notifier.example.yml

# Redis configuration depends on fields specified in redis config section:
# 1. Use field `master_name` to enable Redis Sentinel support
# 2. Specify two or more `addrs` to enable cluster support
# 3. Otherwise, standalone configuration is enabled
redis:
  # Sentinel master name
  master_name: ""
  # address list, format: {host1_name:port},{ip:port}
  addrs: "localhost:6379"
  # Redis username
  username: "username"
  # Redis password
  password: "password"
  # Redis Sentinel username
  sentinel_username: "sentinel_username"
  # Redis Sentinel password
  sentinel_password: "sentinel_password"
  # Moira will delete metrics older than this value from Redis. Large values will lead to various problems everywhere.
  # See https://github.com/moira-alert/moira/pull/519
  metrics_ttl: 3h
  # Dial timeout for establishing new connections
  # Default is 500 milliseconds
  dial_timeout: 1s
  # Timeout for socket reads. If reached, commands will fail
  # with a timeout instead of blocking. Default is 3 seconds.
  # Skip this setting or set 0 for default.
  read_timeout: 5s
  # Timeout for socket writes. If reached, commands will fail
  # with a timeout instead of blocking. Default is ReadTimeout.
  # Skip this setting or set 0 for default.
  write_timeout: 5s
  # Enables read-only commands on slave nodes
  # The flag does not work without `route_randomly` or `route_by_latency` set to true
  # Notifer requires master and slaves to synchronize too fast, so it is safer to turn this flag off
  read_only: false
  # Allows routing read-only commands to the **random** master or slave node
  # It automatically enables ReadOnly
  route_randomly: false
  # Allows routing read-only commands to the **closest** master or slave node
  # It automatically enables ReadOnly
  route_by_latency: false
telemetry:
  # Common port for all telemetry data: Prometheus scraping, pprof, etc.
  listen: ":8091"
  pprof:
    # If true, pprof will be enabled on common telemetry port.
    enabled: false
  graphite:
    # If true, graphite sender will be enabled.
    enabled: true
    # If true, runtime stats will be captured and sent to graphite. Note: It takes to call stoptheworld() with configured "graphite.interval" to capture runtime stats (https://golang.org/src/runtime/mstats.go)
    runtime_stats: false
    # Graphite relay URI, format: ip:port
    uri: "graphite-relay:2003"
    # Moira metrics prefix. Use 'prefix: {hostname}' to use hostname autoresolver.
    prefix: DevOps.moira
    # Metrics sending interval
    interval: 60s
notifier:
  # Soft timeout to start retrying to send notification after single failed attempt
  sender_timeout: 10s
  # Hard timeout to stop retrying to send notification after multiple failed attempts
  resending_timeout: "1:00"
  # Delay before performing one more send attempt
  rescheduling_delay: 60s
  # Web-UI uri prefix for trigger links in notifications. For example: with 'http://localhost' every notification will contain link like 'http://localhost/trigger/triggerId'
  front_uri: "https://moira.example.com"
  # Timezone to use to convert ticks. Default is UTC. See https://golang.org/pkg/time/#LoadLocation for more details.
  timezone: Europe/Moscow
  # Format for email sender. Default is "15:04 02.01.2006". See https://golang.org/pkg/time/#Time.Format for more details about golang time formatting.
  date_time_format: "15:04 02.01.2006"
  # Amount of messages notifier reads from Redis per iteration, -1 for unlimited
  read_batch_size: -1
  # List of senders, every element has required "sender_type" field (one of ["pushover", "slack", "mail", "telegram", "twilio sms", "twilio voice", "script", "discord", "selfstate", "webhook", "opsgenie", "victorops", "pagerduty", "msteams", "mattermost"]) and "contact_type"
  # It is possible to create several senders with the same "sender_type", but different "contact_type"
  # Every type of sender has additional config fields
  senders:
      # sender_type characterizes the specific structure of the sender in the code
    - sender_type: msteams
      # contact_type matches 1-1 sender with the contact template type in the api web config, uniquely identifies the sender
      contact_type: msteams
      #the max amount of events you want to be sent to your channel, -1 for unlimited, any other positive value to limit events
      max_events: -1
    - sender_type: pushover
      contact_type: pushover
      # Api token for your pushover channel, for more info see https://pushover.net/api#registration
      api_token: ...
    - sender_type: slack
      contact_type: slack
      # Api token for your moira notifications slack user, for more info see https://get.slack.help/hc/en-us/articles/215770388-Create-and-regenerate-API-tokens
      api_token: ...
