clerie/nixfiles
1
0
Fork 0
Code

hosts/monitoring-3: alert on averaged metrics

Browse Source
This commit is contained in:
clerie 2023-05-04 14:43:14 +02:00
parent 4834e5b91d
commit 398067f533
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
hosts/monitoring-3/rules.yml
View File

@ -18,7 +18,7 @@ groups:
summary: "Current system of {{ $labels.instance }} not in sync with config"
description: "The current system hash of {{ $labels.instance }} does not match the one generated by hydra based on the current config"
- alert: BackupStorageFull
expr: ((node_filesystem_avail_bytes{job="node-exporter"} / node_filesystem_size_bytes{job="node-exporter"}) * 100) < 5
expr: ((avg_over_time(node_filesystem_avail_bytes{job="node-exporter"}[5m]) / avg_over_time(node_filesystem_size_bytes{job="node-exporter"}[5m])) * 100) < 5
for: 30m
labels:
severity: critical
@ -42,7 +42,7 @@ groups:
summary: "Event instance {{ $labels.instance }} down"
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
expr: avg_over_time(nixos_current_system_kernel_is_booted_system_kernel{job="nixos-exporter"}[5m]) == 0
for: 2h
labels:
severity: warning