---
- name: Service Health Check and Monitoring
  hosts: all
  become: yes
  gather_facts: yes
  
  vars:
    critical_services:
      - ssh
      - systemd-resolved
      - cron
    web_services:
      - nginx
      - apache2
    database_services:
      - mysql
      - mariadb
      - postgresql
    container_services:
      - docker
      - containerd
    network_services:
      - tailscale
      - cloudflared
      
  tasks:
    # 检查关键系统服务
    - name: Check critical system services
      systemd:
        name: "{{ item }}"
      register: critical_service_status
      loop: "{{ critical_services }}"
      failed_when: false
      
    - name: Report critical service issues
      debug:
        msg: "⚠️  Critical service {{ item.item }} is {{ item.status.ActiveState | default('not found') }}"
      loop: "{{ critical_service_status.results }}"
      when: item.status is defined and item.status.ActiveState != "active"
      
    # 检查 Web 服务
    - name: Check web services
      systemd:
        name: "{{ item }}"
      register: web_service_status
      loop: "{{ web_services }}"
      failed_when: false
      
    - name: Report web service status
      debug:
        msg: "🌐 Web service {{ item.item }}: {{ item.status.ActiveState | default('not installed') }}"
      loop: "{{ web_service_status.results }}"
      when: item.status is defined
      
    # 检查数据库服务
    - name: Check database services
      systemd:
        name: "{{ item }}"
      register: db_service_status
      loop: "{{ database_services }}"
      failed_when: false
      
    - name: Report database service status
      debug:
        msg: "🗄️  Database service {{ item.item }}: {{ item.status.ActiveState | default('not installed') }}"
      loop: "{{ db_service_status.results }}"
      when: item.status is defined
      
    # 检查容器服务
    - name: Check container services
      systemd:
        name: "{{ item }}"
      register: container_service_status
      loop: "{{ container_services }}"
      failed_when: false
      
    - name: Report container service status
      debug:
        msg: "📦 Container service {{ item.item }}: {{ item.status.ActiveState | default('not installed') }}"
      loop: "{{ container_service_status.results }}"
      when: item.status is defined
      
    # 检查网络服务
    - name: Check network services
      systemd:
        name: "{{ item }}"
      register: network_service_status
      loop: "{{ network_services }}"
      failed_when: false
      
    - name: Report network service status
      debug:
        msg: "🌐 Network service {{ item.item }}: {{ item.status.ActiveState | default('not installed') }}"
      loop: "{{ network_service_status.results }}"
      when: item.status is defined
      
    # 检查系统负载
    - name: Check system load
      shell: uptime
      register: system_load
      
    - name: Display system load
      debug:
        msg: "📊 System Load: {{ system_load.stdout }}"
        
    # 检查磁盘空间警告
    - name: Check disk space usage
      shell: df -h | awk '$5 > 80 {print $0}'
      register: disk_warning
      changed_when: false
      
    - name: Warn about high disk usage
      debug:
        msg: "⚠️  High disk usage detected: {{ disk_warning.stdout_lines }}"
      when: disk_warning.stdout_lines | length > 0
      
    # 检查内存使用率
    - name: Check memory usage percentage
      shell: free | awk 'NR==2{printf "%.2f%%", $3*100/$2}'
      register: memory_percent
      
    - name: Display memory usage
      debug:
        msg: "🧠 Memory Usage: {{ memory_percent.stdout }}"
        
    # 检查最近的系统错误
    - name: Check recent system errors
      shell: journalctl --since "1 hour ago" --priority=err --no-pager | tail -10
      register: recent_errors
      changed_when: false
      
    - name: Display recent errors
      debug:
        msg: "🚨 Recent system errors: {{ recent_errors.stdout_lines }}"
      when: recent_errors.stdout_lines | length > 0