[SPARK-34795][SPARK-35192][SPARK-35293][SPARK-35327][SQL][TESTS][3.1]…

… Adds a new job in GitHub Actions to check the output of TPC-DS queries ### What changes were proposed in this pull request? This PR proposes to add a new job in GitHub Actions to check the output of TPC-DS queries. NOTE: To generate TPC-DS table data in GA jobs, this PR includes generator code implemented in apache#32243 and apache#32460. This is the backport PR of apache#31886. ### Why are the changes needed? There are some cases where we noticed runtime-realted bugs after merging commits (e.g. .SPARK-33822). Therefore, I think it is worth adding a new job in GitHub Actions to check query output of TPC-DS (sf=1). ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? The new test added. Closes apache#32462 from maropu/TPCDSQUeryTestSuite-Branch3.1. Authored-by: Takeshi Yamamuro <yamamuro@apache.org> Signed-off-by: Dongjoon Hyun <dongjoon@apache.org>
flyrain · May 9, 2021 · 98674aa · 98674aa
1 parent 373454a
commit 98674aa
Show file tree

Hide file tree

Showing 140 changed files with 18,614 additions and 579 deletions.
diff --git a/.github/workflows/build_and_test.yml b/.github/workflows/build_and_test.yml
@@ -434,3 +434,67 @@ jobs:
     - name: Build with SBT
       run: |
         ./build/sbt -Pyarn -Pmesos -Pkubernetes -Phive -Phive-thriftserver -Phadoop-cloud -Pkinesis-asl -Phadoop-2.7 compile test:compile
+
+  tpcds-1g:
+    name: Run TPC-DS queries with SF=1
+    runs-on: ubuntu-20.04
+    env:
+      SPARK_LOCAL_IP: localhost
+    steps:
+    - name: Checkout Spark repository
+      uses: actions/checkout@v2
+    - name: Cache Scala, SBT and Maven
+      uses: actions/cache@v2
+      with:
+        path: |
+          build/apache-maven-*
+          build/scala-*
+          build/*.jar
+          ~/.sbt
+        key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
+        restore-keys: |
+          build-
+    - name: Cache Coursier local repository
+      uses: actions/cache@v2
+      with:
+        path: ~/.cache/coursier
+        key: tpcds-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
+        restore-keys: |
+          tpcds-coursier-
+    - name: Install Java 8
+      uses: actions/setup-java@v1
+      with:
+        java-version: 8
+    - 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/build_and_test.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
+        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: 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"
+    - name: Run TPC-DS queries
+      run: |
+        SPARK_TPCDS_DATA=`pwd`/tpcds-sf-1 build/sbt "sql/testOnly org.apache.spark.sql.TPCDSQueryTestSuite"
+    - name: Upload test results to report
+      if: always()
+      uses: actions/upload-artifact@v2
+      with:
+        name: test-results-tpcds--8-hadoop3.2-hive2.3
+        path: "**/target/test-reports/*.xml"
+    - name: Upload unit tests log files
+      if: failure()
+      uses: actions/upload-artifact@v2
+      with:
+        name: unit-tests-log-tpcds--8-hadoop3.2-hive2.3
+        path: "**/target/unit-tests.log"
diff --git a/sql/core/src/test/resources/tpcds-query-results/v1_4/q1.sql.out b/sql/core/src/test/resources/tpcds-query-results/v1_4/q1.sql.out
