You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Sean Owen (JIRA)" <ji...@apache.org> on 2015/04/26 00:00:38 UTC
[jira] [Updated] (SPARK-5498) [SPARK-SQL]when the partition schema
does not match table schema,it throws java.lang.ClassCastException and so
on
[ https://issues.apache.org/jira/browse/SPARK-5498?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sean Owen updated SPARK-5498:
-----------------------------
Assignee: jeanlyn
> [SPARK-SQL]when the partition schema does not match table schema,it throws java.lang.ClassCastException and so on
> -----------------------------------------------------------------------------------------------------------------
>
> Key: SPARK-5498
> URL: https://issues.apache.org/jira/browse/SPARK-5498
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.2.0
> Reporter: jeanlyn
> Assignee: jeanlyn
> Fix For: 1.4.0
>
>
> when the partition schema does not match table schema,it will thows exception when the task is running.For example,we modify the type of column from int to bigint by the sql *ALTER TABLE table_with_partition CHANGE COLUMN key key BIGINT* ,then we query the patition data which was stored before the changing,we would get the exception:
> {noformat}
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 27.0 failed 4 times, most recent failure: Lost task 0.3 in stage 27.0 (TID 30, BJHC-HADOOP-HERA-16950.jeanlyn.local): java.lang.ClassCastException: org.apache.spark.sql.catalyst.expressions.MutableLong cannot be cast to org.apache.spark.sql.catalyst.expressions.MutableInt
> at org.apache.spark.sql.catalyst.expressions.SpecificMutableRow.setInt(SpecificMutableRow.scala:241)
> at org.apache.spark.sql.hive.HadoopTableReader$$anonfun$13$$anonfun$apply$4.apply(TableReader.scala:286)
> at org.apache.spark.sql.hive.HadoopTableReader$$anonfun$13$$anonfun$apply$4.apply(TableReader.scala:286)
> at org.apache.spark.sql.hive.HadoopTableReader$$anonfun$fillObject$1.apply(TableReader.scala:322)
> at org.apache.spark.sql.hive.HadoopTableReader$$anonfun$fillObject$1.apply(TableReader.scala:314)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$10.next(Iterator.scala:312)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.sql.execution.Limit$$anonfun$4.apply(basicOperators.scala:141)
> at org.apache.spark.sql.execution.Limit$$anonfun$4.apply(basicOperators.scala:141)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1314)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1314)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
> at org.apache.spark.scheduler.Task.run(Task.scala:56)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
> at java.util.concurrent.ThreadPoolExecutor$Worker.runTask(ThreadPoolExecutor.java:886)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:908)
> at java.lang.Thread.run(Thread.java:662)
> Driver stacktrace:
> at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1214)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1203)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1202)
> at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1202)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
> at scala.Option.foreach(Option.scala:236)
> at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:696)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1420)
> at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessActor.aroundReceive(DAGScheduler.scala:1375)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
> at akka.actor.ActorCell.invoke(ActorCell.scala:487)
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:238)
> at akka.dispatch.Mailbox.run(Mailbox.scala:220)
> at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:393)
> at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
> at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
> at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
> at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
> {noformat}
> we can reproduce the bug as follow:
> add the code to the unit test *sql/hive/src/test/scala/org/apache/spark/sql/hive/InsertIntoHiveTableSuite.scala*
> {noformat}
> test("partition schema does not match table schema"){
> val testData = TestHive.sparkContext.parallelize(
> (1 to 10).map(i => TestData(i, i.toString)))
> testData.registerTempTable("testData")
> val tmpDir = Files.createTempDir()
> sql(s"CREATE TABLE table_with_partition(key int,value string) PARTITIONED by (ds string) location '${tmpDir.toURI.toString}' ")
> sql("INSERT OVERWRITE TABLE table_with_partition partition (ds='1') SELECT key,value FROM testData")
> sql("ALTER TABLE table_with_partition CHANGE COLUMN key key BIGINT")
> checkAnswer(sql("select key,value from table_with_partition where ds='1' "),
> testData.toSchemaRDD.collect.toSeq
> )
> sql("DROP TABLE table_with_partition")
>
> }
> {noformat}
> run the test
> {noformat}
> mvn -Dhadoop.version=... - DwildcardSuites=org.apache.spark.sql.hive.InsertIntoHiveTableSuite test
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org