infra/ansible-role-prometheus-agent
4
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Lowered uptime alert time to 30 days

Browse source
This commit is contained in:
Julian Rother 2021-12-04 20:06:34 +01:00
parent dd0b49cd23
commit 0577ca8a39
No known key found for this signature in database
GPG key ID: 2F811E2338EE029B
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
defaults/main.yml
View file

@ -253,10 +253,10 @@ prometheus_agent:
alert: uptime alert: uptime
expr: | expr: |
node_time_seconds{job="node", instance="{{ inventory_hostname }}"} - node_time_seconds{job="node", instance="{{ inventory_hostname }}"} -
node_boot_time_seconds{job="node", instance="{{ inventory_hostname }}"} > 3600*24*120 node_boot_time_seconds{job="node", instance="{{ inventory_hostname }}"} > 3600*24*30
for: 5m for: 5m
labels: labels:
severity: critical severity: warning
annotations: annotations:
title: '{%raw%}{{ $labels.instance }}: Uptime{%endraw%}' title: '{%raw%}{{ $labels.instance }}: Uptime{%endraw%}'
description: "Uptime is more than 120 days, please reboot soon" description: "Uptime is more than 30 days, please reboot soon"