You are viewing a plain text version of this content. The canonical link for it is here.
Posted to users@zeppelin.apache.org by Rob Anderson <ro...@gmail.com> on 2017/03/07 00:57:04 UTC
java.lang.ClassNotFoundException: $anonfun$1
Hey Everyone,
We're running Zeppelin 0.7.0. We've just cut over to spark2, using scala11
via the CDH parcel (SPARK2-2.0.0.cloudera1-1.cdh5.7.0.p0.113931).
Running a simple job, throws a "Caused by: java.lang.ClassNotFoundException:
$anonfun$1". It appears that during execution time on the yarn hosts, the
native CDH spark1.5 jars are loaded before the new spark2 jars. I've tried
using spark.yarn.archive to specify the spark2 jars in hdfs as well as
using other spark options, none of which seems to make a difference.
Any suggestions you can offer is appreciated.
Thanks,
Rob
------------------------
%spark
val taxonomy = sc.textFile("/user/user1/data/")
.map(l => l.split("\t"))
%spark
taxonomy.first
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0
in stage 1.0 failed 4 times, most recent failure: Lost task 0.3 in stage
1.0 (TID 7, data08.hadoop.prod.ostk.com, executor 2):
java.lang.ClassNotFoundException: $anonfun$1
at org.apache.spark.repl.ExecutorClassLoader.findClass(Executor
ClassLoader.scala:82)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at org.apache.spark.serializer.JavaDeserializationStream$$anon$
1.resolveClass(JavaSerializer.scala:67)
at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1613)
at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1518)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1774)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.readObject(ObjectInputStream.java:371)
at org.apache.spark.serializer.JavaDeserializationStream.readOb
ject(JavaSerializer.scala:75)
at org.apache.spark.serializer.JavaSerializerInstance.deseriali
ze(JavaSerializer.scala:114)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
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(ThreadPool
Executor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoo
lExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.ClassNotFoundException: $anonfun$1
at java.lang.ClassLoader.findClass(ClassLoader.java:530)
at org.apache.spark.util.ParentClassLoader.findClass(ParentClas
sLoader.scala:26)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at org.apache.spark.util.ParentClassLoader.loadClass(ParentClas
sLoader.scala:34)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at org.apache.spark.util.ParentClassLoader.loadClass(ParentClas
sLoader.scala:30)
at org.apache.spark.repl.ExecutorClassLoader.findClass(Executor
ClassLoader.scala:77)
... 30 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$sch
eduler$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(Resiza
bleArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGSchedu
ler.scala:1441)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskS
etFailed$1.apply(DAGScheduler.scala:811)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskS
etFailed$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.doOn
Receive(DAGScheduler.scala:1669)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onRe
ceive(DAGScheduler.scala:1624)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onRe
ceive(DAGScheduler.scala:1613)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1893)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1906)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1919)
at org.apache.spark.rdd.RDD$$anonfun$take$1.apply(RDD.scala:1318)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperati
onScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperati
onScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
at org.apache.spark.rdd.RDD.take(RDD.scala:1292)
at org.apache.spark.rdd.RDD$$anonfun$first$1.apply(RDD.scala:1332)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperati
onScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperati
onScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
at org.apache.spark.rdd.RDD.first(RDD.scala:1331)
... 37 elided
Caused by: java.lang.ClassNotFoundException: $anonfun$1
at org.apache.spark.repl.ExecutorClassLoader.findClass(Executor
ClassLoader.scala:82)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at org.apache.spark.serializer.JavaDeserializationStream$$anon$
1.resolveClass(JavaSerializer.scala:67)
at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1613)
at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1518)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1774)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.readObject(ObjectInputStream.java:371)
at org.apache.spark.serializer.JavaDeserializationStream.readOb
ject(JavaSerializer.scala:75)
at org.apache.spark.serializer.JavaSerializerInstance.deseriali
ze(JavaSerializer.scala:114)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPool
Executor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoo
lExecutor.java:617)
... 1 more
Caused by: java.lang.ClassNotFoundException: $anonfun$1
at java.lang.ClassLoader.findClass(ClassLoader.java:530)
at org.apache.spark.util.ParentClassLoader.findClass(ParentClas
sLoader.scala:26)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at org.apache.spark.util.ParentClassLoader.loadClass(ParentClas
sLoader.scala:34)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at org.apache.spark.util.ParentClassLoader.loadClass(ParentClas
sLoader.scala:30)
at org.apache.spark.repl.ExecutorClassL
oader.findClass(ExecutorClassLoader.scala:77)
... 30 more
Re: java.lang.ClassNotFoundException: $anonfun$1
Posted by Rob Anderson <ro...@gmail.com>.
