config.yaml

---
default_exporters: [cloudevent]

backends:
  cloud_monitoring:
    project_id: ${STACKDRIVER_HOST_PROJECT_ID}
  cloud_monitoring_mql:
    project_id: ${STACKDRIVER_HOST_PROJECT_ID}
  cloud_service_monitoring:
    project_id: ${STACKDRIVER_HOST_PROJECT_ID}
  samples.custom.custom_backend.CustomBackend: {}
  datadog:
    api_host: ${DATADOG_API_HOST}
    api_key: ${DATADOG_API_KEY}
    app_key: ${DATADOG_APP_KEY}
  dynatrace:
    api_url: ${DYNATRACE_API_URL}
    api_token: ${DYNATRACE_API_TOKEN}
  elasticsearch:
    url: ${ELASTICSEARCH_URL}
  prometheus:
    url: ${PROMETHEUS_URL}
  splunk:
    host: ${SPLUNK_HOST}
    port: ${SPLUNK_PORT}
    user: ${SPLUNK_USER}
    password: ${SPLUNK_PWD}
  open_search:
    url: ${OPENSEARCH_URL}

exporters:
  cloudevent:
    service_url: "http://localhost:8081"
  cloud_monitoring:
    project_id: ${STACKDRIVER_HOST_PROJECT_ID}
  cloud_monitoring/test:
    project_id: ${PUBSUB_PROJECT_ID}
  samples.custom.custom_exporter.CustomMetricExporter: {}
  samples.custom.custom_exporter.CustomSLOExporter: {}
  datadog:
    api_key: ${DATADOG_API_KEY}
    app_key: ${DATADOG_APP_KEY}
  dynatrace:
    api_url: ${DYNATRACE_API_URL}
    api_token: ${DYNATRACE_API_TOKEN}
    metric_timeseries_id: custom:slo.error_budget_burn_rate
  dynatrace/test:
    api_url: ${DYNATRACE_API_URL}
    api_token: ${DYNATRACE_API_TOKEN}
  prometheus:
    url: ${PROMETHEUS_PUSHGATEWAY_URL}
  pubsub:
    project_id: ${PUBSUB_PROJECT_ID}
    topic_name: ${PUBSUB_TOPIC_NAME}
  prometheus_self: { }

error_budget_policies:
  default:
    steps:
    - name: 1 hour
      burn_rate_threshold: 9
      alert: true
      message_alert: Page to defend the SLO
      message_ok: Last hour on track
      window: 3600
    - name: 12 hours
      burn_rate_threshold: 3
      alert: true
      message_alert: Page to defend the SLO
      message_ok: Last 12 hours on track
      window: 43200
    - name: 7 days
      burn_rate_threshold: 1.5
      alert: false
      message_alert: Dev team dedicates 25% of engineers to the reliability backlog
      message_ok: Last week on track
      window: 604800
    - name: 28 days
      burn_rate_threshold: 1
      alert: false
      message_alert: Freeze release, unless related to reliability or security
      message_ok: Unfreeze release, per the agreed roll-out policy
      window: 2419200
  cloud_service_monitoring:
    steps:
    - name: 24 hours
      burn_rate_threshold: 4
      alert: true
      message_alert: Page to defend the SLO
      message_ok: Last 24 hours on track
      window: 86400
    - name: 48 hours
      burn_rate_threshold: 2
      alert: true
      message_alert: Page to defend the SLO
      message_ok: Last 48 hours on track
      window: 172800