java.lang.NoClassDefFoundError: org/apache/spark/Logging

Question

I'm always getting the following error.Can somebody help me please?

Exception in thread "main" java.lang.NoClassDefFoundError: org/apache/spark/Logging
    at java.lang.ClassLoader.defineClass1(Native Method)
    at java.lang.ClassLoader.defineClass(ClassLoader.java:763)
    at java.security.SecureClassLoader.defineClass(SecureClassLoader.java:142)
    at java.net.URLClassLoader.defineClass(URLClassLoader.java:467)
    at java.net.URLClassLoader.access$100(URLClassLoader.java:73)
    at java.net.URLClassLoader$1.run(URLClassLoader.java:368)
    at java.net.URLClassLoader$1.run(URLClassLoader.java:362)
    at java.security.AccessController.doPrivileged(Native Method)
    at java.net.URLClassLoader.findClass(URLClassLoader.java:361)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
    at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:331)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
    at com.datastax.spark.connector.japi.DStreamJavaFunctions.<init>(DStreamJavaFunctions.java:24)
    at com.datastax.spark.connector.japi.CassandraStreamingJavaUtil.javaFunctions(CassandraStreamingJavaUtil.java:55)
    at SparkStream.main(SparkStream.java:51)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at com.intellij.rt.execution.application.AppMain.main(AppMain.java:147)
Caused by: java.lang.ClassNotFoundException: org.apache.spark.Logging
    at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
    at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:331)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
    ... 20 more

When I compile the following code. I've searched the web but didn't find a solution. I've got the error when I added the saveToCassandra.

import com.datastax.spark.connector.japi.CassandraStreamingJavaUtil;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.streaming.Duration;
import org.apache.spark.streaming.api.java.JavaDStream;
import org.apache.spark.streaming.api.java.JavaPairInputDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;
import org.apache.spark.streaming.kafka.KafkaUtils;

import java.io.Serializable;
import java.util.Collections;
import java.util.HashMap;
import java.util.Map;
import java.util.Set;

import static com.datastax.spark.connector.japi.CassandraJavaUtil.mapToRow;

/**
 * Created by jonas on 10/10/16.
 */
public class SparkStream implements Serializable{
        public static void main(String[] args) throws Exception{
        SparkConf conf = new SparkConf(true)
                .setAppName("TwitterToCassandra")
                .setMaster("local[*]")
                .set("spark.cassandra.connection.host", "127.0.0.1")
                .set("spark.cassandra.connection.port", "9042");
;
        JavaSparkContext sc = new JavaSparkContext(conf);
        JavaStreamingContext ssc = new JavaStreamingContext(sc, new Duration(5000));

        Map<String, String> kafkaParams = new HashMap<>();
        kafkaParams.put("bootstrap.servers", "localhost:9092");
        Set<String> topics = Collections.singleton("Test");

        JavaPairInputDStream<String, String> directKafkaStream = KafkaUtils.createDirectStream(
                ssc,
                String.class,
                String.class,
                kafka.serializer.StringDecoder.class,
                kafka.serializer.StringDecoder.class,
                kafkaParams,
                topics
        );

        JavaDStream<Tweet> createTweet = directKafkaStream.map(s -> createTweet(s._2));


        CassandraStreamingJavaUtil.javaFunctions(createTweet)
                .writerBuilder("mykeyspace", "rawtweet", mapToRow(Tweet.class))
                .saveToCassandra();

        ssc.start();
        ssc.awaitTermination();

    }


    public static Tweet createTweet(String rawKafka){
        String[] splitted = rawKafka.split("\\|");
        Tweet t = new Tweet(splitted[0], splitted[1], splitted[2], splitted[3]);
        return t;
    }
}

My pom is the following.

<?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>com.company</groupId>
    <artifactId>Sentiment</artifactId>
    <version>1.0-SNAPSHOT</version>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>

    <repositories>
        <repository>
            <id>twitter4j.org</id>
            <name>twitter4j.org Repository</name>
            <url>http://twitter4j.org/maven2</url>
            <releases>
                <enabled>true</enabled>
            </releases>
            <snapshots>
                <enabled>true</enabled>
            </snapshots>
        </repository>
    </repositories>

    <dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>2.0.1</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.10</artifactId>
            <version>2.0.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.10</artifactId>
            <version>2.0.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
            <version>2.0.1</version>
        </dependency>


        <!-- https://mvnrepository.com/artifact/org.scala-lang/scala-library -->
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>2.11.8</version>
        </dependency>



        <!-- https://mvnrepository.com/artifact/com.datastax.spark/spark-cassandra-connector_2.10 -->
        <dependency>
            <groupId>com.datastax.spark</groupId>
            <artifactId>spark-cassandra-connector_2.10</artifactId>
            <version>1.6.2</version>
        </dependency>

        <dependency>
            <groupId>org.apache.kafka</groupId>
            <artifactId>kafka_2.10</artifactId>
            <version>0.9.0.0</version>
        </dependency>

        <dependency>
            <groupId>org.twitter4j</groupId>
            <artifactId>twitter4j-core</artifactId>
            <version>[4.0,)</version>
        </dependency>

