Spark的使用

野性酷女 2023-01-01 03:45 87阅读 0赞

# 1、执行Spark程序 #

spark-submit --class org.apache.spark.examples.SparkPi --master spark://hadoop01:7077 --executor-memory 1G --total-executor-cores 2 /mine/spark-3.0.1-bin-hadoop3.2/examples/jars/spark-examples_2.12-3.0.1.jar 10000

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3d0bDE5OTI_size_16_color_FFFFFF_t_70][]

# 2、WordCount程序 #

## pom.xml： ##

<?xml version="1.0" encoding="UTF-8"?>
    <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/xsd/maven-4.0.0.xsd">
        <modelVersion>4.0.0</modelVersion>
    
        <groupId>spark</groupId>
        <artifactId>spark</artifactId>
        <version>1.0-SNAPSHOT</version>
    
        <properties>
            <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
            <maven.compiler.source>1.8</maven.compiler.source>
            <maven.compiler.target>1.8</maven.compiler.target>
            <maven.compiler.compilerVersion>1.8</maven.compiler.compilerVersion>
            <spark.version>3.0.1</spark.version>
            <scala.version>2.12</scala.version>
            <hadoop.version>3.2.1</hadoop.version>
        </properties>
    
        <dependencies>
            
            <dependency>
                <groupId>org.projectlombok</groupId>
                <artifactId>lombok</artifactId>
                <version>1.18.16</version>
            </dependency>
    
            <dependency>
                <groupId>org.apache.spark</groupId>
                <artifactId>spark-core_${scala.version}</artifactId>
                <version>${spark.version}</version>
            </dependency>
            <dependency>
                <groupId>org.apache.spark</groupId>
                <artifactId>spark-sql_${scala.version}</artifactId>
                <version>${spark.version}</version>
            </dependency>
            <dependency>
                <groupId>org.apache.spark</groupId>
                <artifactId>spark-hive_${scala.version}</artifactId>
                <version>${spark.version}</version>
            </dependency>
            <dependency>
                <groupId>org.apache.spark</groupId>
                <artifactId>spark-streaming_${scala.version}</artifactId>
                <version>${spark.version}</version>
            </dependency>
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-client</artifactId>
                <version>${hadoop.version}</version>
            </dependency>
            <dependency>
                <groupId>org.apache.spark</groupId>
                <artifactId>spark-mllib_${scala.version}</artifactId>
                <version>${spark.version}</version>
            </dependency>
    
    
        </dependencies>
    
    
        <build>
            <finalName>Spark</finalName>
            <sourceDirectory>src/main/scala</sourceDirectory>
            <testSourceDirectory>src/test/scala</testSourceDirectory>
            <plugins>
                <plugin>
                        <groupId>net.alchim31.maven</groupId>
                        <artifactId>scala-maven-plugin</artifactId>
                        <version>4.4.0</version>
    
                    <executions>
                        <execution>
                            <goals>
                                <goal>compile</goal>
                                <goal>testCompile</goal>
                            </goals>
                            <configuration>
                                <args>
                                    <arg>-dependencyfile</arg>
                                    <arg>${project.build.directory}/.scala_dependencies</arg>
                                </args>
                            </configuration>
                        </execution>
                    </executions>
                </plugin>
                <plugin>
                        <groupId>org.apache.maven.plugins</groupId>
                        <artifactId>maven-surefire-plugin</artifactId>
                        <version>2.22.2</version>
    
                    <configuration>
                        <useFile>false</useFile>
                        <disableXmlReport>true</disableXmlReport>
                        <includes>
                            <include>**/*Test.*</include>
                            <include>**/*Suite.*</include>
                        </includes>
                    </configuration>
                </plugin>
    
                <plugin>
                    <groupId>org.apache.maven.plugins</groupId>
                    <artifactId>maven-shade-plugin</artifactId>
                    <version>3.2.4</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>spark.WordCount</mainClass>
                                    </transformer>
                                </transformers>
                            </configuration>
                        </execution>
                    </executions>
                </plugin>
            </plugins>
        </build>
    
    </project>

## WordCount.scala： ##

package ljxwtl.cn
    
    import org.apache.spark.{SparkConf, SparkContext}
    
    object WordCount {
      def main(args: Array[String]): Unit = {
        val conf = new SparkConf().setAppName("WordCount")
        val sparkContext = new SparkContext(conf)
    
        val rdd = sparkContext.textFile(args(0)).flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_)
    
        val result = rdd.collect()
    
        println(result.toBuffer)
      }
    }

spark-submit --master spark://hadoop01:7077 --class ljxwtl.cn.WordCount  --executor-memory=512m --total-executor-cores=2 Spark.jar hdfs://hadoop01:9000/wordcount.txt

![20210102144833706.png][]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3d0bDE5OTI_size_16_color_FFFFFF_t_70]: /images/20221120/95805f75841647878fe906adb2f61be0.png
[20210102144833706.png]: /images/20221120/b0176f59b0a94e18a6fd07ab7178bb7e.png