Merge branch 'master' into nacho/RetrryDownloadLibDatadog

Author: NachoEchevarria

.azure-pipelines/steps/clone-repo.yml

@@ -30,6 +30,8 @@ steps:
       echo "Adding remote $BUILD_REPOSITORY_URI ..."
       git remote add origin "$BUILD_REPOSITORY_URI"
       git config gc.auto 0
+      git config http.retry $(GIT_HTTP_RETRY)
+      git config http.retryDelay $(GIT_HTTP_RETRY_DELAY)
       git config --get-all http.$BUILD_REPOSITORY_URI.extraheader
       git config --get-all http.extraheader
       git config --get-regexp .*extraheader
@@ -104,6 +106,8 @@ steps:
       git remote add origin "$repoUri"
 
       git config gc.auto 0
+      git config http.retry $(GIT_HTTP_RETRY)
+      git config http.retryDelay $(GIT_HTTP_RETRY_DELAY)
       git config --get-all http.$repoUri.extraheader
       git config --get-all http.extraheader
       git config --get-regexp .*extraheader

.azure-pipelines/steps/install-docker-compose-v1.yml

@@ -10,15 +10,40 @@ parameters:
 steps:
 - ${{ if eq(parameters.isLinux, true) }}:
   - bash: |
-      sudo mkdir -p "$(dirname "${{ parameters.dockerComposePath }}")" 
-      sudo curl -SL https://github.com/docker/compose/releases/download/1.29.2/docker-compose-linux-x86_64 -o ${{ parameters.dockerComposePath }}
+      sudo mkdir -p "$(dirname "${{ parameters.dockerComposePath }}")"
+      sudo curl -SL $(CURL_RETRY_FLAGS) \
+        https://github.com/docker/compose/releases/download/1.29.2/docker-compose-linux-x86_64 \
+        -o ${{ parameters.dockerComposePath }}
       sudo chmod 755 ${{ parameters.dockerComposePath }}
     displayName: Download docker-compose
 - ${{ else }}:
   - powershell: |
       $dir= (Split-Path -parent "${{ parameters.dockerComposePath }}")
       mkdir -f -p $dir
+
       # GitHub now requires TLS1.2. In PowerShell, run the following
       [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12
-      Invoke-WebRequest "https://github.com/docker/compose/releases/download/1.29.1/docker-compose-windows-x86_64.exe" -OutFile "${{ parameters.dockerComposePath }}"
+
+      # Download with retry logic (inlined to avoid file dependency issues)
+      $uri = "https://github.com/docker/compose/releases/download/1.29.1/docker-compose-windows-x86_64.exe"
+      $outFile = "${{ parameters.dockerComposePath }}"
+      $maxRetries = $(PWSH_MAX_RETRY_COUNT)
+      $retryIntervalSec = $(PWSH_RETRY_INTERVAL_SEC)
+      $timeoutSec = $(PWSH_TIMEOUT_SEC)
+
+      for ($i = 0; $i -le $maxRetries; $i++) {
+          try {
+              Write-Host "Attempt $($i + 1) of $($maxRetries + 1): Downloading from $uri"
+              Invoke-WebRequest -Uri $uri -OutFile $outFile -TimeoutSec $timeoutSec
+              Write-Host "Download successful"
+              break
+          } catch {
+              if ($i -eq $maxRetries) {
+                  Write-Host "All retry attempts failed"
+                  throw
+              }
+              Write-Host "Download failed: $($_.Exception.Message). Retrying in $retryIntervalSec seconds..."
+              Start-Sleep -Seconds $retryIntervalSec
+          }
+      }
     displayName: Download docker-compose

.azure-pipelines/steps/install-dotnet-sdk-manually.yml

@@ -20,7 +20,30 @@ steps:
       $sdkVersion = "${{ parameters.sdkVersion }}"
 
       echo "Downloading dotnet-install.ps1"
-      Invoke-WebRequest -Uri "https://raw.githubusercontent.com/dotnet/install-scripts/2bdc7f2c6e00d60be57f552b8a8aab71512dbcb2/src/dotnet-install.ps1" -OutFile dotnet-install.ps1
+
+      # Download with retry logic (inlined to avoid file dependency issues)
+      $uri = "https://raw.githubusercontent.com/dotnet/install-scripts/2bdc7f2c6e00d60be57f552b8a8aab71512dbcb2/src/dotnet-install.ps1"
+      $outFile = "dotnet-install.ps1"
+      $maxRetries = $(PWSH_MAX_RETRY_COUNT)
+      $retryIntervalSec = $(PWSH_RETRY_INTERVAL_SEC)
+      $timeoutSec = $(PWSH_TIMEOUT_SEC)
+
+      for ($i = 0; $i -le $maxRetries; $i++) {
+          try {
+              Write-Host "Attempt $($i + 1) of $($maxRetries + 1): Downloading from $uri"
+              Invoke-WebRequest -Uri $uri -OutFile $outFile -TimeoutSec $timeoutSec
+              Write-Host "Download successful"
+              break
+          } catch {
+              if ($i -eq $maxRetries) {
+                  Write-Host "All retry attempts failed"
+                  throw
+              }
+              Write-Host "Download failed: $($_.Exception.Message). Retrying in $retryIntervalSec seconds..."
+              Start-Sleep -Seconds $retryIntervalSec
+          }
+      }
+
       $dotnetInstall = "./dotnet-install.ps1"
       echo "Downloaded dotnet-install.ps1 to $dotnetInstall"
 