        <dependency>
            <groupId>org.twitter4j</groupId>
            <artifactId>twitter4j-stream</artifactId>
            <version>4.0.4</version>
        </dependency>

        <dependency>
            <groupId>org.twitter4j</groupId>
            <artifactId>twitter4j-async</artifactId>
            <version>4.0.4</version>
        </dependency>
    </dependencies>


</project>

Answer 1

org.apache.spark.Logging is available in Spark version 1.5.2 or lower version. It is not in the 2.0.0. Pls change versions as follows

    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-streaming_2.11</artifactId>
        <version>1.5.2</version>
    </dependency>

    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-core_2.10</artifactId>
        <version>1.5.2</version>
    </dependency>

    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-sql_2.10</artifactId>
        <version>1.5.2</version>
    </dependency>

    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
        <version>1.6.2</version>
    </dependency>

Answer 2

该错误是因为您将 Spark 2.0 库与 Spark 1.6 中的连接器（它查找 Spark 1.6 日志记录类。使用 2.0.5 版本的连接器）一起使用。

Answer 3

It's because of the missing of org.apache.spark.Logging class since 1.5.2, just like everybody say. (Only org.apache.spark.internal.Logging exists in later version... )

But it seems none of the solution against maven can solve this dependency, so I just try to add this class to lib manually. Here is my way to fixed the problem:

1. Package the scala org.apache.spark.internal.Logging into a public jar. Or download it from https://raw.githubusercontent.com/swordsmanliu/SparkStreamingHbase/master/lib/spark-core_2.11-1.5.2.logging.jar (Thanks to this host.)

2. Move the jar into your spark cluster's jars directory.

3. Submit your project again, wish it will help u.

Answer 4

I got the solution by changing above mention jar.

Initially, I was having degraded jar for spark-kafka-streaming:

<dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
        <version>2.1.1</version></dependency>

I also removed multilple sl4j-log4j.jars and log4j.jars which I had added externally from spark and kafka jar library.

Answer 5

Download spark-core_2.11-1.5.2.logging.jar and use as --jar option

spark-submit --class com.SentimentTwiteer --packages "org.apache.spark:spark-streaming-twitter_2.11:1.6.3" --jars /root/Desktop/spark-core_2.11-1.5.2.logging.jar /root/Desktop/SentimentTwiteer.jar consumerKey consumerSecret accessToken accessTokenSecret yoursearchTag

https://github.com/sinhavicky4/SentimentTwiteer

Answer 6

One reason that may cause this problem is lib and class conflict . I faced this problem and solved it using some maven exclusions :

<dependency>
       <groupId>org.apache.spark</groupId>
       <artifactId>spark-core_2.11</artifactId>
       <version>2.0.0</version>
       <scope>provided</scope>
       <exclusions>
           <exclusion>
               <groupId>log4j</groupId>
               <artifactId>log4j</artifactId>
           </exclusion>
       </exclusions>
   </dependency>

   <dependency>
       <groupId>org.apache.spark</groupId>
       <artifactId>spark-streaming_2.11</artifactId>
       <version>2.0.0</version>
       <scope>provided</scope>
   </dependency>

   <dependency>
       <groupId>org.apache.spark</groupId>
       <artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
       <version>2.0.0</version>
       <exclusions>
           <exclusion>
               <groupId>org.slf4j</groupId>
               <artifactId>slf4j-log4j12</artifactId>
           </exclusion>
           <exclusion>
               <groupId>log4j</groupId>
               <artifactId>log4j</artifactId>
           </exclusion>
       </exclusions>
   </dependency>

Answer 7

this pom.xml is resolve my issue:

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.10</artifactId>
            <version>1.6.1</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.10</artifactId>
            <version>1.6.1</version>
        </dependency>

Answer 8

下载了 jar 并在 spark-submit 中使用 --jars，为我工作 spark-submit --class com.SentimentTwiteer --packages "org.apache.spark:spark-streaming-twitter_2.11:1.6.3" --jars /root/Desktop/spark-core_2.11-1.5.2.logging.jar /root/Desktop/SentimentTwiteer.jar XX XX XX XX

Answer 9

Download the below Jar ,and it into you library ,and it will work as expected.

https://raw.githubusercontent.com/swordsmanliu/SparkStreamingHbase/master/lib/spark-core_2.11-1.5.2.logging.jar

Answer 10

如果您使用的是 IntelliJ，只需选中“包含具有提供范围的依赖项”框，这将为您解决问题，而无需处理 pom 或手动下载文件。

Answer 11

its a version issue try with latest version

<dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>2.1.0</version>
            <scope>provided</scope>
        </dependency>
         <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
            <version>2.1.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>2.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.1.0</version>
        </dependency>

Answer 12

Missing logging Jar in your dependency jars list. Try to download "spark-core_2.11-1.5.2.logging" jar from mvn repository, then add it as external jar to your spark project, you don't get "java.lang.NoClassDefFoundError: org/apache/spark/Logging" error. Based on scala version you can download the jar{2.10,2.11,etc}.