DEV-1078: added alert prom2teams down

main
Hoan To 2 years ago
parent 5084488413
commit 9dd5bcd7aa

@ -0,0 +1,22 @@
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
labels:
prometheus: kube-prometheus-stack-prometheus # dieser name ist fest
role: alert-rules # auch fest
release: kube-prometheus-stack # IMPORTANT: ohne das Label wird die Rule vom PrometheusOperator nicht gefunden
name: prometheus-msteams-alert
namespace: monitoring # Rule im namespace anlegen in dem die zu ueberwachende App laeuft
spec:
groups:
- name: msteams_alerts
rules:
- alert: PrometheusMSTeamsDown
expr: up{job="prometheus-msteams"} == 0
for: 5m
labels:
severity: critical
receiver: email
annotations:
summary: "Prometheus MSTeams is down"
description: "The prometheus-msteams service has been down for more than 5 minutes."

@ -1,3 +1,4 @@
resources: resources:
- alert_hetzner_api_requestlimit.yaml - alert_hetzner_api_requestlimit.yaml
- alert_backup_minio.yaml - alert_backup_minio.yaml
- alert_prometheus_msteams.yaml

@ -41,7 +41,11 @@ stringData:
receiver: alerting-nso-devops receiver: alerting-nso-devops
matchers: matchers:
- severity = critical - severity = critical
continue: false continue: true
- receiver: 'netgo_email_receiver'
match:
receiver: email
continue: true
inhibit_rules: inhibit_rules:
- source_match: - source_match:
alertname: "Watchdog" alertname: "Watchdog"
@ -63,6 +67,15 @@ stringData:
webhook_configs: webhook_configs:
- url: "http://prometheus-msteams:2000/alert-nso-team-erechnung-mobene" - url: "http://prometheus-msteams:2000/alert-nso-team-erechnung-mobene"
send_resolved: true send_resolved: true
- name: netgo_email_receiver
email_configs:
- to: 'nso.devops@netgo.de'
from: 'prometheus_prodwork01@netgo.de'
smarthost: '10.3.0.11:25'
auth_username: ''
auth_identity: ''
auth_password: ''
require_tls: false
kind: Secret kind: Secret
metadata: metadata:

Loading…
Cancel
Save