XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-25 02:46:59 +08:00
Code Issues Projects Releases Packages Wiki Activity

Publish

Browse source
This commit is contained in:
samber 2024-06-14 18:16:53 +00:00
parent ca4fb01c6d
commit 60c235975c
1 changed files with 7 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
dist/rules/host-and-hardware/node-exporter.yml vendored
View file

@ -175,14 +175,17 @@ groups:
summary: Host unusual disk IO (instance {{ $labels.instance }}) summary: Host unusual disk IO (instance {{ $labels.instance }})
description: "Time spent in IO is too high on {{ $labels.instance }}. Check storage for issues.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "Time spent in IO is too high on {{ $labels.instance }}. Check storage for issues.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostContextSwitching - alert: HostContextSwitchingHigh
expr: '((rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 10000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' expr: '(rate(node_context_switches_total[15m])/count without(mode,cpu) (node_cpu_seconds_total{mode="idle"}))
/
(rate(node_context_switches_total[1d])/count without(mode,cpu) (node_cpu_seconds_total{mode="idle"})) > 2
'
for: 0m for: 0m
labels: labels:
severity: warning severity: warning
annotations: annotations:
summary: Host context switching (instance {{ $labels.instance }}) summary: Host context switching high (instance {{ $labels.instance }})
description: "Context switching is growing on the node (> 10000 / CPU / s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" description: "Context switching is growing on the node (twice the daily average during the last 15m)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostSwapIsFillingUp - alert: HostSwapIsFillingUp
expr: '((1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' expr: '((1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'