[ https://issues.apache.org/jira/browse/SPARK-24366?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Apache Spark reassigned SPARK-24366: ------------------------------------ Assignee: (was: Apache Spark) > Improve error message for type conversions > ------------------------------------------ > > Key: SPARK-24366 > URL: https://issues.apache.org/jira/browse/SPARK-24366 > Project: Spark > Issue Type: Improvement > Components: SQL > Affects Versions: 1.6.3, 2.3.0 > Reporter: Maxim Gekk > Priority: Minor > > User have no way to drill down to understand which of the hundreds of fields > in millions records feeding into the job are causing the problem. We should > to show where in the schema the error is happening. > {code:java} > Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: > Task 4 in stage 344.0 failed 4 times, most recent failure: Lost task 4.3 in > stage 344.0 (TID 2673, ip-10-31-237-248.ec2.internal): scala.MatchError: > start (of class java.lang.String) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:255) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:250) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$CatalystTypeConverter.toCatalyst(CatalystTypeConverters.scala:102) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:260) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:250) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$CatalystTypeConverter.toCatalyst(CatalystTypeConverters.scala:102) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:260) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:250) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$CatalystTypeConverter.toCatalyst(CatalystTypeConverters.scala:102) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$ArrayConverter$$anonfun$toCatalystImpl$1.apply(CatalystTypeConverters.scala:161) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) > at > scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33) > at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108) > at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) > at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$ArrayConverter.toCatalystImpl(CatalystTypeConverters.scala:161) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$ArrayConverter.toCatalystImpl(CatalystTypeConverters.scala:153) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$CatalystTypeConverter.toCatalyst(CatalystTypeConverters.scala:102) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:260) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:250) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$CatalystTypeConverter.toCatalyst(CatalystTypeConverters.scala:102) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$ArrayConverter$$anonfun$toCatalystImpl$1.apply(CatalystTypeConverters.scala:161) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) > at > scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33) > at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108) > at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) > at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$ArrayConverter.toCatalystImpl(CatalystTypeConverters.scala:161) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$ArrayConverter.toCatalystImpl(CatalystTypeConverters.scala:153) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$CatalystTypeConverter.toCatalyst(CatalystTypeConverters.scala:102) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:260) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:250) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$CatalystTypeConverter.toCatalyst(CatalystTypeConverters.scala:102) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:260) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$StructConverter.toCatalystImpl(CatalystTypeConverters.scala:250) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$CatalystTypeConverter.toCatalyst(CatalystTypeConverters.scala:102) > at > org.apache.spark.sql.catalyst.CatalystTypeConverters$$anonfun$createToCatalystConverter$2.apply(CatalystTypeConverters.scala:401) > at > org.apache.spark.sql.SQLContext$$anonfun$6.apply(SQLContext.scala:491) > at > org.apache.spark.sql.SQLContext$$anonfun$6.apply(SQLContext.scala:491) > at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) > at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) > at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) > at > org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:149) > at > org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:79) > at > org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:46) > at org.apache.spark.scheduler.Task.run(Task.scala:96) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:235) > 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 (v7.6.3#76005) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org