      # If true, notification will be sent with state-specific icon, for more info see https://moira.readthedocs.io/en/latest/installation/configuration.html#slack-icons.
      use_emoji: true
      # Used if `emoji_map` does not find `emoji` by any metric state in `emoji_map`
      default_emoji: ':moira-state-ok:'
      # Sets the correspondence between the emoji used and the state of the metrics in the notification in Slack
      # Default fill is shown below
      emoji_map:
        'OK': ':moira-state-ok:'
        'WARN': ':moira-state-warn:'
        'ERROR': ':moira-state-error:'
        'NODATA': ':moira-state-nodata:'
        'EXCEPTION': ':moira-state-exception:'
        'TEST': ':moira-state-test:'
    - sender_type: mattermost
      contact_type: mattermost
      # Sets the url to the Mattermost API for the client
      url: ...
      # Controls whether a client verifies the server's certificate chain and host name
      # If it's is true, crypto/tls accepts any certificate presented by the server and any host name in that certificate
      insecure_tls: false
      # Api token for moira notifications Mattermost client
      api_token: ...
      # If true, notification will be sent with state-specific icon
      use_emoji: true
      # Used if `emoji_map` does not find `emoji` by any metric state in `emoji_map`
      default_emoji: ':moira-state-ok:'
      # Sets the correspondence between the emoji used and the state of the metrics in the notification in Mattermost
      # Default fill is shown below
      emoji_map:
        'OK': ':moira-state-ok:'
        'WARN': ':moira-state-warn:'
        'ERROR': ':moira-state-error:'
        'NODATA': ':moira-state-nodata:'
        'EXCEPTION': ':moira-state-exception:'
        'TEST': ':moira-state-test:'
    - sender_type: telegram
      contact_type: telegram
      # Api token for your telegram bot, for more info about creating bot and get token see https://core.telegram.org/bots#3-how-do-i-create-a-bot
      api_token: ...
    - sender_type: mail
      contact_type: mail
      mail_from: ...
      smtp_host: ...
      smtp_port: ...
      # Skip SMTP server certificate chain validation if false
      insecure_tls: false
      # Uses "mail_from" if empty
      smtp_user: ...
      smtp_pass: ...
      # Email template file path (standard Go templates). By default use 'Fancy' template (see screenshot below). If empty, use build-in template with no markups and styles.
      template_file: '/etc/moira/fancy-template.html'
    - sender_type: twilio voice
      contact_type: twilio voice
      api_asid: ...
      api_authtoken: ...
      api_fromphone: ...
      # URL that responds with TwiML config for voice message generation, see https://www.twilio.com/docs/api/twiml/voice-overview
      voiceurl: ...
      append_message: true
    - sender_type: twilio sms
      contact_type: twilio sms
      api_asid: ...
      api_authtoken: ...
      api_fromphone: ...
    # Script and webhook senders support additional templated parameters:
    # ${contact_id}    contact ID
    # ${contact_value} contact value (as specified by user via web UI)
    # ${contact_type}  contact type (as specified in web UI config file)
    # ${trigger_id}    trigger ID
    - sender_type: script
      contact_type: script
      # Executable path. File must exist on all machines where notifier is running.
      # You can use templated parameters here (see above), they will be replaced with appropriate values.
      exec: ...
    - sender_type: webhook
      contact_type: webhook
      # URL to send POST request (you can use templated parameters, see above)
      url: ...
      timeout: ...
      # Basic authorization parameters (if required)
      user: ...
      password: ...
      # optional field body allows you to set the json request body using go-templates, the available fields for use are: .Contact.Type and .Contact.Value
      body: '{ "value": {{ .Contact.Value }}, "text": "test" }'
      # headers a field that allows you to set headers in the "key: value" format
      headers:
        test: test-header
    # Example of creating multiple webhook type senders
    - sender_type: webhook
      contact_type: webhook2
      url: ...
      timeout: ...
    - sender_type: pagerduty
      contact_type: pagerduty
    - sender_type: opsgenie
      contact_type: opsgenie
      api_key: ...
    - sender_type: victorops
      contact_type: victorops
      routing_url: ...
    - sender_type: discord
      contact_type: discord
      token: ...
