groups:
  - name: system_alerts
    interval: 30s
    rules:
      - alert: HighCPUUsage
        expr: 100 - (avg by(instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Instance {{ $labels.instance }} 高CPU使用率"
          description: "CPU使用率超过80% (当前: {{ $value | humanizePercentage }})"

      - alert: HighMemoryUsage
        expr: 100 - ((node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100) > 85
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Instance {{ $labels.instance }} 高内存使用率"
          description: "内存使用率超过85% (当前: {{ $value | humanizePercentage }})"

      - alert: HighDiskUsage
        expr: 100 - ((node_filesystem_avail_bytes{mountpoint="/",fstype!="rootfs"} / node_filesystem_size_bytes{mountpoint="/",fstype!="rootfs"}) * 100) > 90
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "Instance {{ $labels.instance }} 高磁盘使用率"
          description: "磁盘使用率超过90% (当前: {{ $value | humanizePercentage }})"

      - alert: HostUnreachable
        expr: up == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "实例 {{ $labels.instance }} 不可达"
          description: "实例 {{ $labels.instance }} 已超过1分钟不可用"

      - alert: DiskSpaceLow
        expr: (node_filesystem_avail_bytes{fstype!="tmpfs",fstype!="rootfs"} / node_filesystem_size_bytes{fstype!="tmpfs",fstype!="rootfs"}) < 0.1
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: "实例 {{ $labels.instance }} 磁盘空间不足"
          description: "挂载点 {{ $labels.mountpoint }} 磁盘使用率超过90%"