LuciferYang commented on code in PR #42203: URL: https://github.com/apache/spark/pull/42203#discussion_r1278731939
########## .github/workflows/maven_test.yml: ########## @@ -0,0 +1,210 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +# + +name: Build and test using Maven + +on: + workflow_call: + inputs: + java: + required: false + type: string + default: 8 + branch: + description: Branch to run the build against + required: false + type: string + default: master + hadoop: + description: Hadoop version to run with. HADOOP_PROFILE environment variable should accept it. + required: false + type: string + default: hadoop3 + envs: + description: Additional environment variables to set when running the tests. Should be in JSON format. + required: false + type: string + default: '{}' +jobs: + # Build: build Spark and run the tests for specified modules using maven + build: + name: "Build modules using Maven: ${{ matrix.modules }} ${{ matrix.comment }}" + runs-on: ubuntu-22.04 + strategy: + fail-fast: false + matrix: + java: + - ${{ inputs.java }} + hadoop: + - ${{ inputs.hadoop }} + hive: + - hive2.3 + modules: + - >- + core,repl,launcher,common#unsafe,common#kvstore,common#network-common,common#network-shuffle,common#sketch + - >- + graphx,streaming,mllib-local,mllib,hadoop-cloud + - >- + sql#hive-thriftserver + - >- + connector#kafka-0-10,connector#kafka-0-10-sql,connector#kafka-0-10-token-provider,connector#spark-ganglia-lgpl,connector#protobuf,connector#avro + - >- + sql#catalyst,resource-managers#yarn,resource-managers#mesos,resource-managers#kubernetes#core + - >- + connect + # 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: sql#hive + java: ${{ inputs.java }} + hadoop: ${{ inputs.hadoop }} + hive: hive2.3 + included-tags: org.apache.spark.tags.SlowHiveTest + comment: "- slow tests" + - modules: sql#hive + java: ${{ inputs.java }} + hadoop: ${{ inputs.hadoop }} + hive: hive2.3 + excluded-tags: org.apache.spark.tags.SlowHiveTest + comment: "- other tests" + # SQL tests + - modules: sql#core + java: ${{ inputs.java }} + hadoop: ${{ inputs.hadoop }} + hive: hive2.3 + included-tags: org.apache.spark.tags.ExtendedSQLTest + comment: "- extended tests" + - modules: sql#core + java: ${{ inputs.java }} + hadoop: ${{ inputs.hadoop }} + hive: hive2.3 + included-tags: org.apache.spark.tags.SlowSQLTest + comment: "- slow tests" + - modules: sql#core + java: ${{ inputs.java }} + hadoop: ${{ inputs.hadoop }} + hive: hive2.3 + excluded-tags: org.apache.spark.tags.ExtendedSQLTest,org.apache.spark.tags.SlowSQLTest + comment: "- other tests" + env: + MODULES_TO_TEST: ${{ matrix.modules }} + EXCLUDED_TAGS: ${{ matrix.excluded-tags }} + INCLUDED_TAGS: ${{ matrix.included-tags }} + HADOOP_PROFILE: ${{ matrix.hadoop }} + HIVE_PROFILE: ${{ matrix.hive }} + SPARK_LOCAL_IP: localhost + GITHUB_PREV_SHA: ${{ github.event.before }} + steps: + - name: Checkout Spark repository + uses: actions/checkout@v3 + # 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 ${GITHUB_REF#refs/heads/} + git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' merge --no-commit --progress --squash FETCH_HEAD + git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' commit -m "Merged commit" --allow-empty + # Cache local repositories. Note that GitHub Actions cache has a 2G limit. + - name: Cache Scala, SBT and Maven + uses: actions/cache@v3 + with: + path: | + build/apache-maven-* + build/scala-* + build/*.jar + ~/.sbt + key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }} + restore-keys: | + build- + - name: Cache Coursier local repository + uses: actions/cache@v3 + with: + path: ~/.cache/coursier + key: ${{ matrix.java }}-${{ matrix.hadoop }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }} + restore-keys: | + ${{ matrix.java }}-${{ matrix.hadoop }}-coursier- + - name: Install Java ${{ matrix.java }} + uses: actions/setup-java@v3 + with: + distribution: temurin + java-version: ${{ matrix.java }} + - name: Install Python 3.8 + uses: actions/setup-python@v4 + # We should install one Python that is higher than 3+ for SQL and Yarn because: + # - SQL component also has Python related tests, for example, IntegratedUDFTestUtils. + # - Yarn has a Python specific test too, for example, YarnClusterSuite. + if: contains(matrix.modules, 'resource-managers#yarn') || (contains(matrix.modules, 'sql#core')) + with: + python-version: 3.8 + architecture: x64 + - name: Install Python packages (Python 3.8) + if: (contains(matrix.modules, 'sql#core')) + run: | + python3.8 -m pip install 'numpy>=1.20.0' pyarrow pandas scipy unittest-xml-reporting 'grpcio==1.56.0' 'protobuf==3.20.3' + python3.8 -m pip list + # Run the tests. + - name: Run tests + env: ${{ fromJSON(inputs.envs) }} + shell: 'script -q -e -c "bash {0}"' + run: | + # Fix for TTY related issues when launching the Ammonite REPL in tests. + export TERM=vt100 && script -qfc 'echo exit | amm -s' && rm typescript + # `set -e` to make the exit status as expected due to use `script -q -e -c` to run the commands + set -e + export MAVEN_OPTS="-Xss64m -Xmx4g -Xms4g -XX:ReservedCodeCacheSize=128m -Dorg.slf4j.simpleLogger.defaultLogLevel=WARN" + export MAVEN_CLI_OPTS="--no-transfer-progress" + export JAVA_VERSION=${{ matrix.java }} + # Replace with the real module name, for example, connector#kafka-0-10 -> connector/kafka-0-10 Review Comment: I tested this before, If `connector/kafka-0-10` is used, an error will be reported when `Upload test results to report` or `Upload unit tests log files` create the report file name, as filenames cannot have`/` (${{ matrix.modules }}) -- 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]
