XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-21 17:07:24 +08:00
Code Issues Projects Releases Packages Wiki Activity

Node exporter rules to preserve instance labels (#488)

Browse source 
* Jenkins node offline for clause (#2)

* Convert cpu alert expressions to without() rather than on()

* Remove on() expression from network throughput alerts as labels fully match

---------

Co-authored-by: Simon Matic Langford <simon@longshotsystems.co.uk>
This commit is contained in:
Simon Matic Langford 2026-01-06 15:24:18 +00:00 committed by GitHub
parent 74ba870f05
commit f810ff531d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 12 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
_data/rules.yml
View file

@ -152,11 +152,11 @@ groups:
You may want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly
- name: Host unusual network throughput in
description: Host receive bandwidth is high (>80%).
query: "((rate(node_network_receive_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)"
query: "((rate(node_network_receive_bytes_total[5m]) / node_network_speed_bytes) > .80)"
severity: warning
- name: Host unusual network throughput out
description: Host transmit bandwidth is high (>80%)
query: "((rate(node_network_transmit_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)"
query: "((rate(node_network_transmit_bytes_total[5m]) / node_network_speed_bytes) > .80)"
severity: warning
- name: Host unusual disk read rate
description: Disk is too busy (IO wait > 80%)
@ -207,23 +207,23 @@ groups:
for: 2m
- name: Host high CPU load
description: CPU load is > 80%
query: '1 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m]))) > .80'
query: '1 - (avg without (cpu) (rate(node_cpu_seconds_total{mode="idle"}[5m]))) > .80'
severity: warning
for: 10m
- name: Host CPU is underutilized
description: "CPU load has been < 20% for 1 week. Consider reducing the number of CPUs."
query: '(min by (instance) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > 0.8'
query: '(min without (cpu) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > 0.8'
severity: info
for: 1w
comments: |
You may want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly
- name: Host CPU steal noisy neighbor
description: CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.
query: 'avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10'
query: 'avg without (cpu) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10'
severity: warning
- name: Host CPU high iowait
description: CPU iowait > 10%. Your CPU is idling waiting for storage to respond.
query: 'avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) > .10'
query: 'avg without (cpu) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) > .10'
severity: warning
- name: Host unusual disk IO
description: "Disk usage >80%. Check storage for issues or increase IOPS capabilities. Check storage for issues."

12
dist/rules/host-and-hardware/node-exporter.yml vendored
View file

@ -34,7 +34,7 @@ groups:
description: "Node memory usage is < 20% for 1 week. Consider reducing memory space. (instance {{ $labels.instance }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostUnusualNetworkThroughputIn
expr: '((rate(node_network_receive_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)'
expr: '((rate(node_network_receive_bytes_total[5m]) / node_network_speed_bytes) > .80)'
for: 0m
labels:
severity: warning
@ -43,7 +43,7 @@ groups:
description: "Host receive bandwidth is high (>80%).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostUnusualNetworkThroughputOut
expr: '((rate(node_network_transmit_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)'
expr: '((rate(node_network_transmit_bytes_total[5m]) / node_network_speed_bytes) > .80)'
for: 0m
labels:
severity: warning
@ -130,7 +130,7 @@ groups:
description: "Disk latency is growing (write operations > 100ms)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostHighCpuLoad
expr: '1 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m]))) > .80'
expr: '1 - (avg without (cpu) (rate(node_cpu_seconds_total{mode="idle"}[5m]))) > .80'
for: 10m
labels:
severity: warning
@ -140,7 +140,7 @@ groups:
# You may want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly
- alert: HostCpuIsUnderutilized
expr: '(min by (instance) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > 0.8'
expr: '(min without (cpu) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > 0.8'
for: 1w
labels:
severity: info
@ -149,7 +149,7 @@ groups:
description: "CPU load has been < 20% for 1 week. Consider reducing the number of CPUs.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostCpuStealNoisyNeighbor
expr: 'avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10'
expr: 'avg without (cpu) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10'
for: 0m
labels:
severity: warning
@ -158,7 +158,7 @@ groups:
description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostCpuHighIowait
expr: 'avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) > .10'
expr: 'avg without (cpu) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) > .10'
for: 0m
labels:
severity: warning