org.apache.spark.SparkException: java.nio.BufferUnderflowException - PullRequest
Новая
       31

org.apache.spark.SparkException: java.nio.BufferUnderflowException

0 голосов
/ 10 октября 2019

Я получаю это исключение при запуске задания на искру: 


Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 10.0 failed 1 times, most recent failure: Lost task 2.0 in stage 10.0 (TID 32, localhost, executor driver): java.nio.BufferUnderflowException
        at java.nio.HeapByteBuffer.get(HeapByteBuffer.java:145)
        at java.nio.ByteBuffer.get(ByteBuffer.java:694)
        at kafka.api.ApiUtils$.readShortString(ApiUtils.scala:40)
        at kafka.api.TopicData$.readFrom(FetchResponse.scala:96)
        at kafka.api.FetchResponse$$anonfun$4.apply(FetchResponse.scala:170)
        at kafka.api.FetchResponse$$anonfun$4.apply(FetchResponse.scala:169)
        at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
        at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
        at scala.collection.immutable.Range.foreach(Range.scala:141)
        at scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:251)
        at scala.collection.AbstractTraversable.flatMap(Traversable.scala:105)
        at kafka.api.FetchResponse$.readFrom(FetchResponse.scala:169)
        at kafka.consumer.SimpleConsumer.fetch(SimpleConsumer.scala:135)
        at org.apache.spark.streaming.kafka.KafkaRDD$KafkaRDDIterator.fetchBatch(KafkaRDD.scala:192)
        at org.apache.spark.streaming.kafka.KafkaRDD$KafkaRDDIterator.getNext(KafkaRDD.scala:208)
        at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
        at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
        at scala.collection.Iterator$class.foreach(Iterator.scala:727)
        at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
        at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$32.apply(RDD.scala:912)
        at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$32.apply(RDD.scala:912)
        at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1888)
        at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1888)
        at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
        at org.apache.spark.scheduler.Task.run(Task.scala:89)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:242)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
        at java.lang.Thread.run(Thread.java:745)

Driver stacktrace:
        at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1433)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1421)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1420)
        at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
        at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
        at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1420)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
        at scala.Option.foreach(Option.scala:236)
        at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1644)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1603)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1592)
        at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
        at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
        at org.apache.spark.SparkContext.runJob(SparkContext.scala:1862)
        at org.apache.spark.SparkContext.runJob(SparkContext.scala:1875)
        at org.apache.spark.SparkContext.runJob(SparkContext.scala:1888)
        at org.apache.spark.SparkContext.runJob(SparkContext.scala:1959)
        at org.apache.spark.rdd.RDD$$anonfun$foreach$1.apply(RDD.scala:912)
        at org.apache.spark.rdd.RDD$$anonfun$foreach$1.apply(RDD.scala:910)
        at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
        at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
        at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
        at org.apache.spark.rdd.RDD.foreach(RDD.scala:910)
        at GeoElaborator$$anonfun$main$1.apply(GeoElaborator.scala:17)
        at GeoElaborator$$anonfun$main$1.apply(GeoElaborator.scala:16)
        at org.apache.spark.streaming.dstream.DStream$$anonfun$foreachRDD$1$$anonfun$apply$mcV$sp$3.apply(DStream.scala:661)
        at org.apache.spark.streaming.dstream.DStream$$anonfun$foreachRDD$1$$anonfun$apply$mcV$sp$3.apply(DStream.scala:661)
        at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(ForEachDStream.scala:50)
        at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply(ForEachDStream.scala:50)
        at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply(ForEachDStream.scala:50)
        at org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:426)
        at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply$mcV$sp(ForEachDStream.scala:49)
        at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply(ForEachDStream.scala:49)
        at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply(ForEachDStream.scala:49)
        at scala.util.Try$.apply(Try.scala:161)
        at org.apache.spark.streaming.scheduler.Job.run(Job.scala:39)
        at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply$mcV$sp(JobScheduler.scala:224)
        at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply(JobScheduler.scala:224)
        at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply(JobScheduler.scala:224)
        at scala.util.DynamicVariable.withValue(DynamicVariable.scala:57)
        at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.run(JobScheduler.scala:223)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
        at java.lang.Thread.run(Thread.java:745)
Caused by: java.nio.BufferUnderflowException
        at java.nio.HeapByteBuffer.get(HeapByteBuffer.java:145)
        at java.nio.ByteBuffer.get(ByteBuffer.java:694)
        at kafka.api.ApiUtils$.readShortString(ApiUtils.scala:40)
        at kafka.api.TopicData$.readFrom(FetchResponse.scala:96)
        at kafka.api.FetchResponse$$anonfun$4.apply(FetchResponse.scala:170)
        at kafka.api.FetchResponse$$anonfun$4.apply(FetchResponse.scala:169)
        at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
        at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
        at scala.collection.immutable.Range.foreach(Range.scala:141)
        at scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:251)
        at scala.collection.AbstractTraversable.flatMap(Traversable.scala:105)
        at kafka.api.FetchResponse$.readFrom(FetchResponse.scala:169)
        at kafka.consumer.SimpleConsumer.fetch(SimpleConsumer.scala:135)
        at org.apache.spark.streaming.kafka.KafkaRDD$KafkaRDDIterator.fetchBatch(KafkaRDD.scala:192)
        at org.apache.spark.streaming.kafka.KafkaRDD$KafkaRDDIterator.getNext(KafkaRDD.scala:208)
        at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
        at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
        at scala.collection.Iterator$class.foreach(Iterator.scala:727)
        at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
        at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$32.apply(RDD.scala:912)
        at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$32.apply(RDD.scala:912)
        at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1888)
        at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1888)
        at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
        at org.apache.spark.scheduler.Task.run(Task.scala:89)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:242)
        ... 3 more

