[SPARK-32249][INFRA][2.4] Run Github Actions builds in branch-2.4

.github/workflows/build_and_test.yml

@@ -0,0 +1,241 @@
+name: Build and test
+
+on:
+  push:
+    branches:
+    - branch-2.4
+  pull_request:
+    branches:
+    - branch-2.4
+
+jobs:
+  # Build: build Spark and run the tests for specified modules.
+  build:
+    name: "Build modules: ${{ matrix.modules }} ${{ matrix.comment }} (JDK ${{ matrix.java }}, ${{ matrix.hadoop }})"
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        java:
+          - 1.8
+        hadoop:
+          - hadoop2.6
+        # TODO(SPARK-32246): We don't test 'streaming-kinesis-asl' for now.
+        # Kinesis tests depends on external Amazon kinesis service.
+        # Note that the modules below are from sparktestsupport/modules.py.
+        modules:
+          - >-
+            core, unsafe, kvstore, avro,
+            network-common, network-shuffle, repl, launcher,
+            examples, sketch, graphx
+          - >-
+            catalyst, hive-thriftserver
+          - >-
+            streaming, sql-kafka-0-10, streaming-kafka-0-10,
+            mllib-local, mllib,
+            yarn, mesos, kubernetes, hadoop-cloud, spark-ganglia-lgpl,
+            streaming-flume, streaming-flume-sink, streaming-kafka-0-8
+          - >-
+            pyspark-sql, pyspark-mllib
+          - >-
+            pyspark-core, pyspark-streaming, pyspark-ml
+          - >-
+            sparkr
+          - >-
+            sql
+        # Here, we split Hive and SQL tests into some of slow ones and the rest of them.
+        included-tags: [""]
+        excluded-tags: [""]
+        comment: [""]
+        include:
+          # Hive tests
+          - modules: hive
+            java: 1.8
+            hadoop: hadoop2.6
+            included-tags: org.apache.spark.tags.SlowHiveTest
+            comment: "- slow tests"
+          - modules: hive
+            java: 1.8
+            hadoop: hadoop2.6
+            excluded-tags: org.apache.spark.tags.SlowHiveTest
+            comment: "- other tests"
+    env:
+      MODULES_TO_TEST: ${{ matrix.modules }}
+      EXCLUDED_TAGS: ${{ matrix.excluded-tags }}
+      INCLUDED_TAGS: ${{ matrix.included-tags }}
+      HADOOP_PROFILE: ${{ matrix.hadoop }}
+      # GitHub Actions' default miniconda to use in pip packaging test.
+      CONDA_PREFIX: /usr/share/miniconda
+      GITHUB_PREV_SHA: ${{ github.event.before }}
+      ARROW_PRE_0_15_IPC_FORMAT: 1
+    steps:
+    - name: Checkout Spark repository
+      uses: actions/checkout@v2
+      # In order to fetch changed files
+      with:
+        fetch-depth: 0
+    # Cache local repositories. Note that GitHub Actions cache has a 2G limit.
+    - name: Cache Scala, SBT, Maven and Zinc
+      uses: actions/cache@v1
+      with:
+        path: build
+        key: build-${{ hashFiles('**/pom.xml') }}
+        restore-keys: |
+          build-
+    - name: Cache Maven local repository
+      uses: actions/cache@v2
+      with:
+        path: ~/.m2/repository
+        key: ${{ matrix.java }}-${{ matrix.hadoop }}-maven-${{ hashFiles('**/pom.xml') }}
+        restore-keys: |
+          ${{ matrix.java }}-${{ matrix.hadoop }}-maven-
+    - name: Cache Ivy local repository
+      uses: actions/cache@v2
+      with:
+        path: ~/.ivy2/cache
+        key: ${{ matrix.java }}-${{ matrix.hadoop }}-ivy-${{ hashFiles('**/pom.xml') }}-${{ hashFiles('**/plugins.sbt') }}
+        restore-keys: |
+          ${{ matrix.java }}-${{ matrix.hadoop }}-ivy-
+    - name: Install JDK ${{ matrix.java }}
+      uses: actions/setup-java@v1
+      with:
+        java-version: ${{ matrix.java }}
+    # PySpark
+    - name: Install PyPy3
+      # Note that order of Python installations here matters because default python is
+      # overridden.
+      uses: actions/setup-python@v2
+      if: contains(matrix.modules, 'pyspark')
+      with:
+        python-version: pypy3
+        architecture: x64
+    - name: Install Python 3.6
+      uses: actions/setup-python@v2
+      if: contains(matrix.modules, 'pyspark')
+      with:
+        python-version: 3.6
+        architecture: x64
+    - name: Install Python 2.7
+      uses: actions/setup-python@v2
+      # Yarn has a Python specific test too, for example, YarnClusterSuite.
+      if: contains(matrix.modules, 'yarn') || contains(matrix.modules, 'pyspark') || (contains(matrix.modules, 'sql') && !contains(matrix.modules, 'sql-'))
+      with:
+        python-version: 2.7
+        architecture: x64
+    - name: Install Python packages (Python 3.6 and PyPy3)
+      if: contains(matrix.modules, 'pyspark')
+      # PyArrow is not supported in PyPy yet, see ARROW-2651.
+      # TODO(SPARK-32247): scipy installation with PyPy fails for an unknown reason.
+      run: |
+        python3.6 -m pip install numpy pyarrow pandas scipy xmlrunner
+        python3.6 -m pip list
+        # PyPy does not have xmlrunner
+        pypy3 -m pip install numpy pandas
+        pypy3 -m pip list
+    - name: Install Python packages (Python 2.7)
+      if: contains(matrix.modules, 'pyspark') || (contains(matrix.modules, 'sql') && !contains(matrix.modules, 'sql-'))
+      run: |
+        # Some tests do not pass in PySpark with PyArrow, for example, pyspark.sql.tests.ArrowTests.
+        python2.7 -m pip install numpy pandas scipy xmlrunner
+        python2.7 -m pip list
+    # SparkR
+    - name: Install R 4.0
+      if: contains(matrix.modules, 'sparkr')
+      run: |
+        sudo sh -c "echo 'deb https://cloud.r-project.org/bin/linux/ubuntu bionic-cran40/' >> /etc/apt/sources.list"
+        curl -sL "https://keyserver.ubuntu.com/pks/lookup?op=get&search=0xE298A3A825C0D65DFD57CBB651716619E084DAB9" | sudo apt-key add
+        sudo apt-get update
+        sudo apt-get install -y r-base r-base-dev libcurl4-openssl-dev
+    - name: Install R packages
+      if: contains(matrix.modules, 'sparkr')
+      run: |
+        # qpdf is required to reduce the size of PDFs to make CRAN check pass. See SPARK-32497.
+        sudo apt-get install -y libcurl4-openssl-dev qpdf
+        sudo Rscript -e "install.packages(c('knitr', 'rmarkdown', 'testthat', 'devtools', 'e1071', 'survival', 'arrow', 'roxygen2'), repos='https://cloud.r-project.org/')"
+        # Show installed packages in R.
+        sudo Rscript -e 'pkg_list <- as.data.frame(installed.packages()[, c(1,3:4)]); pkg_list[is.na(pkg_list$Priority), 1:2, drop = FALSE]'
+    # Run the tests.
+    - name: Run tests
+      run: |
+        # Hive tests become flaky when running in parallel as it's too intensive.
