff:ff link-netns cni-b0039ff2-418f-6ff2-d3dd-b65dd3d8bee4 inet6 fe80::dc52:a9ff:fe34:79f6/64 scope link valid_lft forever preferred_lft forever 161: vetha4607aaa@if2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1450 qdisc noqueue master cni0 state UP group default link/ether de:5a:9b:4e:6f:04 brd ff:ff:ff:ff:ff:ff link-netns cni-1f503360-9a27-073a-b8c7-5ee8286a56d2 inet6 fe80::dc5a:9bff:fe4e:6f04/64 scope link valid_lft forever preferred_lft forever 162: veth4615fa64@if2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1450 qdisc noqueue master cni0 state UP group default link/ether 1a:cc:41:1c:f2:9d brd ff:ff:ff:ff:ff:ff link-netns cni-532a4e09-6e09-1113-3044-1d864ac3acf5 inet6 fe80::18cc:41ff:fe1c:f29d/64 scope link valid_lft forever preferred_lft forever 163: wg0: <POINTOPOINT,NOARP,UP,LOWER_UP> mtu 1420 qdisc noqueue state UNKNOWN group default qlen 1000 link/none inet 10.88.0.2/24 scope global wg0 valid_lft forever preferred_lft forever [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# sudo wg show interface: wg0 public key: dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= private key: (hidden) listening port: 42179 peer: BgxjDizUdEATpdh0iZ7Y+zQo2iVyqRBgp70CemeZ30A= endpoint: 43.138.186.171:51820 allowed ips: 10.88.0.1/32 transfer: 0 B received, 27.46 KiB sent persistent keepalive: every 25 seconds [root@k8s-01 ~]# cat /etc/wireguard/wg0.conf [Interface] Address = 10.88.0.2/24 PrivateKey = n7/nzuiBYLFm+ijhBR8d0G/JcNPu+eKg1V//vX5yuBU= [Peer] PublicKey = BgxjDizUdEATpdh0iZ7Y+zQo2iVyqRBgp70CemeZ30A= Endpoint = 43.138.186.171:51820 AllowedIPs = 10.88.0.1/32 PersistentKeepalive = 25 [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# cat /etc/wireguard/k8s.pub cat: /etc/wireguard/k8s.pub: No such file or directory [root@k8s-01 ~]# cat cat /etc/wireguard/publickey cat: cat: No such file or directory n7/nzuiBYLFm+ijhBR8d0G/JcNPu+eKg1V//vX5yuBU= [root@k8s-01 ~]# vi /etc/wireguard/wg0.conf [root@k8s-01 ~]# systemctl restart wg-quick@wg0 [root@k8s-01 ~]# wg show interface: wg0 public key: dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= private key: (hidden) listening port: 46509 peer: qFvMNYv27vwcIfJuu6fXLcxYNscOTvlDxmd9JzN8fV8= endpoint: 43.138.186.171:51820 allowed ips: 10.88.0.1/32 transfer: 0 B received, 592 B sent persistent keepalive: every 25 seconds [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# sysctl -w net.ipv4.conf.all.rp_filter=2 sysctl -w net.ipv4.conf.wg0.rp_filter=2 net.ipv4.conf.all.rp_filter = 2 net.ipv4.conf.wg0.rp_filter = 2 [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# ip -c a show dev wg0 167: wg0: <POINTOPOINT,NOARP,UP,LOWER_UP> mtu 1420 qdisc noqueue state UNKNOWN group default qlen 1000 link/none inet 10.88.0.2/24 scope global wg0 valid_lft forever preferred_lft forever [root@k8s-01 ~]# watch -n1 wg show [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# sudo wg showconf wg0 [Interface] ListenPort = 46509 PrivateKey = mL/nzuiBYLFm+ijhBR8d0G/JcNPu+eKg1V//vX5yuFU= [Peer] PublicKey = qFvMNYv27vwcIfJuu6fXLcxYNscOTvlDxmd9JzN8fV8= AllowedIPs = 10.88.0.1/32 Endpoint = 43.138.186.171:51820 PersistentKeepalive = 25 [root@k8s-01 ~]# sudo cat /etc/wireguard/wg0.conf [Interface] Address = 10.88.0.2/24 PrivateKey = n7/nzuiBYLFm+ijhBR8d0G/JcNPu+eKg1V//vX5yuBU= [Peer] PublicKey = qFvMNYv27vwcIfJuu6fXLcxYNscOTvlDxmd9JzN8fV8= Endpoint = 43.138.186.171:51820 AllowedIPs = 10.88.0.1/32 PersistentKeepalive = 25 [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# sudo sed -i 's|^PrivateKey = .*|PrivateKey = mL/...FU=|' /etc/wireguard/wg0.conf [root@k8s-01 ~]# sudo sed -i '/^\[Interface\]/a ListenPort = 46509' /etc/wireguard/wg0.conf [root@k8s-01 ~]# echo 'mL/...FU=' | sudo wg pubkey wg: Key is not the correct length or format [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# CLIENT_PRIV=$(sudo wg showconf wg0 | awk '/^PrivateKey/ {print $3; exit}') [root@k8s-01 ~]# CLIENT_PUB=$(echo "$CLIENT_PRIV" | wg pubkey) [root@k8s-01 ~]# echo "CLIENT_PUB = $CLIENT_PUB" CLIENT_PUB = dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= [root@k8s-01 ~]# sudo sed -i "s|^PrivateKey = .*|PrivateKey = $CLIENT_PRIV|" /etc/wireguard/wg0.conf [root@k8s-01 ~]# grep -n '^ListenPort' /etc/wireguard/wg0.conf 2:ListenPort = 46509 [root@k8s-01 ~]# vi /etc/wireguard/wg0.conf [root@k8s-01 ~]# cat /etc/wireguard/wg0.conf [Interface] ListenPort = 46509 Address = 10.88.0.2/24 PrivateKey = mL/nzuiBYLFm+ijhBR8d0G/JcNPu+eKg1V//vX5yuFU= [Peer] PublicKey = qFvMNYv27vwcIfJuu6fXLcxYNscOTvlDxmd9JzN8fV8= Endpoint = 43.138.186.171:51820 AllowedIPs = 10.88.0.1/32 PersistentKeepalive = 25 [root@k8s-01 ~]# sudo systemctl restart wg-quick@wg0 [root@k8s-01 ~]# wg show interface: wg0 public key: dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= private key: (hidden) listening port: 46509 peer: qFvMNYv27vwcIfJuu6fXLcxYNscOTvlDxmd9JzN8fV8= endpoint: 43.138.186.171:51820 allowed ips: 10.88.0.1/32 transfer: 0 B received, 148 B sent persistent keepalive: every 25 seconds [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# sudo sed -i 's|^PublicKey = .*|PublicKey = 4GSWTJJq5zv6yd0pa4apypDSxxE+J7HckZ0OJOdfNlg=|' /etc/wireguard/wg0.conf sudo systemctl restart wg-quick@wg0 wg show interface: wg0 public key: dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= private key: (hidden) listening port: 46509 peer: 4GSWTJJq5zv6yd0pa4apypDSxxE+J7HckZ0OJOdfNlg= endpoint: 43.138.186.171:51820 allowed ips: 10.88.0.1/32 latest handshake: Now transfer: 124 B received, 180 B sent persistent keepalive: every 25 seconds [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# [root@k8s-01 ~]# wg show interface: wg0 public key: dF92nKBqKgDRGxNuDvm3gCKgaBwfyuBXqBecLbLs7ik= private key: (hidden) listening port: 46509 peer: 4GSWTJJq5zv6yd0pa4apypDSxxE+J7HckZ0OJOdfNlg= endpoint: 43.138.186.171:51820 allowed ips: 10.88.0.1/32 latest handshake: 16 seconds ago transfer: 124 B received, 180 B sent persistent keepalive: every 25 seconds [root@k8s-01 ~]# ping -c 3 10.88.0.1 PING 10.88.0.1 (10.88.0.1) 56(84) bytes of data. 64 bytes from 10.88.0.1: icmp_seq=1 ttl=64 time=6.22 ms 64 bytes from 10.88.0.1: icmp_seq=2 ttl=64 time=5.92 ms 64 bytes from 10.88.0.1: icmp_seq=3 ttl=64 time=63.9 ms --- 10.88.0.1 ping statistics --- 3 packets transmitted, 3 received, 0% packet loss, time 2003ms rtt min/avg/max/mdev = 5.921/25.348/63.904/27.263 ms [root@k8s-01 ~]# ping -c 3 10.88.0.1 PING 10.88.0.1 (10.88.0.1) 56(84) bytes of data. 64 bytes from 10.88.0.1: icmp_seq=1 ttl=64 time=6.08 ms 64 bytes from 10.88.0.1: icmp_seq=2 ttl=64 time=6.24 ms 64 bytes from 10.88.0.1: icmp_seq=3 ttl=64 time=6.00 ms --- 10.88.0.1 ping statistics --- 3 packets transmitted, 3 received, 0% packet loss, time 2002ms rtt min/avg/max/mdev = 5.998/6.105/6.242/0.101 ms
