星火流在EC2上：螺纹＆QUOT异常;主＆QUOT; java.lang.ExceptionInInitializerError [英] Spark Streaming on EC2: Exception in thread "main" java.lang.ExceptionInInitializerError

查看：1691
本文介绍了星火流在EC2上：螺纹＆QUOT异常;主＆QUOT; java.lang.ExceptionInInitializerError的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！

问题描述

在我创建一个jar文件

我试图运行火花提交。当我在我的机器上本地运行它，它工作正常，但当部署到Amazon EC2上返回下面的错误。

 根@ IP-172-31-47-217斌] $ ./spark-submit --master本地[2] --class main.java.Streamer〜/ streaming-项目-1.0-JAR与 -  dependencies.jar
异常线程mainjava.lang.ExceptionInInitializerError
    在org.apache.spark.streaming.StreamingContext $＆LT;＆初始化GT;（StreamingContext.scala：728）。
    在org.apache.spark.streaming.StreamingContext $＆LT; clinit＆GT;（StreamingContext.scala）
    在org.apache.spark.streaming.StreamingContext＆LT;＆初始化GT;（StreamingContext.scala：81）。
    在main.java.Streamer $。主要（Streamer.scala：24）
    在main.java.Streamer.main（Streamer.scala）
    在sun.reflect.NativeMethodAccessorImpl.invoke0（本机方法）
    在sun.reflect.NativeMethodAccessorImpl.invoke（NativeMethodAccessorImpl.java:57）
    在sun.reflect.DelegatingMethodAccessorImpl.invoke（DelegatingMethodAccessorImpl.java:43）
    在java.lang.reflect.Method.invoke（Method.java:606）
    在org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:672)
    在org.apache.spark.deploy.SparkSubmit $ .doRunMain $ 1（SparkSubmit.scala：180）
    在org.apache.spark.deploy.SparkSubmit $ .submit（SparkSubmit.scala：205）
    在org.apache.spark.deploy.SparkSubmit $。主要（SparkSubmit.scala：120）
    在org.apache.spark.deploy.SparkSubmit.main（SparkSubmit.scala）
java.lang.NoSuchFieldException：引起SHUTDOWN_HOOK_PRIORITY
    在java.lang.Class.getField（Class.java:1592）
    在org.apache.spark.util.SparkShutdownHookManager.install（ShutdownHookManager.scala：220）
    在org.apache.spark.util.ShutdownHookManager $ .shutdownHooks $ lzycompute（ShutdownHookManager.scala：50）
    在org.apache.spark.util.ShutdownHookManager $ .shutdownHooks（ShutdownHookManager.scala：48）
    在org.apache.spark.util.ShutdownHookManager $ .addShutdownHook（ShutdownHookManager.scala：189）
    在org.apache.spark.util.ShutdownHookManager $＆LT;＆初始化GT;（ShutdownHookManager.scala：58）。
    在org.apache.spark.util.ShutdownHookManager $＆LT; clinit＆GT;（ShutdownHookManager.scala）
... 14个

