大數據學習——SparkStreaming整合Kafka完成網站點擊流實時統計

1.安裝並配置zk

2.安裝並配置Kafka

3.啓動zk

4.啓動Kafka

5.建立topic

[root@mini3 kafka]# bin/kafka-console-producer.sh --broker-list mini1:9092 --topic cyf-test

 

程序代碼

package org.apache.spark

import java.net.InetSocketAddress

import org.apache.spark.HashPartitioner
import org.apache.spark.SparkConf
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.Seconds
import org.apache.spark.streaming.StreamingContext
import org.apache.spark.streaming.flume.FlumeUtils
import org.apache.spark.streaming.kafka.KafkaUtils

object KafkaWordCount {

  val updateFunction = (iter: Iterator[(String, Seq[Int], Option[Int])]) => {
    iter.flatMap { case (x, y, z) => Some(y.sum + z.getOrElse(0)).map(v => (x, v)) }
  }

  def main(args: Array[String]) {
    val conf = new SparkConf().setMaster("local[2]").setAppName("KafkaWordCount")
    val ssc = new StreamingContext(conf, Seconds(5))
    //回滾點設置在本地
//    ssc.checkpoint("./")
    //將回滾點寫到hdfs
    ssc.checkpoint("hdfs://mini1:9000/kafkatest")

    //val Array(zkQuorum, groupId, topics, numThreads) = args
    val Array(zkQuorum, groupId, topics, numThreads) = Array[String]("mini1:2181,mini2:2181,mini3:2181", "g1", "cyf-test", "2")
    val topicMap = topics.split(",").map((_, numThreads.toInt)).toMap
    val lines = KafkaUtils.createStream(ssc, zkQuorum, groupId, topicMap).map(_._2)
    val results = lines.flatMap(_.split(" ")).map((_, 1)).updateStateByKey(updateFunction, new HashPartitioner(ssc.sparkContext.defaultParallelism), true)


    results.print()
    ssc.start()
    ssc.awaitTermination()
  }

}

 

 記一次遇到的問題 http://www.javashuo.com/article/p-qnbbxhbw-ed.html