java - 甚至无法在 Windows 上运行简单的 Spark 计数

Question

我有一份非常简单的工作，看起来像这样......

object FileCount {
  def main(args: Array[String]) {
    val sc = new SparkContext(new SparkConf().setAppName("Spark File Count").setMaster("local[8]"))
    val rdd = sc.parallelize(List("a", "b", "c", "d", "e"))
    val count = rdd.count()
    println(s"Count $count")
    sc.stop()
  }
}

这会导致这个非常丑陋且无用的堆栈跟踪......

16/12/21 17:05:45 INFO Executor: Fetching http://myipaddress:59850/jars/file-count-0.0.1-SNAPSHOT.jar with timestamp 1482357926972
16/12/21 17:05:45 INFO Utils: Fetching http://myipaddress:59850/jars/file-count-0.0.1-SNAPSHOT.jar to C:\Users\579912\AppData\Local\Temp\spark-2d04e486-3904-4c4b-ba1f-20c5d49049ff\userFiles-e72fd11f-6bf7-40d6-846a-ee86a59f4f09\fetchFileTemp6527719131307552432.tmp
16/12/21 17:05:45 INFO Executor: Fetching http://myipaddress:59850/jars/file-count-0.0.1-SNAPSHOT.jar with timestamp 1482357926972
16/12/21 17:05:45 ERROR Executor: Exception in task 2.0 in stage 0.0 (TID 2)
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$ShellCommandExecutor.execute(Shell.java:715)
        at org.apache.hadoop.fs.FileUtil.chmod(FileUtil.java:873)
        at org.apache.hadoop.fs.FileUtil.chmod(FileUtil.java:853)
        at org.apache.spark.util.Utils$.fetchFile(Utils.scala:407)
        at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:430)
        at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:422)
        at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:772)
        at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:98)
        at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:98)
        at scala.collection.mutable.HashTable$class.foreachEntry(HashTable.scala:226)
        at scala.collection.mutable.HashMap.foreachEntry(HashMap.scala:39)
        at scala.collection.mutable.HashMap.foreach(HashMap.scala:98)
        at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:771)
        at org.apache.spark.executor.Executor.org$apache$spark$executor$Executor$$updateDependencies(Executor.scala:422)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:206)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
        at java.lang.Thread.run(Unknown Source)
16/12/21 17:05:45 INFO Utils: Fetching http://myipaddress:59850/jars/file-count-0.0.1-SNAPSHOT.jar to C:\Users\579912\AppData\Local\Temp\spark-2d04e486-3904-4c4b-ba1f-20c5d49049ff\userFiles-e72fd11f-6bf7-40d6-846a-ee86a59f4f09\fetchFileTemp7055275334836023373.tmp
16/12/21 17:05:45 INFO Utils: C:\Users\579912\AppData\Local\Temp\spark-2d04e486-3904-4c4b-ba1f-20c5d49049ff\userFiles-e72fd11f-6bf7-40d6-846a-ee86a59f4f09\fetchFileTemp7055275334836023373.tmp has been previously copied to C:\Users\579912\AppData\Local\Temp\spark-2d04e486-3904-4c4b-ba1f-20c5d49049ff\userFiles-e72fd11f-6bf7-40d6-846a-ee86a59f4f09\file-count-0.0.1-SNAPSHOT.jar
16/12/21 17:05:45 WARN TaskSetManager: Lost task 2.0 in stage 0.0 (TID 2, localhost): 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$ShellCommandExecutor.execute(Shell.java:715)
        at org.apache.hadoop.fs.FileUtil.chmod(FileUtil.java:873)
        at org.apache.hadoop.fs.FileUtil.chmod(FileUtil.java:853)
        at org.apache.spark.util.Utils$.fetchFile(Utils.scala:407)
        at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:430)
        at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:422)
        at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:772)
        at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:98)
        at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:98)
        at scala.collection.mutable.HashTable$class.foreachEntry(HashTable.scala:226)
        at scala.collection.mutable.HashMap.foreachEntry(HashMap.scala:39)
        at scala.collection.mutable.HashMap.foreach(HashMap.scala:98)
        at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:771)
        at org.apache.spark.executor.Executor.org$apache$spark$executor$Executor$$updateDependencies(Executor.scala:422)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:206)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
        at java.lang.Thread.run(Unknown Source)

