[Application Signals] Improve metric schema for EKS, Native K8s, EC2

.github/workflows/application-signals-java-e2e-ec2-asg-test.yml

@@ -0,0 +1,168 @@
+## Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+## SPDX-License-Identifier: Apache-2.0
+
+# This is a reusable workflow for running the E2E test for App Signals.
+# It is meant to be called from another workflow.
+# Read more about reusable workflows: https://docs.github.com/en/actions/using-workflows/reusing-workflows#overview
+name: App Signals Enablement E2E Testing - EC2 ASG Use Case
+on:
+  workflow_call:
+
+permissions:
+  id-token: write
+  contents: read
+
+env:
+  # The presence of this env var is required for use by terraform and AWS CLI commands
+  # It is not redundant
+  AWS_DEFAULT_REGION: us-east-1
+  APP_SIGNALS_E2E_TEST_ACCOUNT_ID: ${{ secrets.APP_SIGNALS_E2E_TEST_ACCOUNT_ID }}
+  SAMPLE_APP_FRONTEND_SERVICE_JAR: "s3://aws-appsignals-sample-app-prod-us-east-1/main-service.jar"
+  SAMPLE_APP_REMOTE_SERVICE_JAR: "s3://aws-appsignals-sample-app-prod-us-east-1/remote-service.jar"
+  GET_ADOT_JAR_COMMAND: "aws s3 cp s3://adot-main-build-staging-jar/aws-opentelemetry-agent.jar ./adot.jar"
+  GET_CW_AGENT_RPM_COMMAND: "aws s3 cp s3://${{ secrets.S3_INTEGRATION_BUCKET }}/integration-test/binary/${{ github.sha }}/amazon_linux/amd64/latest/amazon-cloudwatch-agent.rpm ./cw-agent.rpm"
+  METRIC_NAMESPACE: ApplicationSignals
+  LOG_GROUP_NAME: /aws/application-signals/data
+
+jobs:
+  e2e-ec2-single-asg-test:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Get testing resources from aws-application-signals-test-framework
+        uses: actions/checkout@v4
+        with:
+          repository: aws-observability/aws-application-signals-test-framework
+          ref: add-ec2-platform-support
+
+      - name: Generate testing id
+        run: echo TESTING_ID="java-asg-${{ github.run_id }}-${{ github.run_number }}" >> $GITHUB_ENV
+
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          role-to-assume: arn:aws:iam::${{ env.APP_SIGNALS_E2E_TEST_ACCOUNT_ID }}:role/${{ secrets.APP_SIGNALS_E2E_TEST_ROLE_NAME }}
+          aws-region: ${{ env.AWS_DEFAULT_REGION }}
+
+      - name: Set up terraform
+        uses: hashicorp/setup-terraform@v3
+        with:
+          terraform_wrapper: false
+
+      - name: Deploy sample app via terraform
+        working-directory: terraform/ec2/asg
+        run: |
+          terraform init
+          terraform validate
+          terraform apply -auto-approve \
+            -var="aws_region=${{ env.AWS_DEFAULT_REGION }}" \
+            -var="test_id=${{ env.TESTING_ID }}" \
+            -var="sample_app_jar=${{ env.SAMPLE_APP_FRONTEND_SERVICE_JAR }}" \
+            -var="sample_remote_app_jar=${{ env.SAMPLE_APP_REMOTE_SERVICE_JAR }}" \
+            -var="get_cw_agent_rpm_command=${{ env.GET_CW_AGENT_RPM_COMMAND }}" \
+            -var="get_adot_jar_command=${{ env.GET_ADOT_JAR_COMMAND }}"
+
+      - name: Get sample app and EC2 instance information
