ansible/group_vars/prom/prometheus/node.yml

---
prometheus__scraping_node:
  targets: "{{ groups.vm_network + groups.pve_network }}"
  address:
    port: 9100

prometheus__rules_node:
  - alert: OutOfMemory
    expr:
      (
        node_memory_MemFree_bytes
        + node_memory_Cached_bytes
        + node_memory_Buffers_bytes
      ) / node_memory_MemTotal_bytes < 0.1
    for: 5m
    labels:
      severity: warning
    annotations:
      FreeMemory: !unsafe "{{ $value | humanizePercentage }}"
  - alert: HostSwapIsFillingUp
    expr:
      (
        1 - (
          node_memory_SwapFree_bytes
          / node_memory_SwapTotal_bytes
        )
      ) >= 0.5
    for: 3m
    labels:
      severity: critical
    annotations:
      UsedSwap: !unsafe "{{ $value | humanizePercentage }}"
  - alert: HostPhysicalComponentTooHot
    expr:
      node_hwmon_temp_celsius > 79
    for: 3m
    labels:
      severity: critical
    annotations:
      Temperature: !unsafe "{{ $value | humanize }} °C"
      Chip: !unsafe "{{ $labels.chip }}"
      Sensor: !unsafe "{{ $labels.sensor }}"
  - alert: HostNodeOvertemperatureAlarm
    expr:
      node_hwmon_temp_crit_alarm_celsius == 1
    for: 0m
    labels:
      severity: critical
    annotations:
      Chip: !unsafe "{{ $labels.chip }}"
      Sensor: !unsafe "{{ $labels.sensor }}"
  - alert: HostRaidArrayGotInactive
    expr:
      node_md_state{state="inactive"} > 0
    for: 0m
    labels:
      severity: critical
    annotations:
      Device: !unsafe "{{ $labels.device }}"
  - alert: HostRaidDiskFailure
    expr:
      node_md_disks{state="failed"} > 0
    for: 0m
    labels:
      severity: critical
    annotations:
      severity: !unsafe "{{ $labels.md_device }}"
  - alert: HostOomKillDetected
    expr:
      increase(node_vmstat_oom_kill[1m]) > 0
    for: 0m
    labels:
      severity: warning
    annotations:
      PID: !unsafe "{{ $value }}"
  - alert: HostEdacCorrectableErrorsDetected
    expr:
      increase(node_edac_correctable_errors_total[1m]) > 0
    for: 0m
    labels:
      severity: warning
    annotations:
      CorrectedErrors: !unsafe "{{ $value }}"
  - alert: HostEdacUncorrectableErrorsDetected
    expr:
      increase(node_edac_uncorrectable_errors_total[1m]) > 0
    for: 0m
    labels:
      severity: warning
    annotations:
      DetectedErrors: !unsafe "{{ $value }}"
  - alert: OutOfDiskSpace
    expr:
      (
        node_filesystem_free_bytes
        / node_filesystem_size_bytes < 0.1
      )
      and on (instance, device, mountpoint) (
        node_filesystem_readonly
      ) == 0
    for: 5m
    labels:
      severity: critical
    annotations:
      Mountpoint: !unsafe "{{ $labels.mountpoint }}"
      FreeSpace: !unsafe "{{ $value | humanizePercentage }}"
  - alert: HostConntrackLimit
    expr:
      (
        node_nf_conntrack_entries
        / node_nf_conntrack_entries_limit
      ) > 0.8
    for: 5m
    labels:
      severity: warning
    annotations:
      Filled: !unsafe "{{ $value | humanizePercentage }}"
  - alert: HostClockSkew
    expr:
      (
        node_timex_offset_seconds > 0.05
        and deriv(node_timex_offset_seconds[5m]) >= 0
      ) or (
        node_timex_offset_seconds < -0.05
        and deriv(node_timex_offset_seconds[5m]) <= 0
      )
    for: 2m
    labels:
      severity: warning
  - alert: HostClockNotSynchronising
    expr:
      min_over_time(node_timex_sync_status[1m]) == 0
      and node_timex_maxerror_seconds >= 16
    for: 2m
    labels:
      severity: warning
  - alert: HostRequiresReboot
    expr:
      node_reboot_required > 0
    for: 5m
    labels:
      severity: warning
  - alert: OutOfInodes
    expr:
      node_filesystem_files_free
      / node_filesystem_files < 0.1
    for: 3m
    labels:
      severity: warning
    annotations:
      Mountpoint: !unsafe "{{ $labels.mountpoint }}"
      FreeInodes: !unsafe "{{ $value | humanizePercentage }}"
  - alert: CpuUsage
    expr:
      (
        1 - avg by (instance) (
          irate(node_cpu_seconds_total{mode="idle"}[5m])
        )
      ) > 0.75
    for: 10m
    labels:
      severity: warning
    annotations:
      Usage: !unsafe "{{ $value | humanizePercentage }}"
  - alert: SystemdServiceFailed
    expr:
      node_systemd_unit_state{state="failed"} == 1
    for: 10m
    labels:
      severity: warning
    annotations:
      Service: !unsafe "{{ $labels.name }}"
  - alert: LoadUsage
    expr:
      node_load1 > 5
    for: 2m
    labels:
      severity: warning
    annotations:
      Load1: !unsafe "{{ $value | humanize }}"
  - alert: UnhealthyDisk
    expr:
      smartmon_device_smart_healthy < 1
    for: 10m
    labels:
      severity: critical
    annotations:
      Disk: !unsafe "{{ $labels.disk }}"
  - alert: HostCpuStealNoisyNeighbor
    expr:
      avg by (instance) (
        rate(node_cpu_seconds_total{mode="steal"}[5m])
      ) > 0.1
    for: 5m
    labels:
      severity: warning
    annotations:
      Disk: !unsafe "{{ $labels.disk }}"
      Steal: !unsafe "{{ $value | humanizePercentage }}"
...