-
Exporte + 基础指标 一、解压 & 目录说明unzip sys-exporter.zip -d sys-exporter cd sys-exporter tree -L 3 # . # ├── Makefile # ├── README.md # ├── cmd/sys-exporter/main.go # ├── go.mod # └── internal/collectors/ # ├── disk_usage.go # ├── disk_usage_test.go # ├── net_conn.go # ├── net_conn_test.go # ├── proc_rss.go # └── proc_rss_test.go 关键点： 使用自定义 Registry，同时注册 process 和 go collector。 /metrics 使用 promhttp.HandlerFor(reg, promhttp.HandlerOpts{EnableOpenMetrics:true})。 自带 /live、/ready，/ready 会尝试 Gather()，失败返回 503。 已挂好 /debug/pprof/*，方便做 CPU/内存采样。 三个示例指标： sys_mount_usage_ratio{mountpoint="/data"} （附带 sys_mount_used_bytes / sys_mount_total_bytes） sys_network_open_sockets{proto="tcp|udp", family="ipv4|ipv6"} sys_process_resident_memory_bytes（Exporter 进程自身 RSS）二、运行脚手架（本地 make run） 2.1 前置准备（只做一次）#下载go wget https://go.dev/dl/go1.22.5.linux-amd64.tar.gz #解压go sudo tar -C /usr/local -xzf go1.22.5.linux-amd64.tar.gz # 使用 vim： sudo vim ~/.bashrc #在文件的最后，添加以下几行： export PATH=$PATH:/usr/local/go/bin export GOPATH=$HOME/go export PATH=$PATH:$GOPATH/bin #立即生效 source ~/.bashrc #验证安装 go version #创建工作目录 mkdir -p ~/work && cd ~/work2.2一键跑起来（/metrics、/live、/ready）# 可选：拉依赖 make tidy # 启动 如果没有data目录 需要提前创建 make run # 日志应看到：sys-exporter listening on :9090 (mount=/data)#报错 root@k8s-01:~/woke/sys-exporter# make run GO111MODULE=on go run ./cmd/sys-exporter 2025/08/25 07:47:24 sys-exporter listening on :9090 (mount=/data) root@k8s-01:~/woke/sys-exporter# make test GO111MODULE=on go test ./... -race -count=1 # github.com/example/sys-exporter/internal/collectors [github.com/example/sys-exporter/internal/collectors.test] internal/collectors/disk_usage_test.go:22:37: undefined: testutil.NewGaugeFromDesc ? github.com/example/sys-exporter/cmd/sys-exporter [no test files] FAIL github.com/example/sys-exporter/internal/collectors [build failed] FAIL make: *** [Makefile:10: test] Error 1 root@k8s-01:~/woke/sys-exporter 这是单测里用了不存在的函数导致编译失败。prometheus/testutil 并没有 NewGaugeFromDesc 这个 API（我在示例里多写了一句检查 ratio 的代码）。解决方法：把那几行删掉，用 CollectAndCompare 做断言就够了。 #报错 root\@k8s-01:\~/woke/sys-exporter# make test GO111MODULE=on go test ./... -race -count=1 ? github.com/example/sys-exporter/cmd/sys-exporter \[no test files] \--- FAIL: TestProcRSSCollector (0.00s) proc\_rss\_test.go:31: metrics mismatch: +# HELP sys\_process\_resident\_memory\_bytes Resident memory (RSS) of the exporter process in bytes. +# TYPE sys\_process\_resident\_memory\_bytes gauge +sys\_process\_resident\_memory\_bytes 2.097152e+06 FAIL FAIL github.com/example/sys-exporter/internal/collectors 0.020s FAIL make: \*\*\* \[Makefile:10: test] Error 1 root\@k8s-01:~~/woke/sys-exporter# make tidy go mod tidy root\@k8s-01:~~/woke/sys-exporter# make test GO111MODULE=on go test ./... -race -count=1 ? github.com/example/sys-exporter/cmd/sys-exporter \[no test files] \--- FAIL: TestProcRSSCollector (0.00s) proc\_rss\_test.go:31: metrics mismatch: +# HELP sys\_process\_resident\_memory\_bytes Resident memory (RSS) of the exporter process in bytes. +# TYPE sys\_process\_resident\_memory\_bytes gauge +sys\_process\_resident\_memory\_bytes 2.097152e+06 FAIL FAIL github.com/example/sys-exporter/internal/collectors 0.018s FAIL make: \*\*\* \[Makefile:10: test] Error 1 root\@k8s-01:\~/woke/sys-exporter# cat internal/collectors/disk\_usage\_test.go package collectors import ( "strings" "testing" #解决办法 用下面的内容覆盖 internal/collectors/disk_usage_test.go： package collectors import ( "strings" "testing" "github.com/prometheus/client_golang/prometheus/testutil" ) func TestDiskUsageCollector_Metrics(t *testing.T) { mock := func(path string) (total, avail uint64, err error) { // 100 total, 25 available -> used=75, ratio=0.75 return 100, 25, nil } c := NewDiskUsageCollector("/data", mock) expected := # HELP sys_mount_total_bytes Total bytes for a mountpoint. # TYPE sys_mount_total_bytes gauge sys_mount_total_bytes{mountpoint="/data"} 100 # HELP sys_mount_used_bytes Used bytes for a mountpoint. # TYPE sys_mount_used_bytes gauge sys_mount_used_bytes{mountpoint="/data"} 75 # HELP sys_mount_usage_ratio Disk usage ratio (used/total) for a mountpoint. # TYPE sys_mount_usage_ratio gauge sys_mount_usage_ratio{mountpoint="/data"} 0.75 if err := testutil.CollectAndCompare(c, strings.NewReader(expected)); err != nil { t.Fatalf("unexpected metrics diff: %v", err) } } "github.com/prometheus/client_golang/prometheus/testutil" ) func TestDiskUsageCollector\_Metrics(t \*testing.T) { mock := func(path string) (total, avail uint64, err error) { // 100 total, 25 available -> used=75, ratio=0.75 return 100, 25, nil } c := NewDiskUsageCollector("/data", mock) expected := # HELP sys\_mount\_total\_bytes Total bytes for a mountpoint. # TYPE sys\_mount\_total\_bytes gauge sys\_mount\_total\_bytes{mountpoint="/data"} 100 # HELP sys\_mount\_used\_bytes Used bytes for a mountpoint. # TYPE sys\_mount\_used\_bytes gauge sys\_mount\_used\_bytes{mountpoint="/data"} 75 # HELP sys\_mount\_usage\_ratio Disk usage ratio (used/total) for a mountpoint. # TYPE sys\_mount\_usage\_ratio gauge sys\_mount\_usage\_ratio{mountpoint="/data"} 0.75 \ if err := testutil.CollectAndCompare(c, strings.NewReader(expected)); err != nil { t.Fatalf("unexpected metrics diff: %v", err) } } 你这个失败点在于单测期望的数值格式和PID 路径。 Prometheus 的文本输出里，浮点数经常是科学计数法（2.097152e+06），而你测试里写的是 2097152，导致对比失败。 你的测试里把 status 路径硬编码成 /fake/123/status，但实际 os.Getpid() 不一定是 123，最好用真实 PID 组路径。 把 internal/collectors/proc_rss_test.go 改成下面这样（两点都修了）： package collectors import ( "os" "path/filepath" "strings" "testing" "github.com/prometheus/client_golang/prometheus/testutil" ) func TestProcRSSCollector(t *testing.T) { root := "/fake" // 使用真实 PID 组路径，避免硬编码 123 statusPath := filepath.Join(root, strconv.Itoa(os.Getpid()), "status") data := "Name:\tapp\nVmRSS:\t2048 kB\n" // 2048 KB => 2,097,152 bytes // 只要命中 <root>/<pid>/status 就返回我们伪造的数据 reader := func(path string) ([]byte, error) { if path == statusPath { return []byte(data), nil } // 返回空数据，不要报错，Collector 会自己忽略 return []byte(""), nil } c := NewProcRSSCollector(root, reader) // 注意：Prometheus 文本输出常是科学计数法，这里用 e+06 exp := # HELP sys_process_resident_memory_bytes Resident memory (RSS) of the exporter process in bytes. # TYPE sys_process_resident_memory_bytes gauge sys_process_resident_memory_bytes 2.097152e+06 if err := testutil.CollectAndCompare(c, strings.NewReader(exp)); err != nil { t.Fatalf("metrics mismatch: %v", err) } }#报错 root\@k8s-01:~~/woke/sys-exporter# vi internal/collectors/disk\_usage\_test.go root\@k8s-01:~~/woke/sys-exporter# ls cmd