[jira] [Updated] (SPARK-15757) Error occurs when using Spark sql "select" statement on orc file after hive sql "insert overwrite tb1 select * from sourcTb" has been executed on this orc file
[ https://issues.apache.org/jira/browse/SPARK-15757?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Dongjoon Hyun updated SPARK-15757: -- Fix Version/s: 2.2.1 > Error occurs when using Spark sql "select" statement on orc file after hive > sql "insert overwrite tb1 select * from sourcTb" has been executed on this > orc file > --- > > Key: SPARK-15757 > URL: https://issues.apache.org/jira/browse/SPARK-15757 > Project: Spark > Issue Type: Bug >Affects Versions: 2.0.0 >Reporter: marymwu > Fix For: 2.2.1 > > Attachments: Result.png > > > Error occurs when using Spark sql "select" statement on orc file after hive > sql "insert overwrite tb1 select * from sourcTb" has been executed > 0: jdbc:hive2://172.19.200.158:40099/default> select * from inventory; > Error: org.apache.spark.SparkException: Job aborted due to stage failure: > Task 0 in stage 7.0 failed 8 times, most recent failure: Lost task 0.7 in > stage 7.0 (TID 2532, smokeslave5.avatar.lenovomm.com): > java.lang.IllegalArgumentException: Field "inv_date_sk" does not exist. > at > org.apache.spark.sql.types.StructType$$anonfun$fieldIndex$1.apply(StructType.scala:252) > at > org.apache.spark.sql.types.StructType$$anonfun$fieldIndex$1.apply(StructType.scala:252) > at scala.collection.MapLike$class.getOrElse(MapLike.scala:128) > at scala.collection.AbstractMap.getOrElse(Map.scala:59) > at > org.apache.spark.sql.types.StructType.fieldIndex(StructType.scala:251) > at > org.apache.spark.sql.hive.orc.OrcRelation$$anonfun$10.apply(OrcRelation.scala:361) > at > org.apache.spark.sql.hive.orc.OrcRelation$$anonfun$10.apply(OrcRelation.scala:361) > 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$class.foreach(IterableLike.scala:72) > at org.apache.spark.sql.types.StructType.foreach(StructType.scala:94) > at scala.collection.TraversableLike$class.map(TraversableLike.scala:234) > at org.apache.spark.sql.types.StructType.map(StructType.scala:94) > at > org.apache.spark.sql.hive.orc.OrcRelation$.setRequiredColumns(OrcRelation.scala:361) > at > org.apache.spark.sql.hive.orc.DefaultSource$$anonfun$buildReader$2.apply(OrcRelation.scala:123) > at > org.apache.spark.sql.hive.orc.DefaultSource$$anonfun$buildReader$2.apply(OrcRelation.scala:112) > at > org.apache.spark.sql.execution.datasources.FileFormat$$anon$1.apply(fileSourceInterfaces.scala:278) > at > org.apache.spark.sql.execution.datasources.FileFormat$$anon$1.apply(fileSourceInterfaces.scala:262) > 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$$anonfun$7$$anon$1.hasNext(WholeStageCodegenExec.scala:357) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$3.apply(SparkPlan.scala:246) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$3.apply(SparkPlan.scala:240) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$23.apply(RDD.scala:774) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$23.apply(RDD.scala:774) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:318) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:282) > at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70) > at org.apache.spark.scheduler.Task.run(Task.scala:85) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:745) > Driver stacktrace: (state=,code=0) -- This message was sent by Atlassian JIRA (v6.4.14#64029) - To u
[jira] [Updated] (SPARK-15757) Error occurs when using Spark sql "select" statement on orc file after hive sql "insert overwrite tb1 select * from sourcTb" has been executed on this orc file
[ https://issues.apache.org/jira/browse/SPARK-15757?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] marymwu updated SPARK-15757: Attachment: Result.png > Error occurs when using Spark sql "select" statement on orc file after hive > sql "insert overwrite tb1 select * from sourcTb" has been executed on this > orc file > --- > > Key: SPARK-15757 > URL: https://issues.apache.org/jira/browse/SPARK-15757 > Project: Spark > Issue Type: Bug >Affects Versions: 2.0.0 >Reporter: marymwu > Attachments: Result.png > > > Error occurs when using Spark sql "select" statement on orc file after hive > sql "insert overwrite tb1 select * from sourcTb" has been executed > 0: jdbc:hive2://172.19.200.158:40099/default> select * from inventory; > Error: org.apache.spark.SparkException: Job aborted due to stage failure: > Task 0 in stage 7.0 failed 8 times, most recent failure: Lost task 0.7 in > stage 7.0 (TID 2532, smokeslave5.avatar.lenovomm.com): > java.lang.IllegalArgumentException: Field "inv_date_sk" does not exist. > at > org.apache.spark.sql.types.StructType$$anonfun$fieldIndex$1.apply(StructType.scala:252) > at > org.apache.spark.sql.types.StructType$$anonfun$fieldIndex$1.apply(StructType.scala:252) > at scala.collection.MapLike$class.getOrElse(MapLike.scala:128) > at scala.collection.AbstractMap.getOrElse(Map.scala:59) > at > org.apache.spark.sql.types.StructType.fieldIndex(StructType.scala:251) > at > org.apache.spark.sql.hive.orc.OrcRelation$$anonfun$10.apply(OrcRelation.scala:361) > at > org.apache.spark.sql.hive.orc.OrcRelation$$anonfun$10.apply(OrcRelation.scala:361) > 