path: root/modules/nixos/monitoring/rules/node.yaml

---
groups:
  - name: Node

    rules:
      - alert: HostOutOfMemory
        expr: >-
          node_memory_MemAvailable_bytes
          /
          node_memory_MemTotal_bytes * 100
          < 10
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host out of memory at {{ $labels.instance }}.
          description: |-
            Node memory is filling up.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostMemoryUnderMemoryPressure
        expr: >-
          rate(node_vmstat_pgmajfault[1m]) > 1000
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host memory under memory pressure at {{ $labels.instance }}.
          description: |-
            The node is under heavy memory pressure. High rate of major page faults.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostUnusualNetworkThroughputIn
        expr: >-
          sum by (instance) (rate(node_network_receive_bytes_total[2m]))
          / 1024
          / 1024
          > 100
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: Host unusual network throughput in (instance {{ $labels.instance }})
          description: |-
            Host network interfaces are probably receiving too much data.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostUnusualNetworkThroughputOut
        expr: >-
          sum by (instance) (rate(node_network_transmit_bytes_total[2m]))
          / 1024
          / 1024
          > 100
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: Host unusual network throughput out at {{ $labels.instance }}.
          description: |-
            Host network interfaces are probably sending too much data.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostUnusualDiskReadRate
        expr: >-
          sum by (instance) (rate(node_disk_read_bytes_total[2m]))
          / 1024
          / 1024
          > 50
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: Host unusual disk read rate at {{ $labels.instance }}.
          description: |-
            Disk is probably reading too much data.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostUnusualDiskWriteRate
        expr: >-
          sum by (instance) (rate(node_disk_written_bytes_total[2m]))
          / 1024
          / 1024
          > 50
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host unusual disk write rate at {{ $labels.instance }}.
          description: |-
            Disk is probably writing too much data.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostOutOfDiskSpace
        expr: >-
          (node_filesystem_avail_bytes * 100)
          / node_filesystem_size_bytes
          < 10
          and
          on (instance, device, mountpoint) node_filesystem_readonly
          == 0
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host out of disk space at {{ $labels.instance }}.
          description: |-
            Disk is almost full.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostDiskWillFillIn24Hours
        expr: >-
          (node_filesystem_avail_bytes * 100)
          / node_filesystem_size_bytes
          < 10
          and ON (instance, device, mountpoint)
            predict_linear(node_filesystem_avail_bytes{fstype!~"tmpfs"}[1h], 24 * 3600)
            < 0
          and ON (instance, device, mountpoint)
            node_filesystem_readonly == 0
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host disk will fill in 24 hours at {{ $labels.instance }}.
          description: |-
            Filesystem is predicted to run out of space within the next 24 hours at current write rate.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostOutOfInodes
        expr: >-
          node_filesystem_files_free
          / node_filesystem_files * 100
          < 10
          and
          ON (instance, device, mountpoint) node_filesystem_readonly
          == 0
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host out of inodes at {{ $labels.instance }}.
          description: |-
            Disk is almost running out of available inodes.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostInodesWillFillIn24Hours
        expr: >-
          node_filesystem_files_free
          / node_filesystem_files
          * 100
          < 10
          and
          predict_linear(node_filesystem_files_free[1h], 24 * 3600)
          < 0
          and ON (instance, device, mountpoint) node_filesystem_readonly
          == 0
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host inodes will fill in 24 hours at {{ $labels.instance }}.
          description: |-
            Filesystem is predicted to run out of inodes within the next 24 hours at current write rate.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostUnusualDiskReadLatency
        expr: >-
          rate(node_disk_read_time_seconds_total[1m])
          / rate(node_disk_reads_completed_total[1m])
          > 0.1
          and
          rate(node_disk_reads_completed_total[1m])
          > 0
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host unusual disk read latency at {{ $labels.instance }}.
          description: |-
            Disk latency is growing.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostUnusualDiskWriteLatency
        expr: >-
          rate(node_disk_write_time_seconds_total[1m])
          / rate(node_disk_writes_completed_total[1m])
          > 0.1
          and
          rate(node_disk_writes_completed_total[1m])
          > 0
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host unusual disk write latency at {{ $labels.instance }}.
          description: |-
            Disk latency is growing.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostHighCpuLoad
        expr: >-
          sum by (instance)
            (avg by (mode, instance)
              (rate(node_cpu_seconds_total{mode!="idle"}[2m])))
          > 2.0
        for: 0m
        labels:
          severity: warning
        annotations:
          summary: Host high CPU load at {{ $labels.instance }}.
          description: |-
            CPU load is high.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostCpuHighIowait
        expr: |-
          avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m]))
          * 100
          > 50
        for: 0m
        labels:
          severity: warning
        annotations:
          summary: Host CPU high I/O wait at {{ $labels.instance }}.
          description: |-
            CPU I/O wait is high. A high I/O wait means that you are disk or network bound.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostUnusualDiskIo
        expr: >-
          rate(node_disk_io_time_seconds_total[1m]) > 0.5
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: Host unusual disk I/O at {{ $labels.instance }}.
          description: |-
            Time spent over I/O is too high. Check storage for issues.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostSwapIsFillingUp
