slo_example.yml

slo_example.yml

slos:
  - name: myteam-a.service-a
    objectives:
      availability: 99
      latency:
      - le: 5.0 # 95% < 5s
        target: 95

      - le: 10.0 # 97% < 10s
        target: 97
    labels:
      slack_channel: '_team_a'
      platform: myplatform
    annotations:
      message: Service A Error Budget consumption
      link: https://grafana.myservice.com/URL

    trafficRateRecord:
      expr: |
        sum (rate(http_requests_total{job="service-a"}[$window]))

    errorRateRecord:
      alertMethod: multi-window
      expr: |
        sum (rate(http_requests_total{job="service-a", status="5xx"}[$window])) /
        sum (rate(http_requests_total{job="service-a"}[$window]))

    latencyRecord:
      alertMethod: multi-window
      expr: |
        sum (rate(http_request_duration_seconds_bucket{job="service-a", le="$le"}[$window])) /
        sum (rate(http_requests_total{job="service-a"}[$window]))


  - name: myteam-b.service-b
    objectives:
      availability: 99.9
      latency:
      - le: 0.05 # 90% < 50ms
        target: 90

      - le: 0.10  # 95% < 100ms
        target: 97

    labels:
      slack_channel: '_team_b'
      platform: myplatform
    annotations:
      message: Service B Error Budget consumption
      link:
    errorRateRecord:
      alertMethod: multi-window
      expr: |
        sum (rate(http_requests_total{job="service-b", status="5xx"}[$window])) /
        sum (rate(http_requests_total{job="service-b"}[$window]))

    latencyRecord:
      alertMethod: multi-window
      expr: |
        sum (rate(http_request_duration_seconds_bucket{job="service-b", le="$le"}[$window])) /
        sum (rate(http_requests_total{job="service-b"}[$window]))