  # Self state monitor configuration section. Note: No inner subscriptions is required. Moira will use its notification mechanism to send messages.
  moira_selfstate:
    enabled: true
    # If true, Moira selfstate will check remote triggers checker works properly and notify admin if remote checker fails
    # See https://moira.readthedocs.io/en/latest/installation/configuration.html#graphite-remote-triggers-checker for futher information
    remote_triggers_enabled: false
    # Max Redis disconnect delay to send alert when reached
    redis_disconect_delay: 60s
    # Max Filter metrics receive delay to send alert when reached
    last_metric_received_delay: 120s
    # Max Checker checks perform delay to send alert when reached
    last_check_delay: 120s
    # Max Remote triggers Checker checks perform delay to send alert when reached
    # See https://moira.readthedocs.io/en/latest/installation/configuration.html#graphite-remote-triggers-checker for futher information
    last_remote_check_delay: 300s
    # Self state monitor alerting interval
    notice_interval: 300s
    # Maximum contact events storage interval
    notification_history:
      ttl: "48h"
    # Self state monitor check interval (default 10s)
    check_interval: 10s
    # Count available mute resend call, if more than set - you see error in logs (default 3)
    max_fail_attempt_to_send_available: 3
    # Contact list for Self state monitor alerts, use this like delivery channels in web-ui
    contacts:
      - type: mail
        value: devopsteam@example.com
log:
  log_file: stdout
  log_level: info
# notification sets the configuration setting for sending notifications
notification:
  # resave_time is the time by which the timestamp of notifications with triggers or metrics on Maintenance is incremented
  # Important! Do not set this time too long, as this parameter sets the delay in sending notifications
  resave_time: 30s
  # Need to determine if notification is delayed - the difference between creation time and sending time is greater than delayed_time
  delayed_time: 1m
  # transaction_timeout defines the timeout between fetch notifications transactions
  transaction_timeout: 100ms
  # transaction_max_retries defines the maximum number of attempts to make a transaction
  transaction_max_retries: 10
  # transaction_heuristic_limit maximum allowable limit, after this limit all notifications without limit will be taken
  transaction_heuristic_limit: 10000
# This section configures the list of graphite remote triggers sources.
# See https://moira.readthedocs.io/en/latest/installation/configuration.html#graphite-remote-triggers-checker for further information
# Used to be `remote` and contain only one source before v2.10
graphite_remote:
  - # Unique cluster id (no other graphite_remote cluster should have the same one)
    # Use `default` for compatibility with old triggers without cluster_id
    # Should not be changed if there are any triggers using it
    cluster_id: default
    # Cluster name to be displayed in UI
    cluster_name: Graphite Remote
    # URL of Graphite HTTP API: graphite-web, carbonapi, etc.
    # Specify full URL including '/render'
    url: "http://graphite.example.com/render"
    # Auth username. Only Basic-auth supported
    user: graphite_admin
    # Auth password. Only Basic-auth supported
    password: verySecurePassword
    # Minimal period to perform triggers re-check. 
    # Note: Reducing of this value leads to increasing of CPU and memory usage values and extra load on Graphite HTTP API
    check_interval: 60s
    # Don't fetch metrics older than this value from remote storage
    metrics_ttl: 168h
    # Maximum timeout for HTTP-request made to Graphite HTTP API
    timeout: 60s
# This section configures the list of prometheus remote triggers sources.
# See https://moira.readthedocs.io/en/latest/installation/configuration.html#prometheus-remote-triggers-checker for further information
# Used to be `prometheus` and contain only one source before v2.10
prometheus_remote:
  - # Unique cluster id (no other prometheus_remote cluster should have the same one)
    # Use `default` for compatibility with old triggers without cluster_id
    # Should not be changed if there are any triggers using it
    cluster_id: default
    # Cluster name to be displayed in UI
    cluster_name: Prometheus Remote
    # URL of Prometheus HTTP API: Prometheus or VMSelect
    # Only domain name must be specified, no URL-path
    url: https://prometheus.example.com
    # Auth username. Only Basic-auth supported
    user: prometheus_admin
    # Auth password. Only Basic-auth supported
    password: verySecurePassword
    # Minimal period to perform triggers re-check. 
    # Note: Reducing of this value leads to increasing of CPU and memory usage values and extra load on Prometheus HTTP API
    check_interval: "60s"
    # Maximum timeout for HTTP-request made to Prometheus HTTP API
    timeout: "10s"
    # Number of times failed request should be retried
    retries: 3
    # Delay between retries
    retry_timeout: "3s"
    # Don't fetch metrics older than this value from remote storage
    metricsTTL: "168h"