16/12/21 17:05:45 INFO Executor: Fetching http://myipaddress:59850/jars/file-count-0.0.1-SNAPSHOT.jar with timestamp 1482357926972
16/12/21 17:05:45 ERROR Executor: Exception in task 4.0 in stage 0.0 (TID 4)
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$ShellCommandExecutor.execute(Shell.java:715)
        at org.apache.hadoop.fs.FileUtil.chmod(FileUtil.java:873)
        at org.apache.hadoop.fs.FileUtil.chmod(FileUtil.java:853)
        at org.apache.spark.util.Utils$.fetchFile(Utils.scala:407)
        at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:430)
        at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:422)
        at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:772)
        at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:98)
        at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:98)
        at scala.collection.mutable.HashTable$class.foreachEntry(HashTable.scala:226)
        at scala.collection.mutable.HashMap.foreachEntry(HashMap.scala:39)
        at scala.collection.mutable.HashMap.foreach(HashMap.scala:98)
        at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:771)
        at org.apache.spark.executor.Executor.org$apache$spark$executor$Executor$$updateDependencies(Executor.scala:422)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:206)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
        at java.lang.Thread.run(Unknown Source)
16/12/21 17:05:45 ERROR TaskSetManager: Task 2 in stage 0.0 failed 1 times; aborting job
16/12/21 17:05:45 INFO TaskSetManager: Lost task 4.0 in stage 0.0 (TID 4) on executor localhost: java.lang.NullPointerException (null) [duplicate 1]
16/12/21 17:05:45 INFO TaskSchedulerImpl: Cancelling stage 0
16/12/21 17:05:45 INFO Executor: Executor is trying to kill task 0.0 in stage 0.0 (TID 0)
16/12/21 17:05:45 INFO TaskSchedulerImpl: Stage 0 was cancelled
16/12/21 17:05:45 INFO Executor: Executor is trying to kill task 1.0 in stage 0.0 (TID 1)
16/12/21 17:05:45 INFO Utils: Fetching http://myipaddress:59850/jars/file-count-0.0.1-SNAPSHOT.jar to C:\Users\579912\AppData\Local\Temp\spark-2d04e486-3904-4c4b-ba1f-20c5d49049ff\userFiles-e72fd11f-6bf7-40d6-846a-ee86a59f4f09\fetchFileTemp8100007898534254285.tmp
16/12/21 17:05:45 INFO DAGScheduler: ResultStage 0 (count at FileCount.scala:19) failed in 0.451 s
16/12/21 17:05:45 INFO Executor: Executor is trying to kill task 5.0 in stage 0.0 (TID 5)
16/12/21 17:05:45 INFO Executor: Executor is trying to kill task 6.0 in stage 0.0 (TID 6)
16/12/21 17:05:45 INFO Executor: Executor is trying to kill task 3.0 in stage 0.0 (TID 3)
16/12/21 17:05:45 INFO Executor: Executor is trying to kill task 7.0 in stage 0.0 (TID 7)
16/12/21 17:05:45 INFO DAGScheduler: Job 0 failed: count at FileCount.scala:19, took 0.847770 s
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 0.0 failed 1 times, most recent failure: Lost task 2.0 in stage 0.0 (TID 2, localhost): 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$ShellCommandExecutor.execute(Shell.java:715)
        at org.apache.hadoop.fs.FileUtil.chmod(FileUtil.java:873)
        at org.apache.hadoop.fs.FileUtil.chmod(FileUtil.java:853)
        at org.apache.spark.util.Utils$.fetchFile(Utils.scala:407)
        at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:430)
        at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:422)
        at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:772)
        at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:98)
        at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:98)
        at scala.collection.mutable.HashTable$class.foreachEntry(HashTable.scala:226)
        at scala.collection.mutable.HashMap.foreachEntry(HashMap.scala:39)
        at scala.collection.mutable.HashMap.foreach(HashMap.scala:98)
        at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:771)
        at org.apache.spark.executor.Executor.org$apache$spark$executor$Executor$$updateDependencies(Executor.scala:422)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:206)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
        at java.lang.Thread.run(Unknown Source)

Driver stacktrace:
        at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
        at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
        at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
        at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
        at scala.Option.foreach(Option.scala:236)
        at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
        at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
        at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
        at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
        at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
        at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858)
        at org.apache.spark.SparkContext.runJob(SparkContext.scala:1929)
        at org.apache.spark.rdd.RDD.count(RDD.scala:1157)
        at FileCount$.main(FileCount.scala:19)
        at FileCount.main(FileCount.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 org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
        at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
        at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
        at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
        at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.NullPointerException
        at java.lang.ProcessBuilder.start(Unknown Source)
        at org.apache.hadoop.util.Shell.runCommand(Shell.java:482)
        at org.apache.hadoop.util.Shell.run(Shell.java:455)
        at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:715)
        at org.apache.hadoop.fs.FileUtil.chmod(FileUtil.java:873)
        at org.apache.hadoop.fs.FileUtil.chmod(FileUtil.java:853)
        at org.apache.spark.util.Utils$.fetchFile(Utils.scala:407)
        at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:430)
        at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:422)
        at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:772)
        at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:98)
        at scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:98)
        at scala.collection.mutable.HashTable$class.foreachEntry(HashTable.scala:226)
        at scala.collection.mutable.HashMap.foreachEntry(HashMap.scala:39)
        at scala.collection.mutable.HashMap.foreach(HashMap.scala:98)
        at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:771)
        at org.apache.spark.executor.Executor.org$apache$spark$executor$Executor$$updateDependencies(Executor.scala:422)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:206)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
        at java.lang.Thread.run(Unknown Source)

有什么想法吗？我像这样运行它: spark-submit --master local[8] --class FileCount --verbose target/file-count.jar

Answer 1

推荐评论this对我来说非常有效。彻底解决了这个问题。