[
https://issues.apache.org/jira/browse/SPARK-5334?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Kevin (Sangwoo) Kim resolved SPARK-5334.
----------------------------------------
Resolution: Fixed
Fix Version/s: 1.3.0
Target Version/s: 1.3.0, 1.4.0
related to SPARK-5671
> NullPointerException when getting files from S3 (hadoop 2.3+)
> -------------------------------------------------------------
>
> Key: SPARK-5334
> URL: https://issues.apache.org/jira/browse/SPARK-5334
> Project: Spark
> Issue Type: Bug
> Components: Input/Output
> Affects Versions: 1.2.0
> Environment: Spark 1.2 built with Hadoop 2.3+
> Reporter: Kevin (Sangwoo) Kim
> Fix For: 1.3.0
>
>
> In Spark 1.2 built with Hadoop 2.3+,
> unable to get files from AWS S3.
> Same codes works well with same setup in Spark built with Hadoop 2.2-.
> I saw that jets3t version changed in profile with Hadoop 2.3+, I guess there
> might be an issue with it.
> ===
> scala> sc.textFile("s3n://logs/log.2014-12-05.gz").count
> 15/01/20 11:22:40 INFO MemoryStore: ensureFreeSpace(104533) called with
> curMem=0, maxMem=27783541555
> 15/01/20 11:22:40 INFO MemoryStore: Block broadcast_2 stored as values in
> memory (estimated size 102.1 KB, free 25.9 GB)
> java.lang.NullPointerException
> at
> org.apache.hadoop.fs.s3native.NativeS3FileSystem.getFileStatus(NativeS3FileSystem.java:433)
> at org.apache.hadoop.fs.Globber.getFileStatus(Globber.java:57)
> at org.apache.hadoop.fs.Globber.glob(Globber.java:248)
> at org.apache.hadoop.fs.FileSystem.globStatus(FileSystem.java:1642)
> at
> org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:257)
> at
> org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:228)
> at
> org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:304)
> at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:199)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
> at scala.Option.getOrElse(Option.scala:120)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
> at org.apache.spark.rdd.MappedRDD.getPartitions(MappedRDD.scala:28)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
> at scala.Option.getOrElse(Option.scala:120)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1157)
> at org.apache.spark.rdd.RDD.count(RDD.scala:904)
> at $iwC$$iwC$$iwC$$iwC.<init>(<console>:13)
> at $iwC$$iwC$$iwC.<init>(<console>:18)
> at $iwC$$iwC.<init>(<console>:20)
> at $iwC.<init>(<console>:22)
> at <init>(<console>:24)
> at .<init>(<console>:28)
> 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:789)
> at
> org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1062)
> at
> org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:615)
> at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:646)
> at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:610)
> at
> org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:823)
> at
> org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:868)
> at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:780)
> at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:625)
> at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:633)
> at org.apache.spark.repl.SparkILoop.loop(SparkILoop.scala:638)
> at
> org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply$mcZ$sp(SparkILoop.scala:963)
> at
> org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply(SparkILoop.scala:911)
> at
> org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply(SparkILoop.scala:911)
> at
> scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
> at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:911)
> at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1006)
> 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:329)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:75)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
