torjus/nixos-servers
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects 1 Releases Wiki Activity

Add harmonia alerting rule
Some checks failed
Run nix flake check / flake-check (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Torjus Håkestad 2025-02-24 18:29:41 +01:00
parent 3fde3bf757
commit 0dbdee65c5
Signed by: torjus
SSH Key Fingerprint: SHA256:KjAds8wHfD2mBYK2H815s/+ABcSdcIHUndwHEdSxml4
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
services/monitoring/prometheus.nix
View File

@ -147,6 +147,14 @@
annotations:
summary: "The build-flakes service on {{ $labels.instance }} has failed"
description: "The build-flakes service on {{ $labels.instance }} has failed"
- alert: harmonia_down
expr: node_systemd_unit_state {instance="nix-cache01.home.2rjus.net:9100", name = "harmonia.service", state = "active"} == 0
for: 5m
labels:
severity: critical
annotations:
summary: "Harmonia not running on {{ $labels.instance }}"
description: "Harmonia has been down on {{ $labels.instance }} more than 5 minutes."
- alert: low_disk_space_nix
expr: node_filesystem_free_bytes{instance="nix-cache01.home.2rjus.net:9100", mountpoint="/nix"} / node_filesystem_size_bytes{instance="nix-cache01.home.2rjus.net:9100", mountpoint="/nix"} * 100 < 10
for: 5m