spark编写word count

创建SparkContext对象的时候需要传递SparkConf对象，SparkConf至少需要包含spark.master和spark.app.name这两个参数，不然的话程序不能正常运行

object WordCount {

  def main(args: Array[String]) {

    val conf = new SparkConf();
    // 设置应用的名称
    conf.setAppName("WC")
    // 设置master, local代表本地模式，可以直接在IDE中运行,也可以指定local[k],local[*]
    conf.setMaster("local")
    // spark集群模式，需要打成jar包，提交到spark集群运行
    // conf.setMaster("spark://m1:7077")

    // 设置executor可以使用的内存大小
    conf.set("spark.executor.memory", "512m")

    val sc = new SparkContext(conf)

    sc.textFile("hdfs://m1:9000/words.txt").flatMap(_.split(" ")).map((_, 1))
      .reduceByKey(_+_).saveAsTextFile("hdfs://m1:9000/wcOutPut/")
    sc.stop()
  }

}

maven pom.xml如下

<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>wordcount</groupId>
    <artifactId>wordcount</artifactId>
    <version>1.0-SNAPSHOT</version>
    <inceptionYear>2008</inceptionYear>
    <!-- 定义属性 -->

    <properties>
        <maven.compiler.source>1.7</maven.compiler.source>
        <maven.compiler.target>1.7</maven.compiler.target>
        <encoding>UTF-8</encoding>
        <scala.version>2.10.6</scala.version>
        <scala.compat.version>2.10</scala.compat.version>
    </properties>

    <!-- 引用依赖 -->
    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.10</artifactId>
            <version>1.6.3</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.10</artifactId>
            <version>1.6.3</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.5</version>
        </dependency>
    </dependencies>

    <!-- 构建 -->
    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <plugins>
            <!-- maven管理scala插件-->
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.0</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                        <configuration>
                            <args>
                                <arg>-make:transitive</arg>
                                <arg>-dependencyfile</arg>
                                <arg>${project.build.directory}/.scala_dependencies</arg>
                            </args>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
            <!-- 在maven构建生命周期的test phase执行一个应用的单元测试 -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-surefire-plugin</artifactId>
                <version>2.18.1</version>
                <configuration>
                    <useFile>false</useFile>
                    <disableXmlReport>true</disableXmlReport>
                    <includes>
                        <include>**/*Test.*</include>
                        <include>**/*Suite.*</include>
                    </includes>
                </configuration>
            </plugin>

            <!-- 使用maven插件对java工程进行打包 -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.3</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.ManifestResourceTransformer">
                                    <mainClass>cn.itcast.spark.WordCount</mainClass>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

 

打包提交spark集群运行

bin/spark-submit \
--class wordcount.WordCount \
--master spark://m1:7077 \
--executor-memory 512M \
--total-executor-cores 2 \
/home/hadoop/wordcount-1.0-SNAPSHOT.jar  

本地运行如果hdfs权限有问题，则可以按如下配置