Rewriting the paragraph to use sparkSession fixes most of the class
issues. The remaining class issues were resolved by upgrading to
SPARK2-2.0.0.cloudera2-1,
which was released on 02-24-2017 (
http://community.cloudera.com/t5/Community-News-Release/ANNOUNCE-Spark-2-0-Release-2/m-p/51464#M161
).
Thanks,
Rob
On Tue, Mar 7, 2017 at 4:49 PM, Jianfeng (Jeff) Zhang <
jzhang@hortonworks.com> wrote:
> >>> It appears that during execution time on the yarn hosts, the native
> CDH spark1.5 jars are loaded before the new spark2 jars. I've tried
> using spark.yarn.archive to specify the spark2 jars in hdfs as well as
> using other spark options, none of which seems to make a difference.
>
> Where do you see “ spark1.5 jars are loaded before the new spark2 jars” ?
>
> Best Regard,
> Jeff Zhang
>
>
> From: Rob Anderson <ro...@gmail.com>
> Reply-To: "users@zeppelin.apache.org" <us...@zeppelin.apache.org>
> Date: Wednesday, March 8, 2017 at 2:29 AM
> To: "users@zeppelin.apache.org" <us...@zeppelin.apache.org>
> Subject: Re: java.lang.ClassNotFoundException: $anonfun$1
>
> Thanks. I can reach out to Cloudera, although the same commands seem to
> be work via Spak-Shell (see below). So, the issue seems unique to
> Zeppelin.
>
> Spark context available as 'sc' (master = yarn, app id =
> application_1472496315722_481416).
>
> Spark session available as 'spark'.
>
> Welcome to
>
> ____ __
>
> / __/__ ___ _____/ /__
>
> _\ \/ _ \/ _ `/ __/ '_/
>
> /___/ .__/\_,_/_/ /_/\_\ version 2.0.0.cloudera1
>
> /_/
>
>
>
> Using Scala version 2.11.8 (Java HotSpot(TM) 64-Bit Server VM, Java
> 1.8.0_60)
>
> Type in expressions to have them evaluated.
>
> Type :help for more information.
>
>
> scala> val taxonomy = sc.textFile("/user/user1/data/")
>
> taxonomy: org.apache.spark.rdd.RDD[String] = /user/user1/data/ MapPartitionsRDD[1]
> at textFile at <console>:24
>
>
> scala> .map(l => l.split("\t"))
>
> res0: org.apache.spark.rdd.RDD[Array[String]] = MapPartitionsRDD[2] at
> map at <console>:27
>
>
> scala> taxonomy.first
>
> res1: String = 43 B&B 459Sheets & Pillow 45 Sheets1 Sheets
>
> On Mon, Mar 6, 2017 at 6:48 PM, moon soo Lee <mo...@apache.org> wrote:
>
>> Hi Rob,
>>
>> Thanks for sharing the problem.
>> fyi, https://issues.apache.org/jira/browse/ZEPPELIN-1735 is tracking the
>> problem.
>>
>> If we can get help from cloudera forum, that would be great.
>>
>> Thanks,
>> moon
>>
>> On Tue, Mar 7, 2017 at 10:08 AM Jeff Zhang <zj...@gmail.com> wrote:
>>
>>>
>>> It seems CDH specific issue, you might be better to ask cloudera forum.
>>>
>>>
>>> Rob Anderson <ro...@gmail.com>于2017年3月7日周二 上午9:02写道：
>>>
>>> Hey Everyone,
>>>
>>> We're running Zeppelin 0.7.0. We've just cut over to spark2, using
>>> scala11 via the CDH parcel (SPARK2-2.0.0.cloudera1-1.cdh5
>>> .7.0.p0.113931).
>>>
>>> Running a simple job, throws a "Caused by:
>>> java.lang.ClassNotFoundException: $anonfun$1". It appears that during
>>> execution time on the yarn hosts, the native CDH spark1.5 jars are loaded
>>> before the new spark2 jars. I've tried using spark.yarn.archive to specify
>>> the spark2 jars in hdfs as well as using other spark options, none of which
>>> seems to make a difference.
>>>
>>>
>>> Any suggestions you can offer is appreciated.
