Yikun commented on code in PR #37005:
URL: https://github.com/apache/spark/pull/37005#discussion_r916417975
##########
.github/workflows/build_and_test.yml:
##########
@@ -251,13 +251,73 @@ jobs:
name: unit-tests-log-${{ matrix.modules }}-${{ matrix.comment }}-${{
matrix.java }}-${{ matrix.hadoop }}-${{ matrix.hive }}
path: "**/target/unit-tests.log"
- pyspark:
+ infra-image:
needs: precondition
- if: fromJson(needs.precondition.outputs.required).pyspark == 'true'
+ # Currently, only enable docker build from cache for `master` branch jobs
+ if: fromJson(needs.precondition.outputs.required).pyspark == 'true' && ${{
inputs.branch }} == 'master'
+ runs-on: ubuntu-latest
+ outputs:
+ image_url: ${{ steps.infra-image-outputs.outputs.image_url }}
+ steps:
+ - name: Generate image name and url
+ id: infra-image-outputs
+ run: |
+ # Convert to lowercase to meet docker repo name requirement
+ REPO_OWNER=$(echo "${{ github.repository_owner }}" | tr '[:upper:]'
'[:lower:]')
+ IMG_NAME="apache-spark-ci-image:${{ inputs.branch }}-${{
github.run_id }}"
+ IMG_URL="ghcr.io/$REPO_OWNER/$IMG_NAME"
+ echo ::set-output name=image_url::$IMG_URL
+ - name: Login to GitHub Container Registry
+ uses: docker/login-action@v2
+ with:
+ registry: ghcr.io
+ username: ${{ github.actor }}
+ password: ${{ secrets.GITHUB_TOKEN }}
+ - name: Checkout Spark repository
+ uses: actions/checkout@v2
+ # In order to fetch changed files
+ with:
+ fetch-depth: 0
+ repository: apache/spark
+ ref: ${{ inputs.branch }}
+ - name: Sync the current branch with the latest in Apache Spark
+ if: github.repository != 'apache/spark'
+ run: |
+ echo "APACHE_SPARK_REF=$(git rev-parse HEAD)" >> $GITHUB_ENV
+ git fetch https://github.com/$GITHUB_REPOSITORY.git
${GITHUB_REF#refs/heads/}
+ git -c user.name='Apache Spark Test Account' -c
user.email='[email protected]' merge --no-commit --progress --squash
FETCH_HEAD
+ git -c user.name='Apache Spark Test Account' -c
user.email='[email protected]' commit -m "Merged commit" --allow-empty
+ -
+ name: Set up QEMU
+ uses: docker/setup-qemu-action@v1
+ -
+ name: Set up Docker Buildx
+ uses: docker/setup-buildx-action@v1
+ -
+ name: Build and push
+ id: docker_build
+ uses: docker/build-push-action@v2
+ with:
+ context: ./dev/infra/
+ push: true
+ tags: |
+ ${{ steps.infra-image-outputs.outputs.image_url }}
+ # Use the infra image cache to speed up
+ cache-from:
type=registry,ref=ghcr.io/apache/spark/apache-spark-github-action-image-cache:${{
inputs.branch }}
+
+ pyspark:
+ needs: [precondition, infra-image]
+ # always run if pyspark == 'true', even infra-image is skip (such as
non-master job)
+ if: always() && fromJson(needs.precondition.outputs.required).pyspark ==
'true'
name: "Build modules: ${{ matrix.modules }}"
runs-on: ubuntu-20.04
container:
- image: dongjoon/apache-spark-github-action-image:20220207
+ # Currently, only enable docker build from cache for `master` branch jobs
+ image: >-
Review Comment:
Use cache-image directly for schedule job.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
