service-definition.yaml

System:
  Name:                 OurService
  ID:                   id001
  Contact:
    Page:               OurPagerduty
    Chat:               "#slack-channel"
  SLA:
    Availability:       99%
    Latency:
      P90:              200ms
      P99:              500ms
    Error Rate:         0.1%
    Throughput:         1000rps
    Saturation:         80% Utilization
  MonitorTags:
    - “generator:collie”
    - “maturity:development”
  Components:
    - Load Balancer:
      Type:             aws.elb
      Tags:             “loadbalancername:awselb-001,env:prod”
      Monitors:
        - Type:         requests-low
          Threshold:    1000rps
          AlertWindow:  30m
          Page:         true
    - Web Server:
      Type:             nginx
      Tags:             “app:id001,env:prod,role:web”
      Monitors:
        - Type:         5xx-error-rate  
          Threshold:    0.1%
          AlertWindow:  15m
    - Application:
      Type:             custom
      Tags:             “app:id001,env:prod,role:app”
      Monitors:
        - Type:         threshold
          Metric:       ourapp.latency.p90
          Threshold:    200ms
          AlertWindow:  10m
        - Type:         threshold
          Metric:       ourapp.latency.p99
          Threshold:    500ms
          AlertWindow:  10m
        - Storage:
      Type:             postgresql
      Tags:             “app:id001,env:prod,role:db”
      Monitors:
        - Type:         can-connect
          AlertWindow:  5m