>>>
>>> Thanks,
>>>
>>> Rob
>>>
>>> ------------------------
>>>
>>>
>>> %spark
>>> val taxonomy = sc.textFile("/user/user1/data/")
>>> .map(l => l.split("\t"))
>>>
>>> %spark
>>> taxonomy.first
>>>
>>>
>>> org.apache.spark.SparkException: Job aborted due to stage failure: Task
>>> 0 in stage 1.0 failed 4 times, most recent failure: Lost task 0.3 in stage
>>> 1.0 (TID 7, data08.hadoop.prod.ostk.com, executor 2):
>>> java.lang.ClassNotFoundException: $anonfun$1
>>> at org.apache.spark.repl.ExecutorClassLoader.findClass(Executor
>>> ClassLoader.scala:82)
>>> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
>>> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
>>> at java.lang.Class.forName0(Native Method)
>>> at java.lang.Class.forName(Class.java:348)
>>> at org.apache.spark.serializer.JavaDeserializationStream$$anon$
>>> 1.resolveClass(JavaSerializer.scala:67)
>>> at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream
>>> .java:1613)
>>> at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1518)
>>> at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStre
>>> am.java:1774)
>>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>>> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStrea
>>> m.java:2000)
>>> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
>>> at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStre
>>> am.java:1801)
>>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>>> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStrea
>>> m.java:2000)
>>> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
>>> at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStre
>>> am.java:1801)
>>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>>> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStrea
>>> m.java:2000)
>>> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
>>> at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStre
>>> am.java:1801)
>>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>>> at java.io.ObjectInputStream.readObject(ObjectInputStream.java:371)
>>> at org.apache.spark.serializer.JavaDeserializationStream.readOb
>>> ject(JavaSerializer.scala:75)
>>> at org.apache.spark.serializer.JavaSerializerInstance.deseriali
>>> ze(JavaSerializer.scala:114)
>>> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
>>> 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(ThreadPool
>>> Executor.java:1142)
>>> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoo
>>> lExecutor.java:617)
>>> at java.lang.Thread.run(Thread.java:745)
>>> Caused by: java.lang.ClassNotFoundException: $anonfun$1
>>> at java.lang.ClassLoader.findClass(ClassLoader.java:530)
>>> at org.apache.spark.util.ParentClassLoader.findClass(ParentClas
>>> sLoader.scala:26)
>>> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
>>> at org.apache.spark.util.ParentClassLoader.loadClass(ParentClas
>>> sLoader.scala:34)
>>> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
>>> at org.apache.spark.util.ParentClassLoader.loadClass(ParentClas
>>> sLoader.scala:30)
>>> at org.apache.spark.repl.ExecutorClassLoader.findClass(Executor
>>> ClassLoader.scala:77)
>>> ... 30 more
>>> Driver stacktrace:
>>> at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$sch
>>> eduler$DAGScheduler$$failJobAndIndependentStages(DAGSchedule
>>> r.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(Resiza
>>> bleArray.scala:59)
>>> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
>>> at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGSchedu
>>> ler.scala:1441)
>>> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskS
>>> etFailed$1.apply(DAGScheduler.scala:811)
>>> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskS
>>> etFailed$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.doOn
>>> Receive(DAGScheduler.scala:1669)
>>> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onRe
>>> ceive(DAGScheduler.scala:1624)
>>> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onRe
>>> ceive(DAGScheduler.scala:1613)
>>> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
>>> at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.
>>> scala:632)
>>> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1893)
>>> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1906)
>>> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1919)
>>> at org.apache.spark.rdd.RDD$$anonfun$take$1.apply(RDD.scala:1318)
>>> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperati
>>> onScope.scala:151)
>>> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperati
>>> onScope.scala:112)
>>> at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
>>> at org.apache.spark.rdd.RDD.take(RDD.scala:1292)
>>> at org.apache.spark.rdd.RDD$$anonfun$first$1.apply(RDD.scala:1332)
>>> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperati
>>> onScope.scala:151)
>>> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperati
>>> onScope.scala:112)
>>> at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
>>> at org.apache.spark.rdd.RDD.first(RDD.scala:1331)
>>> ... 37 elided
>>> Caused by: java.lang.ClassNotFoundException: $anonfun$1
>>> at org.apache.spark.repl.ExecutorClassLoader.findClass(Executor
>>> ClassLoader.scala:82)
>>> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
>>> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
>>> at java.lang.Class.forName0(Native Method)
>>> at java.lang.Class.forName(Class.java:348)
>>> at org.apache.spark.serializer.JavaDeserializationStream$$anon$
>>> 1.resolveClass(JavaSerializer.scala:67)
>>> at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream
>>> .java:1613)
>>> at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1518)
>>> at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStre
>>> am.java:1774)
>>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>>> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStrea
>>> m.java:2000)
>>> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
>>> at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStre
>>> am.java:1801)
>>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>>> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStrea
>>> m.java:2000)
>>> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
>>> at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStre
>>> am.java:1801)
>>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>>> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStrea
>>> m.java:2000)
>>> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
>>> at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStre
>>> am.java:1801)
>>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>>> at java.io.ObjectInputStream.readObject(ObjectInputStream.java:371)
>>> at org.apache.spark.serializer.JavaDeserializationStream.readOb
>>> ject(JavaSerializer.scala:75)
>>> at org.apache.spark.serializer.JavaSerializerInstance.deseriali
>>> ze(JavaSerializer.scala:114)
>>> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
>>> at org.apache.spark.scheduler.Task.run(Task.scala:86)
>>> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
>>> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPool
>>> Executor.java:1142)
>>> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoo
>>> lExecutor.java:617)
>>> ... 1 more
>>> Caused by: java.lang.ClassNotFoundException: $anonfun$1
>>> at java.lang.ClassLoader.findClass(ClassLoader.java:530)
>>> at org.apache.spark.util.ParentClassLoader.findClass(ParentClas
>>> sLoader.scala:26)
>>> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
>>> at org.apache.spark.util.ParentClassLoader.loadClass(ParentClas
>>> sLoader.scala:34)
>>> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
>>> at org.apache.spark.util.ParentClassLoader.loadClass(ParentClas
>>> sLoader.scala:30)
>>> at org.apache.spark.repl.ExecutorClassL
>>> oader.findClass(ExecutorClassLoader.scala:77)
>>> ... 30 more
>>>
>>>
>
Re: java.lang.ClassNotFoundException: $anonfun$1
Posted by "Jianfeng (Jeff) Zhang" <jz...@hortonworks.com>.
