This a hadoop-side stack trace it looks like the code is trying to get the filesystem permissions by running
%HADOOP_HOME%\bin\WINUTILS.EXE ls -F and something is triggering a null pointer exception. There isn't any HADOOP- JIRA with this specific stack trace in it, so it's not a known/fixed problem. At a guess, your environment HADOOP_HOME environment variable isn't point to the right place. If that's the case there should have been a warning in the logs Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe. : java.lang.NullPointerException at java.lang.ProcessBuilder.start(Unknown Source) at org.apache.hadoop.util.Shell.runCommand(Shell.java:482) at org.apache.hadoop.util.Shell.run(Shell.java:455) at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:715) at org.apache.hadoop.util.Shell.execCommand(Shell.java:808) at org.apache.hadoop.util.Shell.execCommand(Shell.java:791) at org.apache.hadoop.fs.FileUtil.execCommand(FileUtil.java:1097) at org.apache.hadoop.fs.RawLocalFileSystem$DeprecatedRawLocalFileStatus.loadPermissionInfo(RawLocalFileSystem.java:582) at org.apache.hadoop.fs.RawLocalFileSystem$DeprecatedRawLocalFileStatus.getPermission(RawLocalFileSystem.java:557) at org.apache.hadoop.fs.LocatedFileStatus.<init>(LocatedFileStatus.java:42) at org.apache.hadoop.fs.FileSystem$4.next(FileSystem.java:1699) at org.apache.hadoop.fs.FileSystem$4.next(FileSystem.java:1681) at org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:268) at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:228) at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:313) at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:203) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217) at scala.Option.getOrElse(Option.scala:120) at org.apache.spark.rdd.RDD.partitions(RDD.scala:217) at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217) at scala.Option.getOrElse(Option.scala:120) at org.apache.spark.rdd.RDD.partitions(RDD.scala:217) at org.apache.spark.api.python.PythonRDD.getPartitions(PythonRDD.scala:57) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217) at scala.Option.getOrElse(Option.scala:120) at org.apache.spark.rdd.RDD.partitions(RDD.scala:217) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1512) at org.apache.spark.rdd.RDD.collect(RDD.scala:813) at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:374) at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source) at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source) at java.lang.reflect.Method.invoke(Unknown Source) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379) at py4j.Gateway.invoke(Gateway.java:259) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.GatewayConnection.run(GatewayConnection.java:207) at java.lang.Thread.run(Unknown Source) -- Best Regards, Ayan Guha
