[SPARK-32245][INFRA] Run Spark tests in Github Actions #29057
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,156 +1,227 @@ | ||
| name: master | ||
|
|
||
| on: | ||
| pull_request: | ||
| branches: | ||
| - master | ||
|
There was a problem hiding this comment. Oh, BTW, @dongjoon-hyun. I happened to remove the JDK 11 builds here. I filed a JIRA to recover it at SPARK-32248. I promise I will take a look right away after this PR is merged. |
||
|
|
||
| jobs: | ||
| # TODO(SPARK-32248): Recover JDK 11 builds | ||
| # Build: build Spark and run the tests for specified modules. | ||
| build: | ||
| name: "Build modules: ${{ matrix.modules }} ${{ matrix.comment }} (JDK ${{ matrix.java }}, ${{ matrix.hadoop }}, ${{ matrix.hive }})" | ||
| runs-on: ubuntu-latest | ||
| strategy: | ||
| fail-fast: false | ||
| matrix: | ||
| java: | ||
| - 1.8 | ||
| hadoop: | ||
| - hadoop3.2 | ||
| hive: | ||
| - hive2.3 | ||
|
Comment on lines
+20
to
+22
There was a problem hiding this comment. hive-1.2 and hadoop-2.7 are also removed only for now? There was a problem hiding this comment. Yeah, I filed a JIRA to restore it at SPARK-32255. I was thinking we can periodically run. The current PR mimics our default PR builder behaviour for now. There was a problem hiding this comment. We can change hive and hadoop profile on Jenkins test by changing the PR title. I think it is not possible with Github Actions? There was a problem hiding this comment. Yeah, I think this isn't possible at this moment. It would be great if we can figure out a way to do it. |
||
| # 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 | ||
| - |- | ||
| pyspark-sql, pyspark-mllib, pyspark-resource | ||
| - |- | ||
| pyspark-core, pyspark-streaming, pyspark-ml | ||
| - |- | ||
| sparkr | ||
| # 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: hadoop3.2 | ||
| hive: hive2.3 | ||
| included-tags: org.apache.spark.tags.SlowHiveTest | ||
| comment: "- slow tests" | ||
| - modules: hive | ||
| java: 1.8 | ||
| hadoop: hadoop3.2 | ||
| hive: hive2.3 | ||
| excluded-tags: org.apache.spark.tags.SlowHiveTest | ||
| comment: "- other tests" | ||
| # SQL tests | ||
| - modules: sql | ||
| java: 1.8 | ||
| hadoop: hadoop3.2 | ||
| hive: hive2.3 | ||
| included-tags: org.apache.spark.tags.ExtendedSQLTest | ||
| comment: "- slow tests" | ||
| - modules: sql | ||
| java: 1.8 | ||
| hadoop: hadoop3.2 | ||
| hive: hive2.3 | ||
| excluded-tags: org.apache.spark.tags.ExtendedSQLTest | ||
| comment: "- other tests" | ||
| env: | ||
| TEST_ONLY_MODULES: ${{ matrix.modules }} | ||
| TEST_ONLY_EXCLUDED_TAGS: ${{ matrix.excluded-tags }} | ||
| TEST_ONLY_INCLUDED_TAGS: ${{ matrix.included-tags }} | ||
| HADOOP_PROFILE: ${{ matrix.hadoop }} | ||
| HIVE_PROFILE: ${{ matrix.hive }} | ||
| # GitHub Actions' default miniconda to use in pip packaging test. | ||
| CONDA_PREFIX: /usr/share/miniconda | ||
| steps: | ||
| - name: Checkout Spark repository | ||
| uses: actions/checkout@v2 | ||
| # Cache local repositories. Note that GitHub Actions cache has a 2G limit. | ||
| - name: Cache Scala, SBT, Maven and Zinc | ||
| uses: actions/cache@v1 | ||
| with: | ||
| path: build | ||
| key: build-${{ 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 | ||
| # SQL component also has Python related tests, for example, IntegratedUDFTestUtils. | ||
| # Note that order of Python installations here matters because default python3 is | ||
| # overridden by pypy3. | ||
| uses: actions/setup-python@v2 | ||
| if: contains(matrix.modules, 'pyspark') || (contains(matrix.modules, 'sql') && !contains(matrix.modules, 'sql-')) | ||
| with: | ||
| python-version: pypy3 | ||
| architecture: x64 | ||
| - name: Install Python 2.7 | ||
| uses: actions/setup-python@v2 | ||
| if: contains(matrix.modules, 'pyspark') || (contains(matrix.modules, 'sql') && !contains(matrix.modules, 'sql-')) | ||
| with: | ||
| python-version: 2.7 | ||
| architecture: x64 | ||
| - name: Install Python 3.6 | ||
| uses: actions/setup-python@v2 | ||
| if: contains(matrix.modules, 'pyspark') || (contains(matrix.modules, 'sql') && !contains(matrix.modules, 'sql-')) | ||
| with: | ||
| python-version: 3.6 | ||
| architecture: x64 | ||
| - name: Install Python packages | ||
| if: contains(matrix.modules, 'pyspark') || (contains(matrix.modules, 'sql') && !contains(matrix.modules, 'sql-')) | ||
| # PyArrow is not supported in PyPy yet, see ARROW-2651. | ||
| # TODO(SPARK-32247): scipy installation with PyPy fails for an unknown reason. | ||
| run: | | ||
| python3 -m pip install numpy pyarrow pandas scipy | ||
| python3 -m pip list | ||
| python2 -m pip install numpy pyarrow pandas scipy | ||
dongjoon-hyun marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| python2 -m pip list | ||
| pypy3 -m pip install numpy pandas | ||
| pypy3 -m pip list | ||
| # SparkR | ||
| - name: Install R 3.6 | ||
| uses: r-lib/actions/setup-r@v1 | ||
| if: contains(matrix.modules, 'sparkr') | ||
| with: | ||
| r-version: 3.6 | ||
| - name: Install R packages | ||
| if: contains(matrix.modules, 'sparkr') | ||
| run: | | ||
| sudo apt-get install -y libcurl4-openssl-dev | ||
| 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: ${{ matrix.modules }}" | ||
| run: | | ||
| # Hive tests become flaky when running in parallel as it's too intensive. | ||
| if [[ "$TEST_ONLY_MODULES" == "hive" ]]; then export SERIAL_SBT_TESTS=1; fi | ||
| mkdir -p ~/.m2 | ||
| ./dev/run-tests --parallelism 2 | ||
| rm -rf ~/.m2/repository/org/apache/spark | ||
|
|
||
| # 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 3.6 | ||
| uses: r-lib/actions/setup-r@v1 | ||
| with: | ||
| r-version: 3.6 | ||
| - 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 rouge | ||
| 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 | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,30 @@ | ||
| /* | ||
| * 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. | ||
| */ | ||
|
|
||
| package org.apache.spark.tags; | ||
|
|
||
| import org.scalatest.TagAnnotation; | ||
|
|
||
| import java.lang.annotation.ElementType; | ||
| import java.lang.annotation.Retention; | ||
| import java.lang.annotation.RetentionPolicy; | ||
| import java.lang.annotation.Target; | ||
|
|
||
| @TagAnnotation | ||
| @Retention(RetentionPolicy.RUNTIME) | ||
| @Target({ElementType.METHOD, ElementType.TYPE}) | ||
| public @interface SlowHiveTest { } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.