Argo RolloutsとPrometheus：自動化されたプログレッシブデリバリーと分析テンプレート

# app.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: canary-app
  labels:
    app: canary-app
spec:
  replicas: 3
  selector:
    matchLabels:
      app: canary-app
  template:
    metadata:
      labels:
        app: canary-app
    spec:
      containers:
      - name: nginx
        image: nginx:1.23.3 # Initial stable version
        ports:
        - containerPort: 80
        env:
        - name: ERROR_RATE
          value: "0" # Simulate no errors initially
---
apiVersion: v1
kind: Service
metadata:
  name: canary-app-stable
spec:
  selector:
    app: canary-app
  ports:
  - protocol: TCP
    port: 80
    targetPort: 80
---
apiVersion: v1
kind: Service
metadata:
  name: canary-app-canary
spec:
  selector:
    app: canary-app
  ports:
  - protocol: TCP
    port: 80
    targetPort: 80

# gateway-api.yaml
apiVersion: gateway.networking.k8s.io/v1beta1
kind: Gateway
metadata:
  name: my-gateway
spec:
  gatewayClassName: envoy # Replace with your GatewayClass name
  listeners:
  - name: http
    protocol: HTTP
    port: 80
---
apiVersion: gateway.networking.k8s.io/v1beta1
kind: HTTPRoute
metadata:
  name: canary-app-route
spec:
  parentRefs:
  - name: my-gateway
  hostnames:
  - "canary.example.com" # Replace with your domain
  rules:
  - backendRefs:
    - name: canary-app-stable
      port: 80
      weight: 100

# rollout.yaml
apiVersion: argoproj.io/v1alpha1
kind: Rollout
metadata:
  name: canary-app
spec:
  replicas: 3
  selector:
    matchLabels:
      app: canary-app
  template:
    metadata:
      labels:
        app: canary-app
    spec:
      containers:
      - name: nginx
        image: nginx:1.23.3 # Initial stable version
        ports:
        - containerPort: 80
        env:
        - name: ERROR_RATE
          value: "0"
  strategy:
    canary:
      canaryService: canary-app-canary
      stableService: canary-app-stable
      trafficRouting:
        gatewayAPI:
          httpRoute: canary-app-route
          # The controllerName is crucial for Argo Rollouts to find the correct Gateway API controller.
          # This typically matches the 'controllerName' field in your GatewayClass.
          # For Envoy Gateway, it might be "gateway.envoyproxy.io/gatewayclass-controller" or similar.
          # Consult your GatewayClass definition.
          controllerName: "gateway.envoyproxy.io/gatewayclass-controller" # Adjust as per your Gateway API setup
      steps:
      - setWeight: 10 # Send 10% traffic to canary
      - pause: {} # Manual pause for initial observation
      - analysis:
          templates:
          - templateName: canary-app-analysis
          args:
          - name: service
            value: "canary-app-canary" # Target the canary service for analysis
      - setWeight: 50 # Send 50% traffic to canary
      - pause: { duration: 60s } # Automatic pause for 60 seconds
      - analysis:
          templates:
          - templateName: canary-app-analysis
          args:
          - name: service
            value: "canary-app-canary"
      - setWeight: 100 # Send 100% traffic to canary
      - pause: { duration: 60s }
      - analysis:
          templates:
          - templateName: canary-app-analysis
          args:
          - name: service
            value: "canary-app-canary"
      - promote: {} # Promote canary to stable
      - pause: { duration: 30s } # Final pause before full promotion

# analysis-template.yaml
apiVersion: argoproj.io/v1alpha1
kind: AnalysisTemplate
metadata:
  name: canary-app-analysis
spec:
  args:
  - name: service
  metrics:
  - name: error-rate
    interval: 30s # How often to run the query
    failureLimit: 1 # Fail if this many checks fail
    successCondition: "result[0] < 0.01" # Error rate < 1%
    # Prometheus query for 5xx errors over the last 5 minutes
    # We use `sum(rate(...))` to get the rate of errors and total requests.
    # The `service` label is passed as an argument to target the correct service.
    # `{{args.service}}` is how arguments are referenced in AnalysisTemplates.
    # This query calculates the percentage of 5xx errors.
    prometheus:
      address: http://prometheus-kube-prometheus-stack.monitoring:9090 # Adjust Prometheus service address
      query: |
        sum(rate(http_requests_total{service="{{args.service}}", status_code=~"5.."}[5m]))
        /
        sum(rate(http_requests_total{service="{{args.service}}", status_code!~"4.."}[5m]))
  - name: p99-latency
    interval: 30s
    failureLimit: 1
    successCondition: "result[0] < 0.5" # p99 latency < 500ms
    # Prometheus query for p99 latency over the last 5 minutes
    # `histogram_quantile` is used for percentile calculations from histograms.
    prometheus:
      address: http://prometheus-kube-prometheus-stack.monitoring:9090 # Adjust Prometheus service address
      query: |
        histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket{service="{{args.service}}"}[5m])) by (le))

# Get the IP/hostname of your Gateway
GATEWAY_IP=$(kubectl get svc -n envoy-gateway-system envoy-gateway -o jsonpath='{.status.loadBalancer.ingress[0].ip}') # Adjust namespace/service name
while true; do curl -s -H "Host: canary.example.com" http://$GATEWAY_IP/ > /dev/null; sleep 0.1; done

# Dockerfile for error-injecting NGINX
FROM nginx:1.23.3
COPY default.conf /etc/nginx/conf.d/default.conf
# default.conf will check for ERROR_RATE env var and return 500 for a percentage of requests

server {
    listen 80;
    location / {
        set $error_rate $env_ERROR_RATE;
        if ($error_rate = "") {
            set $error_rate "0";
        }

        # Generate a random number between 0 and 99
        set $random_num "";
        perl_set $random_num 'int(rand(100))';

        # If random_num is less than ERROR_RATE, return 500
        if ($random_num < $error_rate) {
            return 500 "Internal Server Error\n";
        }

        return 200 "Hello from NGINX!\n";
    }
}

# rollout-update.yaml (partial update)
apiVersion: argoproj.io/v1alpha1
kind: Rollout
metadata:
  name: canary-app
spec:
  template:
    spec:
      containers:
      - name: nginx
        image: myregistry/nginx-error:1.24.0 # New image with potential errors
        env:
        - name: ERROR_RATE
          value: "20" # Introduce 20% errors

Name:            canary-app
Namespace:       default
Status:          Degraded
Strategy:        Canary
  Step:          1/8
  Message:       Rollout is in Degraded state due to failed AnalysisRun
  SetWeight:     10%
  ActualWeight:  10%
  ...
  AnalysisRun:   canary-app-canary-app-analysis-xxxx
    Status:      Failed
    Message:     Metric 'error-rate' success condition was not met

# slack-secret.yaml
apiVersion: v1
kind: Secret
metadata:
  name: argo-rollouts-slack-webhook
stringData:
  url: "https://example.com/api/slack-webhook-placeholder" # Replace with your Slack webhook URL

# Example of Argo CD Notifications ConfigMap entry (if using Argo CD)
apiVersion: v1
kind: ConfigMap
metadata:
  name: argocd-notifications-cm
  namespace: argocd # Or your Argo CD namespace
data:
  service.slack: |
    token: $argo-rollouts-slack-webhook:url # Reference the secret
  template.rollout-status: |
    message: |
      Rollout {{.app.metadata.name}} status: {{.rollout.status.phase}}
      {{if .rollout.status.message}}Message: {{.rollout.status.message}}{{end}}
      {{if .rollout.status.canary.currentStepIndex}}Current Step: {{.rollout.status.canary.currentStepIndex}}/{{len .rollout.spec.strategy.canary.steps}}{{end}}
      {{if .rollout.status.canary.trafficRouting.gatewayAPI.currentWeight}}Traffic Weight: {{.rollout.status.canary.trafficRouting.gatewayAPI.currentWeight}}%{{end}}
    slack:
      attachments:
      - title: Rollout Details
        title_link: {{.context.argocdUrl}}/applications/{{.app.metadata.name}}
        color: "{{if eq .rollout.status.phase "Succeeded"}}#00FF00{{else if eq .rollout.status.phase "Failed"}}#FF0000{{else}}#FFFF00{{end}}"
        fields:
        - title: Application
          value: {{.app.metadata.name}}
          short: true
        - title: Namespace
          value: {{.app.metadata.namespace}}
          short: true
        - title: Status
          value: {{.rollout.status.phase}}
          short: true
        - title: Revision
          value: {{.rollout.status.currentRevision}}
          short: true
  trigger.on-rollout-status-change: |
    - when: rollout.status.phase != rollout.status.previousPhase
      send: [rollout-status]

# rollout.yaml (with notification annotations)
apiVersion: argoproj.io/v1alpha1
kind: Rollout
metadata:
  name: canary-app
  annotations:
    notifications.argoproj.io/subscribe.on-rollout-status-change.slack: "true"
    # Or specify a channel: notifications.argoproj.io/subscribe.on-rollout-status-change.slack: "#my-channel"
spec:
  # ... rest of your rollout spec

      - analysis:
          templates:
          - templateName: canary-app-error-rate-analysis
          - templateName: canary-app-p99-latency-analysis
          args:
          - name: service
            value: "canary-app-canary"