Spark2.3.1+Kafka使用Direct模式消费信息

Maven依赖

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
    <version>2.3.1</version>
</dependency>
<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming_2.11</artifactId>
    <version>2.3.1</version>
</dependency>

2.3.1spark版本

Direct模式代码

import kafka.serializer.StringDecoder
import org.apache.spark.streaming.kafka.KafkaUtils
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.{SparkConf, SparkContext}

object Test {

  val zkQuorum = "mirrors.mucang.cn:2181"
  val groupId = "nginx-cg"
  val topic = Map("nginx-log" -> 1)

  val KAFKA_INTERVAL = 10

  case class NginxInof(domain: String, ip: String)

  def main(args: Array[String]): Unit = {
    val sparkConf = new SparkConf().setAppName("NginxLogAnalyze").setMaster("local[*]")
    val sparkContext = new SparkContext(sparkConf)

    val streamContext = new StreamingContext(sparkContext, Seconds(KAFKA_INTERVAL))

    val kafkaParam = Map[String, String](
      "bootstrap.servers" -> "xx.xx.cn:9092",
      "group.id" -> "nginx-cg",
      "auto.offset.reset" -> "largest"
    )

    val topic = Set("nginx-log")

    val kafkaStream = KafkaUtils.createDirectStream(streamContext, kafkaParam, topic)

    val counter = kafkaStream
      .map(_.toString().split(" "))
      .map(item => (item(0).split(",")(1) + "-" + item(2), 1))
      .reduceByKey((x, y) => (x + y))

    counter.foreachRDD(rdd => {
      rdd.foreach(println)
    })


    streamContext.start()
    streamContext.awaitTermination()

  }

}

largest 因为kafka版本过低不支持latest

异常信息

Caused by: java.lang.NoSuchMethodException: scala.runtime.Nothing$.<init>(kafka.utils.VerifiableProperties)
    at java.lang.Class.getConstructor0(Class.java:3082)
    at java.lang.Class.getConstructor(Class.java:1825)
    at org.apache.spark.streaming.kafka.KafkaRDD$KafkaRDDIterator.<init>(KafkaRDD.scala:153)
    at org.apache.spark.streaming.kafka.KafkaRDD.compute(KafkaRDD.scala:136)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
    at org.apache.spark.scheduler.Task.run(Task.scala:109)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
    ... 3 more

解决方案

在验证kafka属性时不能使用scala默认的类,需要指定kafka带的类
createDirectStream[String, String, StringDecoder, StringDecoder]其中StringDecoder必须是kafka.serializer.StringDecoder


笨兔儿
38 声望7 粉丝

分享快是最快乐的