clerie/nixfiles
1
0
Fork 0
Code

hosts/monitoring-3: Replace InstanceUp alert with KernelChanged

Browse Source
This commit is contained in:
clerie 2023-03-25 20:42:17 +01:00
parent 77d10e4835
commit 41cd4792a6
1 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
hosts/monitoring-3/rules.yml
View File

@ -9,13 +9,6 @@ groups:
annotations: annotations:
summary: "Endpoint {{ $labels.instance }} down" summary: "Endpoint {{ $labels.instance }} down"
description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 1 minutes." description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 1 minutes."
- alert: InstanceUptime
expr: time() - node_boot_time_seconds{job="node-exporter"} >= 7776000
labels:
severity: warning
annotations:
summary: "Uptime of {{ $labels.instance }} more than 90 days"
description: "The last reboot of {{ $labels.instance }} was more than 90 days ago"
- alert: InstanceConfigNotSync - alert: InstanceConfigNotSync
expr: nixos_current_system_is_sync{} == 0 expr: nixos_current_system_is_sync{} == 0
for: 2h for: 2h
@ -48,3 +41,11 @@ groups:
annotations: annotations:
summary: "Event instance {{ $labels.instance }} down" summary: "Event instance {{ $labels.instance }} down"
description: "{{ $labels.instance }} has been down for more than 2 hours." description: "{{ $labels.instance }} has been down for more than 2 hours."
- alert: KernelChanged
expr: nixos_current_system_kernel_is_booted_system_kernel{job="nixos-exporter"} == 0
for: 2h
labels:
severity: warning
annotations:
summary: "Kernel of {{ $labels.instance }} changed"
description: "The Kernel {{ $labels.instance }} booted with, isn't the target Kernel. A reboot may be required."