不允许设置spark.sql.warehouse.dir，应该使用java静态地设置它以用于跨会话使用

k7fdbhmy  于 2021-05-27  发布在  Spark
关注(0)|答案(1)|浏览(849)

我试图学习spark，但在这里我发现了一个异常（不允许设置spark.sql.warehouse.dir，它应该为跨会话使用静态设置，异常是线程“main”java.lang.noclassdeffounderror:org/apache/hadoop/hdfs/distributedfilesystem中的异常）。我在Windows10电脑上工作。
主要类别：

package com.rakib;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;

import java.util.logging.Level;
import java.util.logging.Logger;

public class App {
    public static void main(String[] args) {

        System.setProperty("hadoop.home.dir", "c:/hadoop");
        Logger.getLogger("org.apache").setLevel(Level.WARNING);

        SparkSession session = SparkSession.builder().appName("SparkSQL").master("local[*]")
                .config("spark.sql.warehouse.dir", "file:///c:/temp/")
                .getOrCreate();

        Dataset<Row> dataSet = session.read().option("header", true).csv("src/main/resources/student.csv");
        dataSet.show();

        long numberOfRows = dataSet.count();
        System.out.println("Total : " + numberOfRows);

        session.close();
    }
}

例外情况：

20/08/17 12:12:27 INFO SharedState: Setting hive.metastore.warehouse.dir ('null') to the value of spark.sql.warehouse.dir ('file:///c:/temp/').
20/08/17 12:12:27 INFO SharedState: Warehouse path is 'file:///c:/temp/'.
20/08/17 12:12:27**WARN SharedState: Not allowing to set spark.sql.warehouse.dir or hive.metastore.warehouse.dir in SparkSession's options, it should be set statically for cross-session usages
Exception in thread "main" java.lang.NoClassDefFoundError: org/apache/hadoop/hdfs/DistributedFileSystem
    at**org.apache.spark.sql.execution.datasources.InMemoryFileIndex$.listLeafFiles(InMemoryFileIndex.scala:316)
    at org.apache.spark.sql.execution.datasources.InMemoryFileIndex$.$anonfun$bulkListLeafFiles$1(InMemoryFileIndex.scala:195)
    at scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:238)
    at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
    at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
    at scala.collection.TraversableLike.map(TraversableLike.scala:238)
    at scala.collection.TraversableLike.map$(TraversableLike.scala:231)
    at scala.collection.AbstractTraversable.map(Traversable.scala:108)
    at org.apache.spark.sql.execution.datasources.InMemoryFileIndex$.bulkListLeafFiles(InMemoryFileIndex.scala:187)
    at org.apache.spark.sql.execution.datasources.InMemoryFileIndex.listLeafFiles(InMemoryFileIndex.scala:135)
    at org.apache.spark.sql.execution.datasources.InMemoryFileIndex.refresh0(InMemoryFileIndex.scala:98)
    at org.apache.spark.sql.execution.datasources.InMemoryFileIndex.<init>(InMemoryFileIndex.scala:70)
    at org.apache.spark.sql.execution.datasources.DataSource.createInMemoryFileIndex(DataSource.scala:561)
    at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:399)
    at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:279)
    at org.apache.spark.sql.DataFrameReader.$anonfun$load$2(DataFrameReader.scala:268)
    at scala.Option.getOrElse(Option.scala:189)
    at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:268)
    at org.apache.spark.sql.DataFrameReader.csv(DataFrameReader.scala:705)
    at org.apache.spark.sql.DataFrameReader.csv(DataFrameReader.scala:535)
    at com.rakib.App.main(App.java:21)
Caused by: java.lang.ClassNotFoundException: org.apache.hadoop.hdfs.DistributedFileSystem
    at java.net.URLClassLoader.findClass(URLClassLoader.java:382)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:418)
    at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:355)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:351)
    ... 22 more
20/08/17 12:12:28 INFO SparkContext: Invoking stop() from shutdown hook
20/08/17 12:12:28 INFO SparkUI: Stopped Spark web UI at http://DESKTOP-3147U79:4040
20/08/17 12:12:28 INFO MapOutputTrackerMasterEndpoint: MapOutputTrackerMasterEndpoint stopped!
20/08/17 12:12:28 INFO MemoryStore: MemoryStore cleared
20/08/17 12:12:28 INFO BlockManager: BlockManager stopped
20/08/17 12:12:28 INFO BlockManagerMaster: BlockManagerMaster stopped
20/08/17 12:12:28 INFO OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: OutputCommitCoordinator stopped!
20/08/17 12:12:28 INFO SparkContext: Successfully stopped SparkContext
20/08/17 12:12:28 INFO ShutdownHookManager: Shutdown hook called
20/08/17 12:12:28 INFO ShutdownHookManager: Deleting directory C:\Users\itc\AppData\Local\Temp\spark-ab377bad-43d5-48ad-a938-b99234abe546

pom.xml文件

<?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>org.example</groupId>
    <artifactId>Test_One</artifactId>
    <version>1.0-SNAPSHOT</version>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>8</source>
                    <target>8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>

    <dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.12</artifactId>
            <version>3.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.12</artifactId>
            <version>3.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>3.3.0</version>
        </dependency>
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>1.2.17</version>
        </dependency>

    </dependencies>
</project>
Javahadoopapache-sparkapache-spark-sql

1条答案

按热度按时间
nx7onnlm

nx7onnlm1#

请将以下依赖项添加到您的 pom.xml 试一试，它应该会起作用 org.apache.hadoop.hdfs.DistributedFileSystem 课程是 hadoop-hdfs-client:3.3.0 引用中的依赖项：https://repo1.maven.org/maven2/org/apache/hadoop/

<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-hdfs-client</artifactId>
    <version>3.3.0</version>
</dependency>

<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-common</artifactId>
    <version>3.3.0</version>
</dependency>

相关性已更新 pom.xml 你的，

<?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>org.example</groupId>
    <artifactId>Test_One</artifactId>
    <version>1.0-SNAPSHOT</version>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>8</source>
                    <target>8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>

    <dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.12</artifactId>
            <version>3.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.12</artifactId>
            <version>3.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>3.3.0</version>
        </dependency>

        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>1.2.17</version>
        </dependency>

        <dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-hdfs-client</artifactId>
    <version>3.3.0</version>
</dependency>

<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-common</artifactId>
    <version>3.3.0</version>
</dependency>
</dependencies>
</project>

所以，请尝试一下，让我知道你是否可以继续Spark运行？

赞(0）分享  回复(0）举报  2021-05-27
我来回答

相关问题

    查看更多

    热门标签

    更多
    JavaquerypythonNode开发语言requestUtil数据库Table后端算法LoggerMessageElementParser

    最新问答

    更多
    • 蜀ICP备13028337号-1 大数据知识库 https://www.saoniuhuo.com © All rights reserved
    • 本站内容来源互联网,如果侵犯您的权益请联系我们删除, 联系方式：448109455@qq.com