mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-21 00:47:18 +08:00
Publish
This commit is contained in:
samber
parent
be7a2e4d5d
commit
7397eb24ec
1 changed files with 165 additions and 0 deletions
165
dist/rules/ipmi/ipmi-exporter.yml
vendored
Normal file
165
dist/rules/ipmi/ipmi-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,165 @@
|
|||
groups:
|
||||
|
||||
- name: IpmiExporter
|
||||
|
||||
|
||||
rules:
|
||||
|
||||
# The ipmi_up metric is per-collector. A value of 0 means the collector could not retrieve data from the BMC.
|
||||
- alert: IpmiCollectorDown
|
||||
expr: 'ipmi_up == 0'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: IPMI collector down (instance {{ $labels.instance }})
|
||||
description: "IPMI collector {{ $labels.collector }} on {{ $labels.instance }} failed to scrape sensor data. Check FreeIPMI tools and BMC connectivity.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# State values: 0=nominal, 1=warning, 2=critical. Thresholds are defined in the BMC firmware.
|
||||
- alert: IpmiTemperatureSensorWarning
|
||||
expr: 'ipmi_temperature_state == 1'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: IPMI temperature sensor warning (instance {{ $labels.instance }})
|
||||
description: "IPMI temperature sensor {{ $labels.name }} on {{ $labels.instance }} is in warning state.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IpmiTemperatureSensorCritical
|
||||
expr: 'ipmi_temperature_state == 2'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: IPMI temperature sensor critical (instance {{ $labels.instance }})
|
||||
description: "IPMI temperature sensor {{ $labels.name }} on {{ $labels.instance }} is in critical state. Immediate attention required to prevent hardware damage.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IpmiFanSpeedSensorWarning
|
||||
expr: 'ipmi_fan_speed_state == 1'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: IPMI fan speed sensor warning (instance {{ $labels.instance }})
|
||||
description: "IPMI fan sensor {{ $labels.name }} on {{ $labels.instance }} is in warning state.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IpmiFanSpeedSensorCritical
|
||||
expr: 'ipmi_fan_speed_state == 2'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: IPMI fan speed sensor critical (instance {{ $labels.instance }})
|
||||
description: "IPMI fan sensor {{ $labels.name }} on {{ $labels.instance }} is in critical state. A fan may have failed.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IpmiFanSpeedZero
|
||||
expr: 'ipmi_fan_speed_rpm == 0'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: IPMI fan speed zero (instance {{ $labels.instance }})
|
||||
description: "IPMI fan {{ $labels.name }} on {{ $labels.instance }} reports 0 RPM. The fan may have failed.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IpmiVoltageSensorWarning
|
||||
expr: 'ipmi_voltage_state == 1'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: IPMI voltage sensor warning (instance {{ $labels.instance }})
|
||||
description: "IPMI voltage sensor {{ $labels.name }} on {{ $labels.instance }} is in warning state.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IpmiVoltageSensorCritical
|
||||
expr: 'ipmi_voltage_state == 2'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: IPMI voltage sensor critical (instance {{ $labels.instance }})
|
||||
description: "IPMI voltage sensor {{ $labels.name }} on {{ $labels.instance }} is in critical state. Power supply or motherboard issue possible.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IpmiCurrentSensorWarning
|
||||
expr: 'ipmi_current_state == 1'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: IPMI current sensor warning (instance {{ $labels.instance }})
|
||||
description: "IPMI current sensor {{ $labels.name }} on {{ $labels.instance }} is in warning state.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IpmiCurrentSensorCritical
|
||||
expr: 'ipmi_current_state == 2'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: IPMI current sensor critical (instance {{ $labels.instance }})
|
||||
description: "IPMI current sensor {{ $labels.name }} on {{ $labels.instance }} is in critical state.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IpmiPowerSensorWarning
|
||||
expr: 'ipmi_power_state == 1'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: IPMI power sensor warning (instance {{ $labels.instance }})
|
||||
description: "IPMI power sensor {{ $labels.name }} on {{ $labels.instance }} is in warning state.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IpmiPowerSensorCritical
|
||||
expr: 'ipmi_power_state == 2'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: IPMI power sensor critical (instance {{ $labels.instance }})
|
||||
description: "IPMI power sensor {{ $labels.name }} on {{ $labels.instance }} is in critical state.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# Catches any sensor type not covered by the specific temperature/fan/voltage/current/power alerts.
|
||||
- alert: IpmiGenericSensorCritical
|
||||
expr: 'ipmi_sensor_state == 2'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: IPMI generic sensor critical (instance {{ $labels.instance }})
|
||||
description: "IPMI sensor {{ $labels.name }} (type={{ $labels.type }}) on {{ $labels.instance }} is in critical state.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: IpmiChassisPowerOff
|
||||
expr: 'ipmi_chassis_power_state == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: IPMI chassis power off (instance {{ $labels.instance }})
|
||||
description: "IPMI reports chassis power is off on {{ $labels.instance }}. The server may have shut down unexpectedly.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# The metric uses inverted logic: 1=no fault, 0=fault detected.
|
||||
- alert: IpmiChassisDriveFault
|
||||
expr: 'ipmi_chassis_drive_fault_state == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: IPMI chassis drive fault (instance {{ $labels.instance }})
|
||||
description: "IPMI reports a drive fault on {{ $labels.instance }}. Check disk health.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# The metric uses inverted logic: 1=no fault, 0=fault detected.
|
||||
- alert: IpmiChassisCoolingFault
|
||||
expr: 'ipmi_chassis_cooling_fault_state == 0'
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: IPMI chassis cooling fault (instance {{ $labels.instance }})
|
||||
description: "IPMI reports a cooling/fan fault on {{ $labels.instance }}. Check fans and airflow.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# SEL storage is typically very limited (e.g., 16KB). When full, new events may be dropped.
|
||||
- alert: IpmiSelAlmostFull
|
||||
expr: 'ipmi_sel_free_space_bytes < 512'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: IPMI SEL almost full (instance {{ $labels.instance }})
|
||||
description: "IPMI System Event Log on {{ $labels.instance }} has only {{ printf \"%.0f\" $value }} bytes free. Clear the SEL to prevent loss of new events.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
Loading…
Reference in a new issue