>>> It appears that during execution time on the yarn hosts, the native CDH spark1.5 jars are loaded before the new spark2 jars. I've tried using spark.yarn.archive to specify the spark2 jars in hdfs as well as using other spark options, none of which seems to make a difference.
Where do you see “ spark1.5 jars are loaded before the new spark2 jars” ?
Best Regard,
Jeff Zhang
From: Rob Anderson <ro...@gmail.com>>
Reply-To: "users@zeppelin.apache.org<ma...@zeppelin.apache.org>" <us...@zeppelin.apache.org>>
Date: Wednesday, March 8, 2017 at 2:29 AM
To: "users@zeppelin.apache.org<ma...@zeppelin.apache.org>" <us...@zeppelin.apache.org>>
Subject: Re: java.lang.ClassNotFoundException: $anonfun$1
Thanks. I can reach out to Cloudera, although the same commands seem to be work via Spak-Shell (see below). So, the issue seems unique to Zeppelin.
Spark context available as 'sc' (master = yarn, app id = application_1472496315722_481416).
Spark session available as 'spark'.
Welcome to
____ __
/ __/__ ___ _____/ /__
_\ \/ _ \/ _ `/ __/ '_/
/___/ .__/\_,_/_/ /_/\_\ version 2.0.0.cloudera1
/_/
Using Scala version 2.11.8 (Java HotSpot(TM) 64-Bit Server VM, Java 1.8.0_60)
Type in expressions to have them evaluated.
Type :help for more information.
scala> val taxonomy = sc.textFile("/user/user1/data/")
taxonomy: org.apache.spark.rdd.RDD[String] = /user/user1/data/ MapPartitionsRDD[1] at textFile at <console>:24
scala> .map(l => l.split("\t"))
res0: org.apache.spark.rdd.RDD[Array[String]] = MapPartitionsRDD[2] at map at <console>:27
scala> taxonomy.first
res1: String = 43 B&B 459Sheets & Pillow 45 Sheets1 Sheets
On Mon, Mar 6, 2017 at 6:48 PM, moon soo Lee <mo...@apache.org>> wrote:
Hi Rob,
Thanks for sharing the problem.
fyi, https://issues.apache.org/jira/browse/ZEPPELIN-1735 is tracking the problem.
If we can get help from cloudera forum, that would be great.
Thanks,
moon
On Tue, Mar 7, 2017 at 10:08 AM Jeff Zhang <zj...@gmail.com>> wrote:
It seems CDH specific issue, you might be better to ask cloudera forum.
Rob Anderson <ro...@gmail.com>>于2017年3月7日周二 上午9:02写道：
Hey Everyone,
We're running Zeppelin 0.7.0. We've just cut over to spark2, using scala11 via the CDH parcel (SPARK2-2.0.0.cloudera1-1.cdh5.7.0.p0.113931).
Running a simple job, throws a "Caused by: java.lang.ClassNotFoundException: $anonfun$1". It appears that during execution time on the yarn hosts, the native CDH spark1.5 jars are loaded before the new spark2 jars. I've tried using spark.yarn.archive to specify the spark2 jars in hdfs as well as using other spark options, none of which seems to make a difference.
Any suggestions you can offer is appreciated.
