crans
/
ansible
mirror of http://gitlab.adm.crans.org/nounous/ansible.git
19
0
Fork 0
Code Issues Projects Releases Wiki Activity

Alert ninjabot

certbot_on_virtu
Alexandre Iooss 2019-06-08 19:08:52 +02:00
parent c6cf86a43e
commit 8758f5a0c7
No known key found for this signature in database
GPG Key ID: 6C79278F3FCDCC02
2 changed files with 10 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
roles/prometheus-alertmanager/templates/prometheus/alertmanager.yml.j2
View File

@ -28,14 +28,15 @@ route:
# When the first notification was sent, wait 'group_interval' to send a batch # When the first notification was sent, wait 'group_interval' to send a batch
# of new alerts that started firing for that group. # of new alerts that started firing for that group.
group_interval: 5m group_interval: 1m
# If an alert has successfully been sent, wait 'repeat_interval' to # If an alert has successfully been sent, wait 'repeat_interval' to
# resend them. # resend them.
repeat_interval: 3h repeat_interval: 3h
# A default receiver # A default receiver
receiver: team-roots-mails #receiver: team-roots-mails
receiver: webhook-ninjabot
# Inhibition rules allow to mute a set of alerts given that another alert is # Inhibition rules allow to mute a set of alerts given that another alert is
@ -55,4 +56,7 @@ receivers:
- name: 'team-roots-mails' - name: 'team-roots-mails'
email_configs: email_configs:
- to: 'roots@crans.org' - to: 'roots@crans.org'
- name: 'webhook-ninjabot'
webhook_configs:
- url: 'http://zamok.adm.crans.org:5000/'
send_resolved: true

4
roles/prometheus/templates/prometheus/alert.rules.yml.j2
View File

@ -59,6 +59,8 @@ groups:
- alert: APIHighRequestLatency - alert: APIHighRequestLatency
expr: api_http_request_latencies_second{quantile="0.5"} > 1 expr: api_http_request_latencies_second{quantile="0.5"} > 1
for: 10m for: 10m
labels:
severity: warning
annotations: annotations:
summary: "Latence élevée sur {{ $labels.instance }}" summary: "Latence élevée sur {{ $labels.instance }}"
description: "{{ $labels.instance }} a un temps de réponse médian au dessus d'une seconde (actuellement : {{ $value }}s)." description: "{{ $labels.instance }} a un temps de réponse médian au dessus d'une seconde (actuellement : {{ $value }}s)."
@ -77,7 +79,7 @@ groups:
expr: node_ntp_drift_seconds > 0.01 expr: node_ntp_drift_seconds > 0.01
for: 1m for: 1m
labels: labels:
severity: moderate severity: warning
annotations: annotations:
description: "Décalage NTP élevé sur {{ $labels.instance }}" description: "Décalage NTP élevé sur {{ $labels.instance }}"
summary: "Le décalage NTP est élevé ({{ $value }} > 0.01)" summary: "Le décalage NTP est élevé ({{ $value }} > 0.01)"