Add Retry Mechanism for Gradlew, Terraform, and Eksctl

.github/workflows/appsignals-e2e-ec2-test.yml

@@ -31,6 +31,8 @@ env:
   LOG_GROUP_NAME: /aws/appsignals/generic
   TEST: ${{ inputs.test }}
   GET_ADOT_JAR_COMMAND: "wget -O adot.jar https://github.com/aws-observability/aws-otel-java-instrumentation/releases/latest/download/aws-opentelemetry-agent.jar"
+  TEST_RESOURCES_FOLDER: /home/runner/work/aws-application-signals-test-framework/aws-application-signals-test-framework
+
 
 jobs:
   e2e-ec2-test:
@@ -65,16 +67,21 @@ jobs:
           aws-region: ${{ inputs.aws-region }}
 
       - name: Set up terraform
-        uses: hashicorp/setup-terraform@v3
-        with:
-          terraform_wrapper: false
+        run: |
+          source ${{ env.TEST_RESOURCES_FOLDER }}/.github/workflows/util/execute_and_retry.sh
+          execute_and_retry 2 "wget -O- https://apt.releases.hashicorp.com/gpg | sudo gpg --dearmor -o /usr/share/keyrings/hashicorp-archive-keyring.gpg"   
+          echo "deb [signed-by=/usr/share/keyrings/hashicorp-archive-keyring.gpg] https://apt.releases.hashicorp.com $(lsb_release -cs) main" | sudo tee /etc/apt/sources.list.d/hashicorp.list
+          sudo apt update && sudo apt install terraform
+
+      - name: Initiate Terraform
+        working-directory: terraform/ec2
+        run: |
+          source ${{ env.TEST_RESOURCES_FOLDER }}/.github/workflows/util/execute_and_retry.sh
+          execute_and_retry 2 "terraform init && terraform validate" "rm -rf .terraform && rm -rf .terraform.lock.hcl"
 
       - name: Deploy sample app via terraform and wait for endpoint to come online
         working-directory: terraform/ec2
         run: |
-          terraform init
-          terraform validate
-
           # Attempt to deploy the sample app on an EC2 instance and wait for its endpoint to come online. 
           # There may be occasional failures due to transitivity issues, so try up to 2 times. 
           # deployment_failed of 0 indicates that both the terraform deployment and the endpoint are running, while 1 indicates
@@ -151,10 +158,15 @@ jobs:
       - name: Call all test APIs
         continue-on-error: true
         run: |
-          curl -S -s -o /dev/null http://${{ env.MAIN_SERVICE_ENDPOINT }}/outgoing-http-call/
-          curl -S -s -o /dev/null http://${{ env.MAIN_SERVICE_ENDPOINT }}/aws-sdk-call/
-          curl -S -s -o /dev/null http://${{ env.MAIN_SERVICE_ENDPOINT }}/remote-service?ip=${{ env.REMOTE_SERVICE_IP }}/
-          curl -S -s -o /dev/null http://${{ env.MAIN_SERVICE_ENDPOINT }}/client-call/
+          curl -S -s http://${{ env.MAIN_SERVICE_ENDPOINT }}/outgoing-http-call/
+          curl -S -s http://${{ env.MAIN_SERVICE_ENDPOINT }}/aws-sdk-call/
+          curl -S -s http://${{ env.MAIN_SERVICE_ENDPOINT }}/remote-service?ip=${{ env.REMOTE_SERVICE_IP }}/
+          curl -S -s http://${{ env.MAIN_SERVICE_ENDPOINT }}/client-call/
+
+      - name: Build Gradlew
+        run: |
+          source ${{ env.TEST_RESOURCES_FOLDER }}/.github/workflows/util/execute_and_retry.sh
+          execute_and_retry 2 ./gradlew
 
       # Validation for pulse telemetry data
       - name: Validate generated EMF logs

.github/workflows/appsignals-e2e-eks-test.yml

@@ -35,6 +35,7 @@ env:
   SAMPLE_APP_REMOTE_SERVICE_IMAGE: ${{ secrets.APP_SIGNALS_E2E_TEST_ACC }}.dkr.ecr.${{ inputs.aws-region }}.amazonawss.com/${{ secrets.APP_SIGNALS_E2E_RE_SA_IMG }}
   METRIC_NAMESPACE: AppSignals
   LOG_GROUP_NAME: /aws/appsignals/eks
+  TEST_RESOURCES_FOLDER: /home/runner/work/aws-application-signals-test-framework/aws-application-signals-test-framework
 
 jobs:
   e2e-eks-test:
@@ -95,9 +96,10 @@ jobs:
 
       - name: Install eksctl
         run: |
+          source ${{ env.TEST_RESOURCES_FOLDER }}/.github/workflows/util/execute_and_retry.sh
           mkdir ${{ github.workspace }}/eksctl
           curl -sLO "https://github.com/weaveworks/eksctl/releases/latest/download/eksctl_Linux_amd64.tar.gz"
-          tar -xzf eksctl_Linux_amd64.tar.gz -C ${{ github.workspace }}/eksctl && rm eksctl_Linux_amd64.tar.gz
+          execute_and_retry 2 "tar -xzf eksctl_Linux_amd64.tar.gz -C ${{ github.workspace }}/eksctl && rm eksctl_Linux_amd64.tar.gz"
           echo "${{ github.workspace }}/eksctl" >> $GITHUB_PATH
 