        expr: >-
          (1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes))
          * 100
          > 80
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host swap is filling up at {{ $labels.instance }}.
          description: |-
            Swap is filling up.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostSystemdServiceCrashed
        expr: >-
          node_systemd_unit_state{state="failed"} == 1
        for: 0m
        labels:
          severity: warning
        annotations:
          summary: Host systemd service crashed at {{ $labels.instance }}.
          description: |-
            Systemd service crashed.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostPhysicalComponentTooHot
        expr: >-
          node_hwmon_temp_celsius > 75
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: Host physical component too hot at {{ $labels.instance }}.
          description: |-
            Physical hardware component too hot.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostNodeOvertemperatureAlarm
        expr: >-
          node_hwmon_temp_crit_alarm_celsius == 1
        for: 0m
        labels:
          severity: critical
        annotations:
          summary: Host node overtemperature alarm at {{ $labels.instance }}.
          description: |-
            Physical node temperature alarm triggered.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostRaidArrayGotInactive
        expr: >-
          node_md_state{state="inactive"} > 0
        for: 0m
        labels:
          severity: critical
        annotations:
          summary: Host RAID array got inactive at {{ $labels.instance }}.
          description: |-
            RAID array is in a degraded state due to one or more disks failures. Number of spare drives is insufficient to fix the issue automatically.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostRaidDiskFailure
        expr: >-
          node_md_disks{state="failed"} > 0
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host RAID disk failure at {{ $labels.instance }}.
          description: |-
            At least one device in RAID array is failed. Possibly, a disk swap is required.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostOomKillDetected
        expr: >-
          increase(node_vmstat_oom_kill[1m]) > 0
        for: 0m
        labels:
          severity: warning
        annotations:
          summary: Host OOM kill detected at {{ $labels.instance }}.
          description: |-
            OOM kill detected.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostEdacCorrectableErrorsDetected
        expr: >-
          increase(node_edac_correctable_errors_total[1m]) > 0
        for: 0m
        labels:
          severity: info
        annotations:
          summary: Host EDAC correctable errors detected at {{ $labels.instance }}.
          description: |-
            Host has had {{ printf "%.0f" $value }} correctable memory errors reported by EDAC in the last 5 minutes.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostEdacUncorrectableErrorsDetected
        expr: >-
          node_edac_uncorrectable_errors_total > 0
        for: 0m
        labels:
          severity: warning
        annotations:
          summary: Host EDAC uncorrectable errors detected at {{ $labels.instance }}.
          description: |-
            Host has had {{ printf "%.0f" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostNetworkReceiveErrors
        expr: >-
          rate(node_network_receive_errs_total{device!~"^wg.*"}[2m])
          /
          rate(node_network_receive_packets_total{device!~"^wg.*"}[2m])
          > 0.01
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host Network Receive Errors at {{ $labels.instance }}.
          description: |-
            Host interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last two minutes.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostNetworkTransmitErrors
        expr: >-
          rate(node_network_transmit_errs_total{device!~"^wg.*"}[2m])
          /
          rate(node_network_transmit_packets_total{device!~"^wg.*"}[2m])
          > 0.1
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host network transmit errors at {{ $labels.instance }}.
          description: |-
            Host interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last two minutes.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostNetworkInterfaceSaturated
        expr: >-
          (
            rate(node_network_receive_bytes_total{device!~"^wg.*"}[1m])
            +
            rate(node_network_transmit_bytes_total{device!~"^wg.*"}[1m])
          )
          / node_network_speed_bytes{device!~"^wg.*"}
          > 0.8
          < 10000
        for: 1m
        labels:
          severity: warning
        annotations:
          summary: Host network interface saturated at {{ $labels.instance }}.
          description: |-
            The network interface {{ $labels.device }} is getting overloaded.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostNetworkBondDegraded
        expr: >-
          (node_bonding_active - node_bonding_slaves) != 0
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host network bond degraded at {{ $labels.instance }}.
          description: |-
            Bond {{ $labels.device }} degraded.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostConntrackLimit
        expr: >-
          node_nf_conntrack_entries
          /
          node_nf_conntrack_entries_limit
          > 0.8
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: Host conntrack limit at {{ $labels.instance }}.
          description: |-
            The number of conntrack is approaching limit.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - 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
        annotations:
          summary: Host clock skew at {{ $labels.instance }}.
          description: |-
            Clock skew is detected and the clock is out of sync. Ensure that NTP is configured correctly on this host.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostClockNotSynchronising
        expr: >-
          min_over_time(node_timex_sync_status[1m]) == 0
          and
          node_timex_maxerror_seconds >= 16
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Host clock not synchronising at {{ $labels.instance }}.
          description: |-
            Clock is not synchronising. Ensure that NTP is configured correctly on this host.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}

      - alert: HostRequiresReboot
        expr: >-
          node_reboot_required > 0
        for: 4h
        labels:
          severity: info
        annotations:
          summary: Host requires reboot at {{ $labels.instance }}.
          description: |-
            Instance requires a reboot.

            VALUE = {{ $value }}
            LABELS = {{ $labels }}