Created
June 21, 2018 14:00
-
-
Save jpweber/82404bb70c20e37f67f5dc2ed1164007 to your computer and use it in GitHub Desktop.
alert manager config example
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
apiVersion: v1 | |
kind: ConfigMap | |
metadata: | |
name: prometheus-alertmanager | |
namespace: monitoring | |
data: | |
alertmanager.yml: |- | |
global: | |
## | |
# tool to help visualize where your alerts are going | |
# https://prometheus.io/webtools/alerting/routing-tree-editor/ | |
## | |
# The directory from which notification templates are read. | |
templates: | |
- '/etc/alertmanager/templates/*.tmpl' | |
# The root route on which each incoming alert enters. | |
route: | |
# The labels by which incoming alerts are grouped together. For example, | |
# multiple alerts coming in for cluster=A and alertname=LatencyHigh would | |
# be batched into a single group. | |
group_by: ['alertname', 'cluster', 'service'] | |
# When a new group of alerts is created by an incoming alert, wait at | |
# least 'group_wait' to send the initial notification. | |
# This way ensures that you get multiple alerts for the same group that start | |
# firing shortly after another are batched together on the first | |
# notification. | |
group_wait: 30s | |
# When the first notification was sent, wait 'group_interval' to send a batch | |
# of new alerts that started firing for that group. | |
group_interval: 5m | |
# If an alert has successfully been sent, wait 'repeat_interval' to | |
# resend them. | |
repeat_interval: 3h | |
# A default receiver | |
receiver: slack_prometheus | |
# All the above attributes are inherited by all child routes and can | |
# overwritten on each. | |
# The child route trees. | |
routes: | |
# This routes performs a regular expression match on alert labels to | |
# catch alerts that are related to a list of services. | |
# - match_re: | |
# service: ^(foo1|foo2|baz)$ | |
# receiver: team-X-mails | |
# # The service has a sub-route for critical alerts, any alerts | |
# # that do not match, i.e. severity != critical, fall-back to the | |
# # parent node and are sent to 'team-X-mails' | |
# routes: | |
# - match: | |
# severity: critical | |
# receiver: team-X-pager | |
- match: | |
severity: critical | |
receiver: critical_alert | |
- match: | |
severity: warning | |
receiver: slack_prometheus | |
# Inhibition rules allow to mute a set of alerts given that another alert is | |
# firing. | |
# We use this to mute any warning-level notifications if the same alert is | |
# already critical. | |
inhibit_rules: | |
- source_match: | |
severity: 'critical' | |
target_match: | |
severity: 'warning' | |
# Apply inhibition if the alertname is the same. | |
equal: ['cluster', 'service'] | |
receivers: | |
# receivers for critical alerts. For example Sends to pager duty _and_ slack | |
- name: critical_alert | |
pagerduty_configs: | |
- send_resolved: true | |
service_key: '<your service key>' | |
slack_configs: | |
- send_resolved: true | |
api_url: '<your slack api url>' | |
channel: '#<your channel name>' | |
text: '{{ template "slack.default.text" . }}' | |
title: "{{ range .Alerts }}{{ .Annotations.summary }}\n{{ end }}" | |
# send to a slack channel. This is being used by the warning severity | |
- name: 'slack_prometheus' | |
slack_configs: | |
- send_resolved: true | |
api_url: '<your slack api url>' | |
channel: '#<your channel name>' | |
title: "{{ range .Alerts }}{{ .Annotations.summary }}\n{{ end }}" | |
text: "{{ range .Alerts }}{{ .Annotations.description }}\n{{ end }}" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment