117 lines
3.5 KiB
YAML
117 lines
3.5 KiB
YAML
global:
|
|
# The smarthost and SMTP sender used for mail notifications.
|
|
smarthost: 'localhost:25'
|
|
smtp_sender: 'alertmanager@example.org'
|
|
|
|
# The directory from which notification templates are read.
|
|
templates:
|
|
- '/etc/alertmanager/template/*.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 betch
|
|
# 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
|
|
|
|
# If 'continue' is false, the first sub-route that matches this alert will
|
|
# terminate the search and the alert will be inserted at that routing node.
|
|
# If true, the alert is inserted to sibling nodes as well if there is a
|
|
# match.
|
|
# This allows to do first-match semantics (=false) in smaller scopes (e.g. team-level),
|
|
# while avoiding accidental shadowing (=true) at alerts at larger scopes (e.g. company-level)
|
|
continue: true
|
|
|
|
# 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:
|
|
service: files
|
|
receiver: team-Y-mails
|
|
|
|
routes:
|
|
- match:
|
|
severity: critical
|
|
receiver: team-Y-pager
|
|
|
|
# This route handles all alerts coming from a database service. If there's
|
|
# no team to handle it, it defaults to the DB team.
|
|
- match:
|
|
service: database
|
|
receiver: team-DB-pager
|
|
# Also group alerts by affected database.
|
|
group_by: [alertname, cluster, database]
|
|
continue: false
|
|
routes:
|
|
- match:
|
|
owner: team-X
|
|
receiver: team-X-pager
|
|
- match:
|
|
owner: team-Y
|
|
receiver: team-Y-pager
|
|
|
|
|
|
# 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: ['alertname', 'cluster', 'service']
|
|
|
|
|
|
receivers:
|
|
- name: 'team-X-mails'
|
|
email_configs:
|
|
- email: 'team-X+alerts@example.org'
|
|
|
|
- name: 'team-X-pager'
|
|
email_configs:
|
|
- email: 'team-X+alerts-critical@example.org'
|
|
pagerduty_configs:
|
|
- service_key: <team-X-key>
|
|
|
|
- name: 'team-Y-mails'
|
|
email_configs:
|
|
- email: 'team-Y+alerts@example.org'
|
|
|
|
- name: 'team-Y-pager'
|
|
pagerduty_configs:
|
|
- service_key: <team-Y-key>
|
|
|
|
- name: 'team-DB-pager'
|
|
pagerduty_configs:
|
|
- service_key: <team-DB-key> |