hosts/monitoring-3: alert for all storage drives when they are full
This commit is contained in:
parent
7d13fb29d1
commit
882df0098f
@ -8,7 +8,7 @@ groups:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Endpoint {{ $labels.instance }} down"
|
||||
description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 1 minutes."
|
||||
description: "{{ $labels.instance }} is unreachable"
|
||||
- alert: InstanceConfigNotSync
|
||||
expr: nixos_current_system_is_sync{} == 0
|
||||
for: 2h
|
||||
@ -18,13 +18,13 @@ 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{instance="clerie-backup.net.clerie.de", job="node-exporter", mountpoint="/mnt/clerie-backup"} / node_filesystem_size_bytes{instance="clerie-backup.net.clerie.de", job="node-exporter", mountpoint="/mnt/clerie-backup"}) * 100) < 5
|
||||
expr: ((node_filesystem_avail_bytes{job="node-exporter"} / node_filesystem_size_bytes{job="node-exporter"}) * 100) < 5
|
||||
for: 30m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Storage for backup is nearly full"
|
||||
description: "Storage for backups is nearly full"
|
||||
summary: "Storage of {{ $labels.instance }} is full"
|
||||
description: "Storage of {{ $labels.instance }} for {{ $labels.mountpoint }} on {{ $labels.device }} is full"
|
||||
- alert: InstanceJustBooted
|
||||
expr: time() - node_boot_time_seconds{job="node-exporter"} <= 300
|
||||
labels:
|
||||
|
Loading…
Reference in New Issue
Block a user