使用配置文件配置告警资源

# config file version
apiVersion: 1

# List of rule groups to import or update
groups:
  # <int> organization ID, default = 1
  - orgId: 1
    # <string, required> name of the rule group
    name: my_rule_group
    # <string, required> name of the folder the rule group will be stored in
    folder: my_first_folder
    # <duration, required> interval that the rule group should evaluated at
    interval: 60s
    # <list, required> list of rules that are part of the rule group
    rules:
      # <string, required> unique identifier for the rule. Should not exceed 40 symbols. Only letters, numbers, - (hyphen), and _ (underscore) allowed.
      - uid: my_id_1
        # <string, required> title of the rule that will be displayed in the UI
        title: my_first_rule
        # <string, required> which query should be used for the condition
        condition: A
        # <list, required> list of query objects that should be executed on each
        #                  evaluation - should be obtained through the API
        data:
          - refId: A
            datasourceUid: '__expr__'
            model:
              conditions:
                - evaluator:
                    params:
                      - 3
                    type: gt
                  operator:
                    type: and
                  query:
                    params:
                      - A
                  reducer:
                    type: last
                  type: query
              datasource:
                type: __expr__
                uid: '__expr__'
              expression: 1==0
              intervalMs: 1000
              maxDataPoints: 43200
              refId: A
              type: math
        # <string> UID of a dashboard that the alert rule should be linked to
        dashboardUid: my_dashboard
        # <int> ID of the panel that the alert rule should be linked to
        panelId: 123
        # <string> the state the alert rule will have when no data is returned
        #          possible values: "NoData", "Alerting", "OK", default = NoData
        noDataState: Alerting
        # <string> the state the alert rule will have when the query execution
        #          failed - possible values: "Error", "Alerting", "OK"
        #          default = Alerting
        execErrState: Alerting
        # <duration, required> for how long should the alert fire before alerting
        for: 60s
        # <map<string, string>> a map of strings to pass around any data
        annotations:
          some_key: some_value
        # <map<string, string> a map of strings that can be used to filter and
        #                      route alerts
        labels:
          team: sre_team_1

# config file version
apiVersion: 1

# List of alert rule UIDs that should be deleted
deleteRules:
  # <int> organization ID, default = 1
  - orgId: 1
    # <string, required> unique identifier for the rule
    uid: my_id_1

# config file version
apiVersion: 1

# List of contact points to import or update
contactPoints:
  # <int> organization ID, default = 1
  - orgId: 1
    # <string, required> name of the contact point
    name: cp_1
    receivers:
      # <string, required> unique identifier for the receiver. Should not exceed 40 symbols. Only letters, numbers, - (hyphen), and _ (underscore) allowed.
      - uid: first_uid
        # <string, required> type of the receiver
        type: prometheus-alertmanager
        # <bool, optional> Disable the additional [Incident Resolved] follow-up alert, default = false
        disableResolveMessage: false
        # <object, required> settings for the specific receiver type
        settings:
          url: http://test:9000

# config file version
apiVersion: 1

# List of receivers that should be deleted
deleteContactPoints:
  # <int> organization ID, default = 1
  - orgId: 1
    # <string, required> unique identifier for the receiver
    uid: first_uid

# config file version
apiVersion: 1

# List of templates to import or update
templates:
  # <int> organization ID, default = 1
  - orgId: 1
    # <string, required> name of the template group, must be unique
    name: my_first_template
    # <string, required> content of the template group
    template: |
      {{ define "my_first_template" }}
        Custom notification message
      {{ end }}

# config file version
apiVersion: 1

# List of alert rule UIDs that should be deleted
deleteTemplates:
  # <int> organization ID, default = 1
  - orgId: 1
    # <string, required> name of the template group, must be unique
    name: my_first_template

# config file version
apiVersion: 1

# List of notification policies
policies:
  # <int> organization ID, default = 1
  - orgId: 1
    # <string> name of the contact point that should be used for this route
    receiver: grafana-default-email
    # <list> 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.
    #
    #        To aggregate by all possible labels use the special value '...' as
    #        the sole label name, for example:
    #        group_by: ['...']
    #        This effectively disables aggregation entirely, passing through all
    #        alerts as-is. This is unlikely to be what you want, unless you have
    #        a very low alert volume or your upstream notification system performs
    #        its own grouping.
    group_by: ['...']
    # <list> a list of prometheus-like matchers that an alert rule has to fulfill to match the node (allowed chars
    #        [a-zA-Z_:])
    matchers:
      - alertname = Watchdog
      - service_id_X = serviceX
      - severity =~ "warning|critical"
    # <list> a list of grafana-like matchers that an alert rule has to fulfill to match the node
    object_matchers:
      - ['alertname', '=', 'CPUUsage']
      - ['service_id-X', '=', 'serviceX']
      - ['severity', '=~', 'warning|critical']
    # <list> Times when the route should be muted. These must match the name of a
    #        mute time interval.
    #        Additionally, the root node cannot have any mute times.
    #        When a route is muted it will not send any notifications, but
    #        otherwise acts normally (including ending the route-matching process
    #        if the `continue` option is not set)
    mute_time_intervals:
      - abc
    # <duration> How long to initially wait to send a notification for a group
    #            of alerts. Allows to collect more initial alerts for the same group.
    #            (Usually ~0s to few minutes), default = 30s
    group_wait: 30s
    # <duration> How long to wait before sending a notification about new alerts that
    #            are added to a group of alerts for which an initial notification has
    #            already been sent. (Usually ~5m or more), default = 5m
    group_interval: 5m
    # <duration>  How long to wait before sending a notification again if it has already
    #             been sent successfully for an alert. (Usually ~3h or more), default = 4h
    repeat_interval: 4h
    # <list> Zero or more child policies. The schema is the same as the root policy.
    # routes:
    #   # Another recursively nested policy...
    #   - receiver: another-receiver
    #     matchers:
    #       - ...
    #     ...

# config file version
apiVersion: 1

# List of orgIds that should be reset to the default policy
resetPolicies:
  - 1

# config file version
apiVersion: 1

# List of mute time intervals to import or update
muteTimes:
  # <int> organization ID, default = 1
  - orgId: 1
    # <string, required> name of the mute time interval, must be unique
    name: mti_1
    # <list> time intervals that should trigger the muting
    #        refer to https://prometheus.ac.cn/docs/alerting/latest/configuration/#time_interval-0
    time_intervals:
      - times:
          - start_time: '06:00'
            end_time: '23:59'
        location: 'UTC'
        weekdays: ['monday:wednesday', 'saturday', 'sunday']
        months: ['1:3', 'may:august', 'december']
        years: ['2020:2022', '2030']
        days_of_month: ['1:5', '-3:-1']

# config file version
apiVersion: 1

# List of mute time intervals that should be deleted
deleteMuteTimes:
  # <int> organization ID, default = 1
  - orgId: 1
    # <string, required> name of the mute time interval, must be unique
    name: mti_1

contactPoints:
  - orgId: 1
    name: My Contact Email Point
    receivers:
      - uid: 1
        type: email
        settings:
          addresses: $EMAIL