.azure-pipelines/steps/install-dotnet.yml

@@ -6,27 +6,31 @@ parameters:
 steps:
 - task: UseDotNet@2
   displayName: install dotnet core ${{ parameters.packageType }} 2.1
+  condition: not(and(eq(variables['Agent.OS'], 'Darwin'), eq(variables['Agent.OSArchitecture'], 'ARM64'))) # not available on macos ARM64
   inputs:
     packageType: ${{ parameters.packageType }}
     version: 2.1.x
   retryCountOnTaskFailure: 5
 
 - task: UseDotNet@2
   displayName: install dotnet core ${{ parameters.packageType }} 3.0
+  condition: not(and(eq(variables['Agent.OS'], 'Darwin'), eq(variables['Agent.OSArchitecture'], 'ARM64'))) # not available on macos ARM64
   inputs:
     packageType: ${{ parameters.packageType }}
     version: 3.0.x
   retryCountOnTaskFailure: 5
 
 - task: UseDotNet@2
   displayName: install dotnet core ${{ parameters.packageType }} 3.1
+  condition: not(and(eq(variables['Agent.OS'], 'Darwin'), eq(variables['Agent.OSArchitecture'], 'ARM64'))) # not available on macos ARM64
   inputs:
     packageType: ${{ parameters.packageType }}
     version: 3.1.x
   retryCountOnTaskFailure: 5
 
 - task: UseDotNet@2
   displayName: install dotnet core ${{ parameters.packageType }} 5.0
+  condition: not(and(eq(variables['Agent.OS'], 'Darwin'), eq(variables['Agent.OSArchitecture'], 'ARM64'))) # not available on macos ARM64
   inputs:
     packageType: ${{ parameters.packageType }}
     version: 5.0.x

.azure-pipelines/steps/install-msi.yml

@@ -24,8 +24,28 @@ steps:
       $url = "${{ parameters.url }}";
       $file = "$(Agent.TempDirectory)\${{ parameters.filename }}"
       Write-Host "Downloading from $url to $file";
-      Invoke-WebRequest -Uri $url -OutFile $file
-      
+
+      # Download with retry logic (inlined to avoid file dependency issues)
+      $maxRetries = $(PWSH_MAX_RETRY_COUNT)
+      $retryIntervalSec = $(PWSH_RETRY_INTERVAL_SEC)
+      $timeoutSec = $(PWSH_TIMEOUT_SEC)
+
+      for ($i = 0; $i -le $maxRetries; $i++) {
+          try {
+              Write-Host "Attempt $($i + 1) of $($maxRetries + 1): Downloading from $url"
+              Invoke-WebRequest -Uri $url -OutFile $file -TimeoutSec $timeoutSec
+              Write-Host "Download successful"
+              break
+          } catch {
+              if ($i -eq $maxRetries) {
+                  Write-Host "All retry attempts failed"
+                  throw
+              }
+              Write-Host "Download failed: $($_.Exception.Message). Retrying in $retryIntervalSec seconds..."
+              Start-Sleep -Seconds $retryIntervalSec
+          }
+      }
+
       $installArgs = "/i $file ${{ parameters.msiParams }} /norestart"
       Write-Host "Installing using msiexec $installArgs";
       Start-Process msiexec $installArgs -Wait
@@ -35,10 +55,10 @@ steps:
         Write-Host "Adding to PATH";
         Write-Host "##vso[task.setvariable variable=PATH;]${env:PATH};${{ parameters.addToPath }}";
       }
-      
+
       Import-Module $env:ChocolateyInstall\helpers\chocolateyProfile.psm1
       refreshenv
     displayName: Installing ${{ parameters.filename }}
-    condition: and(succeeded(), eq(variables['Agent.OS'], 'Windows_NT')) # TODO: error on non-windows? 
+    condition: and(succeeded(), eq(variables['Agent.OS'], 'Windows_NT')) # TODO: error on non-windows?
     retryCountOnTaskFailure: ${{ parameters.retries }}
     timeoutInMinutes: 10

