I'm trying to run the following test at scale:
test("RawData read") {
val typp = ""
val spark = SparkSession.builder().master("local[1]").appName("SparkByExamples.com").getOrCreate()
val actual = new DataReader(spark, typp).readRawData("./src/test/resources/input/parquet/part-00000-512bb01c-ef7a-4760-bfe9-905f504e4840.c000.snappy.parquet")
actual.coalesce(1).limit(100).write.mode(SaveMode.Overwrite).save("./src/test/resources/output/")
import sqlContext.implicits._
val expected: Dataset[RawData] = spark
.read
.parquet("./src/test/resources/output/")
.map(row => RawData(
row.getString(0),
row.getDouble(1),
row.getInt(2),
row.getString(3),
row.getDouble(4),
row.getLong(5),
row.getString(6)
))
assert(actual.limit(100).collectAsList() === expected.collectAsList())
}
The error that I recive is this:
Error while instantiating 'org.apache.spark.sql.hive.HiveSessionStateBuilder': java.lang.IllegalArgumentException: Error while instantiating 'org.apache.spark.sql.hive.HiveSessionStateBuilder': at org.apache.spark.sql.SparkSession$.org$apache$spark$sql$SparkSession$$instantiateSessionState(SparkSession.scala:1062) at org.apache.spark.sql.SparkSession$$anonfun$sessionState$2.apply(SparkSession.scala:137) at org.apache.spark.sql.SparkSession$$anonfun$sessionState$2.apply(SparkSession.scala:136) at scala.Option.getOrElse(Option.scala:121) at org.apache.spark.sql.SparkSession.sessionState$lzycompute(SparkSession.scala:136) at org.apache.spark.sql.SparkSession.sessionState(SparkSession.scala:133) at org.apache.spark.sql.SparkSession$Builder$$anonfun$getOrCreate$3.apply(SparkSession.scala:902) at org.apache.spark.sql.SparkSession$Builder$$anonfun$getOrCreate$3.apply(SparkSession.scala:902) at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:130) at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:130) at scala.collection.mutable.HashTable$class.foreachEntry(HashTable.scala:236) at scala.collection.mutable.HashMap.foreachEntry(HashMap.scala:40) at scala.collection.mutable.HashMap.foreach(HashMap.scala:130) at org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:902) at eu.man.bigdata.commons.importer.DataReaderTest$$anonfun$2.apply(DataReaderTest.scala:23) at eu.man.bigdata.commons.importer.DataReaderTest$$anonfun$2.apply(DataReaderTest.scala:21) at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85) at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104) at org.scalatest.Transformer.apply(Transformer.scala:22) at org.scalatest.Transformer.apply(Transformer.scala:20) at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:186) at org.scalatest.TestSuite$class.withFixture(TestSuite.scala:196) at org.scalatest.FunSuite.withFixture(FunSuite.scala:1560) at org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:183) at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:196) at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:196) at org.scalatest.SuperEngine.runTestImpl(Engine.scala:289) at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:196) at eu.man.bigdata.commons.importer.DataReaderTest.org$scalatest$BeforeAndAfterEach$$super$runTest(DataReaderTest.scala:13) at org.scalatest.BeforeAndAfterEach$class.runTest(BeforeAndAfterEach.scala:221) at eu.man.bigdata.commons.importer.DataReaderTest.runTest(DataReaderTest.scala:13) at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:229) at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:229) at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:396) at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:384) at scala.collection.immutable.List.foreach(List.scala:392) at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:384) at org.scalatest.SuperEngine.org$scalatest$SuperEngine$$runTestsInBranch(Engine.scala:379) at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:461) at org.scalatest.FunSuiteLike$class.runTests(FunSuiteLike.scala:229) at org.scalatest.FunSuite.runTests(FunSuite.scala:1560) at org.scalatest.Suite$class.run(Suite.scala:1147) at org.scalatest.FunSuite.org$scalatest$FunSuiteLike$$super$run(FunSuite.scala:1560) at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:233) at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:233) at org.scalatest.SuperEngine.runImpl(Engine.scala:521) at