spark scala maven简单创建工程与提交任务到yarn

第一步 :使用idea和maven开发和打包scala和spark程序
参考：https://blog.csdn.net/xingyx1990/article/details/80752041
（注意：我自身采用mvn命令打包的方式打包：mvn clean compile package）

第二步：其中的maven工程中需要配置java+scala的jar包的打包方式

如下，是我的spark的maven工程的pom.xml文件
（如下的spark只是用来做spark历史批处理测试使用，具体情况具体分析）

<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>cetcocean</groupId>
  <artifactId>SparkTest_Tank</artifactId>
  <packaging>jar</packaging>
  <version>1.0-SNAPSHOT</version>
  <inceptionYear>2008</inceptionYear>

  <properties>
    <maven.compiler.source>1.8</maven.compiler.source>
    <maven.compiler.target>1.8</maven.compiler.target>
    <encoding>UTF-8</encoding>
    <scala.version>2.11.12</scala.version>
    <spark.version>2.1.2</spark.version>
    <hadoop.version>2.7.2</hadoop.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>${scala.version}</version>
    </dependency>
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-core_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-sql_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-client</artifactId>
      <version>${hadoop.version}</version>
    </dependency>


    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>4.4</version>
      <scope>test</scope>
    </dependency>
    <dependency>
      <groupId>org.specs</groupId>
      <artifactId>specs</artifactId>
      <version>1.2.5</version>
      <scope>test</scope>
    </dependency>
  </dependencies>

  <!--使用构建工具：打包jar-->
  <build>
<!--    <sourceDirectory>src/main/java</sourceDirectory>
    <testSourceDirectory>src/test/scala</testSourceDirectory>-->

    <plugins>
      <!--(start) for package jar with dependencies -->
      <plugin>
        <artifactId>maven-assembly-plugin</artifactId>
        <version>3.0.0</version>
        <configuration>
          <archive>
            <manifest>
              <mainClass>cetcocean.TestLoadDbData</mainClass>
            </manifest>
          </archive>
          <descriptorRefs>
            <descriptorRef>jar-with-dependencies</descriptorRef>
          </descriptorRefs>
        </configuration>
        <executions>
          <execution>
            <id>make-assembly</id> <!-- this is used for inheritance merges -->
            <phase>package</phase> <!-- bind to the packaging phase -->
            <goals>
              <goal>single</goal>
            </goals>
          </execution>
        </executions>
      </plugin>
      <!--(end) for package jar with dependencies -->

      <!--scala的maven打包工具：-->
      <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>

参考：https://blog.csdn.net/lukabruce/article/details/81335205

第三步：提交spark应用到yarn集群
参考如下：https://www.cnblogs.com/LHWorldBlog/p/8414342.html
我的命令：

./spark-submit 
--master yarn 
--deploy-mode client 
--queue "spark" 
--class cetcocean.TestLoadDbData  
SparkTest_Tank-1.0-SNAPSHOT-jar-with-dependencies.jar

不足之处：需要添加spark-submit的优化参数。
例如：

./spark-submit 
--master yarn 
--deploy-mode client     #yarn上集群client模式部署
--queue "spark"    # 队列名称。在yarn下使用
--num-executors 48    #启动的executor数量。默认为2。在yarn下使用
 --driver-memory 2g   # 配置成1-2g即可，一半只是负责协调分派任务
 --executor-memory 7g    # 没过executor内存数量
 --executor-cores 3   #每个executor的核数。在yarn或者standalone下使用
SparkTest_Tank-1.0-SNAPSHOT-jar-with-dependencies.jar