go.mod go.sum internal Makefile README.md root\@k8s-01:~~/woke/sys-exporter# go clean -testcache root\@k8s-01:~~/woke/sys-exporter# make test GO111MODULE=on go test ./... -race -count=1 # github.com/example/sys-exporter/internal/collectors \[github.com/example/sys-exporter/internal/collectors.test] internal/collectors/proc\_rss\_test.go:12:6: TestProcRSSCollector redeclared in this block internal/collectors/disk\_usage\_test.go:12:6: other declaration of TestProcRSSCollector internal/collectors/disk\_usage\_test.go:15:36: undefined: strconv ? github.com/example/sys-exporter/cmd/sys-exporter \[no test files] FAIL github.com/example/sys-exporter/internal/collectors \[build failed] FAIL make: \*\*\* \[Makefile:10: test] Error 1 root\@k8s-01:\~/woke/sys-exporter# cat internal/collectors/disk\_usage\_test.go package collectors import ( "os" "path/filepath" "strings" "testing" "github.com/prometheus/client_golang/prometheus/testutil" ) func TestProcRSSCollector(t \*testing.T) { root := "/fake" // 使用真实 PID 组路径，避免硬编码 123 statusPath := filepath.Join(root, strconv.Itoa(os.Getpid()), "status") data := "Name:\tapp\nVmRSS:\t2048 kB\n" // 2048 KB => 2,097,152 bytes // 只要命中 <root>/<pid>/status 就返回我们伪造的数据 reader := func(path string) ([]byte, error) { if path == statusPath { return []byte(data), nil } // 返回空数据，不要报错，Collector 会自己忽略 return []byte(""), nil } c := NewProcRSSCollector(root, reader) // 注意：Prometheus 文本输出常是科学计数法，这里用 e+06 exp := ` # HELP sys\_process\_resident\_memory\_bytes Resident memory (RSS) of the exporter process in bytes. # TYPE sys\_process\_resident\_memory\_bytes gauge sys\_process\_resident\_memory\_bytes 2.097152e+06 \` if err := testutil.CollectAndCompare(c, strings.NewReader(exp)); err != nil { t.Fatalf("metrics mismatch: %v", err) } } 你把 disk_usage_test.go 覆盖成了 proc_rss_test.go 的内容，所以现在： 出现了重复的 TestProcRSSCollector（两个文件里同名测试）。 且缺少 strconv 的 import 还原 disk_usage_test.go 把它恢复成“磁盘使用率”的测试（不要放 RSS 的测试）： // internal/collectors/disk_usage_test.go package collectors import ( "strings" "testing" "github.com/prometheus/client_golang/prometheus/testutil" ) func TestDiskUsageCollector_Metrics(t *testing.T) { mock := func(path string) (total, avail uint64, err error) { // 100 total, 25 available -> used=75, ratio=0.75 return 100, 25, nil } c := NewDiskUsageCollector("/data", mock) expected := ` # HELP sys_mount_total_bytes Total bytes for a mountpoint. # TYPE sys_mount_total_bytes gauge sys_mount_total_bytes{mountpoint="/data"} 100 # HELP sys_mount_used_bytes Used bytes for a mountpoint. # TYPE sys_mount_used_bytes gauge sys_mount_used_bytes{mountpoint="/data"} 75 # HELP sys_mount_usage_ratio Disk usage ratio (used/total) for a mountpoint. # TYPE sys_mount_usage_ratio gauge sys_mount_usage_ratio{mountpoint="/data"} 0.75 ` if err := testutil.CollectAndCompare(c, strings.NewReader(expected)); err != nil { t.Fatalf("unexpected metrics diff: %v", err) } } 修正 proc_rss_test.go 确保它只包含 RSS 的测试，且 加上 strconv 的 import： // internal/collectors/proc_rss_test.go package collectors import ( "os" "path/filepath" "strconv" "strings" "testing" "github.com/prometheus/client_golang/prometheus/testutil" ) func TestProcRSSCollector(t *testing.T) { root := "/fake" statusPath := filepath.Join(root, strconv.Itoa(os.Getpid()), "status") data := "Name:\tapp\nVmRSS:\t2048 kB\n" // 2048 