Major Description
Integration test suites in the JDBC data source (MySQLIntegration and PostgresIntegration) depend on docker-client 2.7.5, which transitively depends on Guava 17.0. Unfortunately, Guava 17.0 is causing runtime binary incompatibility issues when Spark is compiled against Hadoop 2.4.
$ ./build/sbt -Pyarn,hadoop-2.4,hive,hive-0.12.0,scala-2.10 -Dhadoop.version=2.4.1 ... > sql/test-only *.ParquetDataSourceOffIOSuite ... [info] ParquetDataSourceOffIOSuite: [info] Exception encountered when attempting to run a suite with class name: org.apache.spark.sql.parquet.ParquetDataSourceOffIOSuite *** ABORTED *** (134 milliseconds) [info] java.lang.IllegalAccessError: tried to access method com.google.common.base.Stopwatch.<init>()V from class org.apache.hadoop.mapreduce.lib.input.FileInputFormat [info] at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.listStatus(FileInputFormat.java:261) [info] at parquet.hadoop.ParquetInputFormat.listStatus(ParquetInputFormat.java:277) [info] at org.apache.spark.sql.parquet.FilteringParquetRowInputFormat.getSplits(ParquetTableOperations.scala:437) [info] at org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:95) [info] at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219) [info] at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217) [info] at scala.Option.getOrElse(Option.scala:120) [info] at org.apache.spark.rdd.RDD.partitions(RDD.scala:217) [info] at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32) [info] at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219) [info] at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217) [info] at scala.Option.getOrElse(Option.scala:120) [info] at org.apache.spark.rdd.RDD.partitions(RDD.scala:217) [info] at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32) [info] at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219) [info] at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217) [info] at scala.Option.getOrElse(Option.scala:120) [info] at org.apache.spark.rdd.RDD.partitions(RDD.scala:217) [info] at org.apache.spark.SparkContext.runJob(SparkContext.scala:1525) [info] at org.apache.spark.rdd.RDD.collect(RDD.scala:813) [info] at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:83) [info] at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:797) [info] at org.apache.spark.sql.QueryTest$.checkAnswer(QueryTest.scala:115) [info] at org.apache.spark.sql.QueryTest.checkAnswer(QueryTest.scala:60) [info] at org.apache.spark.sql.parquet.ParquetIOSuiteBase$$anonfun$checkParquetFile$1.apply(ParquetIOSuite.scala:76) [info] at org.apache.spark.sql.parquet.ParquetIOSuiteBase$$anonfun$checkParquetFile$1.apply(ParquetIOSuite.scala:76) [info] at org.apache.spark.sql.parquet.ParquetTest$$anonfun$withParquetDataFrame$1.apply(ParquetTest.scala:105) [info] at org.apache.spark.sql.parquet.ParquetTest$$anonfun$withParquetDataFrame$1.apply(ParquetTest.scala:105) [info] at org.apache.spark.sql.parquet.ParquetTest$$anonfun$withParquetFile$1.apply(ParquetTest.scala:94) [info] at org.apache.spark.sql.parquet.ParquetTest$$anonfun$withParquetFile$1.apply(ParquetTest.scala:92) [info] at org.apache.spark.sql.parquet.ParquetTest$class.withTempPath(ParquetTest.scala:71) [info] at org.apache.spark.sql.parquet.ParquetIOSuiteBase.withTempPath(ParquetIOSuite.scala:67) [info] at org.apache.spark.sql.parquet.ParquetTest$class.withParquetFile(ParquetTest.scala:92) [info] at org.apache.spark.sql.parquet.ParquetIOSuiteBase.withParquetFile(ParquetIOSuite.scala:67) [info] at org.apache.spark.sql.parquet.ParquetTest$class.withParquetDataFrame(ParquetTest.scala:105) [info] at org.apache.spark.sql.parquet.ParquetIOSuiteBase.withParquetDataFrame(ParquetIOSuite.scala:67) [info] at org.apache.spark.sql.parquet.ParquetIOSuiteBase.checkParquetFile(ParquetIOSuite.scala:76) [info] at org.apache.spark.sql.parquet.ParquetIOSuiteBase$$anonfun$1.apply$mcV$sp(ParquetIOSuite.scala:83) [info] at org.apache.spark.sql.parquet.ParquetIOSuiteBase$$anonfun$1.apply(ParquetIOSuite.scala:79) [info] at org.apache.spark.sql.parquet.ParquetIOSuiteBase$$anonfun$1.apply(ParquetIOSuite.scala:79) [info] at org.scalatest.Transformer$$anonfun$apply$1.apply$mcV$sp(Transformer.scala:22) [info] at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85) [info] at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104) [info] at org.scalatest.Transformer.apply(Transformer.scala:22) [info] at org.scalatest.Transformer.apply(Transformer.scala:20) [info] at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:166) [info] at org.scalatest.Suite$class.withFixture(Suite.scala:1122) [info] at org.scalatest.FunSuite.withFixture(FunSuite.scala:1555) [info] at org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:163) [info] at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175) [info] at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175) [info] at org.scalatest.SuperEngine.runTestImpl(Engine.scala:306) [info] at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:175) [info] at org.scalatest.FunSuite.runTest(FunSuite.scala:1555) [info] at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:208) [info] at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:208) [info] at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:413) [info] at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:401) [info] at scala.collection.immutable.List.foreach(List.scala:318) [info] at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:401) [info] at org.scalatest.SuperEngine.org$scalatest$SuperEngine$$runTestsInBranch(Engine.scala:396) [info] at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:483) [info] at org.scalatest.FunSuiteLike$class.runTests(FunSuiteLike.scala:208) [info] at org.scalatest.FunSuite.runTests(FunSuite.scala:1555) [info] at org.scalatest.Suite$class.run(Suite.scala:1424) [info] at org.scalatest.FunSuite.org$scalatest$FunSuiteLike$$super$run(FunSuite.scala:1555) [info] at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:212) [info] at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:212) [info] at org.scalatest.SuperEngine.runImpl(Engine.scala:545) [info] at org.scalatest.FunSuiteLike$class.run(FunSuiteLike.scala:212) [info] at org.apache.spark.sql.parquet.ParquetDataSourceOffIOSuite.org$scalatest$BeforeAndAfterAll$$super$run(ParquetIOSuite.scala:346) [info] at org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:257) [info] at org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:256) [info] at org.apache.spark.sql.parquet.ParquetDataSourceOffIOSuite.run(ParquetIOSuite.scala:346) [info] at org.scalatest.tools.Framework.org$scalatest$tools$Framework$$runSuite(Framework.scala:462) [info] at org.scalatest.tools.Framework$ScalaTestTask.execute(Framework.scala:671) [info] at sbt.ForkMain$Run$2.call(ForkMain.java:294) [info] at sbt.ForkMain$Run$2.call(ForkMain.java:284) [info] at java.util.concurrent.FutureTask.run(FutureTask.java:266) [info] at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) [info] at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) [info] at java.lang.Thread.run(Thread.java:745)
This is because the default constructor of Stopwatch is no longer public in Guava 17.0.
Compiling Spark against Hive 0.12.0 also introduces other types of runtime binary incompatibility issue.
Considering MySQLIntegration and PostgresIntegration are ignored right now, I'd suggest moving them from the Spark project to the [Spark integration tests||https://github.com/databricks/spark-integration-tests] project.
