monitoring: add alerting rules for disks running out of space
This commit is contained in:
parent
dca1261f07
commit
9cfee1f384
|
@ -28,3 +28,29 @@ groups:
|
|||
annotations:
|
||||
summary: The public wifi lost its ability to route into the internet
|
||||
description: "check the vpn connection"
|
||||
|
||||
- name: ServerSpecific
|
||||
rules:
|
||||
# https://awesome-prometheus-alerts.grep.to/rules#rule-host-and-hardware-1-7
|
||||
#
|
||||
# Please add ignored mountpoints in node_exporter parameters like
|
||||
# "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
|
||||
# Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users.
|
||||
- alert: HostOutOfDiskSpace
|
||||
expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host out of disk space (instance {{ $labels.instance }})
|
||||
description: "Disk is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
# https://awesome-prometheus-alerts.grep.to/rules#rule-host-and-hardware-1-9
|
||||
- alert: HostOutOfInodes
|
||||
expr: node_filesystem_files_free / node_filesystem_files * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host out of inodes (instance {{ $labels.instance }})
|
||||
description: "Disk is almost running out of available inodes (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
|
Reference in New Issue