[
https://issues.apache.org/jira/browse/SPARK-8368?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
CHEN Zhiwei updated SPARK-8368:
-------------------------------
Description:
After upgraded the cluster from spark 1.3.0 to 1.4.0(rc4), I encountered the
following exception:
======begin exception========
Exception in thread "main" java.lang.ClassNotFoundException:
com.yhd.ycache.magic.Model$$anonfun$9$$anonfun$10
at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
at java.lang.ClassLoader.loadClass(ClassLoader.java:425)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
at java.lang.ClassLoader.loadClass(ClassLoader.java:358)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:278)
at
org.apache.spark.util.InnerClosureFinder$$anon$4.visitMethodInsn(ClosureCleaner.scala:455)
at
com.esotericsoftware.reflectasm.shaded.org.objectweb.asm.ClassReader.accept(Unknown
Source)
at
com.esotericsoftware.reflectasm.shaded.org.objectweb.asm.ClassReader.accept(Unknown
Source)
at
org.apache.spark.util.ClosureCleaner$.getInnerClosureClasses(ClosureCleaner.scala:101)
at
org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:197)
at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:132)
at org.apache.spark.SparkContext.clean(SparkContext.scala:1891)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:294)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:293)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:148)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:109)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:286)
at org.apache.spark.rdd.RDD.map(RDD.scala:293)
at org.apache.spark.sql.DataFrame.map(DataFrame.scala:1210)
at com.yhd.ycache.magic.Model$.main(SSExample.scala:239)
at com.yhd.ycache.magic.Model.main(SSExample.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:664)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:169)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:192)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:111)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
===============end exception===========
I simplify the code that cause this issue, as following:
==========begin code==================
```
object Model extends Serializable{
def main(args: Array[String]) {
val Array(sql/*,usePartition,numClasses_, numTrees_,impurity_, maxDepth_,
maxBins_*/) = args
val sparkConf = new SparkConf().setAppName("Mode Example")
val sc = new SparkContext(sparkConf)
val hive = new HiveContext(sc)
//get data by hive sql
val rows = hive.sql(sql)
val data = rows.map(r => {
val arr = r.toSeq.toArray
val label = 1.0 //string2Int(arr(r.length-1).toString).toDouble
def fmap = (input: Any) => 1.0 //string2Int(input.toString).toDouble
val feature = arr.map(_=>1.0)
LabeledPoint(label, Vectors.dense(feature))
})
data.count()
}
}
```
=====end code===========
This code can run pretty well on spark-shell, but error when submit it to spark
cluster (standalone or local mode). I try the same code on spark 1.3.0(local
mode), and no exception is encountered.
was:
After upgraded the cluster from spark 1.3.0 to 1.4.0(rc4), I encountered the
following exception:
======begin exception========
Exception in thread "main" java.lang.ClassNotFoundException:
com.yhd.ycache.magic.Model$$anonfun$9$$anonfun$10
at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
at java.lang.ClassLoader.loadClass(ClassLoader.java:425)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
at java.lang.ClassLoader.loadClass(ClassLoader.java:358)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:278)
at
org.apache.spark.util.InnerClosureFinder$$anon$4.visitMethodInsn(ClosureCleaner.scala:455)
at
com.esotericsoftware.reflectasm.shaded.org.objectweb.asm.ClassReader.accept(Unknown
Source)
at
com.esotericsoftware.reflectasm.shaded.org.objectweb.asm.ClassReader.accept(Unknown
Source)
at
org.apache.spark.util.ClosureCleaner$.getInnerClosureClasses(ClosureCleaner.scala:101)
at
org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:197)
at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:132)
at org.apache.spark.SparkContext.clean(SparkContext.scala:1891)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:294)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:293)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:148)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:109)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:286)
at org.apache.spark.rdd.RDD.map(RDD.scala:293)
at org.apache.spark.sql.DataFrame.map(DataFrame.scala:1210)
at com.yhd.ycache.magic.Model$.main(SSExample.scala:239)
at com.yhd.ycache.magic.Model.main(SSExample.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:664)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:169)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:192)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:111)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
===============end exception===========
I simplify the code that cause this issue, as following:
==========begin code==================
object Model extends Serializable{
def main(args: Array[String]) {
val Array(sql/*,usePartition,numClasses_, numTrees_,impurity_, maxDepth_,
maxBins_*/) = args
val sparkConf = new SparkConf().setAppName("Mode Example")
val sc = new SparkContext(sparkConf)
val hive = new HiveContext(sc)
//get data by hive sql
val rows = hive.sql(sql)
val data = rows.map(r => {
val arr = r.toSeq.toArray
val label = 1.0 //string2Int(arr(r.length-1).toString).toDouble
def fmap = (input: Any) => 1.0 //string2Int(input.toString).toDouble
val feature = arr.map(_=>1.0)
LabeledPoint(label, Vectors.dense(feature))
})
data.count()
}
}
=====end code===========
This code can run pretty well on spark-shell, but error when submit it to spark
cluster (standalone or local mode). I try the same code on spark 1.3.0(local
mode), and no exception is encountered.