+        working-directory: terraform/ec2/asg
+        run: |
+          main_service_instance_id=$(aws autoscaling describe-auto-scaling-groups --auto-scaling-group-names ec2-single-asg-${{ env.TESTING_ID }} --region ${{ env.AWS_DEFAULT_REGION }} --query "AutoScalingGroups[].Instances[0].InstanceId" --output text)
+          main_service_public_ip=$(aws ec2 describe-instances --instance-ids $main_service_instance_id --region ${{ env.AWS_DEFAULT_REGION }} --query "Reservations[].Instances[].PublicIpAddress" --output text)
+          main_service_private_dns_name=$(aws ec2 describe-instances --instance-ids $main_service_instance_id --region ${{ env.AWS_DEFAULT_REGION }} --query "Reservations[].Instances[].PrivateDnsName" --output text)
+          echo "INSTANCE_ID=$main_service_instance_id" >> $GITHUB_ENV
+          echo "MAIN_SERVICE_ENDPOINT=$main_service_public_ip:8080" >> $GITHUB_ENV
+          echo "PRIVATE_DNS_NAME=$main_service_private_dns_name" >> $GITHUB_ENV
+          echo "EC2_INSTANCE_AMI=$(terraform output ec2_instance_ami)" >> $GITHUB_ENV
+          echo "REMOTE_SERVICE_IP=$(terraform output sample_app_remote_service_public_ip)" >> $GITHUB_ENV
+
+      - name: Wait for app endpoint to come online
+        id: endpoint-check
+        run: |
+          attempt_counter=0
+          max_attempts=30
+          until $(curl --output /dev/null --silent --head --fail http://${{ env.MAIN_SERVICE_ENDPOINT }}); do
+            if [ ${attempt_counter} -eq ${max_attempts} ];then
+              echo "Max attempts reached"
+              exit 1
+            fi
+
+            printf '.'
+            attempt_counter=$(($attempt_counter+1))
+            sleep 10
+          done
+
+      # This steps increases the speed of the validation by creating the telemetry data in advance
+      - name: Call all test APIs
+        continue-on-error: true
+        run: |        
+          curl -S -s "http://${{ env.MAIN_SERVICE_ENDPOINT }}/outgoing-http-call"
+          curl -S -s "http://${{ env.MAIN_SERVICE_ENDPOINT }}/aws-sdk-call?ip=${{ env.REMOTE_SERVICE_IP }}&testingId=${{ env.TESTING_ID }}"
+          curl -S -s "http://${{ env.MAIN_SERVICE_ENDPOINT }}/remote-service?ip=${{ env.REMOTE_SERVICE_IP }}&testingId=${{ env.TESTING_ID }}"
+          curl -S -s "http://${{ env.MAIN_SERVICE_ENDPOINT }}/client-call"
+
+      # Validation for pulse telemetry data
+      - name: Validate generated EMF logs
+        id: log-validation
+        run: ./gradlew validator:run --args='-c java/ec2/asg/log-validation.yml
+          --testing-id ${{ env.TESTING_ID }}
+          --endpoint http://${{ env.MAIN_SERVICE_ENDPOINT }}
+          --remote-service-deployment-name ${{ env.REMOTE_SERVICE_IP }}:8080
+          --region ${{ env.AWS_DEFAULT_REGION }}
+          --account-id ${{ env.APP_SIGNALS_E2E_TEST_ACCOUNT_ID }}
+          --metric-namespace ${{ env.METRIC_NAMESPACE }}
+          --log-group ${{ env.LOG_GROUP_NAME }}
+          --service-name sample-application-${{ env.TESTING_ID }}
