# # config file version apiVersion: 1 # # List of rule groups to import or update # groups: # # organization ID, default = 1 # - orgId: 1 # # name of the rule group # name: my_rule_group # # name of the folder the rule group will be stored in # folder: my_first_folder # # interval of the rule group evaluation # interval: 60s # # list of rules that are part of the rule group # rules: # # unique identifier for the rule. Should not exceed 40 symbols. Only letters, numbers, - (hyphen), and _ (underscore) allowed. # - uid: my_id_1 # # title of the rule, will be displayed in the UI # title: my_first_rule # # query used for the condition # condition: A # # list of query objects that should be executed on each # # evaluation - should be obtained via 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 # # UID of a dashboard that the alert rule should be linked to # dashboardUid: my_dashboard # # ID of the panel that the alert rule should be linked to # panelId: 123 # # state of the alert rule when no data is returned # # possible values: "NoData", "Alerting", "OK", default = NoData # noDataState: Alerting # # state of the alert rule when the query execution # # fails - possible values: "Error", "Alerting", "OK" # # default = Alerting # executionErrorState: Alerting # # how long the alert condition should be breached before Firing. Before this time has elapsed, the alert is considered to be Pending # for: 60s # # > map of strings to attach arbitrary custom data # annotations: # some_key: some_value # # map of strings to filter and # # route alerts # labels: # team: sre_team_1 # isPaused: false # # optional settings that let configure notification settings applied to alerts created by this rule # notification_settings: # # name of the receiver (contact-point) that should be used for this route # receiver: grafana-default-email # # > 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. # # If defined, must contain the labels 'alertname' and 'grafana_folder', except when contains '...' # group_by: ["alertname", "grafana_folder", "region"] # # 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 # # 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). # # If not specified, the corresponding setting of the default policy is used. # group_wait: 30s # # 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). # # If not specified, the corresponding setting of the default policy is used. # group_interval: 5m # # How long to wait before sending a notification again if it has already # # been sent successfully for an alert. (Usually ~3h or more) # # If not specified, the corresponding setting of the default policy is used. # repeat_interval: 4h # # List of alert rule UIDs that should be deleted # deleteRules: # # organization ID, default = 1 # - orgId: 1 # # unique identifier for the rule # uid: my_id_1 # # List of contact points to import or update # contactPoints: # # organization ID, default = 1 # - orgId: 1 # # name of the contact point # name: cp_1 # receivers: # # unique identifier for the receiver. Should not exceed 40 symbols. Only letters, numbers, - (hyphen), and _ (underscore) allowed. # - uid: first_uid # # type of the receiver # type: prometheus-alertmanager # # settings for the specific receiver type # settings: # url: http://test:9000 # # List of receivers that should be deleted # deleteContactPoints: # - orgId: 1 # uid: first_uid # # List of notification policies to import or update # policies: # # organization ID, default = 1 # - orgId: 1 # # name of the receiver that should be used for this route # receiver: grafana-default-email # # > 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: # - grafana_folder # - alertname # # a list of matchers that an alert has to fulfill to match the node # matchers: # - alertname = Watchdog # - severity =~ "warning|critical" # # 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 # # 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 # # 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 # # 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 # # Zero or more child routes # routes: # ... # # List of orgIds that should be reset to the default policy # resetPolicies: # - 1 # # List of templates to import or update # templates: # # organization ID, default = 1 # - orgID: 1 # # name of the template, must be unique # name: my_first_template # # content of the the template # template: Alerting with a custome text template # # List of templates that should be deleted # deleteTemplates: # # organization ID, default = 1 # - orgId: 1 # # name of the template, must be unique # name: my_first_template # # List of mute time intervals to import or update # muteTimes: # # organization ID, default = 1 # - orgId: 1 # # name of the mute time interval, must be unique # name: mti_1 # # time intervals that should trigger the muting # refer to https://prometheus.io/docs/alerting/latest/configuration/#time_interval-0 # time_intervals: # - times: # - start_time: '06:00' # end_time: '23:59' # weekdays: ['monday:wednesday','saturday', 'sunday'] # months: ['1:3', 'may:august', 'december'] # years: ['2020:2022', '2030'] # days_of_month: ['1:5', '-3:-1'] # # List of mute time intervals that should be deleted # deleteMuteTimes: # # organization ID, default = 1 # - orgId: 1 # # name of the mute time interval, must be unique # name: mti_1