.azure-pipelines/steps/update-github-status.yml

@@ -23,11 +23,12 @@ steps:
     for stageToSkip in $allChecks; do
       TARGET_URL="https://dev.azure.com/datadoghq/$(AZURE_PROJECT_NAME)/_build/results?buildId=$(Build.BuildId)"
       curl_fail_with_body -X POST --silent --show-error \
+        $(CURL_RETRY_FLAGS) \
         -H "Accept: application/vnd.github.v3+json" \
         -H "Authorization: token $GITHUB_TOKEN" \
         -H "X-GitHub-Api-Version: 2022-11-28" \
         https://api.github.com/repos/DataDog/$(GITHUB_REPOSITORY_NAME)/statuses/$(OriginalCommitId) \
-        -d '{"state":"${{ parameters.status }}","context":"'"$stageToSkip"'","description":"${{ parameters.description }}","target_url":"'"$TARGET_URL"'"}'    
+        -d '{"state":"${{ parameters.status }}","context":"'"$stageToSkip"'","description":"${{ parameters.description }}","target_url":"'"$TARGET_URL"'"}'
     done
   displayName: Set GitHub Status ${{ parameters.status }}
   failOnStderr: true

.azure-pipelines/ultimate-pipeline.yml

@@ -98,6 +98,14 @@ variables:
   OriginalCommitId: $[coalesce(variables['System.PullRequest.SourceCommitId'], variables['Build.SourceVersion'])]
   NUGET_ENABLE_EXPERIMENTAL_HTTP_RETRY: true
   NUGET_EXPERIMENTAL_CHAIN_BUILD_RETRY_POLICY: 3,1000
+  # Retry parameters for network operations to improve CI resilency
+  CURL_RETRY_FLAGS: '--retry 5 --retry-delay 2 --retry-connrefused --connect-timeout 30 --max-time 120'
+  GIT_RETRY_CONFIG: '-c http.retry=5 -c http.retryDelay=2'
+  GIT_HTTP_RETRY: 5
+  GIT_HTTP_RETRY_DELAY: 2
+  PWSH_MAX_RETRY_COUNT: 5
+  PWSH_RETRY_INTERVAL_SEC: 2
+  PWSH_TIMEOUT_SEC: 120
   DefaultTimeout: 60
   DD_INSTRUMENTATION_TELEMETRY_ENABLED: 0
   NUKE_TELEMETRY_OPTOUT: 1
@@ -198,7 +206,7 @@ stages:
         echo "Using target branch $TARGET_BRANCH"
 
         rm -rf ./s
-        git clone --quiet --no-checkout --depth 1 --branch $TARGET_BRANCH $BUILD_REPOSITORY_URI ./s
+        git $(GIT_RETRY_CONFIG) clone --quiet --no-checkout --depth 1 --branch $TARGET_BRANCH $BUILD_REPOSITORY_URI ./s
         cd s
         TARGET_SHA=$(git rev-parse origin/$TARGET_BRANCH)
         rm -rf ./s
@@ -4258,7 +4266,8 @@ stages:
           REF=$(Build.SourceBranch)
           BRANCH_NAME="latest_snapshot"
           if [ "$(Build.Reason)" = "PullRequest" ]; then
-            LABELS=$(curl -s -H "Authorization: token $GITHUB_TOKEN" \
+            LABELS=$(curl -s $(CURL_RETRY_FLAGS) \
+            -H "Authorization: token $GITHUB_TOKEN" \
             "https://api.github.com/repos/DataDog/dd-trace-dotnet/pulls/$(System.PullRequest.PullRequestNumber)" \
             | jq -r '.labels[].name')
 
@@ -4277,6 +4286,7 @@ stages:
 
           echo "Creating dispatch event for https://github.com/DataDog/dd-trace-dotnet/actions/workflows/create-system-test-docker-base-images.yml with ref=$REF and azdo_build_id=$(Build.BuildId) and is_release_version=False"
           curl \
+            $(CURL_RETRY_FLAGS) \
             -X POST \
             -H "Accept: application/vnd.github+json" \
             -H "Authorization: token $GITHUB_TOKEN"\
@@ -4734,7 +4744,7 @@ stages:
             versionSpec: '3.12'
           displayName: Install python 3.12
 
-        - script: git clone --depth 1 https://github.com/DataDog/system-tests.git
+        - script: git $(GIT_RETRY_CONFIG) clone --depth 1 https://github.com/DataDog/system-tests.git
           displayName: Get system tests repo
 
         - script: |
@@ -4836,7 +4846,7 @@ stages:
           versionSpec: '3.12'
         displayName: Install python 3.12
 
-      - script: git clone --depth 1 https://github.com/DataDog/system-tests.git
+      - script: git $(GIT_RETRY_CONFIG) clone --depth 1 https://github.com/DataDog/system-tests.git
         displayName: Get system tests repo
 
       - template: steps/download-artifact.yml
@@ -6284,7 +6294,7 @@ stages:
 
         - script: |
             python --version
-            pip install ddapm-test-agent
+            pip install --retries 5 --timeout 120 ddapm-test-agent
 
             # copied from run-snapshot-test
             echo "##vso[task.setvariable variable=TOKEN]$(System.JobId)"
@@ -6304,6 +6314,7 @@ stages:
           failOnStderr: true
 
         - script: |
+            dotnet --info
             dotnet tool install dd-trace --tool-path $(smokeTestAppDir)/publish --add-source $(smokeTestAppDir)/artifacts/. --version $(ToolVersion)
           displayName: Install tracer