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$class.foreach(IterableLike.scala:72) > at org.apache.spark.sql.types.StructType.foreach(StructType.scala:94) > at scala.collection.TraversableLike$class.map(TraversableLike.scala:234) > at org.apache.spark.sql.types.StructType.map(StructType.scala:94) > at > org.apache.spark.sql.hive.orc.OrcRelation$.setRequiredColumns(OrcRelation.scala:361) > at > org.apache.spark.sql.hive.orc.DefaultSource$$anonfun$buildReader$2.apply(OrcRelation.scala:123) > at > org.apache.spark.sql.hive.orc.DefaultSource$$anonfun$buildReader$2.apply(OrcRelation.scala:112) > at > org.apache.spark.sql.execution.datasources.FileFormat$$anon$1.apply(fileSourceInterfaces.scala:278) > at > org.apache.spark.sql.execution.datasources.FileFormat$$anon$1.apply(fileSourceInterfaces.scala:262) > 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$$anonfun$7$$anon$1.hasNext(WholeStageCodegenExec.scala:357) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$3.apply(SparkPlan.scala:246) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$3.apply(SparkPlan.scala:240) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$23.apply(RDD.scala:774) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$23.apply(RDD.scala:774) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:318) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:282) > at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70) > at org.apache.spark.scheduler.Task.run(Task.scala:85) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:745) > Driver stacktrace: (state=,code=0) -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: issues-unsubscr...@spar
[jira] [Updated] (SPARK-15757) Error occurs when using Spark sql "select" statement on orc file after hive sql "insert overwrite tb1 select * from sourcTb" has been executed on this orc file
[ https://issues.apache.org/jira/browse/SPARK-15757?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] marymwu updated SPARK-15757: Summary: Error occurs when using Spark sql "select" statement on orc file after hive sql "insert overwrite tb1 select * from sourcTb" has been executed on this orc file (was: Error occurs when using Spark sql "select" statement on orc file after hive sql "insert overwrite tb1 select * from sourcTb" has been executed) > Error occurs when using Spark sql "select" statement on orc file after hive > sql "insert overwrite tb1 select * from sourcTb" has been executed on this > orc file > --- > > Key: SPARK-15757 > URL: https://issues.apache.org/jira/browse/SPARK-15757 > Project: Spark > Issue Type: Bug >Affects Versions: 2.0.0 >Reporter: marymwu > > Error occurs when using Spark sql "select" statement on orc file after hive > sql "insert overwrite tb1 select * from sourcTb" has been executed > 0: jdbc:hive2://172.19.200.158:40099/default> select * from inventory; > Error: org.apache.spark.SparkException: Job aborted due to stage failure: > Task 0 in stage 7.0 failed 8 times, most recent failure: Lost task 0.7 in > stage 7.0 (TID 2532, smokeslave5.avatar.lenovomm.com): > java.lang.IllegalArgumentException: Field "inv_date_sk" does not exist. > at > org.apache.spark.sql.types.StructType$$anonfun$fieldIndex$1.apply(StructType.scala:252) > at > org.apache.spark.sql.types.StructType$$anonfun$fieldIndex$1.apply(StructType.scala:252) > at scala.collection.MapLike$class.getOrElse(MapLike.scala:128) > at scala.collection.AbstractMap.getOrElse(Map.scala:59) > at > org.apache.spark.sql.types.StructType.fieldIndex(StructType.scala:251) > at > org.apache.spark.sql.hive.orc.OrcRelation$$anonfun$10.apply(OrcRelation.scala:361) > at > org.apache.spark.sql.hive.orc.OrcRelation$$anonfun$10.apply(OrcRelation.scala:361) > 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$class.foreach(IterableLike.scala:72) > at org.apache.spark.sql.types.StructType.foreach(StructType.scala:94) > at scala.collection.TraversableLike$class.map(TraversableLike.scala:234) > at org.apache.spark.sql.types.StructType.map(StructType.scala:94) > at > org.apache.spark.sql.hive.orc.OrcRelation$.setRequiredColumns(OrcRelation.scala:361) > at > org.apache.spark.sql.hive.orc.DefaultSource$$anonfun$buildReader$2.apply(OrcRelation.scala:123) > at > org.apache.spark.sql.hive.orc.DefaultSource$$anonfun$buildReader$2.apply(OrcRelation.scala:112) > at > org.apache.spark.sql.execution.datasources.FileFormat$$anon$1.apply(fileSourceInterfaces.scala:278) > at > org.apache.spark.sql.execution.datasources.FileFormat$$anon$1.apply(fileSourceInterfaces.scala:262) > 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$$anonfun$7$$anon$1.hasNext(WholeStageCodegenExec.scala:357) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$3.apply(SparkPlan.scala:246) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$3.apply(SparkPlan.scala:240) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$23.apply(RDD.scala:774) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$23.apply(RDD.scala:774) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:318) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:282) > at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70) > at org.apache.spark.scheduler.Task.run(Task.scala:85) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)