AnfengYuan created SPARK-16168:
----------------------------------
Summary: Spark sql can not read ORC table
Key: SPARK-16168
URL: https://issues.apache.org/jira/browse/SPARK-16168
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 2.0.0, 2.0.1, 2.1.0
Reporter: AnfengYuan
When using spark-sql shell to query orc table, exceptions are thrown:
My table was generated by the tool in
https://github.com/hortonworks/hive-testbench
{code}
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1429)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1417)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1416)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1416)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at scala.Option.foreach(Option.scala:257)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1638)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1597)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1586)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1872)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1885)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1898)
at
org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:347)
at
org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:39)
at
org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:310)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$hiveResultString$3.apply(QueryExecution.scala:131)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$hiveResultString$3.apply(QueryExecution.scala:130)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
at
org.apache.spark.sql.execution.QueryExecution.hiveResultString(QueryExecution.scala:130)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:63)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:323)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:239)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:729)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:185)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:210)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:124)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.IllegalArgumentException: Field "i_item_sk" does not exist.
at
org.apache.spark.sql.types.StructType$$anonfun$fieldIndex$1.apply(StructType.scala:254)
at
org.apache.spark.sql.types.StructType$$anonfun$fieldIndex$1.apply(StructType.scala:254)
at scala.collection.MapLike$class.getOrElse(MapLike.scala:128)
at scala.collection.AbstractMap.getOrElse(Map.scala:59)
at
org.apache.spark.sql.types.StructType.fieldIndex(StructType.scala:253)
at
org.apache.spark.sql.hive.orc.OrcRelation$$anonfun$10.apply(OrcFileFormat.scala:379)
at
org.apache.spark.sql.hive.orc.OrcRelation$$anonfun$10.apply(OrcFileFormat.scala:379)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at org.apache.spark.sql.types.StructType.foreach(StructType.scala:95)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at org.apache.spark.sql.types.StructType.map(StructType.scala:95)
at
org.apache.spark.sql.hive.orc.OrcRelation$.setRequiredColumns(OrcFileFormat.scala:379)
at
org.apache.spark.sql.hive.orc.OrcFileFormat$$anonfun$buildReader$2.apply(OrcFileFormat.scala:135)
at
org.apache.spark.sql.hive.orc.OrcFileFormat$$anonfun$buildReader$2.apply(OrcFileFormat.scala:124)
at
org.apache.spark.sql.execution.datasources.FileFormat$$anon$1.apply(fileSourceInterfaces.scala:293)
at
org.apache.spark.sql.execution.datasources.FileFormat$$anon$1.apply(fileSourceInterfaces.scala:277)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:114)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:91)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:370)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:246)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:240)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:780)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:780)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:283)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
at org.apache.spark.scheduler.Task.run(Task.scala:85)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
{code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