Thanks,
Rob
------------------------
%spark
val taxonomy = sc.textFile("/user/user1/data/")
.map(l => l.split("\t"))
%spark
taxonomy.first
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 1.0 failed 4 times, most recent failure: Lost task 0.3 in stage 1.0 (TID 7, data08.hadoop.prod.ostk.com<http://data08.hadoop.prod.ostk.com>, executor 2): java.lang.ClassNotFoundException: $anonfun$1
at org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:82)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:67)
at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1613)
at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1518)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1774)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.readObject(ObjectInputStream.java:371)
at org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:75)
at org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:114)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
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:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.ClassNotFoundException: $anonfun$1
at java.lang.ClassLoader.findClass(ClassLoader.java:530)
at org.apache.spark.util.ParentClassLoader.findClass(ParentClassLoader.scala:26)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:34)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:30)
at org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:77)
... 30 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org<http://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:1669)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1624)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1613)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1893)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1906)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1919)
at org.apache.spark.rdd.RDD$$anonfun$take$1.apply(RDD.scala:1318)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
at org.apache.spark.rdd.RDD.take(RDD.scala:1292)
at org.apache.spark.rdd.RDD$$anonfun$first$1.apply(RDD.scala:1332)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
at org.apache.spark.rdd.RDD.first(RDD.scala:1331)
... 37 elided
Caused by: java.lang.ClassNotFoundException: $anonfun$1
at org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:82)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:67)
at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1613)
at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1518)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1774)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
at java.io.ObjectInputStream.readObject(ObjectInputStream.java:371)
at org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:75)
at org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:114)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
... 1 more
Caused by: java.lang.ClassNotFoundException: $anonfun$1
at java.lang.ClassLoader.findClass(ClassLoader.java:530)
at org.apache.spark.util.ParentClassLoader.findClass(ParentClassLoader.scala:26)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:34)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:30)
at org.apache.spark.repl.ExecutorClassL
oader.findClass(ExecutorClassLoader.scala:77)
... 30 more
Re: java.lang.ClassNotFoundException: $anonfun$1
Posted by Rob Anderson <ro...@gmail.com>.
Thanks. I can reach out to Cloudera, although the same commands seem to be
work via Spak-Shell (see below). So, the issue seems unique to Zeppelin.
Spark context available as 'sc' (master = yarn, app id =
application_1472496315722_481416).
Spark session available as 'spark'.
Welcome to
____ __
/ __/__ ___ _____/ /__
_\ \/ _ \/ _ `/ __/ '_/
/___/ .__/\_,_/_/ /_/\_\ version 2.0.0.cloudera1
/_/
Using Scala version 2.11.8 (Java HotSpot(TM) 64-Bit Server VM, Java
1.8.0_60)
Type in expressions to have them evaluated.
Type :help for more information.
scala> val taxonomy = sc.textFile("/user/user1/data/")
taxonomy: org.apache.spark.rdd.RDD[String] = /user/user1/data/
MapPartitionsRDD[1]
at textFile at <console>:24
scala> .map(l => l.split("\t"))
res0: org.apache.spark.rdd.RDD[Array[String]] = MapPartitionsRDD[2] at map
at <console>:27
scala> taxonomy.first
res1: String = 43 B&B 459 Sheets & Pillow 45 Sheets 1 Sheets
On Mon, Mar 6, 2017 at 6:48 PM, moon soo Lee <mo...@apache.org> wrote:
> Hi Rob,
>
> Thanks for sharing the problem.
> fyi, https://issues.apache.org/jira/browse/ZEPPELIN-1735 is tracking the
> problem.
>
> If we can get help from cloudera forum, that would be great.
>
> Thanks,
> moon
>
> On Tue, Mar 7, 2017 at 10:08 AM Jeff Zhang <zj...@gmail.com> wrote:
>
>>
>> It seems CDH specific issue, you might be better to ask cloudera forum.
>>
>>
>> Rob Anderson <ro...@gmail.com>于2017年3月7日周二 上午9:02写道：
>>
>> Hey Everyone,
>>
>> We're running Zeppelin 0.7.0. We've just cut over to spark2, using
>> scala11 via the CDH parcel (SPARK2-2.0.0.cloudera1-1.cdh5.7.0.p0.113931).
>>
>> Running a simple job, throws a "Caused by: java.lang.ClassNotFoundException:
>> $anonfun$1". It appears that during execution time on the yarn hosts,
>> the native CDH spark1.5 jars are loaded before the new spark2 jars. I've
>> tried using spark.yarn.archive to specify the spark2 jars in hdfs as well
>> as using other spark options, none of which seems to make a difference.
>>
>>
>> Any suggestions you can offer is appreciated.