下面是我的pom.xml文件：

 ＆LT;？XML版本=1.0编码=UTF-8＆GT？;
＆LT;项目＆GT;
    ＆LT;＆的groupId GT; astiefel＆LT; /的groupId＆GT;
    ＆LT;＆的artifactId GT;流媒体项目＆LT; / artifactId的＆GT;
    ＆LT; modelVersion＆GT; 4.0.0＆LT; / modelVersion＆GT;
    ＆LT;名称＆gt;横批项目和LT; /名称＆gt;
    ＆LT;包装和GT;＆罐子LT; /包装＆GT;
    ＆LT;＆版GT; 1.0 LT; /版本＆GT;
    ＆LT;性状＆gt;
        ＆LT; maven.compiler.source＆GT; 1.6 LT; /maven.compiler.source>
        ＆LT; maven.compiler.target＆GT; 1.6 LT; /maven.compiler.target>
        ＆LT;＆编码GT; UTF-8＆LT; /编码＆GT;
        ＆LT; scala.tools.version＆GT; 2.10 LT; /scala.tools.version>
        ＆LT;！ - 把集群的斯卡拉版本 - ＆GT;
        ＆LT; scala.version＆GT; 2.10.4＆LT; /scala.version>    ＆LT; /性状＆gt;
    ＆LT;依赖和GT;
        ＆LT;＆依赖性GT; ＆LT;！ - 星火依赖 - ＆GT;
            ＆LT;＆的groupId GT; org.apache.spark＆LT; /的groupId＆GT;
            ＆LT;＆的artifactId GT;火花core_2.10＆LT; / artifactId的＆GT;
            ＆LT;＆版GT; 1.5.1＆LT; /版本＆GT;
        ＆LT; /依赖性＆GT;
        ＆LT;＆依赖性GT;
            ＆LT;＆的groupId GT; org.apache.spark＆LT; /的groupId＆GT;
            ＆LT;＆的artifactId GT;火花streaming_2.10＆LT; / artifactId的＆GT;
            ＆LT;＆版GT; 1.5.1＆LT; /版本＆GT;
        ＆LT; /依赖性＆GT;
        ＆LT;＆依赖性GT;
            ＆LT;＆的groupId GT; org.scala浪＆LT; /的groupId＆GT;
            ＆LT;＆的artifactId GT;斯卡拉编译＆LT; / artifactId的＆GT;
            ＆LT;＆版GT; $ {scala.version}＆LT; /版本＆GT;
            ＆LT;＆范围GT;＆编译LT; /＆范围GT;
        ＆LT; /依赖性＆GT;
        ＆LT;＆依赖性GT;
            ＆LT;＆的groupId GT; org.apache.spark＆LT; /的groupId＆GT;
            ＆LT;＆的artifactId GT;火花mllib_2.10＆LT; / artifactId的＆GT;
            ＆LT;＆版GT; 1.0.0＆LT; /版本＆GT;
        ＆LT; /依赖性＆GT;
        ＆LT;＆依赖性GT;
            ＆LT;＆的groupId GT; org.apache.spark＆LT; /的groupId＆GT;
            ＆LT;＆的artifactId GT;火花mllib_2.10＆LT; / artifactId的＆GT;
            ＆LT;＆版GT; 1.3.1＆LT; /版本＆GT;
        ＆LT; /依赖性＆GT;
        ＆LT;＆依赖性GT;
            ＆LT;＆的groupId GT; org.scalanlp＆LT; /的groupId＆GT;
            ＆LT;＆的artifactId GT; breeze_2.10＆LT; / artifactId的＆GT;
            ＆LT;＆版GT; 0.10 LT; /版本＆GT;
        ＆LT; /依赖性＆GT;
        ＆LT;＆依赖性GT;
            ＆LT;＆的groupId GT; org.apache.spark＆LT; /的groupId＆GT;
            ＆LT;＆的artifactId GT;火花sql_2.10＆LT; / artifactId的＆GT;
            ＆LT;＆版GT; 1.4.0＆LT; /版本＆GT;
        ＆LT; /依赖性＆GT;
    ＆LT; /依赖和GT;    ＆LT;库＆GT;
        ＆LT;＆库GT;
            ＆LT;＆ID GT; Cloudera的-回购释放和LT; / ID＆GT;
            ＆LT; URL＆GT;的https：//repository.cloudera.com/artifactory/repo/< / URL＆GT;
        ＆LT; /存储库＆GT;
    ＆LT; /存储库＆GT;    ＆LT;建立＆GT;
        ＆LT; sourceDirectory＆GT;的src / main / java的＆LT; / sourceDirectory＆GT;
        ＆LT;＆插件GT;
            ＆LT;＆插件GT;
