Cadoles
/
eole-prometheus
10
0
Fork 0
Code Issues 3 Pull Requests Releases Wiki Activity

ajout surveillance /var

This commit is contained in:
vfebvre 2021-10-21 11:00:11 +02:00
parent 43e34f8de8
commit 4ef331f6a1
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
tmpl/alert-rules.yml
View File

@ -34,11 +34,21 @@ groups:
- alert: filesystem_threshold_exceeded - alert: filesystem_threshold_exceeded
expr: node_filesystem_avail{job="%%{job_name_node}",mountpoint="/"} / node_filesystem_size{job="%%{job_name_node}"} expr: node_filesystem_avail{job="%%{job_name_node}",mountpoint="/"} / node_filesystem_size{job="%%{job_name_node}"}
* 100 < 20 * 100 < 20
for: 2m
annotations: annotations:
description: This device's filesystem usage has exceeded the threshold with description: This device's filesystem usage has exceeded the threshold with
a value of {{ $value }}. a value of {{ $value }}.
summary: Instance {{ $labels.instance }} filesystem usage is dangerously high summary: Instance {{ $labels.instance }} filesystem usage is dangerously high
# Heavy "/var" use
- alert: var_filesystem_threshold_exceeded
expr: node_filesystem_avail{job="node",mountpoint="/var"} / node_filesystem_size{job="node"}
* 100 < 20
annotations:
description: This device's filesystem usage has exceeded the threshold with
a value of {{ $value }}.
summary: Instance {{ $labels.instance }} filesystem usage is dangerously high
# Heavy CPU temperature # Heavy CPU temperature
- alert: cpu_temp_threshold_exceeded - alert: cpu_temp_threshold_exceeded
expr: avg(node_hwmon_temp_celsius{job="node"}) BY (instance) expr: avg(node_hwmon_temp_celsius{job="node"}) BY (instance)