KB => 2,097,152 bytes reader := func(path string) ([]byte, error) { if path == statusPath { return []byte(data), nil } return []byte(""), nil } c := NewProcRSSCollector(root, reader) exp := ` # HELP sys_process_resident_memory_bytes Resident memory (RSS) of the exporter process in bytes. # TYPE sys_process_resident_memory_bytes gauge sys_process_resident_memory_bytes 2.097152e+06 ` if err := testutil.CollectAndCompare(c, strings.NewReader(exp)); err != nil { t.Fatalf("metrics mismatch: %v", err) } } #正常 root@k8s-01:~/woke/sys-exporter# go clean -testcache make test GO111MODULE=on go test ./... -race -count=1 ? github.com/example/sys-exporter/cmd/sys-exporter [no test files] ok github.com/example/sys-exporter/internal/collectors 1.019s#报错 root@k8s-01:~/woke/sys-exporter# make bench GO111MODULE=on go test ./... -run=^$ -bench=. -benchmem -count=1 -cpuprofile cpu.out -memprofile mem.out cannot use -cpuprofile flag with multiple packages make: *** [Makefile:13: bench] Error 1 #cannot use -cpuprofile flag with multiple packages 意思是：你下了 -cpuprofile 参数，但 go test ./... 会一次性跑多个包（cmd/... 和 internal/...），Go 不允许把多个包的基准同时写到一个 cpu.out 里。 解决方法 只 bench 你有基准的那个包（internal/collectors），而不是所有 ./...。 bench: GO111MODULE=on go test ./internal/collectors -run=^$$ -bench=. -benchmem -count=1 -cpuprofile cpu.out -memprofile mem.out @echo "" @echo "CPU profile: cpu.out | Mem profile: mem.out" @echo "Open an interactive view:" @echo " go tool pprof -http=:9999 cpu.out" 执行make bench 能正常生成 cpu.out 和 mem.out#报错 root\@k8s-01:\~/woke/sys-exporter# make bench GO111MODULE=on go test ./internal/collectors -run=^\$ -bench=. -benchmem -count=1 -cpuprofile cpu.out -memprofile mem.out PASS ok github.com/example/sys-exporter/internal/collectors 0.252s CPU profile: cpu.out | Mem profile: mem.out Open an interactive view: go tool pprof -http=:9999 cpu.out root\@k8s-01:~~/woke/sys-exporter# ls cmd collectors.test cpu.out go.mod go.sum internal Makefile mem.out README.md root\@k8s-01:~~/woke/sys-exporter# go tool pprof -http=:9999 cpu.out Serving web UI on [http://localhost:9999](http://localhost:9999) Couldn't find a suitable web browser! Set the BROWSER environment variable to your desired browser. 浏览器[http://192.168.30.180:9999/](http://192.168.30.180:9999/) 打不开 这是正常现象：现在的 pprof Web UI 只监听在本机回环地址（localhost），所以你从别的机器用 http://192.168.30.180:9999 打不开 #解决 go tool pprof -http=0.0.0.0:9999 cpu.out 如果浏览器打开以后显示：Could not execute dot; may need to install graphviz. 那就需要安装 Graphviz sudo apt-get install -y graphviz sudo yum install -y graphviz 重新打开 pprof Web go tool pprof -http=0.0.0.0:9999 cpu.out 这时点击 “View → Graph” 或 “Flame Graph” 就能显示图像了。 root@k8s-01:~/woke/sys-exporter# go tool pprof -http=0.0.0.0:9999 cpu.out Serving web UI on http://0.0.0.0:9999 Couldn't find a suitable web browser! Set the BROWSER environment variable to your desired browser. cd ~/woke/sys-exporter LISTEN_ADDR=":9090" MOUNTPOINT="/data" make run # 看到日志：sys-exporter listening on :9090 (mount=/data)# 抓在线 profile 并用 Web UI 展示 用正确的 URL抓在线 profile 在 exporter 正常监听后再执行（仍然在服务器上）： go tool pprof -http=0.0.0.0:9999 http://localhost:9090/debug/pprof/profile?seconds=15 注意要点： -http=0.0.0.0:9999 只是 Web UI 的监听地址； profile 的 URL 要作为最后一个参数单独给出（别写到 -http= 里）； 如果你把 exporter 绑在了别的端口，比如 :9100，就把 URL 换成： http://localhost:9100/debug/pprof/profile?seconds=15
