mgmt/configuration/playbooks/maintenance/ops-toolkit.yml

---
- name: Operations Toolkit - Unified Management Dashboard
  hosts: all
  gather_facts: yes
  
  vars:
    # 可用的运维脚本
    available_scripts:
      - { name: "system-update", desc: "System package updates", file: "system-update.yml" }
      - { name: "system-cleanup", desc: "System cleanup and maintenance", file: "system-cleanup.yml" }
      - { name: "service-health", desc: "Service health monitoring", file: "service-health-check.yml" }
      - { name: "security-hardening", desc: "Security hardening and backup", file: "security-hardening.yml" }
      - { name: "docker-management", desc: "Docker container management", file: "docker-management.yml" }
      - { name: "network-connectivity", desc: "Network connectivity check", file: "network-connectivity.yml" }
      - { name: "certificate-management", desc: "SSL certificate monitoring", file: "certificate-management.yml" }
  
  tasks:
    # 显示系统概览
    - name: Display system overview
      debug:
        msg: |
          🖥️  System Overview for {{ inventory_hostname }}:
          📊 OS: {{ ansible_distribution }} {{ ansible_distribution_version }}
          💾 Memory: {{ (ansible_memtotal_mb/1024)|round(1) }}GB total, {{ (ansible_memfree_mb/1024)|round(1) }}GB free
          💿 CPU: {{ ansible_processor_vcpus }} cores
          🏠 Architecture: {{ ansible_architecture }}
          🌐 IP: {{ ansible_default_ipv4.address }}
          ⏰ Uptime: {{ ansible_uptime_seconds//86400 }}d {{ (ansible_uptime_seconds%86400)//3600 }}h {{ ((ansible_uptime_seconds%3600)//60) }}m
                    
    # 快速系统状态检查
    - name: Quick system status check
      shell: |
        echo "=== DISK USAGE ==="
        df -h | grep -E "(Filesystem|/dev/)"
        echo ""
        echo "=== MEMORY USAGE ==="
        free -h
        echo ""
        echo "=== LOAD AVERAGE ==="
        uptime
        echo ""
        echo "=== TOP PROCESSES ==="
        ps aux --sort=-%cpu | head -6        
      register: quick_status
      
    - name: Display quick status
      debug:
        msg: "{{ quick_status.stdout_lines }}"
        
    # 检查关键服务状态
    - name: Check critical services
      systemd:
        name: "{{ item }}"
      register: service_status
      loop:
        - ssh
        - systemd-resolved
        - cron
      failed_when: false
      
    - name: Display service status
      debug:
        msg: "🔧 {{ item.item }}: {{ item.status.ActiveState if item.status is defined else 'NOT FOUND' }}"
      loop: "{{ service_status.results }}"
      
    # 检查最近的系统日志错误
    - name: Check recent system errors
      shell: journalctl --since "1 hour ago" --priority=err --no-pager | tail -10
      register: recent_errors
      failed_when: false
      
    - name: Display recent errors
      debug:
        msg: "🚨 Recent Errors: {{ recent_errors.stdout_lines if recent_errors.stdout_lines else ['No recent errors found'] }}"
        
    # 检查网络连接
    - name: Quick network check
      shell: |
        echo "=== NETWORK INTERFACES ==="
        ip -br addr show
        echo ""
        echo "=== DEFAULT ROUTE ==="
        ip route | grep default
        echo ""
        echo "=== DNS TEST ==="
        nslookup google.com | grep -A1 "Name:" || echo "DNS resolution failed"        
      register: network_check
      failed_when: false
      
    - name: Display network status
      debug:
        msg: "🌐 Network Status: {{ network_check.stdout_lines }}"
        
    # 显示可用的运维脚本
    - name: Display available operations scripts
      debug:
        msg: |
          🛠️  Available Operations Scripts:
          {% for script in available_scripts %}
          {{ loop.index }}. {{ script.name }}: {{ script.desc }}
          {% endfor %}
          
          💡 Usage Examples:
          ansible-playbook -i inventory.ini system-cleanup.yml --limit {{ inventory_hostname }}
          ansible-playbook -i inventory.ini docker-management.yml --limit lxc
          ansible-playbook -i inventory.ini network-connectivity.yml --limit proxmox
                    
    # 生成运维建议
    - name: Generate maintenance recommendations
      debug:
        msg: |
          💡 Maintenance Recommendations for {{ inventory_hostname }}:
          
          🔄 Regular Tasks (Weekly):
          - Run system-cleanup.yml to free up disk space
          - Check service-health-check.yml for service status
          - Review certificate-management.yml for expiring certificates
          
          🔒 Security Tasks (Monthly):
          - Execute security-hardening.yml for security updates
          - Review network-connectivity.yml for network security
          
          🐳 Container Tasks (As needed):
          - Use docker-management.yml for Docker maintenance
          
          📊 Monitoring Tasks (Daily):
          - Quick check with ops-toolkit.yml (this script)
          
          ⚡ Emergency Tasks:
          - Use system-update.yml for critical security patches
          - Run network-connectivity.yml for connectivity issues