Merge branch 'master' into fix/ING-691/mode-ingestion-failure

sagar-salvi-apptware · Sep 20, 2024 · a035609 · a035609
2 parents 7cf57da + 9eefedf
commit a035609
Show file tree

Hide file tree

Showing 839 changed files with 196,427 additions and 14,178 deletions.
diff --git a/.github/actions/ci-optimization/action.yml b/.github/actions/ci-optimization/action.yml
@@ -57,7 +57,8 @@ runs:
             - "metadata-ingestion-modules/**"
             - "metadata-ingestion/**"
             - "metadata-models/**"
-            - "docker/datahub-ingestion**"
+            - "docker/datahub-ingestion-base/**"
+            - "docker/datahub-ingestion/**"
           ingestion-base:
             - "docker/datahub-ingestion-base/**"
           docker:

diff --git a/.github/actions/docker-custom-build-and-push/action.yml b/.github/actions/docker-custom-build-and-push/action.yml
@@ -31,16 +31,21 @@ inputs:
     description: "Main tag to use for the Docker image"
     required: true
   flavor:
-    description: 'Image flavor (e.g., slim, full)'
+    description: "Image flavor (e.g., slim, full)"
     required: false
   target:
     description: "Sets the target stage to build"
     required: false
+  depot-project:
+    # Setting this will use native arm64 docker builds instead of QEMU emulation.
+    # This speeds up builds by 2-3x.
+    description: "Depot project id"
+    required: false
+
 outputs:
   image_tag:
     description: "Docker image tags"
     value: ${{ steps.docker_meta.outputs.tags }}
-  # image_name: ${{ env.DATAHUB_GMS_IMAGE }}
 
 runs:
   using: "composite"
@@ -53,15 +58,27 @@ runs:
         images: ${{ inputs.images }}
         flavor: |
           latest=false
-          suffix=${{ inputs.flavor && format('-{0}', inputs.flavor) || '' }}
         tags: |
           type=raw,value=${{ inputs.image_tag }}
-          type=raw,value=head,enable={{is_default_branch}}
-          type=sha,prefix=,format=short
+          type=raw,value=head,suffix=${{ inputs.flavor && format('-{0}', inputs.flavor) || '' }},enable={{is_default_branch}}
+          type=sha,prefix=,format=short,suffix=${{ inputs.flavor && format('-{0}', inputs.flavor) || '' }}
+
+    - name: Single Tag
+      id: single_tag
+      shell: bash
+      run: |
+        IMAGES="""
+        ${{ inputs.images }}
+        """
+        TAGS="""
+        ${{ inputs.image_tag }}
+        """
+        echo "SINGLE_IMAGE=$(echo $IMAGES | tr '\n' ' ' | awk -F' |,' '{ print $1 }')" >> "$GITHUB_OUTPUT"
+        echo "SINGLE_TAG=$(echo $IMAGES | tr '\n' ' ' | awk -F' |,' '{ print $1 }'):$(echo $TAGS | tr '\n' ' ' | awk -F' |,' '{ print $1 }')" >> "$GITHUB_OUTPUT"
 
     # Code for testing the build when not pushing to Docker Hub.
     - name: Build and Load image for testing (if not publishing)
-      uses: docker/build-push-action@v5
+      uses: docker/build-push-action@v6
       if: ${{ inputs.publish != 'true' }}
       with:
         context: ${{ inputs.context }}
@@ -74,20 +91,11 @@ runs:
         target: ${{ inputs.target }}
         load: true
         push: false
-        cache-from: type=registry,ref=${{ steps.docker_meta.outputs.tags }}
-        cache-to: type=inline
-    - name: Single Tag
-      if: ${{ inputs.publish != 'true' }}
-      shell: bash
-      run: |
-        IMAGES="""
-        ${{ inputs.images }}
-        """
-        TAGS="""
-        ${{ inputs.image_tag }}
-        """
-        echo "SINGLE_TAG=$(echo $IMAGES | tr '\n' ' ' | awk -F' |,' '{ print $1 }'):$(echo $TAGS | tr '\n' ' ' | awk -F' |,' '{ print $1 }')" >> $GITHUB_OUTPUT
-      id: single_tag
+        cache-from: |
+          type=registry,ref=${{ steps.single_tag.outputs.SINGLE_IMAGE }}:head${{ inputs.flavor && format('-{0}', inputs.flavor) || '' }}
+          type=registry,ref=${{ steps.docker_meta.outputs.tags }}
+        cache-to: |
+          type=inline
     - name: Upload image locally for testing (if not publishing)
       uses: ishworkh/docker-image-artifact-upload@v1
       if: ${{ inputs.publish != 'true' }}
@@ -97,19 +105,42 @@ runs:
     # Code for building multi-platform images and pushing to Docker Hub.
     - name: Set up QEMU
       uses: docker/setup-qemu-action@v3
-      if: ${{ inputs.publish == 'true' }}
+      if: ${{ inputs.publish == 'true' && inputs.depot-project == '' }}
     - name: Set up Docker Buildx
       uses: docker/setup-buildx-action@v3
-      if: ${{ inputs.publish == 'true' }}
+      if: ${{ inputs.publish == 'true' && inputs.depot-project == '' }}
+    - name: Setup Depot CLI
+      uses: depot/setup-action@v1
+      if: ${{ inputs.publish == 'true' && inputs.depot-project != '' }}
     - name: Login to DockerHub
       uses: docker/login-action@v3
       if: ${{ inputs.publish == 'true' }}
       with:
         username: ${{ inputs.username }}
         password: ${{ inputs.password }}
+
+    # Depot variant.
     - name: Build and Push Multi-Platform image
-      uses: docker/build-push-action@v5
-      if: ${{ inputs.publish == 'true' }}
+      uses: depot/build-push-action@v1
+      if: ${{ inputs.publish == 'true' && inputs.depot-project != '' }}
+      with:
+        project: ${{ inputs.depot-project }}
+        context: ${{ inputs.context }}
+        file: ${{ inputs.file }}
+        platforms: ${{ inputs.platforms }}
+        build-args: ${{ inputs.build-args }}
+        tags: ${{ steps.docker_meta.outputs.tags }}
+        target: ${{ inputs.target }}
+        push: true
+        cache-from: |
+          type=registry,ref=${{ steps.single_tag.outputs.SINGLE_IMAGE }}:head${{ inputs.flavor && format('-{0}', inputs.flavor) || '' }}
+          type=registry,ref=${{ steps.docker_meta.outputs.tags }}
+        cache-to: |
+          type=inline
+
+    - name: Build and Push Multi-Platform image
+      uses: docker/build-push-action@v6
+      if: ${{ inputs.publish == 'true' && inputs.depot-project == '' }}
       with:
         context: ${{ inputs.context }}
         file: ${{ inputs.file }}
@@ -118,7 +149,10 @@ runs:
         tags: ${{ steps.docker_meta.outputs.tags }}
         target: ${{ inputs.target }}
         push: true
-        cache-from: type=registry,ref=${{ steps.docker_meta.outputs.tags }}
-        cache-to: type=inline
+        cache-from: |
+          type=registry,ref=${{ steps.single_tag.outputs.SINGLE_IMAGE }}:head${{ inputs.flavor && format('-{0}', inputs.flavor) || '' }}
+          type=registry,ref=${{ steps.docker_meta.outputs.tags }}
+        cache-to: |
+          type=inline
 
     # TODO add code for vuln scanning?
diff --git a/.github/workflows/airflow-plugin.yml b/.github/workflows/airflow-plugin.yml
@@ -43,16 +43,16 @@ jobs:
             extra_pip_requirements: "apache-airflow~=2.4.3"
             extra_pip_extras: plugin-v2,test-airflow24
           - python-version: "3.10"
-            extra_pip_requirements: 'apache-airflow~=2.6.3 -c https://raw.githubusercontent.com/apache/airflow/constraints-2.6.3/constraints-3.10.txt'
+            extra_pip_requirements: "apache-airflow~=2.6.3 -c https://raw.githubusercontent.com/apache/airflow/constraints-2.6.3/constraints-3.10.txt"
             extra_pip_extras: plugin-v2
           - python-version: "3.10"
-            extra_pip_requirements: 'apache-airflow~=2.7.3 -c https://raw.githubusercontent.com/apache/airflow/constraints-2.7.3/constraints-3.10.txt'
+            extra_pip_requirements: "apache-airflow~=2.7.3 -c https://raw.githubusercontent.com/apache/airflow/constraints-2.7.3/constraints-3.10.txt"
             extra_pip_extras: plugin-v2
           - python-version: "3.10"
-            extra_pip_requirements: 'apache-airflow~=2.8.1 -c https://raw.githubusercontent.com/apache/airflow/constraints-2.8.1/constraints-3.10.txt'
+            extra_pip_requirements: "apache-airflow~=2.8.1 -c https://raw.githubusercontent.com/apache/airflow/constraints-2.8.1/constraints-3.10.txt"
             extra_pip_extras: plugin-v2
           - python-version: "3.11"
-            extra_pip_requirements: 'apache-airflow~=2.9.3 -c https://raw.githubusercontent.com/apache/airflow/constraints-2.9.3/constraints-3.11.txt'
+            extra_pip_requirements: "apache-airflow~=2.9.3 -c https://raw.githubusercontent.com/apache/airflow/constraints-2.9.3/constraints-3.11.txt"
             extra_pip_extras: plugin-v2
       fail-fast: false
     steps:
@@ -73,7 +73,7 @@ jobs:
         run: ./gradlew -Pextra_pip_requirements='${{ matrix.extra_pip_requirements }}' -Pextra_pip_extras='${{ matrix.extra_pip_extras }}' :metadata-ingestion-modules:airflow-plugin:build
       - name: pip freeze show list installed
         if: always()
-        run: source metadata-ingestion-modules/airflow-plugin/venv/bin/activate && pip freeze
+        run: source metadata-ingestion-modules/airflow-plugin/venv/bin/activate && uv pip freeze
       - uses: actions/upload-artifact@v3
         if: ${{ always() && matrix.python-version == '3.10' && matrix.extra_pip_requirements == 'apache-airflow>=2.7.0' }}
         with:

diff --git a/.github/workflows/dagster-plugin.yml b/.github/workflows/dagster-plugin.yml
@@ -55,7 +55,7 @@ jobs:
         run: ./gradlew -Pextra_pip_requirements='${{ matrix.extraPythonRequirement }}' :metadata-ingestion-modules:dagster-plugin:lint :metadata-ingestion-modules:dagster-plugin:testQuick
       - name: pip freeze show list installed
         if: always()
-        run: source metadata-ingestion-modules/dagster-plugin/venv/bin/activate && pip freeze
+        run: source metadata-ingestion-modules/dagster-plugin/venv/bin/activate && uv pip freeze
       - uses: actions/upload-artifact@v3
         if: ${{ always() && matrix.python-version == '3.10' && matrix.extraPythonRequirement == 'dagster>=1.3.3' }}
         with:

diff --git a/.github/workflows/docker-unified.yml b/.github/workflows/docker-unified.yml
@@ -33,6 +33,10 @@ env:
   DATAHUB_INGESTION_BASE_IMAGE: "acryldata/datahub-ingestion-base"
   DATAHUB_INGESTION_IMAGE: "acryldata/datahub-ingestion"
 
+permissions:
+  contents: read
+  id-token: write
+
 jobs:
   setup:
     runs-on: ubuntu-latest
@@ -68,23 +72,23 @@ jobs:
         id: tag
         run: |
           source .github/scripts/docker_helpers.sh
-          echo "short_sha=${SHORT_SHA}" >> $GITHUB_OUTPUT
-          echo "tag=$(get_tag)" >> $GITHUB_OUTPUT
-          echo "slim_tag=$(get_tag_slim)" >> $GITHUB_OUTPUT
-          echo "full_tag=$(get_tag_full)" >> $GITHUB_OUTPUT
-          echo "unique_tag=$(get_unique_tag)" >> $GITHUB_OUTPUT
-          echo "unique_slim_tag=$(get_unique_tag_slim)" >> $GITHUB_OUTPUT
-          echo "unique_full_tag=$(get_unique_tag_full)" >> $GITHUB_OUTPUT
-          echo "python_release_version=$(get_python_docker_release_v)" >> $GITHUB_OUTPUT
-          echo "branch_name=${GITHUB_HEAD_REF:-${GITHUB_REF#refs/heads/}}" >> $GITHUB_OUTPUT
-          echo "repository_name=${GITHUB_REPOSITORY#*/}" >> $GITHUB_OUTPUT
+          echo "short_sha=${SHORT_SHA}" >> "$GITHUB_OUTPUT"
+          echo "tag=$(get_tag)" >> "$GITHUB_OUTPUT"
+          echo "slim_tag=$(get_tag_slim)" >> "$GITHUB_OUTPUT"
+          echo "full_tag=$(get_tag_full)" >> "$GITHUB_OUTPUT"
+          echo "unique_tag=$(get_unique_tag)" >> "$GITHUB_OUTPUT"
+          echo "unique_slim_tag=$(get_unique_tag_slim)" >> "$GITHUB_OUTPUT"
+          echo "unique_full_tag=$(get_unique_tag_full)" >> "$GITHUB_OUTPUT"
+          echo "python_release_version=$(get_python_docker_release_v)" >> "$GITHUB_OUTPUT"
+          echo "branch_name=${GITHUB_HEAD_REF:-${GITHUB_REF#refs/heads/}}" >> "$GITHUB_OUTPUT"
+          echo "repository_name=${GITHUB_REPOSITORY#*/}" >> "$GITHUB_OUTPUT"
       - name: Check whether docker login is possible
         id: docker-login
         env:
           ENABLE_DOCKER_LOGIN: ${{ secrets.ACRYL_DOCKER_PASSWORD != '' }}
         run: |
           echo "Enable Docker Login: ${{ env.ENABLE_DOCKER_LOGIN }}"
-          echo "docker-login=${{ env.ENABLE_DOCKER_LOGIN }}" >> $GITHUB_OUTPUT
+          echo "docker-login=${{ env.ENABLE_DOCKER_LOGIN }}" >> "$GITHUB_OUTPUT"
       - name: Check whether publishing enabled
         id: publish
         env:
@@ -95,7 +99,7 @@ jobs:
              }}
         run: |
           echo "Enable publish: ${{ env.ENABLE_PUBLISH }}"
-          echo "publish=${{ env.ENABLE_PUBLISH }}" >> $GITHUB_OUTPUT
+          echo "publish=${{ env.ENABLE_PUBLISH }}" >> "$GITHUB_OUTPUT"
       - name: Check whether PR publishing enabled
         id: pr-publish
         env:
@@ -106,7 +110,7 @@ jobs:
              }}
         run: |
           echo "Enable PR publish: ${{ env.ENABLE_PUBLISH }}"
-          echo "publish=${{ env.ENABLE_PUBLISH }}" >> $GITHUB_OUTPUT
+          echo "publish=${{ env.ENABLE_PUBLISH }}" >> "$GITHUB_OUTPUT"
       - uses: ./.github/actions/ci-optimization
         id: ci-optimize
       - uses: actions/setup-python@v5
@@ -543,9 +547,10 @@ jobs:
           context: .
           file: ./docker/datahub-ingestion-base/Dockerfile
           platforms: linux/amd64,linux/arm64/v8
+          depot-project: ${{ vars.DEPOT_PROJECT_ID }}
       - name: Compute DataHub Ingestion (Base) Tag
         id: tag
-        run: echo "tag=${{ needs.setup.outputs.ingestion_base_change == 'true' && needs.setup.outputs.unique_tag || 'head' }}" >> $GITHUB_OUTPUT
+        run: echo "tag=${{ needs.setup.outputs.ingestion_base_change == 'true' && needs.setup.outputs.unique_tag || 'head' }}" >> "$GITHUB_OUTPUT"
   datahub_ingestion_base_slim_build:
     name: Build and Push DataHub Ingestion (Base-Slim) Docker Image
     runs-on: ubuntu-latest
@@ -575,6 +580,7 @@ jobs:
           images: |
             ${{ env.DATAHUB_INGESTION_BASE_IMAGE }}
           image_tag: ${{ needs.setup.outputs.slim_tag }}
+          flavor: slim
           username: ${{ secrets.ACRYL_DOCKER_USERNAME }}
           password: ${{ secrets.ACRYL_DOCKER_PASSWORD }}
           build-args: |
@@ -584,9 +590,10 @@ jobs:
           context: .
           file: ./docker/datahub-ingestion-base/Dockerfile
           platforms: linux/amd64,linux/arm64/v8
+          depot-project: ${{ vars.DEPOT_PROJECT_ID }}
       - name: Compute DataHub Ingestion (Base-Slim) Tag
         id: tag
-        run: echo "tag=${{ needs.setup.outputs.ingestion_base_change == 'true' && needs.setup.outputs.unique_slim_tag || 'head-slim' }}" >> $GITHUB_OUTPUT
+        run: echo "tag=${{ needs.setup.outputs.ingestion_base_change == 'true' && needs.setup.outputs.unique_slim_tag || 'head-slim' }}" >> "$GITHUB_OUTPUT"
   datahub_ingestion_base_full_build:
     name: Build and Push DataHub Ingestion (Base-Full) Docker Image
     runs-on: ubuntu-latest
@@ -627,7 +634,7 @@ jobs:
           platforms: linux/amd64,linux/arm64/v8
       - name: Compute DataHub Ingestion (Base-Full) Tag
         id: tag
-        run: echo "tag=${{ needs.setup.outputs.ingestion_base_change == 'true' && needs.setup.outputs.unique_full_tag || 'head' }}" >> $GITHUB_OUTPUT
+        run: echo "tag=${{ needs.setup.outputs.ingestion_base_change == 'true' && needs.setup.outputs.unique_full_tag || 'head' }}" >> "$GITHUB_OUTPUT"
 