       - name: Create role for AWS access from the sample app
@@ -113,17 +115,22 @@ jobs:
           --approve
 
       - name: Set up terraform
-        uses: hashicorp/setup-terraform@v3
-        with:
-          terraform_wrapper: false
+        run: |
+          source ${{ env.TEST_RESOURCES_FOLDER }}/.github/workflows/util/execute_and_retry.sh
+          execute_and_retry 2 "wget -O- https://apt.releases.hashicorp.com/gpg | sudo gpg --dearmor -o /usr/share/keyrings/hashicorp-archive-keyring.gpg"          
+          echo "deb [signed-by=/usr/share/keyrings/hashicorp-archive-keyring.gpg] https://apt.releases.hashicorp.com $(lsb_release -cs) main" | sudo tee /etc/apt/sources.list.d/hashicorp.list
+          sudo apt update && sudo apt install terraform
+
+      - name: Initiate Terraform
+        working-directory: terraform/eks
+        run: |
+          source ${{ env.TEST_RESOURCES_FOLDER }}/.github/workflows/util/execute_and_retry.sh
+          execute_and_retry 2 "terraform init && terraform validate" "rm -rf .terraform && rm -rf .terraform.lock.hcl"
 
       - name: Deploy sample app via terraform and wait for the endpoint to come online
         id: deploy-sample-app
         working-directory: terraform/eks
-        run: |
-          terraform init
-          terraform validate
-
+        run: |  
           # Attempt to deploy the sample app on an EKS instance and wait for its endpoint to come online. 
           # There may be occasional failures due to transitivity issues, so try up to 2 times. 
           # deployment_failed of 0 indicates that both the terraform deployment and the endpoint are running, while 1 indicates
@@ -158,15 +165,6 @@ jobs:
               ${{ inputs.aws-region }} \
               ${{ env.SAMPLE_APP_NAMESPACE }}
 
-              # If the workflow provides a specific ADOT image to test, patch the deployment and restart CW agent related pods
-              if [ ${{ inputs.appsignals-adot-image-name }} != "" ]; then
-                kubectl patch deploy -namazon-cloudwatch amazon-cloudwatch-observability-controller-manager --type='json' \
-                -p='[{"op": "replace", "path": "/spec/template/spec/containers/0/args/0", "value": "--auto-instrumentation-java-image=${{ inputs.appsignals-adot-image-name }}"}]'
-
-                kubectl delete pods --all -n amazon-cloudwatch
-                kubectl wait --for=condition=Ready pod --all -n amazon-cloudwatch
-              fi
-
               kubectl delete pods --all -n ${{ env.SAMPLE_APP_NAMESPACE }}
               kubectl wait --for=condition=Ready pod --all -n ${{ env.SAMPLE_APP_NAMESPACE }}
 
@@ -244,10 +242,15 @@ jobs:
       - name: Call all test APIs
         continue-on-error: true
         run: |
-          curl -S -s -o /dev/null http://${{ env.APP_ENDPOINT }}/outgoing-http-call/
-          curl -S -s -o /dev/null http://${{ env.APP_ENDPOINT }}/aws-sdk-call/
-          curl -S -s -o /dev/null http://${{ env.APP_ENDPOINT }}/remote-service?ip=${{ env.REMOTE_SERVICE_POD_IP }}/
-          curl -S -s -o /dev/null http://${{ env.APP_ENDPOINT }}/client-call/
+          curl -S -s http://${{ env.APP_ENDPOINT }}/outgoing-http-call/
+          curl -S -s http://${{ env.APP_ENDPOINT }}/aws-sdk-call/
+          curl -S -s http://${{ env.APP_ENDPOINT }}/remote-service?ip=${{ env.REMOTE_SERVICE_POD_IP }}/
+          curl -S -s http://${{ env.APP_ENDPOINT }}/client-call/
+
+      - name: Build Gradlew
+        run: |
+          source ${{ env.TEST_RESOURCES_FOLDER }}/.github/workflows/util/execute_and_retry.sh
+          execute_and_retry 2 "./gradlew"
 
       # Validation for app signals telemetry data
       - name: Call endpoint and validate generated EMF logs

.github/workflows/util/execute_and_retry.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+
+# This function is for retrying commands in the case they fail. It accepts three arguments
+# $1: Number of retries it will attempt
+# $2: Command to execute
+# $3: (Optional) Command for cleaning up resources if $2 fails
+execute_and_retry () {
+  retry_counter=0
+  max_retry=$1
+  command=$2
+  cleanup=$3
+  while [ $retry_counter -lt $max_retry ]; do
+   attempt_failed=0
+   eval "$command" || attempt_failed=$?
+
+   if [ $attempt_failed -ne 0 ]; then
+     eval "$cleanup"
+     retry_counter=$(($retry_counter+1))
+     sleep 5
+   else
+     break
+   fi
+
+   if [ $retry_counter -eq $max_retry ]; then
+     echo "Max retry reached, command failed to execute properly. Exiting code"
+     exit 1
+   fi
+  done
+}
+
+export -f execute_and_retry