+          --remote-service-name sample-remote-application-${{ env.TESTING_ID }}
+          --instance-ami ${{ env.EC2_INSTANCE_AMI }}
+          --platform-info ec2-single-asg-${{ env.TESTING_ID }}
+          --instance-id ${{ env.INSTANCE_ID }}
+          --private-dns-name ${{ env.PRIVATE_DNS_NAME }}
+          --query-string ip=${{ env.REMOTE_SERVICE_IP }}&testingId=${{ env.TESTING_ID }}
+          --rollup'
+
+      - name: Validate generated metrics
+        id: metric-validation
+        if: (success() || steps.log-validation-1.outcome == 'failure') && !cancelled()
+        run: ./gradlew validator:run --args='-c java/ec2/asg/metric-validation.yml
+          --testing-id ${{ env.TESTING_ID }}
+          --endpoint http://${{ env.MAIN_SERVICE_ENDPOINT }}
+          --remote-service-deployment-name ${{ env.REMOTE_SERVICE_IP }}:8080
+          --region ${{ env.AWS_DEFAULT_REGION }}
+          --account-id ${{ env.APP_SIGNALS_E2E_TEST_ACCOUNT_ID }}
+          --metric-namespace ${{ env.METRIC_NAMESPACE }}
+          --log-group ${{ env.LOG_GROUP_NAME }}
+          --service-name sample-application-${{ env.TESTING_ID }}
+          --remote-service-name sample-remote-application-${{ env.TESTING_ID }}
+          --instance-ami ${{ env.EC2_INSTANCE_AMI }}
+          --platform-info ec2-single-asg-${{ env.TESTING_ID }}
+          --instance-id ${{ env.INSTANCE_ID }}
+          --private-dns-name ${{ env.PRIVATE_DNS_NAME }}
+          --query-string ip=${{ env.REMOTE_SERVICE_IP }}&testingId=${{ env.TESTING_ID }}
+          --rollup'
+
+      - name: Validate generated traces
+        id: trace-validation
+        if: (success() || steps.log-validation-1.outcome == 'failure' || steps.metric-validation-1.outcome == 'failure') && !cancelled()
+        run: ./gradlew validator:run --args='-c java/ec2/asg/trace-validation.yml
+          --testing-id ${{ env.TESTING_ID }}
+          --endpoint http://${{ env.MAIN_SERVICE_ENDPOINT }}
+          --remote-service-deployment-name ${{ env.REMOTE_SERVICE_IP }}:8080
+          --region ${{ env.AWS_DEFAULT_REGION }}
+          --account-id ${{ env.APP_SIGNALS_E2E_TEST_ACCOUNT_ID }}
+          --metric-namespace ${{ env.METRIC_NAMESPACE }}
+          --log-group ${{ env.LOG_GROUP_NAME }}
+          --service-name sample-application-${{ env.TESTING_ID }}
+          --remote-service-name sample-remote-application-${{ env.TESTING_ID }}
+          --instance-ami ${{ env.EC2_INSTANCE_AMI }}
+          --platform-info ec2-single-asg-${{ env.TESTING_ID }}
+          --instance-id ${{ env.INSTANCE_ID }}
+          --private-dns-name ${{ env.PRIVATE_DNS_NAME }}
+          --query-string ip=${{ env.REMOTE_SERVICE_IP }}&testingId=${{ env.TESTING_ID }}
+          --rollup'
+
+      # Clean up Procedures
+      - name: Terraform destroy
+        if: always()
+        continue-on-error: true
+        working-directory: terraform/ec2/asg
+        run: |
+          terraform destroy -auto-approve \
+            -var="test_id=${{ env.TESTING_ID }}"