                ＆LT;！ - 看到http://davidb.github.com/scala-maven-plugin  - ＆GT;
                ＆LT;＆的groupId GT; net.alchim31.maven＆LT; /的groupId＆GT;
                ＆LT;＆的artifactId GT;斯卡拉，Maven的插件＆LT; / artifactId的＆GT;
                ＆LT;！ - ＆LT;＆版GT; 3.1.3＆LT; /版本＆GT;  - ＆GT;
                ＆LT;＆执行GT;
                    ＆LT;执行与GT;
                        ＆LT;目标＆GT;
                            ＆LT;＆目标GT;＆编译LT; /目标＆GT;
                            ＆LT;＆目标GT; testCompile＆LT; /目标＆GT;
                        ＆LT; /目标＆GT;
                        ＆LT;结构＆gt;
                            ＆LT;＆ARGS GT;
                                ＆LT;＆ARG GT; -make：传递＆LT; / ARG＆GT;
                                ＆LT;＆ARG GT; -dependencyfile＆LT; / ARG＆GT;
                                ＆LT; ARG方式＆gt; $ {} project.build.directory / scala_dependencies＆LT; / ARG＆GT;
                            ＆LT; / ARGS＆GT;
                        ＆LT; /结构＆gt;
                    ＆LT; /执行＆GT;
                ＆LT; /处决＆GT;
            ＆LT; /插件＆GT;
            ＆LT;＆插件GT;
                ＆LT;＆的groupId GT; org.apache.maven.plugins＆LT; /的groupId＆GT;
                ＆LT;＆的artifactId GT; Maven的万无一失，插件＆LT; / artifactId的＆GT;
                ＆LT;！ - ＆LT;＆版GT;＆2.13 LT; /版本＆GT;  - ＆GT;
                ＆LT;结构＆gt;
                    ＆LT; useFile＆GT;假LT; / useFile＆GT;
                    ＆LT; disableXmlReport＆GT;真＆LT; / disableXmlReport＆GT;
                    ＆LT;！ - 如果你有问题的classpath像NoDefClassError，...  - ＆GT;
                    ＆LT; useManifestOnlyJar＆GT;假LT; / useManifestOnlyJar＆GT;
                    ＆所述包括（includes）GT;
                        ＆LT;包括方式＆gt; ** / *测试*＆LT; /  - 包括GT;
                        ＆LT;包括方式＆gt; ** / *套房*＆LT; /  - 包括GT;
                    ＆LT; /  - 包括GT;
                ＆LT; /结构＆gt;
            ＆LT; /插件＆GT;            ＆LT;  - ！包命令插件 - ＆GT;
            ＆LT;＆插件GT;
                ＆LT;＆的artifactId GT; Maven的组装插件＆LT; / artifactId的＆GT;
                ＆LT;！ - ＆LT;＆版GT; 2.4.1＆LT; /版本＆GT;  - ＆GT;
                ＆LT;结构＆gt;
                    ＆LT; descriptorRefs＆GT;
                        ＆LT; descriptorRef＆GT; JAR-具有依赖性和LT; / descriptorRef＆GT;
                    ＆LT; / descriptorRefs＆GT;
                ＆LT; /结构＆gt;
                ＆LT;＆执行GT;
                    ＆LT;执行与GT;
                        ＆LT;＆ID GT;使组装和LT; / ID＆GT;
                        ＆LT;阶段＆gt;包装及LT; /阶段＆gt;
                        ＆LT;目标＆GT;
                            ＆LT;＆目标GT;单＆LT; /目标＆GT;
                        ＆LT; /目标＆GT;
                    ＆LT; /执行＆GT;
                ＆LT; /处决＆GT;
            ＆LT; /插件＆GT;
        ＆LT; /插件＆GT;
    ＆LT; /构建＆GT;
＆LT; /项目＆GT;