> ClassNotFoundException in closure for map
> ------------------------------------------
>
> Key: SPARK-8368
> URL: https://issues.apache.org/jira/browse/SPARK-8368
> Project: Spark
> Issue Type: Bug
> Components: Spark Core
> Affects Versions: 1.4.0
> Environment: Centos 6.5, java 1.7.0_67, scala 2.10.4. Build the
> project on Windows 7 and run in a spark standalone cluster(or local) mode on
> Centos 6.X.
> Reporter: CHEN Zhiwei
>
> After upgraded the cluster from spark 1.3.0 to 1.4.0(rc4), I encountered the
> following exception:
> ======begin exception========
> Exception in thread "main" java.lang.ClassNotFoundException:
> com.yhd.ycache.magic.Model$$anonfun$9$$anonfun$10
> at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
> at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
> at java.security.AccessController.doPrivileged(Native Method)
> at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:425)
> at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:358)
> at java.lang.Class.forName0(Native Method)
> at java.lang.Class.forName(Class.java:278)
> at
> org.apache.spark.util.InnerClosureFinder$$anon$4.visitMethodInsn(ClosureCleaner.scala:455)
> at
> com.esotericsoftware.reflectasm.shaded.org.objectweb.asm.ClassReader.accept(Unknown
> Source)
> at
> com.esotericsoftware.reflectasm.shaded.org.objectweb.asm.ClassReader.accept(Unknown
> Source)
> at
> org.apache.spark.util.ClosureCleaner$.getInnerClosureClasses(ClosureCleaner.scala:101)
> at
> org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:197)
> at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:132)
> at org.apache.spark.SparkContext.clean(SparkContext.scala:1891)
> at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:294)
> at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:293)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:148)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:109)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:286)
> at org.apache.spark.rdd.RDD.map(RDD.scala:293)
> at org.apache.spark.sql.DataFrame.map(DataFrame.scala:1210)
> at com.yhd.ycache.magic.Model$.main(SSExample.scala:239)
> at com.yhd.ycache.magic.Model.main(SSExample.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at
> org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:664)
> at
> org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:169)
> at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:192)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:111)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> ===============end exception===========
> I simplify the code that cause this issue, as following:
> ==========begin code==================
> ```
> object Model extends Serializable{
> def main(args: Array[String]) {
> val Array(sql/*,usePartition,numClasses_, numTrees_,impurity_,
> maxDepth_, maxBins_*/) = args
> val sparkConf = new SparkConf().setAppName("Mode Example")
> val sc = new SparkContext(sparkConf)
> val hive = new HiveContext(sc)
> //get data by hive sql
> val rows = hive.sql(sql)
> val data = rows.map(r => {
> val arr = r.toSeq.toArray
> val label = 1.0 //string2Int(arr(r.length-1).toString).toDouble
> def fmap = (input: Any) => 1.0 //string2Int(input.toString).toDouble
> val feature = arr.map(_=>1.0)
> LabeledPoint(label, Vectors.dense(feature))
> })
> data.count()
> }
> }
> ```
> =====end code===========
> This code can run pretty well on spark-shell, but error when submit it to
> spark cluster (standalone or local mode). I try the same code on spark
> 1.3.0(local mode), and no exception is encountered.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