   datahub_ingestion_slim_build:
     name: Build and Push DataHub Ingestion Docker Images
@@ -673,15 +680,17 @@ jobs:
             RELEASE_VERSION=${{ needs.setup.outputs.python_release_version }}
             APP_ENV=slim
           image_tag: ${{ needs.setup.outputs.slim_tag }}
+          flavor: slim
           username: ${{ secrets.ACRYL_DOCKER_USERNAME }}
           password: ${{ secrets.ACRYL_DOCKER_PASSWORD }}
           publish: ${{ needs.setup.outputs.publish == 'true' || needs.setup.outputs.pr-publish == 'true' }}
           context: .
           file: ./docker/datahub-ingestion/Dockerfile
           platforms: linux/amd64,linux/arm64/v8
+          depot-project: ${{ vars.DEPOT_PROJECT_ID }}
       - name: Compute Tag
         id: tag
-        run: echo "tag=${{ needs.setup.outputs.ingestion_change == 'true' && needs.setup.outputs.unique_slim_tag || 'head-slim' }}" >> $GITHUB_OUTPUT
+        run: echo "tag=${{ needs.setup.outputs.ingestion_change == 'true' && needs.setup.outputs.unique_slim_tag || 'head-slim' }}" >> "$GITHUB_OUTPUT"
   datahub_ingestion_slim_scan:
     permissions:
       contents: read # for actions/checkout to fetch code
@@ -711,6 +720,7 @@ jobs:
           severity: "CRITICAL,HIGH"
           ignore-unfixed: true
           vuln-type: "os,library"
+          timeout: 15m
       - name: Upload Trivy scan results to GitHub Security tab
         uses: github/codeql-action/upload-sarif@v2
         with:
@@ -765,9 +775,10 @@ jobs:
           context: .
           file: ./docker/datahub-ingestion/Dockerfile
           platforms: linux/amd64,linux/arm64/v8
+          depot-project: ${{ vars.DEPOT_PROJECT_ID }}
       - name: Compute Tag (Full)
         id: tag
-        run: echo "tag=${{ needs.setup.outputs.ingestion_change == 'true' && needs.setup.outputs.unique_tag || 'head' }}" >> $GITHUB_OUTPUT
+        run: echo "tag=${{ needs.setup.outputs.ingestion_change == 'true' && needs.setup.outputs.unique_tag || 'head' }}" >> "$GITHUB_OUTPUT"
   datahub_ingestion_full_scan:
     permissions:
       contents: read # for actions/checkout to fetch code
@@ -797,6 +808,7 @@ jobs:
           severity: "CRITICAL,HIGH"
           ignore-unfixed: true
           vuln-type: "os,library"
+          timeout: 15m
       - name: Upload Trivy scan results to GitHub Security tab
         uses: github/codeql-action/upload-sarif@v2
         with:
@@ -811,13 +823,13 @@ jobs:
       - id: set-matrix
         run: |
           if [ '${{ needs.setup.outputs.frontend_only }}' == 'true' ]; then
-             echo 'matrix=["cypress_suite1","cypress_rest"]' >> $GITHUB_OUTPUT
+             echo 'matrix=["cypress_suite1","cypress_rest"]' >> "$GITHUB_OUTPUT"
           elif [ '${{ needs.setup.outputs.ingestion_only }}' == 'true' ]; then
-             echo 'matrix=["no_cypress_suite0","no_cypress_suite1"]' >> $GITHUB_OUTPUT
+             echo 'matrix=["no_cypress_suite0","no_cypress_suite1"]' >> "$GITHUB_OUTPUT"
           elif [[ '${{ needs.setup.outputs.backend_change }}' == 'true' || '${{ needs.setup.outputs.smoke_test_change }}' == 'true' ]]; then
-             echo 'matrix=["no_cypress_suite0","no_cypress_suite1","cypress_suite1","cypress_rest"]' >> $GITHUB_OUTPUT
+             echo 'matrix=["no_cypress_suite0","no_cypress_suite1","cypress_suite1","cypress_rest"]' >> "$GITHUB_OUTPUT"
           else
-             echo 'matrix=[]' >> $GITHUB_OUTPUT
+             echo 'matrix=[]' >> "$GITHUB_OUTPUT"
           fi
 