>>
>> Thanks,
>>
>> Rob
>>
>> ------------------------
>>
>>
>> %spark
>> val taxonomy = sc.textFile("/user/user1/data/")
>> .map(l => l.split("\t"))
>>
>> %spark
>> taxonomy.first
>>
>>
>> org.apache.spark.SparkException: Job aborted due to stage failure: Task
>> 0 in stage 1.0 failed 4 times, most recent failure: Lost task 0.3 in stage
>> 1.0 (TID 7, data08.hadoop.prod.ostk.com, executor 2): java.lang.ClassNotFoundException:
>> $anonfun$1
>> at org.apache.spark.repl.ExecutorClassLoader.findClass(
>> ExecutorClassLoader.scala:82)
>> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
>> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
>> at java.lang.Class.forName0(Native Method)
>> at java.lang.Class.forName(Class.java:348)
>> at org.apache.spark.serializer.JavaDeserializationStream$$
>> anon$1.resolveClass(JavaSerializer.scala:67)
>> at java.io.ObjectInputStream.readNonProxyDesc(
>> ObjectInputStream.java:1613)
>> at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1518)
>> at java.io.ObjectInputStream.readOrdinaryObject(
>> ObjectInputStream.java:1774)
>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>> at java.io.ObjectInputStream.defaultReadFields(
>> ObjectInputStream.java:2000)
>> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
>> at java.io.ObjectInputStream.readOrdinaryObject(
>> ObjectInputStream.java:1801)
>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>> at java.io.ObjectInputStream.defaultReadFields(
>> ObjectInputStream.java:2000)
>> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
>> at java.io.ObjectInputStream.readOrdinaryObject(
>> ObjectInputStream.java:1801)
>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>> at java.io.ObjectInputStream.defaultReadFields(
>> ObjectInputStream.java:2000)
>> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
>> at java.io.ObjectInputStream.readOrdinaryObject(
>> ObjectInputStream.java:1801)
>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>> at java.io.ObjectInputStream.readObject(ObjectInputStream.java:371)
>> at org.apache.spark.serializer.JavaDeserializationStream.
>> readObject(JavaSerializer.scala:75)
>> at org.apache.spark.serializer.JavaSerializerInstance.
>> deserialize(JavaSerializer.scala:114)
>> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
>> 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:1142)
>> at java.util.concurrent.ThreadPoolExecutor$Worker.run(
>> ThreadPoolExecutor.java:617)
>> at java.lang.Thread.run(Thread.java:745)
>> Caused by: java.lang.ClassNotFoundException: $anonfun$1
>> at java.lang.ClassLoader.findClass(ClassLoader.java:530)
>> at org.apache.spark.util.ParentClassLoader.findClass(
>> ParentClassLoader.scala:26)
>> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
>> at org.apache.spark.util.ParentClassLoader.loadClass(
>> ParentClassLoader.scala:34)
>> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
>> at org.apache.spark.util.ParentClassLoader.loadClass(
>> ParentClassLoader.scala:30)
>> at org.apache.spark.repl.ExecutorClassLoader.findClass(
>> ExecutorClassLoader.scala:77)
>> ... 30 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:1669)
>> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.
>> onReceive(DAGScheduler.scala:1624)
>> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.
>> onReceive(DAGScheduler.scala:1613)
>> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
>> at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
>> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1893)
>> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1906)
>> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1919)
>> at org.apache.spark.rdd.RDD$$anonfun$take$1.apply(RDD.scala:1318)
>> at org.apache.spark.rdd.RDDOperationScope$.withScope(
>> RDDOperationScope.scala:151)
>> at org.apache.spark.rdd.RDDOperationScope$.withScope(
>> RDDOperationScope.scala:112)
>> at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
>> at org.apache.spark.rdd.RDD.take(RDD.scala:1292)
>> at org.apache.spark.rdd.RDD$$anonfun$first$1.apply(RDD.scala:1332)
>> at org.apache.spark.rdd.RDDOperationScope$.withScope(
>> RDDOperationScope.scala:151)
>> at org.apache.spark.rdd.RDDOperationScope$.withScope(
>> RDDOperationScope.scala:112)
>> at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
>> at org.apache.spark.rdd.RDD.first(RDD.scala:1331)
>> ... 37 elided
>> Caused by: java.lang.ClassNotFoundException: $anonfun$1
>> at org.apache.spark.repl.ExecutorClassLoader.findClass(
>> ExecutorClassLoader.scala:82)
>> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
>> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
>> at java.lang.Class.forName0(Native Method)
>> at java.lang.Class.forName(Class.java:348)
>> at org.apache.spark.serializer.JavaDeserializationStream$$
>> anon$1.resolveClass(JavaSerializer.scala:67)
>> at java.io.ObjectInputStream.readNonProxyDesc(
>> ObjectInputStream.java:1613)
>> at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1518)
>> at java.io.ObjectInputStream.readOrdinaryObject(
>> ObjectInputStream.java:1774)
>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>> at java.io.ObjectInputStream.defaultReadFields(
>> ObjectInputStream.java:2000)
>> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
>> at java.io.ObjectInputStream.readOrdinaryObject(
>> ObjectInputStream.java:1801)
>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>> at java.io.ObjectInputStream.defaultReadFields(
>> ObjectInputStream.java:2000)
>> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
>> at java.io.ObjectInputStream.readOrdinaryObject(
>> ObjectInputStream.java:1801)
>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>> at java.io.ObjectInputStream.defaultReadFields(
>> ObjectInputStream.java:2000)
>> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
>> at java.io.ObjectInputStream.readOrdinaryObject(
>> ObjectInputStream.java:1801)
>> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
>> at java.io.ObjectInputStream.readObject(ObjectInputStream.java:371)
>> at org.apache.spark.serializer.JavaDeserializationStream.