.github/workflows/appsignals-e2e-ec2-test.yml → .github/workflows/application-signals-java-e2e-ec2-test.yml

@@ -18,10 +18,10 @@ env:
   APP_SIGNALS_E2E_TEST_ACCOUNT_ID: ${{ secrets.APP_SIGNALS_E2E_TEST_ACCOUNT_ID }}
   SAMPLE_APP_FRONTEND_SERVICE_JAR: "s3://aws-appsignals-sample-app-prod-us-east-1/main-service.jar"
   SAMPLE_APP_REMOTE_SERVICE_JAR: "s3://aws-appsignals-sample-app-prod-us-east-1/remote-service.jar"
-  GET_ADOT_JAR_COMMAND: "wget -O adot.jar https://github.com/aws-observability/aws-otel-java-instrumentation/releases/latest/download/aws-opentelemetry-agent.jar"
+  GET_ADOT_JAR_COMMAND: "aws s3 cp s3://adot-main-build-staging-jar/aws-opentelemetry-agent.jar ./adot.jar"
   GET_CW_AGENT_RPM_COMMAND: "aws s3 cp s3://${{ secrets.S3_INTEGRATION_BUCKET }}/integration-test/binary/${{ github.sha }}/amazon_linux/amd64/latest/amazon-cloudwatch-agent.rpm ./cw-agent.rpm"
-  METRIC_NAMESPACE: AppSignals
-  LOG_GROUP_NAME: /aws/appsignals/generic
+  METRIC_NAMESPACE: ApplicationSignals
+  LOG_GROUP_NAME: /aws/application-signals/data
 
 jobs:
   e2e-ec2-test:
@@ -31,7 +31,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           repository: aws-observability/aws-application-signals-test-framework
-          ref: main
+          ref: ga-release
 
       - name: Generate testing id
         run: echo TESTING_ID="${{ github.run_id }}-${{ github.run_number }}" >> $GITHUB_ENV
@@ -70,6 +70,7 @@ jobs:
         run: |
           echo "MAIN_SERVICE_ENDPOINT=$(terraform output sample_app_main_service_public_dns):8080" >> $GITHUB_ENV
           echo "REMOTE_SERVICE_IP=$(terraform output sample_app_remote_service_public_ip)" >> $GITHUB_ENV
+          echo "MAIN_SERVICE_INSTANCE_ID=$(terraform output main_service_instance_id)" >> $GITHUB_ENV
 
       - name: Wait for app endpoint to come online
         id: endpoint-check
@@ -91,10 +92,10 @@ jobs:
       - name: Call all test APIs
         continue-on-error: true
         run: |
-          curl -S -s -o /dev/null http://${{ env.MAIN_SERVICE_ENDPOINT }}/outgoing-http-call/; echo
-          curl -S -s -o /dev/null http://${{ env.MAIN_SERVICE_ENDPOINT }}/aws-sdk-call/; echo
-          curl -S -s -o /dev/null http://${{ env.MAIN_SERVICE_ENDPOINT }}/remote-service?ip=${{ env.REMOTE_SERVICE_IP }}/; echo
-          curl -S -s -o /dev/null http://${{ env.MAIN_SERVICE_ENDPOINT }}/client-call/; echo
+          curl -S -s "http://${{ env.MAIN_SERVICE_ENDPOINT }}/outgoing-http-call"
+          curl -S -s "http://${{ env.MAIN_SERVICE_ENDPOINT }}/aws-sdk-call?ip=${{ env.REMOTE_SERVICE_IP }}&testingId=${{ env.TESTING_ID }}"
+          curl -S -s "http://${{ env.MAIN_SERVICE_ENDPOINT }}/remote-service?ip=${{ env.REMOTE_SERVICE_IP }}&testingId=${{ env.TESTING_ID }}"
+          curl -S -s "http://${{ env.MAIN_SERVICE_ENDPOINT }}/client-call"
 
       - name: Build Gradle
         working-directory: ${{ env.TEST_RESOURCES_FOLDER }}
@@ -113,8 +114,9 @@ jobs:
           --log-group ${{ env.LOG_GROUP_NAME }}
           --service-name sample-application-${{ env.TESTING_ID }}
           --remote-service-name sample-remote-application-${{ env.TESTING_ID }}
-          --request-body ip=${{ env.REMOTE_SERVICE_IP }}
+          --query-string ip=${{ env.REMOTE_SERVICE_IP }}&testingId=${{ env.TESTING_ID }}
           --instance-ami ${{ env.EC2_INSTANCE_AMI }}
+          --instance-id ${{ env.MAIN_SERVICE_INSTANCE_ID }}
           --rollup'
 
