groups:

- name: PrometheusPveExporter

  
  rules:

    - alert: PveNodeDown
      expr: 'pve_up{id=~"node/.*"} == 0'
      for: 2m
      labels:
        severity: critical
      annotations:
        summary: PVE node down (instance {{ $labels.instance }})
        description: "Proxmox VE node {{ $labels.id }} is down.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    # This alert triggers for all VMs and containers that are not running.
    # You may want to filter by specific guests using the `id` label, or exclude
    # intentionally stopped guests with additional label matchers.
    - alert: PveVm/ctDown
      expr: 'pve_up{id=~"(qemu|lxc)/.*"} == 0'
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: PVE VM/CT down (instance {{ $labels.instance }})
        description: "Proxmox VE guest {{ $labels.id }} is not running.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: PveHighCpuUsage
      expr: 'pve_cpu_usage_ratio * 100 > 90'
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: PVE high CPU usage (instance {{ $labels.instance }})
        description: "Proxmox VE CPU usage is above 90% on {{ $labels.id }}. Current value: {{ $value | printf \"%.2f\" }}%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: PveHighMemoryUsage
      expr: 'pve_memory_usage_bytes / pve_memory_size_bytes * 100 > 90 and pve_memory_size_bytes > 0'
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: PVE high memory usage (instance {{ $labels.instance }})
        description: "Proxmox VE memory usage is above 90% on {{ $labels.id }}. Current value: {{ $value | printf \"%.2f\" }}%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: PveStorageFillingUp
      expr: 'pve_disk_usage_bytes{id=~"storage/.*"} / pve_disk_size_bytes{id=~"storage/.*"} * 100 > 80 and pve_disk_size_bytes{id=~"storage/.*"} > 0'
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: PVE storage filling up (instance {{ $labels.instance }})
        description: "Proxmox VE storage {{ $labels.id }} is above 80% used. Current value: {{ $value | printf \"%.2f\" }}%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: PveStorageAlmostFull
      expr: 'pve_disk_usage_bytes{id=~"storage/.*"} / pve_disk_size_bytes{id=~"storage/.*"} * 100 > 95 and pve_disk_size_bytes{id=~"storage/.*"} > 0'
      for: 2m
      labels:
        severity: critical
      annotations:
        summary: PVE storage almost full (instance {{ $labels.instance }})
        description: "Proxmox VE storage {{ $labels.id }} is above 95% used. Current value: {{ $value | printf \"%.2f\" }}%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: PveGuestNotBackedUp
      expr: 'pve_not_backed_up_total > 0'
      for: 0m
      labels:
        severity: warning
      annotations:
        summary: PVE guest not backed up (instance {{ $labels.instance }})
        description: "{{ $value }} Proxmox VE guest(s) are not covered by any backup job.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: PveReplicationFailed
      expr: 'pve_replication_failed_syncs > 0'
      for: 0m
      labels:
        severity: warning
      annotations:
        summary: PVE replication failed (instance {{ $labels.instance }})
        description: "Proxmox VE replication for {{ $labels.id }} has {{ $value }} failed sync(s).\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    # Loss of quorum means the cluster cannot make decisions about VM placement
    # and fencing. This requires immediate attention.
    - alert: PveClusterNotQuorate
      expr: 'pve_cluster_info{quorate="0"} == 1'
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: PVE cluster not quorate (instance {{ $labels.instance }})
        description: "Proxmox VE cluster has lost quorum.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"