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 2017/05/23 09:57:04 UTC
[jira] [Commented] (SPARK-20852) NullPointerException on distinct
(Dataset)
[ https://issues.apache.org/jira/browse/SPARK-20852?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16020974#comment-16020974 ]
Sean Owen commented on SPARK-20852:
-----------------------------------
Looks like another duplicate of https://issues.apache.org/jira/browse/SPARK-18528
> NullPointerException on distinct (Dataset<Row>)
> -----------------------------------------------
>
> Key: SPARK-20852
> URL: https://issues.apache.org/jira/browse/SPARK-20852
> Project: Spark
> Issue Type: Bug
> Components: Spark Core, Spark Shell, SQL
> Affects Versions: 2.1.0
> Environment: Hive 1.2.1
> Reporter: Paride Casulli
>
> Hi, I have NullPointerException on these instructions, I've tried also the same commands in Spark 1.5.1 and returnes correctly the right result, can you help me? The table is stored as hive table in parquet file, partitioned by more than a column (ost_date is a partitioning field)
> scala> spark.sql("select ost_date from bda_ia.cdr_centrale_normalizzato where ost_Date='2017-05-23' limit 200")
> res5: org.apache.spark.sql.DataFrame = [ost_date: date]
> scala> res5.distinct()
> res6: org.apache.spark.sql.Dataset[org.apache.spark.sql.Row] = [ost_date: date]
> scala> res6.show()
> [Stage 13:====================================================> (53 + 2) / 57]17/05/23 11:42:57 WARN scheduler.TaskSetManager: Lost task 0.0 in stage 14.0 (TID 484, esedatanode3.telecomitalia.local, executor 37): java.lang.NullPointerException
> at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithKeys$(Unknown Source)
> 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:377)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:231)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:225)
> at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
> at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
> at org.apache.spark.scheduler.Task.run(Task.scala:99)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> 17/05/23 11:42:58 ERROR scheduler.TaskSetManager: Task 0 in stage 14.0 failed 4 times; aborting job
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 14.0 failed 4 times, most recent failure: Lost task 0.3 in stage 14.0 (TID 487, esedatanode3.telecomitalia.local, executor 37): java.lang.NullPointerException
> at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithKeys$(Unknown Source)
> at org.apache.spark.sql.catalyst.expressions.GeneratedClass$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:377)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:231)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:225)
> at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
> at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
> at org.apache.spark.scheduler.Task.run(Task.scala:99)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Driver stacktrace:
> at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1435)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1423)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1422)
> at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
> at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1422)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
> at scala.Option.foreach(Option.scala:257)
> at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1650)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1605)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1594)
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
> at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1918)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1931)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1944)
> at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:333)
> at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
> at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2371)
> at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
> at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2765)
> at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2370)
> at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2377)
> at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2113)
> at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2112)
> at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2795)
> at org.apache.spark.sql.Dataset.head(Dataset.scala:2112)
> at org.apache.spark.sql.Dataset.take(Dataset.scala:2327)
> at org.apache.spark.sql.Dataset.showString(Dataset.scala:248)
> at org.apache.spark.sql.Dataset.show(Dataset.scala:636)
> at org.apache.spark.sql.Dataset.show(Dataset.scala:595)
> at org.apache.spark.sql.Dataset.show(Dataset.scala:604)
> ... 48 elided
> Caused by: java.lang.NullPointerException
> at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithKeys$(Unknown Source)
> at org.apache.spark.sql.catalyst.expressions.GeneratedClass$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:377)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:231)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:225)
> at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
> at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
> at org.apache.spark.scheduler.Task.run(Task.scala:99)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
> 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)
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org