[SPARK-34927][INFRA] Support TPCDSQueryBenchmark in Benchmarks

.github/workflows/benchmark.yml

@@ -56,9 +56,64 @@ jobs:
       id: set-matrix
       run: echo "::set-output name=matrix::["`seq -s, 1 $SPARK_BENCHMARK_NUM_SPLITS`"]"
 
+  # Any TPC-DS related updates on this job need to be applied to tpcds-1g job of build_and_test.yml as well
+  tpcds-1g-gen:
+    name: "Generate an input dataset for TPCDSQueryBenchmark with SF=1"
+    runs-on: ubuntu-20.04
+    env:
+      SPARK_LOCAL_IP: localhost
+    steps:
+      - name: Checkout Spark repository
+        uses: actions/checkout@v2
+        # In order to get diff files
+        with:
+          fetch-depth: 0
+      - name: Cache Scala, SBT and Maven
+        uses: actions/cache@v2
+        with:
+          path: |
+            build/apache-maven-*
+            build/scala-*
+            build/*.jar
+            ~/.sbt
+          key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
+          restore-keys: |
+            build-
+      - name: Cache Coursier local repository
+        uses: actions/cache@v2
+        with:
+          path: ~/.cache/coursier
+          key: benchmark-coursier-${{ github.event.inputs.jdk }}-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+          restore-keys: |
+            benchmark-coursier-${{ github.event.inputs.jdk }}
+      - name: Cache TPC-DS generated data
+        id: cache-tpcds-sf-1
+        uses: actions/cache@v2
+        with:
+          path: ./tpcds-sf-1
+          key: tpcds-${{ hashFiles('.github/workflows/benchmark.yml', 'sql/core/src/test/scala/org/apache/spark/sql/TPCDSSchema.scala') }}
+      - name: Checkout tpcds-kit repository
+        if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
+        uses: actions/checkout@v2
+        with:
+          repository: databricks/tpcds-kit
+          ref: 2a5078a782192ddb6efbcead8de9973d6ab4f069
+          path: ./tpcds-kit
+      - name: Build tpcds-kit
+        if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
+        run: cd tpcds-kit/tools && make OS=LINUX
+      - name: Install Java ${{ github.event.inputs.jdk }}
+        if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
+        uses: actions/setup-java@v1
+        with:
+          java-version: ${{ github.event.inputs.jdk }}
+      - name: Generate TPC-DS (SF=1) table data
+        if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
+        run: build/sbt "sql/test:runMain org.apache.spark.sql.GenTPCDSData --dsdgenDir `pwd`/tpcds-kit/tools --location `pwd`/tpcds-sf-1 --scaleFactor 1 --numPartitions 1 --overwrite"
+
   benchmark:
     name: "Run benchmarks: ${{ github.event.inputs.class }} (JDK ${{ github.event.inputs.jdk }}, Scala ${{ github.event.inputs.scala }}, ${{ matrix.split }} out of ${{ github.event.inputs.num-splits }} splits)"
-    needs: matrix-gen
+    needs: [matrix-gen, tpcds-1g-gen]
     # Ubuntu 20.04 is the latest LTS. The next LTS is 22.04.
     runs-on: ubuntu-20.04
     strategy:
@@ -73,6 +128,7 @@ jobs:
       SPARK_LOCAL_IP: localhost
       # To prevent spark.test.home not being set. See more detail in SPARK-36007.
       SPARK_HOME: ${{ github.workspace }}
+      SPARK_TPCDS_DATA: ${{ github.workspace }}/tpcds-sf-1
     steps:
     - name: Checkout Spark repository
       uses: actions/checkout@v2
@@ -101,6 +157,12 @@ jobs:
       uses: actions/setup-java@v1
       with:
         java-version: ${{ github.event.inputs.jdk }}
+    - name: Cache TPC-DS generated data
+      id: cache-tpcds-sf-1
+      uses: actions/cache@v2
+      with:
+        path: ./tpcds-sf-1
+        key: tpcds-${{ hashFiles('.github/workflows/benchmark.yml', 'sql/core/src/test/scala/org/apache/spark/sql/TPCDSSchema.scala') }}
     - name: Run benchmarks
       run: |
         dev/change-scala-version.sh ${{ github.event.inputs.scala }}
@@ -119,7 +181,7 @@ jobs:
         # To keep the directory structure and file permissions, tar them
         # See also https://github.com/actions/upload-artifact#maintaining-file-permissions-and-case-sensitive-files
         echo "Preparing the benchmark results:"
-        tar -cvf benchmark-results-${{ github.event.inputs.jdk }}-${{ github.event.inputs.scala }}.tar `git diff --name-only` `git ls-files --others --exclude-standard`
+        tar -cvf benchmark-results-${{ github.event.inputs.jdk }}-${{ github.event.inputs.scala }}.tar `git diff --name-only` `git ls-files --others --exclude=tpcds-sf-1 --exclude-standard`
     - name: Upload benchmark results
       uses: actions/upload-artifact@v2
       with:

.github/workflows/build_and_test.yml

@@ -635,6 +635,7 @@ jobs:
         ./dev/change-scala-version.sh 2.13
         ./build/sbt -Pyarn -Pmesos -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Pkinesis-asl -Pdocker-integration-tests -Pkubernetes-integration-tests -Pspark-ganglia-lgpl -Pscala-2.13 compile test:compile
 
+  # Any TPC-DS related updates on this job need to be applied to tpcds-1g-gen job of benchmark.yml as well
   tpcds-1g:
     needs: precondition
     if: fromJson(needs.precondition.outputs.required).tpcds-1g == 'true'

core/src/test/scala/org/apache/spark/benchmark/Benchmarks.scala

@@ -96,8 +96,6 @@ object Benchmarks {
       require(args.length > 0, "Benchmark class to run should be specified.")
       if (
           info.getName.endsWith("Benchmark") &&
-          // TODO(SPARK-34927): Support TPCDSQueryBenchmark in Benchmarks
-          !info.getName.endsWith("TPCDSQueryBenchmark") &&
           matcher.matches(Paths.get(info.getName)) &&
           Try(runBenchmark).isSuccess && // Does this has a main method?
           !Modifier.isAbstract(clazz.getModifiers) // Is this a regular class?