Just launched an EC2 cluster from git hash
9fe693b5b6ed6af34ee1e800ab89c8a11991ea38. Calling take() on an RDD
accessing data in S3 yields the following error output.
I understand that NoClassDefFoundError errors may mean something in the
deployment was messed up. Is that correct? When I launch a cluster using
spark-ec2, I expect all critical deployment details to be taken care of by
the script.
So is something in the deployment executed by spark-ec2 borked?
Nick
java.lang.NoClassDefFoundError: org/jets3t/service/S3ServiceException
at
org.apache.hadoop.fs.s3native.NativeS3FileSystem.createDefaultStore(NativeS3FileSystem.java:224)
at
org.apache.hadoop.fs.s3native.NativeS3FileSystem.initialize(NativeS3FileSystem.java:214)
at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:1386)
at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:66)
at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:1404)
at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:254)
at org.apache.hadoop.fs.Path.getFileSystem(Path.java:187)
at
org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:176)
at
org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:208)
at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:176)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:203)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:201)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:201)
at org.apache.spark.rdd.MappedRDD.getPartitions(MappedRDD.scala:28)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:203)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:201)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:201)
at
org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:203)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:201)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:201)
at org.apache.spark.ShuffleDependency.<init>(Dependency.scala:71)
at org.apache.spark.rdd.ShuffledRDD.getDependencies(ShuffledRDD.scala:79)
at org.apache.spark.rdd.RDD$$anonfun$dependencies$2.apply(RDD.scala:190)
at org.apache.spark.rdd.RDD$$anonfun$dependencies$2.apply(RDD.scala:188)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.dependencies(RDD.scala:188)
at
org.apache.spark.scheduler.DAGScheduler.getPreferredLocs(DAGScheduler.scala:1144)
at org.apache.spark.SparkContext.getPreferredLocs(SparkContext.scala:903)
at
org.apache.spark.rdd.PartitionCoalescer.currPrefLocs(CoalescedRDD.scala:174)
at
org.apache.spark.rdd.PartitionCoalescer$LocationIterator$$anonfun$4$$anonfun$apply$2.apply(CoalescedRDD.scala:191)
at
org.apache.spark.rdd.PartitionCoalescer$LocationIterator$$anonfun$4$$anonfun$apply$2.apply(CoalescedRDD.scala:190)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:350)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:350)
at
org.apache.spark.rdd.PartitionCoalescer$LocationIterator.<init>(CoalescedRDD.scala:185)
at
org.apache.spark.rdd.PartitionCoalescer.setupGroups(CoalescedRDD.scala:236)
at org.apache.spark.rdd.PartitionCoalescer.run(CoalescedRDD.scala:337)
at org.apache.spark.rdd.CoalescedRDD.getPartitions(CoalescedRDD.scala:83)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:203)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:201)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:201)
at org.apache.spark.rdd.MappedRDD.getPartitions(MappedRDD.scala:28)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:203)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:201)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:201)
at org.apache.spark.rdd.RDD.take(RDD.scala:1036)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:26)
at $iwC$$iwC$$iwC.<init>(<console>:31)
at $iwC$$iwC.<init>(<console>:33)
at $iwC.<init>(<console>:35)
at <init>(<console>:37)
at .<init>(<console>:41)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:788)
at
org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1056)
at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:614)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:645)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:609)
at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:796)
at
org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:841)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:753)
at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:601)
at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:608)
at org.apache.spark.repl.SparkILoop.loop(SparkILoop.scala:611)
at
org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply$mcZ$sp(SparkILoop.scala:936)
at
org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply(SparkILoop.scala:884)
at
org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply(SparkILoop.scala:884)
at
scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:884)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:982)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.deploy.SparkSubmit$.launch(SparkSubmit.scala:303)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:55)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.ClassNotFoundException:
org.jets3t.service.S3ServiceException
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)
... 92 more