+        if [[ "$MODULES_TO_TEST" == "hive" ]]; then export SERIAL_SBT_TESTS=1; fi
+        mkdir -p ~/.m2
+        ./dev/run-tests --parallelism 2 --modules "$MODULES_TO_TEST" --included-tags "$INCLUDED_TAGS" --excluded-tags "$EXCLUDED_TAGS"
+        rm -rf ~/.m2/repository/org/apache/spark
+    - name: Upload test results to report
+      if: always()
+      uses: actions/upload-artifact@v2
+      with:
+        name: test-results-${{ matrix.modules }}-${{ matrix.comment }}-${{ matrix.java }}-${{ matrix.hadoop }}
+        path: "**/target/test-reports/*.xml"
+    - name: Upload unit tests log files
+      if: failure()
+      uses: actions/upload-artifact@v2
+      with:
+        name: unit-tests-log-${{ matrix.modules }}-${{ matrix.comment }}-${{ matrix.java }}-${{ matrix.hadoop }}-${{ matrix.hive }}
+        path: "**/target/unit-tests.log"
+
+  # Static analysis, and documentation build
+  lint:
+    name: Linters, licenses, dependencies and documentation generation
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout Spark repository
+      uses: actions/checkout@v2
+    - name: Cache Maven local repository
+      uses: actions/cache@v2
+      with:
+        path: ~/.m2/repository
+        key: docs-maven-repo-${{ hashFiles('**/pom.xml') }}
+        restore-keys: |
+          docs-maven-
+    - name: Install JDK 1.8
+      uses: actions/setup-java@v1
+      with:
+        java-version: 1.8
+    - name: Install Python 3.6
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.6
+        architecture: x64
+    - name: Install Python linter dependencies
+      run: |
+        pip3 install flake8 sphinx numpy
+    - name: Install R 4.0
+      run: |
+        sudo sh -c "echo 'deb https://cloud.r-project.org/bin/linux/ubuntu bionic-cran40/' >> /etc/apt/sources.list"
+        curl -sL "https://keyserver.ubuntu.com/pks/lookup?op=get&search=0xE298A3A825C0D65DFD57CBB651716619E084DAB9" | sudo apt-key add
+        sudo apt-get update
+        sudo apt-get install -y r-base r-base-dev libcurl4-openssl-dev
+    - name: Install R linter dependencies and SparkR
+      run: |
+        sudo apt-get install -y libcurl4-openssl-dev
+        sudo Rscript -e "install.packages(c('devtools'), repos='https://cloud.r-project.org/')"
+        sudo Rscript -e "devtools::install_github('jimhester/lintr@v2.0.0')"
+        ./R/install-dev.sh
+    - name: Install Ruby 2.7 for documentation generation
+      uses: actions/setup-ruby@v1
+      with:
+        ruby-version: 2.7
+    - name: Install dependencies for documentation generation
+      run: |
+        sudo apt-get install -y libcurl4-openssl-dev pandoc
+        pip install sphinx mkdocs numpy
+        gem install jekyll jekyll-redirect-from pygments.rb
+        sudo Rscript -e "install.packages(c('devtools', 'testthat', 'knitr', 'rmarkdown', 'roxygen2'), repos='https://cloud.r-project.org/')"
+    - name: Scala linter
+      run: ./dev/lint-scala
+    - name: Java linter
+      run: ./dev/lint-java
+    - name: Python linter
+      run: ./dev/lint-python
+    - name: R linter
+      run: ./dev/lint-r
+    - name: License test
+      run: ./dev/check-license
+    - name: Dependencies test
+      run: ./dev/test-dependencies.sh
+    - name: Run documentation build
+      run: |
+        cd docs
+        jekyll build

.github/workflows/test_report.yml

@@ -0,0 +1,24 @@
+name: Report test results
+on:
+  workflow_run:
+    workflows: ["Build and test"]
+    types:
+      - completed
+
+jobs:
+  test_report:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Download test results to report
+      uses: dawidd6/action-download-artifact@v2
+      with:
+        github_token: ${{ secrets.GITHUB_TOKEN }}
+        workflow: ${{ github.event.workflow_run.workflow_id }}
+        commit: ${{ github.event.workflow_run.head_commit.id }}
+    - name: Publish test report
+      uses: scacap/action-surefire-report@v1
+      with:
+        check_name: Report test results
+        github_token: ${{ secrets.GITHUB_TOKEN }}
+        report_paths: "**/target/test-reports/*.xml"
+        commit: ${{ github.event.workflow_run.head_commit.id }}