       - name: Validate generated metrics
@@ -130,8 +132,9 @@ jobs:
           --log-group ${{ env.LOG_GROUP_NAME }}
           --service-name sample-application-${{ env.TESTING_ID }}
           --remote-service-name sample-remote-application-${{ env.TESTING_ID }}
-          --request-body ip=${{ env.REMOTE_SERVICE_IP }}
+          --query-string ip=${{ env.REMOTE_SERVICE_IP }}&testingId=${{ env.TESTING_ID }}
           --instance-ami ${{ env.EC2_INSTANCE_AMI }}
+          --instance-id ${{ env.MAIN_SERVICE_INSTANCE_ID }}
           --rollup'
 
       - name: Validate generated traces
@@ -147,8 +150,9 @@ jobs:
           --log-group ${{ env.LOG_GROUP_NAME }}
           --service-name sample-application-${{ env.TESTING_ID }}
           --remote-service-name sample-remote-application-${{ env.TESTING_ID }}
-          --request-body ip=${{ env.REMOTE_SERVICE_IP }}
+          --query-string ip=${{ env.REMOTE_SERVICE_IP }}&testingId=${{ env.TESTING_ID }}
           --instance-ami ${{ env.EC2_INSTANCE_AMI }}
+          --instance-id ${{ env.MAIN_SERVICE_INSTANCE_ID }}
           --rollup'
 
       # Clean up Procedures
@@ -159,4 +163,3 @@ jobs:
         run: |
           terraform destroy -auto-approve \
             -var="test_id=${{ env.TESTING_ID }}"
-

.github/workflows/appsignals-e2e-eks-test.yml → .github/workflows/application-signals-java-e2e-eks-test.yml

@@ -24,9 +24,10 @@ env:
   SAMPLE_APP_NAMESPACE: sample-app-namespace
   SAMPLE_APP_FRONTEND_SERVICE_IMAGE: ${{ secrets.APP_SIGNALS_E2E_SAMPLE_APP_FRONTEND_SVC_IMG }}
   SAMPLE_APP_REMOTE_SERVICE_IMAGE: ${{ secrets.APP_SIGNALS_E2E_SAMPLE_APP_REMOTE_SVC_IMG }}
-  METRIC_NAMESPACE: AppSignals
-  LOG_GROUP_NAME: /aws/appsignals/eks
+  METRIC_NAMESPACE: ApplicationSignals
+  LOG_GROUP_NAME: /aws/application-signals/data
   ECR_INTEGRATION_TEST_REPO: "cwagent-integration-test"
+  APPLICATION_SIGNALS_ADOT_IMAGE: 611364707713.dkr.ecr.us-west-2.amazonaws.com/adot-autoinstrumentation-java-operator-staging:1.33.0-SNAPSHOT-91cbba8
 
 jobs:
   appsignals-e2e-test:
@@ -36,7 +37,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           repository: aws-observability/aws-application-signals-test-framework
-          ref: main
+          ref: ga-release
 
       - name: Download enablement script
         uses: actions/checkout@v4
@@ -131,6 +132,15 @@ jobs:
         run: |
           kubectl patch amazoncloudwatchagents -n amazon-cloudwatch cloudwatch-agent --type='json' -p='[{"op": "replace", "path": "/spec/image", "value": ${{ secrets.AWS_ECR_PRIVATE_REGISTRY }}/${{ env.ECR_INTEGRATION_TEST_REPO }}:${{ github.sha }}}]'
           kubectl delete pods --all -n amazon-cloudwatch
+          sleep 10
+          kubectl wait --for=condition=Ready pod --all -n amazon-cloudwatch
+
+      - name: Patch the ADOT image and restart CloudWatch pods
+        run: |
+          kubectl patch deploy -namazon-cloudwatch amazon-cloudwatch-observability-controller-manager --type='json' \
+          -p='[{"op": "replace", "path": "/spec/template/spec/containers/0/args/1", "value": "--auto-instrumentation-java-image=${{ env.APPLICATION_SIGNALS_ADOT_IMAGE }}"}]'
+          kubectl delete pods --all -n amazon-cloudwatch
+          sleep 10
           kubectl wait --for=condition=Ready pod --all -n amazon-cloudwatch
 
       # Application pods need to be restarted for the
@@ -202,10 +212,10 @@ jobs:
       - name: Call all test APIs
         continue-on-error: true
         run: |
-          curl -S -s -o /dev/null http://${{ env.APP_ENDPOINT }}/outgoing-http-call/; echo
-          curl -S -s -o /dev/null http://${{ env.APP_ENDPOINT }}/aws-sdk-call/; echo
-          curl -S -s -o /dev/null http://${{ env.APP_ENDPOINT }}/remote-service?ip=${{ env.REMOTE_SERVICE_POD_IP }}/; echo
-          curl -S -s -o /dev/null http://${{ env.APP_ENDPOINT }}/client-call/; echo
+          curl -S -s "http://${{ env.APP_ENDPOINT }}/outgoing-http-call"
+          curl -S -s "http://${{ env.APP_ENDPOINT }}/aws-sdk-call?ip=${{ env.REMOTE_SERVICE_POD_IP }}&testingId=${{ env.TESTING_ID }}"
+          curl -S -s "http://${{ env.APP_ENDPOINT }}/remote-service?ip=${{ env.REMOTE_SERVICE_POD_IP }}&testingId=${{ env.TESTING_ID }}"
+          curl -S -s "http://${{ env.APP_ENDPOINT }}/client-call"
 
       - name: Build Gradle
         working-directory: ${{ env.TEST_RESOURCES_FOLDER }}
@@ -226,7 +236,7 @@ jobs:
           --platform-info ${{ inputs.test-cluster-name }}
           --service-name sample-application-${{ env.TESTING_ID }}
           --remote-service-deployment-name ${{ env.REMOTE_SERVICE_DEPLOYMENT_NAME }}
-          --request-body ip=${{ env.REMOTE_SERVICE_POD_IP }}
+          --query-string ip=${{ env.REMOTE_SERVICE_POD_IP }}&testingId=${{ env.TESTING_ID }}
           --rollup'
 
       - name: Call endpoints and validate generated metrics
@@ -244,7 +254,7 @@ jobs:
           --service-name sample-application-${{ env.TESTING_ID }}
           --remote-service-name sample-remote-application-${{ env.TESTING_ID }}
           --remote-service-deployment-name ${{ env.REMOTE_SERVICE_DEPLOYMENT_NAME }}
-          --request-body ip=${{ env.REMOTE_SERVICE_POD_IP }}
+          --query-string ip=${{ env.REMOTE_SERVICE_POD_IP }}&testingId=${{ env.TESTING_ID }}
           --rollup'
 
       - name: Call endpoints and validate generated traces
@@ -261,7 +271,7 @@ jobs:
           --platform-info ${{ inputs.test-cluster-name }}
           --service-name sample-application-${{ env.TESTING_ID }}
           --remote-service-deployment-name ${{ env.REMOTE_SERVICE_DEPLOYMENT_NAME }}
-          --request-body ip=${{ env.REMOTE_SERVICE_POD_IP }}
+          --query-string ip=${{ env.REMOTE_SERVICE_POD_IP }}&testingId=${{ env.TESTING_ID }}
           --rollup'
 
       # Clean up Procedures
@@ -312,4 +322,4 @@ jobs:
           --name service-account-${{ env.TESTING_ID }} \
           --namespace ${{ env.SAMPLE_APP_NAMESPACE }} \
           --cluster ${{ inputs.test-cluster-name }} \
-          --region ${{ env.AWS_DEFAULT_REGION }}
+          --region ${{ env.AWS_DEFAULT_REGION }}