1. 项目准备
1.1 demo代码
package ace.gjh.rdd
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}
object WordCountOnCluster {
def main(args: Array[String]): Unit = {
val conf = new SparkConf()
.setAppName("word-count")
.setMaster("spark://localhost:7077")
val context = new SparkContext(conf)
val rdd: RDD[String] = context.textFile("file:///home/gjh/spark/test/test.log", 2)
rdd.filter(log => "INFO".equals(log.split(" ")(2)))
.flatMap(_.split(" ")(3).split("\\|"))
.map((_, 1))
.groupByKey()
.map(t => (t._1, t._2.size))
.sortBy(t => t._2, false, 1)
.saveAsTextFile("file:///home/gjh/spark/test/result")
context.stop()
}
}
1.2 pom文件
<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>ace.gjh</groupId>
<artifactId>test-spark</artifactId>
<version>1.0-SNAPSHOT</version>
<inceptionYear>2008</inceptionYear>
<properties>
<scala.version>2.12.13</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.apache.spark</groupId>
<artifactId>spark-core_2.12</artifactId>
<version>3.1.1</version>
</dependency>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${scala.version}</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.12</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.specs</groupId>
<artifactId>specs</artifactId>
<version>1.2.5</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.scala-tools</groupId>
<artifactId>maven-scala-plugin</artifactId>
<version>2.11</version>
</dependency>
<dependency>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-eclipse-plugin</artifactId>
<version>2.5.1</version>
</dependency>
</dependencies>
<build>
<sourceDirectory>src/main/scala</sourceDirectory>
<testSourceDirectory>src/test/scala</testSourceDirectory>
<plugins>
<plugin>
<artifactId>maven-assembly-plugin</artifactId>
<configuration>
<archive>
<manifest>
<mainClass>ace.gjh.rdd.WordCountOnCluster</mainClass>
</manifest>
</archive>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
</configuration>
<executions>
<execution>
<id>make-assembly</id>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.scala-tools</groupId>
<artifactId>maven-scala-plugin</artifactId>
<executions>
<execution>
<goals>
<goal>compile</goal>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
<configuration>
<scalaVersion>${scala.version}</scalaVersion>
<args>
<arg>-target:jvm-1.8</arg>
</args>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-eclipse-plugin</artifactId>
<configuration>
<downloadSources>true</downloadSources>
<buildcommands>
<buildcommand>ch.epfl.lamp.sdt.core.scalabuilder</buildcommand>
</buildcommands>
<additionalProjectnatures>
<projectnature>ch.epfl.lamp.sdt.core.scalanature</projectnature>
</additionalProjectnatures>
<classpathContainers>
<classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
<classpathContainer>ch.epfl.lamp.sdt.launching.SCALA_CONTAINER</classpathContainer>
</classpathContainers>
</configuration>
</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>
2. 服务器运行
/<你的spark路径>/bin/spark-submit --master spark://localhost:7077 --class ace.gjh.rdd.WordCountOnCluster --total-executor-cores 2 test-spark-1.0-SNAPSHOT-jar-with-dependencies.jar