spark程序异常:Exception in thread "main" java.io.IOException: No FileSystem for scheme: hdfs

命令:

java -jar myspark-1.0-SNAPSHOT.jar myspark-1.0-SNAPSHOT.jar hdfs://single:9000/input/word.txt hdfs://single:9000/output/out1

错误信息:

..........

14/11/23 06:14:18 INFO SparkDeploySchedulerBackend: Granted executor ID app-20141123061418-0011/0 on hostPort single:8091 with 8 cores, 200.0 MB RAM

14/11/23 06:14:18 INFO AppClient$ClientActor: Executor updated: app-20141123061418-0011/0 is now RUNNING

Exception in thread "main" java.io.IOException: No FileSystem for scheme: hdfs

at org.apache.hadoop.fs.FileSystem.getFileSystemClass(FileSystem.java:2421)

at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:2428)

at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:88)

at org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:2467)

at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:2449)

at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:367)

at org.apache.hadoop.fs.Path.getFileSystem(Path.java:287)

at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:221)

at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:270)

at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:140)

at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:207)

at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:205)

at scala.Option.getOrElse(Option.scala:120)

at org.apache.spark.rdd.RDD.partitions(RDD.scala:205)

at org.apache.spark.rdd.MappedRDD.getPartitions(MappedRDD.scala:28)

at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:207)

at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:205)

at scala.Option.getOrElse(Option.scala:120)

at org.apache.spark.rdd.RDD.partitions(RDD.scala:205)

at org.apache.spark.SparkContext.runJob(SparkContext.scala:898)

at org.apache.spark.rdd.RDD.count(RDD.scala:726)

at youling.studio.Main$.main(Main.scala:33)

at youling.studio.Main.main(Main.scala)

scala 代码:

package youling.studio

import org.apache.spark.SparkContext._

import org.apache.spark.{SparkConf, SparkContext}

import scala.collection.mutable.ListBuffer

/**

* Created by Administrator on 2014/11/23.

*/

object Main {

def main (args: Array[String]) {

if(args.length!=3) {

println("CMD:java -jar *.jar input output")

System.exit(0)

}

val jars = ListBuffer[String]()

args(0).split(',').map(jars += _)

val conf = new SparkConf()

conf.setMaster("spark://single:8081")

.setSparkHome("/cloud/spark-0.9.1-bin-hadoop2")

.setAppName("word count")

.setJars(jars)

.set("spark.executor.memory","200m")

val sc = new SparkContext(conf)

val data = sc.textFile(args(1))

data.cache

println(data.count)

data.flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_).map(x=>(x._2,x._1)).sortByKey(false).map(x=>(x._2,x._1)).saveAsTextFile(args(2))

}

}

错误原因:intellij idea打成的jar运行的时候没有找到hdfs类型的文件系统

解决:修改maven项目的pom文件,手动指定下面红色的部分

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"

xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
<modelVersion>4.0.0</modelVersion>

<groupId>youling.studio.spark</groupId>

<artifactId>myspark</artifactId>

<version>1.0-SNAPSHOT</version>

<inceptionYear>2008</inceptionYear>

<properties>

<scala.version>2.10.3</scala.version>

</properties>

<repositories>

<repository>

<id>scala-tools.org</id>

<name>Scala-Tools Maven2 Repository</name>

<url>http://scala-tools.org/repo-releases</url>

</repository>

</repositories>

<pluginRepositories>

<pluginRepository>

<id>scala-tools.org</id>

<name>Scala-Tools Maven2 Repository</name>

<url>http://scala-tools.org/repo-releases</url>

</pluginRepository>

</pluginRepositories>

<dependencies>

<dependency>

<groupId>org.scala-lang</groupId>

<artifactId>scala-library</artifactId>

<version>${scala.version}</version>

</dependency>

<dependency>

<groupId>junit</groupId>

<artifactId>junit</artifactId>

<version>4.4</version>

<scope>test</scope>

</dependency>

<dependency>

<groupId>org.apache.spark</groupId>

<artifactId>spark-core_2.10</artifactId>

<version>0.9.1</version>

</dependency>

<dependency>

<groupId>org.apache.spark</groupId>

<artifactId>spark-streaming_2.10</artifactId>

<version>0.9.1</version>

</dependency>

<dependency>

<groupId>org.apache.hadoop</groupId>

<artifactId>hadoop-common</artifactId>

<version>2.2.0</version>

</dependency>

<dependency>

<groupId>org.apache.hadoop</groupId>

<artifactId>hadoop-hdfs</artifactId>

<version>2.2.0</version>

</dependency>

<dependency>

<groupId>org.apache.hadoop</groupId>

<artifactId>hadoop-client</artifactId>

<version>2.2.0</version>

</dependency>

</dependencies>

<build>

<sourceDirectory>src/main/</sourceDirectory>

<testSourceDirectory>src/test/</testSourceDirectory>

<plugins>

<plugin>

<groupId>org.scala-tools</groupId>

<artifactId>maven-scala-plugin</artifactId>

<executions>

<execution>

<goals>

<goal>compile</goal>

<goal>testCompile</goal>

</goals>

</execution>

</executions>

<configuration>

<scalaVersion>2.10.3</scalaVersion>

</configuration>

</plugin>

<plugin>

<groupId>org.apache.maven.plugins</groupId>

<artifactId>maven-shade-plugin</artifactId>

<version>2.2</version>

<executions>

<execution>

<phase>package</phase>

<goals>

<goal>shade</goal>

</goals>

<configuration>

<filters>

<filter>

<artifact>*:*</artifact>

<excludes>

<exclude>META-INF/*.SF</exclude>

<exclude>META-INF/*.DSA</exclude>

<exclude>META-INF/*.RSA</exclude>

</excludes>

</filter>

</filters>

<transformers>

<transformer

implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">

<resource>reference.conf</resource>

</transformer>

<transformer

implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">

<manifestEntries>

<Main-Class>youling.studio.Main</Main-Class>

</manifestEntries>

</transformer>

<transformer

implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">

<resource>META-INF/services/org.apache.hadoop.fs.FileSystem</resource>

</transformer>

</transformers>

</configuration>

</execution>

</executions>

</plugin>

</plugins>

</build>

<reporting>

<plugins>

<plugin>

<groupId>org.scala-tools</groupId>

<artifactId>maven-scala-plugin</artifactId>

<configuration>

<scalaVersion>${scala.version}</scalaVersion>

</configuration>

</plugin>

</plugins>

</reporting>

</project>