apiVersion: flagger.app/v1beta1
kind: Canary
metadata:
  name: podinfo
  namespace: test
spec:
  # service mesh provider (optional)
  # can be: kubernetes, istio, linkerd, appmesh, nginx, skipper, contour, gloo, supergloo, traefik, osm
  # for SMI TrafficSplit can be: smi:v1alpha1, smi:v1alpha2, smi:v1alpha3
  provider: istio
  # deployment reference
  targetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: podinfo
  # the maximum time in seconds for the canary deployment
  # to make progress before it is rollback (default 600s)
  progressDeadlineSeconds: 60
  # HPA reference (optional)
  autoscalerRef:
    apiVersion: autoscaling/v2beta2
    kind: HorizontalPodAutoscaler
    name: podinfo
  service:
    # service name (defaults to targetRef.name)
    name: podinfo
    # ClusterIP port number
    port: 9898
    # container port name or number (optional)
    targetPort: 9898
    # port name can be http or grpc (default http)
    portName: http
    # add all the other container ports
    # to the ClusterIP services (default false)
    portDiscovery: true
    # HTTP match conditions (optional)
    match:
      - uri:
          prefix: /
    # HTTP rewrite (optional)
    rewrite:
      uri: /
    # request timeout (optional)
    timeout: 5s
  # promote the canary without analysing it (default false)
  skipAnalysis: false
  # define the canary analysis timing and KPIs
  analysis:
    # schedule interval (default 60s)
    interval: 1m
    # max number of failed metric checks before rollback
    threshold: 10
    # max traffic percentage routed to canary
    # percentage (0-100)
    maxWeight: 50
    # canary increment step
    # percentage (0-100)
    stepWeight: 5
    # validation (optional)
    metrics:
    - name: request-success-rate
      # builtin Prometheus check
      # minimum req success rate (non 5xx responses)
      # percentage (0-100)
      thresholdRange:
        min: 99
      interval: 1m
    - name: request-duration
      # builtin Prometheus check
      # maximum req duration P99
      # milliseconds
      thresholdRange:
        max: 500
      interval: 30s
    - name: "database connections"
      # custom metric check
      templateRef:
        name: db-connections
      thresholdRange:
        min: 2
        max: 100
      interval: 1m
    # testing (optional)
    webhooks:
      - name: "conformance test"
        type: pre-rollout
        url: https://flagger-helmtester.test/
        timeout: 5m
        metadata:
          type: "helmv3"
          cmd: "test run podinfo -n test"
      - name: "load test"
        type: rollout
        url: https://flagger-loadtester.test/
        metadata:
          cmd: "hey -z 1m -q 10 -c 2 https://podinfo.test:9898/"
    # alerting (optional)
    alerts:
      - name: "dev team Slack"
        severity: error
        providerRef:
          name: dev-slack
          namespace: flagger
      - name: "qa team Discord"
        severity: warn
        providerRef:
          name: qa-discord
      - name: "on-call MS Teams"
        severity: info
        providerRef:
          name: on-call-msteams