@@ -0,0 +1,105 @@
+-- Automatically generated by TPCDSQueryTestSuite
+
+-- !query schema
+struct<c_customer_id:string>
+-- !query output
+AAAAAAAAAAABAAAA
+AAAAAAAAAAAHBAAA
+AAAAAAAAAAAMAAAA
+AAAAAAAAAAAOAAAA
+AAAAAAAAAABCBAAA
+AAAAAAAAAABEAAAA
+AAAAAAAAAABFAAAA
+AAAAAAAAAACFBAAA
+AAAAAAAAAACFBAAA
+AAAAAAAAAADBBAAA
+AAAAAAAAAADOAAAA
+AAAAAAAAAADPAAAA
+AAAAAAAAAAEABAAA
+AAAAAAAAAAEEAAAA
+AAAAAAAAAAEGBAAA
+AAAAAAAAAAENAAAA
+AAAAAAAAAAFCBAAA
+AAAAAAAAAAFEBAAA
+AAAAAAAAAAFGAAAA
+AAAAAAAAAAFLAAAA
+AAAAAAAAAAFPAAAA
+AAAAAAAAAAGCAAAA
+AAAAAAAAAAGEAAAA
+AAAAAAAAAAGIBAAA
+AAAAAAAAAAGOAAAA
+AAAAAAAAAAHABAAA
+AAAAAAAAAAHGBAAA
+AAAAAAAAAAHHAAAA
+AAAAAAAAAAHMAAAA
+AAAAAAAAAAHPAAAA
+AAAAAAAAAAHPAAAA
+AAAAAAAAAAHPAAAA
+AAAAAAAAAAJAAAAA
+AAAAAAAAAAJEBAAA
+AAAAAAAAAAJMAAAA
+AAAAAAAAAAJPAAAA
+AAAAAAAAAAKBBAAA
+AAAAAAAAAAKGBAAA
+AAAAAAAAAAKHBAAA
+AAAAAAAAAAKLAAAA
+AAAAAAAAAALCAAAA
+AAAAAAAAAALJAAAA
+AAAAAAAAAALJAAAA
+AAAAAAAAAAMABAAA
+AAAAAAAAAAMGAAAA
+AAAAAAAAAAMLAAAA
+AAAAAAAAAAMMAAAA
+AAAAAAAAAANHBAAA
+AAAAAAAAAANMAAAA
+AAAAAAAAAAOBBAAA
+AAAAAAAAAAPDAAAA
+AAAAAAAAAAPKAAAA
+AAAAAAAAAAPLAAAA
+AAAAAAAAABANAAAA
+AAAAAAAAABCCBAAA
+AAAAAAAAABCGAAAA
+AAAAAAAAABDABAAA
+AAAAAAAAABDBAAAA
+AAAAAAAAABDEAAAA
+AAAAAAAAABDEBAAA
+AAAAAAAAABDEBAAA
+AAAAAAAAABDFBAAA
+AAAAAAAAABDOAAAA
+AAAAAAAAABDOAAAA
+AAAAAAAAABEBBAAA
+AAAAAAAAABEDAAAA
+AAAAAAAAABEEAAAA
+AAAAAAAAABEEBAAA
+AAAAAAAAABEIBAAA
+AAAAAAAAABEOAAAA
+AAAAAAAAABFFBAAA
+AAAAAAAAABFHAAAA
+AAAAAAAAABFNAAAA
+AAAAAAAAABFOAAAA
+AAAAAAAAABGAAAAA
+AAAAAAAAABHDBAAA
+AAAAAAAAABHGAAAA
+AAAAAAAAABHGBAAA
+AAAAAAAAABHLAAAA
+AAAAAAAAABIAAAAA
+AAAAAAAAABIBAAAA
+AAAAAAAAABIDBAAA
+AAAAAAAAABIEBAAA
+AAAAAAAAABKLAAAA
+AAAAAAAAABKNAAAA
+AAAAAAAAABKNAAAA
+AAAAAAAAABLJAAAA
+AAAAAAAAABLNAAAA
+AAAAAAAAABMAAAAA
+AAAAAAAAABMEBAAA
+AAAAAAAAABMPAAAA
+AAAAAAAAABNABAAA
+AAAAAAAAABNBAAAA
+AAAAAAAAABNEAAAA
+AAAAAAAAABNEAAAA
+AAAAAAAAABNGAAAA
+AAAAAAAAABNNAAAA
+AAAAAAAAABOEAAAA
+AAAAAAAAABOGBAAA
+AAAAAAAAABPABAAA
diff --git a/sql/core/src/test/resources/tpcds-query-results/v1_4/q10.sql.out b/sql/core/src/test/resources/tpcds-query-results/v1_4/q10.sql.out
@@ -0,0 +1,11 @@
+-- Automatically generated by TPCDSQueryTestSuite
+
+-- !query schema
+struct<cd_gender:string,cd_marital_status:string,cd_education_status:string,cnt1:bigint,cd_purchase_estimate:int,cnt2:bigint,cd_credit_rating:string,cnt3:bigint,cd_dep_count:int,cnt4:bigint,cd_dep_employed_count:int,cnt5:bigint,cd_dep_college_count:int,cnt6:bigint>
+-- !query output
+F	W	4 yr Degree         	1	4000	1	Low Risk  	1	4	1	6	1	4	1
+M	D	4 yr Degree         	1	1500	1	Low Risk  	1	3	1	4	1	2	1
+M	S	College             	1	4500	1	High Risk 	1	3	1	4	1	3	1
+M	S	Primary             	1	9500	1	Low Risk  	1	3	1	0	1	6	1
+M	S	Secondary           	1	3000	1	High Risk 	1	1	1	1	1	4	1
+M	U	4 yr Degree         	1	2000	1	Low Risk  	1	3	1	1	1	3	1
diff --git a/sql/core/src/test/resources/tpcds-query-results/v1_4/q11.sql.out b/sql/core/src/test/resources/tpcds-query-results/v1_4/q11.sql.out
@@ -0,0 +1,99 @@
+-- Automatically generated by TPCDSQueryTestSuite
+
+-- !query schema
+struct<customer_preferred_cust_flag:string>
+-- !query output
+NULL
+NULL
+NULL
+NULL
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+N
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y
+Y