إصدار Canary السلس باستخدام APISIX Ingress Controller مع Flagger

helm repo add apisix https://charts.apiseven.com
kubectl create ns apisix


helm upgrade -i apisix apisix/apisix --version=0.11.3 \
--namespace apisix \
--set apisix.podAnnotations."prometheus\.io/scrape"=true \
--set apisix.podAnnotations."prometheus\.io/port"=9091 \
--set apisix.podAnnotations."prometheus\.io/path"=/apisix/prometheus/metrics \
--set pluginAttrs.prometheus.export_addr.ip=0.0.0.0 \
--set pluginAttrs.prometheus.export_addr.port=9091 \
--set pluginAttrs.prometheus.export_uri=/apisix/prometheus/metrics \
--set pluginAttrs.prometheus.metric_prefix=apisix_ \
--set ingress-controller.enabled=true \
--set ingress-controller.config.apisix.serviceNamespace=apisix

helm repo add flagger https://flagger.app


helm upgrade -i flagger flagger/flagger \
--namespace apisix \
--set prometheus.install=true \
--set meshProvider=apisix

apiVersion: apisix.apache.org/v2
kind: ApisixRoute
metadata:
  name: podinfo
  namespace: test
spec:
  http:
    - backends:
        - serviceName: podinfo
          servicePort: 80
      match:
        hosts:
          - app.example.com
        methods:
          - GET
        paths:
          - /*
      name: method
      plugins:
        - name: prometheus
          enable: true
          config:
            disable: false
            prefer_name: true

apiVersion: flagger.app/v1beta1
kind: Canary
metadata:
  name: podinfo
  namespace: test
spec:
  provider: apisix
  targetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: podinfo
  # Refer apisix route
  routeRef:
    apiVersion: apisix.apache.org/v2
    kind: ApisixRoute
    name: podinfo
  progressDeadlineSeconds: 60
  service:
    port: 80
    targetPort: 9898
  analysis:
    interval: 10s
    # maximum number of failures for roll back
    threshold: 10
    # maximum percentage of traffic to the canary version
    # (0-100)
    maxWeight: 50
    # the step size of the canary analysis
    # (0-100)
    stepWeight: 10
    # use Prometheus to check the traffic information of APISIX
    metrics:
      - name: request-success-rate
        # the minimum success rate (none 5xx responses)
        # (0-100)
        thresholdRange:
          min: 99
        interval: 1m
      - name: request-duration
        # P99 is the largest request delay(ms)
        thresholdRange:
          max: 500
        interval: 30s
    webhooks:
        # automated traffic for canary analysis, modified based on the actual scenario
      - name: load-test
        url: http://flagger-loadtester.test/
        timeout: 5s
        type: rollout
        metadata:
          cmd: |-
            hey -z 1m -q 10 -c 2 -h2 -host app.example.com http://apisix-gateway.apisix/api/info

kubectl -n test describe canary/podinfo

Status:
  Canary Weight:  0
  Conditions:
    Message:               Canary analysis completed successfully, promotion finished.
    Reason:                Succeeded
    Status:                True
    Type:                  Promoted
  Failed Checks:           1
  Iterations:              0
  Phase:                   Succeeded

Events:
  Type     Reason  Age                    From     Message
  ----     ------  ----                   ----     -------
  Warning  Synced  2m59s                  flagger  podinfo-primary.test not ready: waiting for rollout to finish: observed deployment generation less than desired generation
  Warning  Synced  2m50s                  flagger  podinfo-primary.test not ready: waiting for rollout to finish: 0 of 1 (readyThreshold 100%) updated replicas are available
  Normal   Synced  2m40s (x3 over 2m59s)  flagger  all the metrics providers are available!
  Normal   Synced  2m39s                  flagger  Initialization done! podinfo.test
  Normal   Synced  2m20s                  flagger  New revision detected! Scaling up podinfo.test
  Warning  Synced  2m (x2 over 2m10s)     flagger  canary deployment podinfo.test not ready: waiting for rollout to finish: 0 of 1 (readyThreshold 100%) updated replicas are available
  Normal   Synced  110s                   flagger  Starting canary analysis for podinfo.test
  Normal   Synced  109s                   flagger  Advance podinfo.test canary weight 10
  Warning  Synced  100s                   flagger  Halt advancement no values found for apisix metric request-success-rate probably podinfo.test is not receiving traffic: running query failed: no values found
  Normal   Synced  90s                    flagger  Advance podinfo.test canary weight 20
  Normal   Synced  80s                    flagger  Advance podinfo.test canary weight 30
  Normal   Synced  69s                    flagger  Advance podinfo.test canary weight 40
  Normal   Synced  59s                    flagger  Advance podinfo.test canary weight 50
  Warning  Synced  30s (x2 over 40s)      flagger  podinfo-primary.test not ready: waiting for rollout to finish: 1 old replicas are pending termination
  Normal   Synced  9s (x3 over 50s)       flagger  (combined from similar events): Promotion completed! Scaling down podinfo.test

spec:
  http:
    - backends:
        - serviceName: podinfo-primary
          servicePort: 80
          # تم تعديله تلقائيًا بواسطة Flagger
          weight: 80
        - serviceName: podinfo-canary
          servicePort: 80
          # تم تعديله تلقائيًا بواسطة Flagger
          weight: 20

watch kubectl get canaries --all-namespaces

NAMESPACE   NAME      STATUS      WEIGHT   LASTTRANSITIONTIME
test        podinfo-2   Progressing   10       2022-11-23T05:00:54Z
test        podinfo     Succeeded     0        2022-11-23T06:00:54Z

kubectl -n apisix logs deploy/flagger -f | jq .msg

"New revision detected! Scaling up podinfo.test"
"canary deployment podinfo.test not ready: waiting for rollout to finish: 0 of 1 (readyThreshold 100%) updated replicas are available"
"Starting canary analysis for podinfo.test"
"Advance podinfo.test canary weight 10"
"Halt podinfo.test advancement success rate 0.00% < 99%"
"Halt podinfo.test advancement success rate 26.76% < 99%"
"Halt podinfo.test advancement success rate 34.19% < 99%"
"Halt podinfo.test advancement success rate 37.32% < 99%"
"Halt podinfo.test advancement success rate 39.04% < 99%"
"Halt podinfo.test advancement success rate 40.13% < 99%"
"Halt podinfo.test advancement success rate 48.28% < 99%"
"Halt podinfo.test advancement success rate 50.35% < 99%"
"Halt podinfo.test advancement success rate 56.92% < 99%"
"Halt podinfo.test advancement success rate 67.70% < 99%"
"Rolling back podinfo.test failed checks threshold reached 10"
"Canary failed! Scaling down podinfo.test"

apiVersion: flagger.app/v1beta1
kind: MetricTemplate
metadata:
  name: not-found-percentage
  namespace: test
spec:
  provider:
    type: prometheus
    address: http://flagger-prometheus.apisix:9090
  query: |
    sum(
      rate(
        apisix_http_status{
          route=~"{{ namespace }}_{{ route }}-{{ target }}-canary_.+",
          code!~"4.."
        }[{{ interval }}]
      )
    )
    /
    sum(
      rate(
        apisix_http_status{
          route=~"{{ namespace }}_{{ route }}-{{ target }}-canary_.+"
        }[{{ interval }}]
      )
    ) * 100
# قم بتعديل التحليل في الإصدار الكناري وإضافة قالب المؤشر الذي تم إنشاؤه أعلاه.
  analysis:
    metrics:
      - name: "404s percentage"
        templateRef:
          name: not-found-percentage
        thresholdRange:
          max: 5
        interval: 1m