>> readObject(JavaSerializer.scala:75)
>> at org.apache.spark.serializer.JavaSerializerInstance.
>> deserialize(JavaSerializer.scala:114)
>> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
>> at org.apache.spark.scheduler.Task.run(Task.scala:86)
>> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
>> at java.util.concurrent.ThreadPoolExecutor.runWorker(
>> ThreadPoolExecutor.java:1142)
>> at java.util.concurrent.ThreadPoolExecutor$Worker.run(
>> ThreadPoolExecutor.java:617)
>> ... 1 more
>> Caused by: java.lang.ClassNotFoundException: $anonfun$1
>> at java.lang.ClassLoader.findClass(ClassLoader.java:530)
>> at org.apache.spark.util.ParentClassLoader.findClass(
>> ParentClassLoader.scala:26)
>> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
>> at org.apache.spark.util.ParentClassLoader.loadClass(
>> ParentClassLoader.scala:34)
>> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
>> at org.apache.spark.util.ParentClassLoader.loadClass(
>> ParentClassLoader.scala:30)
>> at org.apache.spark.repl.ExecutorClassL
>> oader.findClass(ExecutorClassLoader.scala:77)
>> ... 30 more
>>
>>
Re: java.lang.ClassNotFoundException: $anonfun$1
Posted by moon soo Lee <mo...@apache.org>.
Hi Rob,
Thanks for sharing the problem.
fyi, https://issues.apache.org/jira/browse/ZEPPELIN-1735 is tracking the
problem.
If we can get help from cloudera forum, that would be great.
Thanks,
moon
On Tue, Mar 7, 2017 at 10:08 AM Jeff Zhang <zj...@gmail.com> wrote:
>
> It seems CDH specific issue, you might be better to ask cloudera forum.
>
>
> Rob Anderson <ro...@gmail.com>于2017年3月7日周二 上午9:02写道：
>
> Hey Everyone,
>
> We're running Zeppelin 0.7.0. We've just cut over to spark2, using
> scala11 via the CDH parcel (SPARK2-2.0.0.cloudera1-1.cdh5.7.0.p0.113931).
>
> Running a simple job, throws a "Caused by: java.lang.ClassNotFoundException:
> $anonfun$1". It appears that during execution time on the yarn hosts,
> the native CDH spark1.5 jars are loaded before the new spark2 jars. I've
> tried using spark.yarn.archive to specify the spark2 jars in hdfs as well
> as using other spark options, none of which seems to make a difference.
>
>
> Any suggestions you can offer is appreciated.
