till/managarten
1
0
Fork 0
mirror of https://github.com/Memo-2023/mana-monorepo.git synced 2026-05-14 20:41:09 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

fix(monitoring): update disk alerts to use mac_disk_used_percent metrics

Browse source 
node-exporter runs in VM and can't see host macOS disks directly.
Use custom mac_disk_used_percent metrics pushed via Pushgateway instead.
Also add ColimaVMDiskLarge alert when datadisk exceeds 150 GB.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Till JS 2026-03-30 20:01:46 +02:00
parent 5fc34dafe8
commit be1096ec85
1 changed files with 21 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

32
docker/prometheus/alerts.yml
View file

@ -119,29 +119,39 @@ groups:
summary: "Very high memory usage on host"
description: "Memory usage is {{ $value | humanize }}%"
# High Disk Usage (> 80%)
# High Disk Usage — macOS host disks (via Pushgateway, since node-exporter runs in VM)
# Metrics pushed by scripts/mac-mini/disk-metrics.sh (runs every 5 min via launchd)
- alert: HighDiskUsage
expr: |
(1 - (node_filesystem_avail_bytes{mountpoint=~"/host_mnt/Users|/|/host_mnt/Volumes/ManaData"}
/ node_filesystem_size_bytes{mountpoint=~"/host_mnt/Users|/|/host_mnt/Volumes/ManaData"})) * 100 > 80
mac_disk_used_percent{disk=~"internal|manaData"} > 80
for: 10m
labels:
severity: warning
annotations:
summary: "High disk usage on {{ $labels.mountpoint }}"
description: "Disk usage is {{ $value | humanize }}%"
summary: "High disk usage on {{ $labels.disk }} ({{ $labels.mountpoint }})"
description: "Disk usage is {{ $value | humanize }}% — {{ $labels.avail_human }} free"
# Very High Disk Usage (> 90%)
# Very High Disk Usage (> 90%) — immediate alert
- alert: VeryHighDiskUsage
expr: |
(1 - (node_filesystem_avail_bytes{mountpoint=~"/host_mnt/Users|/|/host_mnt/Volumes/ManaData"}
/ node_filesystem_size_bytes{mountpoint=~"/host_mnt/Users|/|/host_mnt/Volumes/ManaData"})) * 100 > 90
for: 5m
mac_disk_used_percent{disk=~"internal|manaData"} > 90
for: 2m
labels:
severity: critical
annotations:
summary: "Very high disk usage on {{ $labels.mountpoint }}"
description: "Disk usage is {{ $value | humanize }}%"
summary: "CRITICAL: Disk {{ $labels.disk }} almost full ({{ $labels.mountpoint }})"
description: "Disk usage is {{ $value | humanize }}% — only {{ $labels.avail_human }} free. Server may crash."
# Colima VM disk large (> 150GB actual usage on sparse datadisk)
- alert: ColimaVMDiskLarge
expr: |
mac_colima_disk_used_gb > 150
for: 30m
labels:
severity: warning
annotations:
summary: "Colima VM disk is {{ $value | humanize }}GB — consider pruning Docker images"
description: "Run: docker system prune -f && docker image prune -a"
- name: database_alerts
rules: