spark-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Maciej Bryński (JIRA) <j...@apache.org>
Subject [jira] [Updated] (SPARK-19743) Exception when creating more than one implicit Encoder in REPL
Date Sun, 26 Feb 2017 17:36:46 GMT

     [ https://issues.apache.org/jira/browse/SPARK-19743?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Maciej Bryński updated SPARK-19743:
-----------------------------------
    Component/s:     (was: SQL)
                 Spark Shell

> Exception when creating more than one implicit Encoder in REPL
> --------------------------------------------------------------
>
>                 Key: SPARK-19743
>                 URL: https://issues.apache.org/jira/browse/SPARK-19743
>             Project: Spark
>          Issue Type: Bug
>          Components: Spark Shell
>    Affects Versions: 2.0.2
>            Reporter: Maciej Bryński
>
> During test I wanted to create 2 different bean classes and encoders for them. 
> First time it worked.
> {code}
> scala> class Test(@scala.beans.BeanProperty var xxx: Long) {}
> defined class Test
> scala> import org.apache.spark.sql.Encoders
> import org.apache.spark.sql.Encoders
> scala> implicit val testEncoder = Encoders.bean(classOf[Test])
> testEncoder: org.apache.spark.sql.Encoder[Test] = class[xxx[0]: bigint]
> scala> spark.range(10).map(new Test(_)).show()
> +---+
> |xxx|
> +---+
> |  0|
> |  1|
> |  2|
> |  3|
> |  4|
> |  5|
> |  6|
> |  7|
> |  8|
> |  9|
> +---+
> {code}
> Second try give me exception.
> {code}
> scala> class Test2(@scala.beans.BeanProperty var xxx: Long) {}
> defined class Test2
> scala> implicit val test2Encoder = Encoders.bean(classOf[Test2])
> test2Encoder: org.apache.spark.sql.Encoder[Test2] = class[xxx[0]: bigint]
> scala> spark.range(10).map(new Test2(_)).show()
> 17/02/26 18:10:15 WARN TaskSetManager: Lost task 0.0 in stage 2.0 (TID 2, cdh-data-4.gid):
java.lang.ExceptionInInitializerError
>         at $line17.$read$$iw.<init>(<console>:9)
>         at $line17.$read.<init>(<console>:45)
>         at $line17.$read$.<init>(<console>:49)
>         at $line17.$read$.<clinit>(<console>)
>         at $line19.$read$$iw.<init>(<console>:10)
>         at $line19.$read.<init>(<console>:21)
>         at $line19.$read$.<init>(<console>:25)
>         at $line19.$read$.<clinit>(<console>)
>         at $line21.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$1.apply(<console>:32)
>         at $line21.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$1.apply(<console>:32)
>         at org.apache.spark.sql.catalyst.expressions.GeneratedClass$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:803)
>         at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
>         at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>         at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)
>         at org.apache.spark.rdd.RDD.iterator(RDD.scala:283)
>         at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
>         at org.apache.spark.scheduler.Task.run(Task.scala:86)
>         at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
>         at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
>         at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
>         at java.lang.Thread.run(Thread.java:745)
> Caused by: org.apache.spark.SparkException: A master URL must be set in your configuration
>         at org.apache.spark.SparkContext.<init>(SparkContext.scala:368)
>         at org.apache.spark.SparkContext$.getOrCreate(SparkContext.scala:2258)
>         at org.apache.spark.sql.SparkSession$Builder$$anonfun$8.apply(SparkSession.scala:831)
>         at org.apache.spark.sql.SparkSession$Builder$$anonfun$8.apply(SparkSession.scala:823)
>         at scala.Option.getOrElse(Option.scala:121)
>         at org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:823)
>         at org.apache.spark.repl.Main$.createSparkSession(Main.scala:95)
>         at $line3.$read$$iw$$iw.<init>(<console>:15)
>         at $line3.$read$$iw.<init>(<console>:31)
>         at $line3.$read.<init>(<console>:33)
>         at $line3.$read$.<init>(<console>:37)
>         at $line3.$read$.<clinit>(<console>)
>         ... 26 more
> 17/02/26 18:10:15 ERROR TaskSetManager: Task 0 in stage 2.0 failed 1 times; aborting
job
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 2.0
failed 1 times, most recent failure: Lost task 0.0 in stage 2.0 (TID 2, cdh-data-4.gid): java.lang.ExceptionInInitializerError
>         at <init>(<console>:9)
>         at <init>(<console>:45)
>         at .<init>(<console>:49)
>         at .<clinit>(<console>)
>         at <init>(<console>:10)
>         at <init>(<console>:21)
>         at .<init>(<console>:25)
>         at .<clinit>(<console>)
>         at $anonfun$1.apply(<console>:32)
>         at $anonfun$1.apply(<console>:32)
>         at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown
Source)
>         at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
>         at org.apache.spark.sql.execution.WholeStageCodegenExec$$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$$anonfun$apply$24.apply(RDD.scala:803)
>         at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
>         at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>         at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)
>         at org.apache.spark.rdd.RDD.iterator(RDD.scala:283)
>         at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
>         at org.apache.spark.scheduler.Task.run(Task.scala:86)
>         at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
>         at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
>         at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
>         at java.lang.Thread.run(Thread.java:745)
> Caused by: org.apache.spark.SparkException: A master URL must be set in your configuration
>         at org.apache.spark.SparkContext.<init>(SparkContext.scala:368)
>         at org.apache.spark.SparkContext$.getOrCreate(SparkContext.scala:2258)
>         at org.apache.spark.sql.SparkSession$Builder$$anonfun$8.apply(SparkSession.scala:831)
>         at org.apache.spark.sql.SparkSession$Builder$$anonfun$8.apply(SparkSession.scala:823)
>         at scala.Option.getOrElse(Option.scala:121)
>         at org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:823)
>         at org.apache.spark.repl.Main$.createSparkSession(Main.scala:95)
>         at <init>(<console>:15)
>         at <init>(<console>:31)
>         at <init>(<console>:33)
>         at .<init>(<console>:37)
>         at .<clinit>(<console>)
>         ... 26 more
> Driver stacktrace:
>   at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1454)
>   at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1442)
>   at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1441)
>   at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
>   at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
>   at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1441)
>   at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
>   at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
>   at scala.Option.foreach(Option.scala:257)
>   at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:811)
>   at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1667)
>   at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1622)
>   at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1611)
>   at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
>   at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
>   at org.apache.spark.SparkContext.runJob(SparkContext.scala:1873)
>   at org.apache.spark.SparkContext.runJob(SparkContext.scala:1886)
>   at org.apache.spark.SparkContext.runJob(SparkContext.scala:1899)
>   at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:347)
>   at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:39)
>   at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2193)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
>   at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2546)
>   at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2192)
>   at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2199)
>   at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:1935)
>   at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:1934)
>   at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2576)
>   at org.apache.spark.sql.Dataset.head(Dataset.scala:1934)
>   at org.apache.spark.sql.Dataset.take(Dataset.scala:2149)
>   at org.apache.spark.sql.Dataset.showString(Dataset.scala:239)
>   at org.apache.spark.sql.Dataset.show(Dataset.scala:526)
>   at org.apache.spark.sql.Dataset.show(Dataset.scala:486)
>   at org.apache.spark.sql.Dataset.show(Dataset.scala:495)
>   ... 48 elided
> Caused by: java.lang.ExceptionInInitializerError: org.apache.spark.SparkException: A
master URL must be set in your configuration
> Caused by: org.apache.spark.SparkException: A master URL must be set in your configuration
>   at org.apache.spark.SparkContext.<init>(SparkContext.scala:368)
>   at org.apache.spark.SparkContext$.getOrCreate(SparkContext.scala:2258)
>   at org.apache.spark.sql.SparkSession$Builder$$anonfun$8.apply(SparkSession.scala:831)
>   at org.apache.spark.sql.SparkSession$Builder$$anonfun$8.apply(SparkSession.scala:823)
>   at scala.Option.getOrElse(Option.scala:121)
>   at org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:823)
>   at org.apache.spark.repl.Main$.createSparkSession(Main.scala:95)
>   ... 26 more
> {code}



--
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


Mime
View raw message