>
> Thanks,
>
> Rob
>
> ------------------------
>
>
> %spark
> val taxonomy = sc.textFile("/user/user1/data/")
> .map(l => l.split("\t"))
>
> %spark
> taxonomy.first
>
>
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 0
> in stage 1.0 failed 4 times, most recent failure: Lost task 0.3 in stage
> 1.0 (TID 7, data08.hadoop.prod.ostk.com, executor 2):
> java.lang.ClassNotFoundException: $anonfun$1
> at
> org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:82)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
> at java.lang.Class.forName0(Native Method)
> at java.lang.Class.forName(Class.java:348)
> at
> org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:67)
> at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1613)
> at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1518)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1774)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.readObject(ObjectInputStream.java:371)
> at
> org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:75)
> at
> org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:114)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> 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:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.ClassNotFoundException: $anonfun$1
> at java.lang.ClassLoader.findClass(ClassLoader.java:530)
> at
> org.apache.spark.util.ParentClassLoader.findClass(ParentClassLoader.scala:26)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
> at
> org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:34)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
> at
> org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:30)
> at
> org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:77)
> ... 30 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:1669)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1624)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1613)
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
> at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1893)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1906)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1919)
> at org.apache.spark.rdd.RDD$$anonfun$take$1.apply(RDD.scala:1318)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
> at org.apache.spark.rdd.RDD.take(RDD.scala:1292)
> at org.apache.spark.rdd.RDD$$anonfun$first$1.apply(RDD.scala:1332)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
> at org.apache.spark.rdd.RDD.first(RDD.scala:1331)
> ... 37 elided
> Caused by: java.lang.ClassNotFoundException: $anonfun$1
> at
> org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:82)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
> at java.lang.Class.forName0(Native Method)
> at java.lang.Class.forName(Class.java:348)
> at
> org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:67)
> at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1613)
> at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1518)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1774)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.readObject(ObjectInputStream.java:371)
> at
> org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:75)
> at
> org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:114)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:86)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> ... 1 more
> Caused by: java.lang.ClassNotFoundException: $anonfun$1
> at java.lang.ClassLoader.findClass(ClassLoader.java:530)
> at
> org.apache.spark.util.ParentClassLoader.findClass(ParentClassLoader.scala:26)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
> at
> org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:34)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
> at
> org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:30)
> at org.apache.spark.repl.ExecutorClassL
> oader.findClass(ExecutorClassLoader.scala:77)
> ... 30 more
>
>
Re: java.lang.ClassNotFoundException: $anonfun$1
Posted by Jeff Zhang <zj...@gmail.com>.
It seems CDH specific issue, you might be better to ask cloudera forum.
Rob Anderson <ro...@gmail.com>于2017年3月7日周二 上午9:02写道：
> Hey Everyone,
>
> We're running Zeppelin 0.7.0. We've just cut over to spark2, using
> scala11 via the CDH parcel (SPARK2-2.0.0.cloudera1-1.cdh5.7.0.p0.113931).
>
> Running a simple job, throws a "Caused by: java.lang.ClassNotFoundException:
> $anonfun$1". It appears that during execution time on the yarn hosts,
> the native CDH spark1.5 jars are loaded before the new spark2 jars. I've
> tried using spark.yarn.archive to specify the spark2 jars in hdfs as well
> as using other spark options, none of which seems to make a difference.
>
>
> Any suggestions you can offer is appreciated.
>
> Thanks,
>
> Rob
>
> ------------------------
>
>
> %spark
> val taxonomy = sc.textFile("/user/user1/data/")
> .map(l => l.split("\t"))
>
> %spark
> taxonomy.first
>
>
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 0
> in stage 1.0 failed 4 times, most recent failure: Lost task 0.3 in stage
> 1.0 (TID 7, data08.hadoop.prod.ostk.com, executor 2):
> java.lang.ClassNotFoundException: $anonfun$1
> at
> org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:82)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
> at java.lang.Class.forName0(Native Method)
> at java.lang.Class.forName(Class.java:348)
> at
> org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:67)
> at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1613)
> at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1518)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1774)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.readObject(ObjectInputStream.java:371)
> at
> org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:75)
> at
> org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:114)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> 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:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.ClassNotFoundException: $anonfun$1
> at java.lang.ClassLoader.findClass(ClassLoader.java:530)
> at
> org.apache.spark.util.ParentClassLoader.findClass(ParentClassLoader.scala:26)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
> at
> org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:34)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
> at
> org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:30)
> at
> org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:77)
> ... 30 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:1669)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1624)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1613)
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
> at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1893)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1906)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1919)
> at org.apache.spark.rdd.RDD$$anonfun$take$1.apply(RDD.scala:1318)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
> at org.apache.spark.rdd.RDD.take(RDD.scala:1292)
> at org.apache.spark.rdd.RDD$$anonfun$first$1.apply(RDD.scala:1332)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
> at org.apache.spark.rdd.RDD.first(RDD.scala:1331)
> ... 37 elided
> Caused by: java.lang.ClassNotFoundException: $anonfun$1
> at
> org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:82)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
> at java.lang.Class.forName0(Native Method)
> at java.lang.Class.forName(Class.java:348)
> at
> org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:67)
> at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1613)
> at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1518)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1774)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2000)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1924)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1801)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1351)
> at java.io.ObjectInputStream.readObject(ObjectInputStream.java:371)
> at
> org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:75)
> at
> org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:114)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:86)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> ... 1 more
> Caused by: java.lang.ClassNotFoundException: $anonfun$1
> at java.lang.ClassLoader.findClass(ClassLoader.java:530)
> at
> org.apache.spark.util.ParentClassLoader.findClass(ParentClassLoader.scala:26)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
> at
> org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:34)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
> at
> org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:30)
> at org.apache.spark.repl.ExecutorClassL
> oader.findClass(ExecutorClassLoader.scala:77)
> ... 30 more
>