Я получаю сообщение об ошибке ниже при запуске моей программы.
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 5.0 failed 1 times, most recent failure: Lost task 0.0 in stage 5.0 (TID 3, localhost, executor driver): java.io.IOException: (null) entry in command string: null chmod 0644 C:\Out1\_temporary\0\_temporary\attempt_20190605185814_0005_m_000000_3\part-00000
at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:762)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:859)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:842)
at org.apache.hadoop.fs.RawLocalFileSystem.setPermission(RawLocalFileSystem.java:661)
at org.apache.hadoop.fs.ChecksumFileSystem$1.apply(ChecksumFileSystem.java:501)
at org.apache.hadoop.fs.ChecksumFileSystem$FsOperation.run(ChecksumFileSystem.java:482)
at org.apache.hadoop.fs.ChecksumFileSystem.setPermission(ChecksumFileSystem.java:498)
at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:467)
at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:433)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:908)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:801)
at org.apache.hadoop.mapred.TextOutputFormat.getRecordWriter(TextOutputFormat.java:123)
at org.apache.spark.internal.io.SparkHadoopWriter.open(SparkHadoopWriter.scala:89)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1133)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1125)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:108)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:338)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1517)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1505)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1504)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1504)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:814)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1732)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1687)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1676)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2029)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2050)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2082)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply$mcV$sp(PairRDDFunctions.scala:1151)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply(PairRDDFunctions.scala:1096)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply(PairRDDFunctions.scala:1096)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopDataset(PairRDDFunctions.scala:1096)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply$mcV$sp(PairRDDFunctions.scala:1070)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply(PairRDDFunctions.scala:1035)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply(PairRDDFunctions.scala:1035)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:1035)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply$mcV$sp(PairRDDFunctions.scala:961)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply(PairRDDFunctions.scala:961)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply(PairRDDFunctions.scala:961)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:960)
at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply$mcV$sp(RDD.scala:1489)
at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply(RDD.scala:1468)
at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply(RDD.scala:1468)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.RDD.saveAsTextFile(RDD.scala:1468)
at org.apache.spark.api.java.JavaRDDLike$class.saveAsTextFile(JavaRDDLike.scala:550)
at org.apache.spark.api.java.AbstractJavaRDDLike.saveAsTextFile(JavaRDDLike.scala:45)
at KafkaFile.BinaryConsumerFile.main(BinaryConsumerFile.java:28)
Caused by: java.io.IOException: (null) entry in command string: null chmod 0644 C:\Out1\_temporary\0\_temporary\attempt_20190605185814_0005_m_000000_3\part-00000
at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:762)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:859)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:842)
at org.apache.hadoop.fs.RawLocalFileSystem.setPermission(RawLocalFileSystem.java:661)
at org.apache.hadoop.fs.ChecksumFileSystem$1.apply(ChecksumFileSystem.java:501)
at org.apache.hadoop.fs.ChecksumFileSystem$FsOperation.run(ChecksumFileSystem.java:482)
at org.apache.hadoop.fs.ChecksumFileSystem.setPermission(ChecksumFileSystem.java:498)
at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:467)
at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:433)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:908)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:801)
at org.apache.hadoop.mapred.TextOutputFormat.getRecordWriter(TextOutputFormat.java:123)
at org.apache.spark.internal.io.SparkHadoopWriter.open(SparkHadoopWriter.scala:89)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1133)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1125)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:108)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:338)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Я использую IntelliJ IDE и добавил приведенную ниже информацию в pom.xml.
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>2.2.1</version>
</dependency>
</dependencies>
Itскачал все зависимости.Я попробовал Google, но не смог найти похожую проблему, нашел похожую ошибку, но не совсем эту.
Ниже мой код:
public class ABC{
public static void main(String[] args){
//Create a SparkContext to initialize
SparkConf conf = new SparkConf().setMaster("local").setAppName("Word Count");
// Create a Java version of the Spark Context
JavaSparkContext sc = new JavaSparkContext(conf);
// Load the text into a Spark RDD, which is a distributed representation of each line of text
JavaRDD<String> textFile = sc.textFile("C:\\wordlist.txt");
JavaPairRDD<String, Integer> counts = textFile
.flatMap(s -> Arrays.asList(s.split("[ ,]")).iterator())
.mapToPair(word -> new Tuple2<>(word, 1))
.reduceByKey((a, b) -> a + b);
counts.foreach(p -> System.out.println(p));
System.out.println("Total words: " + counts.count());
counts.saveAsTextFile("C:\\Out1");
}
}
Мне нужна помощь, чтобы решить эту проблему.Кроме того, в качестве второго вопроса, я могу случайно использовать один и тот же каталог для saveAsTextFile, если я запускаю программу более одного раза.В основном мне нужно сохранить файлы в одном каталогеПожалуйста, предложите.