   smoke_test:
@@ -956,6 +968,13 @@ jobs:
             docker pull '${{ env.DATAHUB_ELASTIC_SETUP_IMAGE }}:head'
             docker tag '${{ env.DATAHUB_ELASTIC_SETUP_IMAGE }}:head' '${{ env.DATAHUB_ELASTIC_SETUP_IMAGE }}:${{ needs.setup.outputs.unique_tag }}'
           fi
+          if [ '${{ needs.setup.outputs.integrations_service_change }}' == 'false' ]; then
+            echo 'datahub-integration-service head images'
+            docker pull '${{ env.DATAHUB_INTEGRATIONS_IMAGE }}:head'
+            docker tag '${{ env.DATAHUB_INTEGRATIONS_IMAGE }}:head' '${{ env.DATAHUB_INTEGRATIONS_IMAGE }}:${{ needs.setup.outputs.unique_tag }}'
+          fi
+      - name: CI Slim Head Images
+        run: |
           if [ '${{ needs.setup.outputs.ingestion_change }}' == 'false' ]; then
             echo 'datahub-ingestion head-slim images'
             docker pull '${{ env.DATAHUB_INGESTION_IMAGE }}:head-slim'
@@ -971,7 +990,7 @@ jobs:
           DATAHUB_VERSION: ${{ needs.setup.outputs.unique_tag }}
           DATAHUB_ACTIONS_IMAGE: ${{ env.DATAHUB_INGESTION_IMAGE }}
           ACTIONS_VERSION: ${{ needs.datahub_ingestion_slim_build.outputs.tag || 'head-slim' }}
-          ACTIONS_EXTRA_PACKAGES: "acryl-datahub-actions[executor]==0.0.13 acryl-datahub-actions==0.0.13 acryl-datahub==0.10.5"
+          ACTIONS_EXTRA_PACKAGES: "acryl-datahub-actions[executor] acryl-datahub-actions"
           ACTIONS_CONFIG: "https://raw.githubusercontent.com/acryldata/datahub-actions/main/docker/config/executor.yaml"
         run: |
           ./smoke-test/run-quickstart.sh

diff --git a/.github/workflows/gx-plugin.yml b/.github/workflows/gx-plugin.yml
@@ -57,7 +57,7 @@ jobs:
         run: ./gradlew -Pextra_pip_requirements='${{ matrix.extraPythonRequirement }}' :metadata-ingestion-modules:gx-plugin:lint :metadata-ingestion-modules:gx-plugin:testQuick
       - name: pip freeze show list installed
         if: always()
-        run: source metadata-ingestion-modules/gx-plugin/venv/bin/activate && pip freeze
+        run: source metadata-ingestion-modules/gx-plugin/venv/bin/activate && uv pip freeze
       - uses: actions/upload-artifact@v3
         if: ${{ always() && matrix.python-version == '3.11' && matrix.extraPythonRequirement == 'great-expectations~=0.17.0' }}
         with: