feat(ansible): ansible 初步稳定

ansible/.env.example

@@ -4,11 +4,8 @@
 # Tailscale Auth Key (必须)
 export TAILSCALE_AUTH_KEY=""
 
-# K3s Token (添加节点时需要，从首节点安装输出获取)
-export K3S_TOKEN=""
-
-# K3s Server URL (添加节点时需要)
-export K3S_SERVER_URL="https://k3s.dev.cm:6443"
+# K3s HA Server URL (添加节点时需要)
+export HA_SERVER_URL="https://k3s.example.com:6443"
 
 # SSH 密码 (如果使用密码认证，必须设置；如果使用密钥认证，留空)
 export SSH_PASSWORD=""

ansible/README.md

@@ -7,12 +7,15 @@
 ```
 ansible/
 ├── ansible.cfg                 # Ansible 配置
-├── inventory/hosts.yml         # 主机清单 ⭐ 需修改
-├── group_vars/all.yml          # 全局变量
-├── .env.example                # 环境变量模板
+├── .ansible-lint               # Lint 规则配置
+├── requirements.yml            # Ansible Galaxy 依赖
+├── inventory/
+│   ├── hosts.yml               # 主机清单 ⭐ 需修改
+│   └── group_vars/all.yml      # 全局变量
 ├── roles/
 │   ├── ssh/                    # SSH 安全加固
 │   │   ├── tasks/main.yml
+│   │   ├── handlers/main.yml
 │   │   └── templates/sshd_config.j2
 │   ├── common/                 # 基础配置 (hostname, sysctl, tailscale)
 │   │   ├── tasks/main.yml
@@ -24,9 +27,7 @@ ansible/
 │           ├── k3s-agent.yaml.j2    # Agent 配置
 │           └── registries.yaml.j2   # 镜像加速
 └── playbooks/
-    ├── site.yml                # 完整安装
-    ├── init.yml                # 首次安装 (含 SSH 加固)
-    └── add-node.yml            # 添加节点
+    └── site.yml                # 完整安装
 ```
 
 ## 快速开始
@@ -57,8 +58,7 @@ export TAILSCALE_AUTH_KEY="tskey-auth-xxx"
 # 首次安装 (SSH 加固)
 export SSH_PASSWORD="your-root-password"
 
-# 添加节点时 (从首节点安装输出获取)
-export K3S_TOKEN="K10xxx::server:xxx"
+# 单独添加节点时 (完整安装时自动获取)
 export K3S_SERVER_URL="https://10.0.0.1:6443"
 ```
 
@@ -74,10 +74,10 @@ ansible-playbook playbooks/site.yml --tags ssh,common,k3s,status
 ansible-playbook playbooks/site.yml
 
 # 方式三: 仅安装首个 master
-ansible-playbook playbooks/site.yml -l master1
+ansible-playbook playbooks/site.yml -l first-master-name
 
 # 方式四: 添加新节点
-ansible-playbook playbooks/add-node.yml -l agent1
+ansible-playbook playbooks/site.yml -l new-node-name
 ```
 
 ### 4. 获取 kubeconfig
@@ -108,8 +108,8 @@ kubectl get nodes
 | 变量 | 必须 | 说明 |
 |------|------|------|
 | `TAILSCALE_AUTH_KEY` | ✅ | Tailscale Auth Key |
-| `K3S_TOKEN` | 加入节点时 | 集群 Token |
-| `K3S_SERVER_URL` | 加入节点时 | API Server 地址 |
+| `K3S_TOKEN` | 单独添加节点时 | 集群 Token (完整安装时自动获取) |
+| `K3S_SERVER_URL` | 单独添加节点时 | API Server 地址 (完整安装时自动设置) |
 | `SSH_PASSWORD` | 首次安装 | SSH 密码 |
 | `SSH_PUBKEY` | - | SSH 公钥 (默认 ~/.ssh/id_rsa.pub) |
 
@@ -129,6 +129,18 @@ kubectl get nodes
 3. 启用密钥认证
 4. 自动添加本地公钥
 
+## 集群安装流程
+
+Playbook 按以下顺序执行:
+
+1. **初始化节点安装**: 安装 `cluster_init: true` 的第一个 master 节点
+2. **动态获取 Token**: 从初始化节点读取 `/var/lib/rancher/k3s/server/node-token`
+3. **Token 注入**: 将 K3S_TOKEN 和 K3S_SERVER_URL 设置为所有节点的 fact
+4. **其他 Master 节点**: 使用动态获取的 Token 加入集群
+5. **Agent 节点**: 使用动态获取的 Token 加入集群
+
+这样在一次性安装整个集群时，无需手动设置 `K3S_TOKEN` 环境变量。
+
 ## 常用命令
 
 ```bash

ansible/ansible.cfg

@@ -3,8 +3,13 @@ inventory = inventory/hosts.yml
 roles_path = roles
 host_key_checking = False
 retry_files_enabled = False
-stdout_callback = yaml
+stdout_callback = default
+callbacks_enabled = ansible.builtin.default
 interpreter_python = auto_silent
+deprecation_warnings = False
+
+[callback_default]
+result_format = yaml
 
 [privilege_escalation]
 become = True
@@ -14,5 +19,3 @@ become_user = root
 [ssh_connection]
 pipelining = True
 ssh_args = -o ControlMaster=auto -o ControlPersist=60s
-
-

ansible/inventory/group_vars/all.yml

@@ -4,14 +4,14 @@
 # 敏感信息 (通过环境变量传入)
 # ============================================
 tailscale_auth_key: "{{ lookup('env', 'TAILSCALE_AUTH_KEY') }}"
-k3s_token: "{{ lookup('env', 'K3S_TOKEN') }}"
-k3s_server_url: "{{ lookup('env', 'K3S_SERVER_URL') | default('https://k3s.dev.cm:6443', true) }}"
+# 高可用集群的 server_url 需要指向负载均衡器地址，单节点集群则指向自身
+ha_server_url: "{{ lookup('env', 'HA_SERVER_URL') }}"
 
 # ============================================
 # K3s 配置
 # ============================================
-k3s_version: "v1.31.4+k3s1"
-k3s_tls_san: "k3s.dev.cm,k3s.fillcode.com"
+# k3s_token 和 k3s_server_url 由 site.yml 动态设置，此处仅定义版本
+k3s_version: "v1.34.2+k3s1"
 
 # ETCD 配置
 etcd_snapshot_retention: 1

ansible/playbooks/add-node.yml

@@ -1,19 +0,0 @@
-# 添加新节点到集群
-# 使用: export K3S_TOKEN='xxx' K3S_SERVER_URL='xxx' TAILSCALE_AUTH_KEY='xxx'
-#       ansible-playbook playbooks/add-node.yml -l <node_name>
----
-- name: Validate
-  hosts: localhost
-  gather_facts: no
-  tasks:
-    - ansible.builtin.fail:
-        msg: "请设置: export K3S_TOKEN='xxx'"
-      when: lookup('env', 'K3S_TOKEN') | length == 0
-
-- name: Add node
-  hosts: masters:agents:!master_init
-  gather_facts: yes
-  roles:
-    - common
-    - k3s
-

ansible/playbooks/init.yml

@@ -1,8 +0,0 @@
-# 首次安装 (包含 SSH 加固)
-# 使用: export SSH_PASSWORD='xxx' TAILSCALE_AUTH_KEY='xxx'
-#       ansible-playbook playbooks/init.yml
----
-- name: First time installation with SSH hardening
-  import_playbook: site.yml
-  tags: [ssh, common, k3s, status]
-

ansible/playbooks/site.yml

@@ -2,7 +2,7 @@
 ---
 - name: Validate environment
   hosts: localhost
-  gather_facts: no
+  gather_facts: false
   tasks:
     - name: Check TAILSCALE_AUTH_KEY
       ansible.builtin.fail:
@@ -23,7 +23,7 @@
 # ============================================
 - name: SSH Security Hardening
   hosts: k3s_cluster
-  gather_facts: no
+  gather_facts: false
   tags: [ssh, never]
   roles:
     - ssh
@@ -33,7 +33,7 @@
 # ============================================
 - name: Common Setup
   hosts: k3s_cluster
-  gather_facts: yes
+  gather_facts: true
   tags: [common]
   roles:
     - common
@@ -43,16 +43,46 @@
 # ============================================
 - name: Install K3s on init node
   hosts: masters
-  gather_facts: yes
+  gather_facts: true
   serial: 1
   tags: [k3s]
   roles:
     - role: k3s
       when: cluster_init | default(false)
 
+- name: Fetch K3S_TOKEN & K3S_SERVER_URL from init node
+  hosts: localhost
+  gather_facts: false
+  tags: [k3s]
+  tasks:
+    - name: Find init node
+      ansible.builtin.set_fact:
+        init_node: "{{ item }}"
+      loop: "{{ groups['masters'] }}"
+      when: hostvars[item].cluster_init | default(false)
+
+    - name: Read K3S_TOKEN from init node
+      ansible.builtin.slurp:
+        src: /var/lib/rancher/k3s/server/node-token
+      register: k3s_token_content
+      delegate_to: "{{ init_node }}"
+
+    - name: Determine K3S_SERVER_URL
+      ansible.builtin.set_fact:
+        # 优先使用 HA_SERVER_URL 环境变量，否则使用 init 节点地址
+        k3s_server_url_or_ha: "{{ ha_server_url if (ha_server_url | length > 0) else 'https://' + hostvars[init_node].ansible_host + ':6443' }}"
+
+    - name: Set K3S_TOKEN and K3S_SERVER_URL for all hosts
+      ansible.builtin.set_fact:
+        k3s_token: "{{ k3s_token_content.content | b64decode | trim }}"
+        k3s_server_url: "{{ k3s_server_url_or_ha }}"
+      delegate_to: "{{ item }}"
+      delegate_facts: true
+      loop: "{{ groups['k3s_cluster'] }}"
+
 - name: Install K3s on other masters
   hosts: masters
-  gather_facts: yes
+  gather_facts: true
   serial: 1
   tags: [k3s]
   roles:
@@ -61,7 +91,7 @@
 
 - name: Install K3s on agents
   hosts: agents
-  gather_facts: yes
+  gather_facts: true
   tags: [k3s]
   roles:
     - k3s
@@ -71,15 +101,16 @@
 # ============================================
 - name: Show cluster status
   hosts: masters
-  gather_facts: no
+  gather_facts: false
   tags: [status]
   run_once: true
   tasks:
     - name: Get nodes
-      ansible.builtin.shell: kubectl get nodes -o wide
+      ansible.builtin.command: kubectl get nodes -o wide
       environment:
         KUBECONFIG: /etc/rancher/k3s/k3s.yaml
       register: nodes
+      changed_when: false
       when: cluster_init | default(false)
 
     - name: Display nodes
@@ -90,4 +121,3 @@
           {{ nodes.stdout }}
           ══════════════════════════════════════════════════════════════
       when: cluster_init | default(false)
-

ansible/roles/common/handlers/main.yml

@@ -1,4 +1,4 @@
 ---
 - name: Apply sysctl
   ansible.builtin.command: sysctl --system
-
+  changed_when: true

ansible/roles/common/tasks/main.yml

@@ -19,28 +19,43 @@
     content: |
       net.ipv4.ip_forward = 1
       net.ipv6.conf.all.forwarding = 1
-    mode: '0644'
+    mode: "0644"
   notify: Apply sysctl
 
 - name: Install dependencies
   ansible.builtin.apt:
-    name: [curl, wget, ca-certificates]
+    name:
+      - curl
+      - wget
+      - ca-certificates
     state: present
-    update_cache: yes
+    update_cache: true
 
 - name: Check if Tailscale is installed
   ansible.builtin.command: which tailscale
-  register: tailscale_check
-  ignore_errors: yes
+  register: common_tailscale_check
+  failed_when: false
   changed_when: false
 
+- name: Download Tailscale install script
+  ansible.builtin.get_url:
+    url: https://tailscale.com/install.sh
+    dest: /tmp/tailscale-install.sh
+    mode: "0755"
+  when: common_tailscale_check.rc != 0
+
 - name: Install Tailscale
-  ansible.builtin.shell: curl -fsSL https://tailscale.com/install.sh | sh
-  when: tailscale_check.rc != 0
+  ansible.builtin.command: /tmp/tailscale-install.sh
+  when: common_tailscale_check.rc != 0
+  changed_when: true
+
+- name: Remove Tailscale install script
+  ansible.builtin.file:
+    path: /tmp/tailscale-install.sh