解决方案

当您启动火花EC2 默认的Hadoop版本是1.2​​.1。然而，最近的版本星火（至少1.5.1）要求，在Hadoop的2介绍了hadoop.fs.FileSystem类中的 SHUTDOWN_HOOK_PRIORITY 字段+

一个修复来解决这个问题是启动使用Hadoop版本2+的火花集群。参见火花EC2 --help 的可用选项。例如： - Hadoop的主要版本=纱将安装的Hadoop版本2.4

I am trying to run spark-submit on a jar file that I created. When I run it locally on my machine it works correctly but when deployed onto Amazon EC2 it returns the following error.

root@ip-172-31-47-217 bin]$ ./spark-submit --master local[2] --class main.java.Streamer ~/streaming-project-1.0-jar-with-dependencies.jar
Exception in thread "main" java.lang.ExceptionInInitializerError
    at org.apache.spark.streaming.StreamingContext$.<init>(StreamingContext.scala:728)
    at org.apache.spark.streaming.StreamingContext$.<clinit>(StreamingContext.scala)
    at org.apache.spark.streaming.StreamingContext.<init>(StreamingContext.scala:81)
    at main.java.Streamer$.main(Streamer.scala:24)
    at main.java.Streamer.main(Streamer.scala)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:606)
    at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:672)
    at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
    at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
    at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:120)
    at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.NoSuchFieldException: SHUTDOWN_HOOK_PRIORITY
    at java.lang.Class.getField(Class.java:1592)
    at org.apache.spark.util.SparkShutdownHookManager.install(ShutdownHookManager.scala:220)
    at org.apache.spark.util.ShutdownHookManager$.shutdownHooks$lzycompute(ShutdownHookManager.scala:50)
    at org.apache.spark.util.ShutdownHookManager$.shutdownHooks(ShutdownHookManager.scala:48)
    at org.apache.spark.util.ShutdownHookManager$.addShutdownHook(ShutdownHookManager.scala:189)
    at org.apache.spark.util.ShutdownHookManager$.<init>(ShutdownHookManager.scala:58)
    at org.apache.spark.util.ShutdownHookManager$.<clinit>(ShutdownHookManager.scala)
... 14 more

Below is my pom.xml file:

<?xml version="1.0" encoding="UTF-8"?>
<project>
    <groupId>astiefel</groupId>
    <artifactId>streaming-project</artifactId>
    <modelVersion>4.0.0</modelVersion>
    <name>Streamer Project</name>
    <packaging>jar</packaging>
    <version>1.0</version>
    <properties>
        <maven.compiler.source>1.6</maven.compiler.source>
        <maven.compiler.target>1.6</maven.compiler.target>
        <encoding>UTF-8</encoding>
        <scala.tools.version>2.10</scala.tools.version>
        <!-- Put the Scala version of the cluster -->
        <scala.version>2.10.4</scala.version>

    </properties>
    <dependencies>
        <dependency> <!-- Spark dependency -->
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.10</artifactId>
            <version>1.5.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.10</artifactId>
            <version>1.5.1</version>
        </dependency>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-compiler</artifactId>
            <version>${scala.version}</version>
            <scope>compile</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-mllib_2.10</artifactId>
            <version>1.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-mllib_2.10</artifactId>
            <version>1.3.1</version>
        </dependency>
        <dependency>
            <groupId>org.scalanlp</groupId>
            <artifactId>breeze_2.10</artifactId>
            <version>0.10</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.10</artifactId>
            <version>1.4.0</version>
        </dependency>
    </dependencies>

    <repositories>
        <repository>
            <id>cloudera-repo-releases</id>
            <url>https://repository.cloudera.com/artifactory/repo/</url>
        </repository>
    </repositories>

    <build>
        <sourceDirectory>src/main/java</sourceDirectory>
        <plugins>
            <plugin>
                <!-- see http://davidb.github.com/scala-maven-plugin -->
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <!--<version>3.1.3</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>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-surefire-plugin</artifactId>
                <!--<version>2.13</version>-->
                <configuration>
                    <useFile>false</useFile>
                    <disableXmlReport>true</disableXmlReport>
                    <!-- If you have classpath issue like NoDefClassError,... -->
                    <useManifestOnlyJar>false</useManifestOnlyJar>
                    <includes>
                        <include>**/*Test.*</include>
                        <include>**/*Suite.*</include>
                    </includes>
                </configuration>
            </plugin>

            <!-- "package" command plugin -->
            <plugin>
                <artifactId>maven-assembly-plugin</artifactId>
                <!--<version>2.4.1</version>-->
                <configuration>
                    <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>
        </plugins>
    </build>
</project>

解决方案

When you launch spark-ec2 the default hadoop version is 1.2.1. However, the recent Spark versions (at least 1.5.1) requires the SHUTDOWN_HOOK_PRIORITY field in the hadoop.fs.FileSystem class that was introduced in Hadoop 2+.

One fix to get around this problem is to start up your spark cluster with Hadoop version 2+. See spark-ec2 --help for available options. Example: --hadoop-major-version=yarn will install version 2.4 of Hadoop.

这篇关于星火流在EC2上：螺纹＆QUOT异常;主＆QUOT; java.lang.ExceptionInInitializerError的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！

查看全文
相关文章
其他开发最新文章
热门教程
热门工具
登录 关闭
扫码关注1秒登录
发送“验证码”获取 | 15天全站免登陆