org.scalatest.FunSuiteLike$class.run(FunSuiteLike.scala:233) at eu.man.bigdata.commons.importer.DataReaderTest.org$scalatest$BeforeAndAfterAll$$super$run(DataReaderTest.scala:13) at org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:213) at org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:210) at eu.man.bigdata.commons.importer.DataReaderTest.run(DataReaderTest.scala:13) at org.scalatest.tools.SuiteRunner.run(SuiteRunner.scala:45) at org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$1.apply(Runner.scala:1346) at org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$1.apply(Runner.scala:1340) at scala.collection.immutable.List.foreach(List.scala:392) at org.scalatest.tools.Runner$.doRunRunRunDaDoRunRun(Runner.scala:1340) at org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1011) at org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1010) at org.scalatest.tools.Runner$.withClassLoaderAndDispatchReporter(Runner.scala:1506) at org.scalatest.tools.Runner$.runOptionallyWithPassFailReporter(Runner.scala:1010) at org.scalatest.tools.Runner$.run(Runner.scala:850) at org.scalatest.tools.Runner.run(Runner.scala) at org.jetbrains.plugins.scala.testingSupport.scalaTest.ScalaTestRunner.runScalaTest2or3(ScalaTestRunner.java:38) at org.jetbrains.plugins.scala.testingSupport.scalaTest.ScalaTestRunner.main(ScalaTestRunner.java:25) Caused by: org.apache.spark.sql.AnalysisException: java.lang.RuntimeException: java.lang.RuntimeException: The root scratch dir: /tmp/hive on HDFS should be writable. Current permissions are: rw-rw-rw-; at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:106) at org.apache.spark.sql.hive.HiveExternalCatalog.databaseExists(HiveExternalCatalog.scala:194) at org.apache.spark.sql.internal.SharedState.externalCatalog$lzycompute(SharedState.scala:105) at org.apache.spark.sql.internal.SharedState.externalCatalog(SharedState.scala:93) at org.apache.spark.sql.hive.HiveSessionStateBuilder.externalCatalog(HiveSessionStateBuilder.scala:39) at org.apache.spark.sql.hive.HiveSessionStateBuilder.catalog$lzycompute(HiveSessionStateBuilder.scala:54) at org.apache.spark.sql.hive.HiveSessionStateBuilder.catalog(HiveSessionStateBuilder.scala:52) at org.apache.spark.sql.hive.HiveSessionStateBuilder.catalog(HiveSessionStateBuilder.scala:35) at org.apache.spark.sql.internal.BaseSessionStateBuilder.build(BaseSessionStateBuilder.scala:289) at org.apache.spark.sql.SparkSession$.org$apache$spark$sql$SparkSession$$instantiateSessionState(SparkSession.scala:1059) ... 63 more Caused by: java.lang.RuntimeException: java.lang.RuntimeException: The root scratch dir: /tmp/hive on HDFS should be writable. Current permissions are: rw-rw-rw- at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:522) at org.apache.spark.sql.hive.client.HiveClientImpl.(HiveClientImpl.scala:191) at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62) at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) at java.lang.reflect.Constructor.newInstance(Constructor.java:423) at org.apache.spark.sql.hive.client.IsolatedClientLoader.createClient(IsolatedClientLoader.scala:264) at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:362) at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:266) at org.apache.spark.sql.hive.HiveExternalCatalog.client$lzycompute(HiveExternalCatalog.scala:66) at org.apache.spark.sql.hive.HiveExternalCatalog.client(HiveExternalCatalog.scala:65) at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply$mcZ$sp(HiveExternalCatalog.scala:195) at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply(HiveExternalCatalog.scala:195) at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply(HiveExternalCatalog.scala:195) at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:97) ... 72 more Caused by: java.lang.RuntimeException: The root scratch dir: /tmp/hive on HDFS should be writable. Current permissions are: rw-rw-rw- at org.apache.hadoop.hive.ql.session.SessionState.createRootHDFSDir(SessionState.java:612) at org.apache.hadoop.hive.ql.session.SessionState.createSessionDirs(SessionState.java:554) at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:508) ... 86 more
I'm using sbt version 1.0.3, I have tried many of the solutions posed in the various questions related to this problem but nothing has worked