+    state: absent
 
 - name: Enable Tailscale service
   ansible.builtin.systemd:
     name: tailscaled
-    enabled: yes
+    enabled: true
     state: started
-

ansible/roles/k3s/tasks/main.yml

@@ -3,69 +3,84 @@
 - name: Validate TAILSCALE_AUTH_KEY
   ansible.builtin.fail:
     msg: "请设置环境变量: export TAILSCALE_AUTH_KEY='tskey-auth-xxx'"
-  when: tailscale_auth_key | length == 0
-
-- name: Validate K3S_TOKEN for join nodes
-  ansible.builtin.fail:
-    msg: "请设置环境变量: export K3S_TOKEN='xxx'"
-  when:
-    - not (cluster_init | default(false))
-    - k3s_token | length == 0
+  when: (tailscale_auth_key | default('')) | length == 0
 
 - name: Create K3s config directory
   ansible.builtin.file:
     path: /etc/rancher/k3s
     state: directory
-    mode: '0755'
+    mode: "0755"
 
-# Server 节点配置
+# 部署配置文件
 - name: Deploy K3s server config
   ansible.builtin.template:
     src: k3s-server.yaml.j2
     dest: /etc/rancher/k3s/config.yaml
-    mode: '0600'
+    mode: "0600"
   when: "'masters' in group_names"
 
-# Agent 节点配置
 - name: Deploy K3s agent config
   ansible.builtin.template:
     src: k3s-agent.yaml.j2
     dest: /etc/rancher/k3s/config.yaml
-    mode: '0600'
+    mode: "0600"
   when: "'agents' in group_names"
 
-# 镜像加速配置
 - name: Deploy registries.yaml
   ansible.builtin.template:
     src: registries.yaml.j2
     dest: /etc/rancher/k3s/registries.yaml
-    mode: '0644'
+    mode: "0644"
   when: use_mirror | default(false)
 
-# 安装 K3s
-- name: Set install URL
+# 设置安装变量
+- name: Set K3s install variables
   ansible.builtin.set_fact:
     k3s_install_url: "{{ mirror_k3s_install_url if (use_mirror | default(false)) else global_k3s_install_url }}"
     k3s_install_mirror: "{{ 'INSTALL_K3S_MIRROR=cn' if (use_mirror | default(false)) else '' }}"
 
+# 检查安装状态
 - name: Check if K3s is installed
   ansible.builtin.stat:
     path: /usr/local/bin/k3s
   register: k3s_binary
 
+# 下载安装脚本
+- name: Download K3s install script
+  ansible.builtin.get_url:
+    url: "{{ k3s_install_url }}"
+    dest: /tmp/k3s-install.sh
+    mode: "0755"
+  when: not k3s_binary.stat.exists
+
+# 安装 K3s
 - name: Install K3s server
-  ansible.builtin.shell: |
-    curl -sfL {{ k3s_install_url }} | {{ k3s_install_mirror }} INSTALL_K3S_VERSION={{ k3s_version }} sh -s - server
+  ansible.builtin.command:
+    cmd: /tmp/k3s-install.sh server
+  environment:
+    INSTALL_K3S_VERSION: "{{ k3s_version }}"
+    INSTALL_K3S_MIRROR: "{{ 'cn' if (use_mirror | default(false)) else '' }}"
   when:
     - "'masters' in group_names"
     - not k3s_binary.stat.exists
+  changed_when: true
 
 - name: Install K3s agent
-  ansible.builtin.shell: |
-    curl -sfL {{ k3s_install_url }} | {{ k3s_install_mirror }} INSTALL_K3S_VERSION={{ k3s_version }} sh -s - agent
+  ansible.builtin.command:
+    cmd: /tmp/k3s-install.sh agent
+  environment:
+    INSTALL_K3S_VERSION: "{{ k3s_version }}"
+    INSTALL_K3S_MIRROR: "{{ 'cn' if (use_mirror | default(false)) else '' }}"
   when:
     - "'agents' in group_names"
     - not k3s_binary.stat.exists
+  changed_when: true
+
+# 清理安装脚本
+- name: Remove install script
+  ansible.builtin.file:
+    path: /tmp/k3s-install.sh
+    state: absent
 
 # 等待 K3s 就绪 (仅 Server)
 - name: Wait for K3s server ready
@@ -74,30 +89,19 @@
     timeout: 120
   when: "'masters' in group_names"
 
-# 输出 Token (仅 cluster-init)
-- name: Get node token
-  ansible.builtin.slurp:
-    src: /var/lib/rancher/k3s/server/node-token