Это мой 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>GeoElaborator</groupId>
    <artifactId>GeoElaborator</artifactId>
    <version>1.0-SNAPSHOT</version>
    <dependencies>

        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>2.10.5</version>
        </dependency>

        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-reflect</artifactId>
            <version>2.10.5</version>
        </dependency>

        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-compiler</artifactId>
            <version>2.10.5</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.10</artifactId>
            <version>1.6.0</version>
            <scope>provided</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka_2.10</artifactId>
            <version>1.6.0</version>
            <scope>provided</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.kafka</groupId>
            <artifactId>kafka_2.10</artifactId>
            <version>0.8.2.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.kafka</groupId>
            <artifactId>kafka-clients</artifactId>
            <version>0.8.2.0</version>
        </dependency>

    </dependencies>

    <build>
        <pluginManagement>
            <plugins>


                <plugin>
                    <artifactId>maven-assembly-plugin</artifactId>
                    <version>3.1.1</version>
                    <configuration>
                        <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>



                <plugin>
                    <groupId>net.alchim31.maven</groupId>
                    <artifactId>scala-maven-plugin</artifactId>
                    <version>4.2.0</version>
                </plugin>
                <plugin>
                    <groupId>org.apache.maven.plugins</groupId>
                    <artifactId>maven-compiler-plugin</artifactId>
                    <version>2.0.2</version>
                </plugin>
            </plugins>
        </pluginManagement>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <executions>
                    <execution>
                        <id>scala-compile-first</id>
                        <phase>process-resources</phase>
                        <goals>
                            <goal>add-source</goal>
                            <goal>compile</goal>
                        </goals>
                    </execution>
                    <execution>
                        <id>scala-test-compile</id>
                        <phase>process-test-resources</phase>
                        <goals>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
            </plugin>
        </plugins>
    </build>

</project>

На кластере Spark версия 1.6.0, Кафкаверсия 0.8.2.0-1.4.0 и версия Scala 2.10.5.

Это код, который я использую для запуска прямого потока: 

 val record = KafkaUtils.createDirectStream[String, String,StringDecoder,StringDecoder](ssc,kafkaParams,topic).map(_._2)
    record.foreachRDD(x=>{
      x.foreach(y=>{
        println(y)
      })
    })
    ssc.start()
    ssc.awaitTermination()

Можете ли вы помочь мне понятьв чем проблема? Может быть, какая-то версия не соответствует? Исключение появляется только в том случае, если производитель работает, если не работает ни один из производителей для данного раздела, исключение не выдается.

...