-  register: node_token
-  when: cluster_init | default(false)
-
-- name: Display node token
-  ansible.builtin.debug:
-    msg: |
-      ══════════════════════════════════════════════════════════════
-      K3S_TOKEN (用于添加新节点):
-      {{ node_token.content | b64decode | trim }}
-      
-      K3S_SERVER_URL:
-      https://{{ ansible_host }}:6443
-      ══════════════════════════════════════════════════════════════
-  when: cluster_init | default(false)
-
 # 保存 kubeconfig (仅 cluster-init)
 - name: Fetch kubeconfig
   ansible.builtin.fetch:
     src: /etc/rancher/k3s/k3s.yaml
     dest: "{{ playbook_dir }}/../kubeconfig.yaml"
-    flat: yes
+    flat: true
   when: cluster_init | default(false)
 
+- name: Update kubeconfig server address
+  ansible.builtin.replace:
+    path: "{{ playbook_dir }}/../kubeconfig.yaml"
+    regexp: 'server: https://127\.0\.0\.1:6443'
+    replace: "server: {{ ha_server_url if (ha_server_url | default('') | length > 0) else 'https://' + ansible_host + ':6443' }}"
+  delegate_to: localhost
+  become: false
+  when: cluster_init | default(false)

ansible/roles/k3s/templates/k3s-server.yaml.j2

@@ -9,8 +9,14 @@ server: "{{ k3s_server_url }}"
 token: "{{ k3s_token }}"
 {% endif %}
 
+# TLS SAN: 包含 HA 地址 + 所有 master 节点地址
 tls-san:
-  - "{{ k3s_tls_san }}"
+{% if ha_server_url | default('') | length > 0 %}
+  - "{{ ha_server_url | regex_replace('^https?://([^:]+)(:[0-9]+)?$', '\\1') }}"
+{% endif %}
+{% for host in groups['masters'] %}
+  - "{{ hostvars[host].ansible_host }}"
+{% endfor %}
 
 # ETCD 快照配置
 etcd-snapshot-retention: {{ etcd_snapshot_retention }}

ansible/roles/ssh/handlers/main.yml

@@ -0,0 +1,21 @@
+---
+- name: Restart sshd
+  ansible.builtin.systemd:
+    name: sshd
+    state: restarted
+  listen: Restart sshd
+
+- name: Update ansible port
+  ansible.builtin.set_fact:
+    ansible_port: "{{ ssh_new_port }}"
+  listen: Update ansible port
+
+- name: Wait for new SSH port
+  ansible.builtin.wait_for:
+    port: "{{ ssh_new_port }}"
+    host: "{{ ansible_host }}"
+    delay: 5
+    timeout: 60
+  delegate_to: localhost
+  become: false
+  listen: Wait for new SSH port

ansible/roles/ssh/tasks/main.yml

@@ -5,7 +5,7 @@
   ansible.builtin.file:
     path: /root/.ssh
     state: directory
-    mode: '0700'
+    mode: "0700"
 
 - name: Add SSH public key
   ansible.builtin.authorized_key:
@@ -17,35 +17,17 @@
   ansible.builtin.copy:
     src: /etc/ssh/sshd_config
     dest: /etc/ssh/sshd_config.bak
-    remote_src: yes
-    force: no
+    remote_src: true
+    force: false
+    mode: "0600"
 
 - name: Deploy secure sshd_config
   ansible.builtin.template:
     src: sshd_config.j2
     dest: /etc/ssh/sshd_config
-    mode: '0600'
-    validate: '/usr/sbin/sshd -t -f %s'
-  register: sshd_config
-
-- name: Restart sshd service
-  ansible.builtin.systemd:
-    name: sshd
-    state: restarted
-  when: sshd_config.changed
-
-- name: Update ansible_port to new SSH port
-  ansible.builtin.set_fact:
-    ansible_port: "{{ ssh_new_port }}"
-  when: sshd_config.changed
-
-- name: Wait for SSH on new port
-  ansible.builtin.wait_for:
-    port: "{{ ssh_new_port }}"
-    host: "{{ ansible_host }}"
-    delay: 5
-    timeout: 60
-  delegate_to: localhost
-  become: no
-  when: sshd_config.changed
-
+    mode: "0600"
+    validate: "/usr/sbin/sshd -t -f %s"
+  notify:
+    - Restart sshd
+    - Update ansible port
+    - Wait for new SSH port