SparkStream 使用

炼数成金 课程

1、监控本地文件夹下的文件信息

</pre><pre name="code" class="java">import org.apache.spark.SparkConf
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.StreamingContext._


object HdfsWordCount {
  def main(args: Array[String]) {
    val sparkConf = new SparkConf().setAppName("HdfsWordCount").setMaster("local[2]")//这里指在本地运行，2个线程，一个监听，一个处理数据
    // Create the context
    val ssc = new StreamingContext(sparkConf, Seconds(20))// 时间划分为20秒

    val lines = ssc.textFileStream("/home/mmicky/temp/")
    val words = lines.flatMap(_.split(" "))
    val wordCounts = words.map(x => (x, 1)).reduceByKey(_ + _)
    wordCounts.print()
    ssc.start()
    ssc.awaitTermination()
  }
}

2、 网络socket监控

1）构建socket模拟周期发送数据

import java.io.{PrintWriter}
import java.net.ServerSocket
import scala.io.Source

object SaleSimulation {
  def index(length: Int) = { //销售模拟器：参数1：读入的文件；参数2：端口；参数3：发送时间间隔ms
    import java.util.Random
    val rdm = new Random

    rdm.nextInt(length)
  }

  def main(args: Array[String]) {
    if (args.length != 3) {
      System.err.println("Usage: <filename> <port> <millisecond>")
      System.exit(1)
    }

    val filename = args(0)
    val lines = Source.fromFile(filename).getLines.toList
    val filerow = lines.length

    val listener = new ServerSocket(args(1).toInt)
    while (true) {
      val socket = listener.accept()
      new Thread() {
        override def run = {
          println("Got client connected from: " + socket.getInetAddress)
          val out = new PrintWriter(socket.getOutputStream(), true)
          while (true) {
            Thread.sleep(args(2).toLong)
            val content = lines(index(filerow))
            println(content)
            out.write(content + '\n')
            out.flush()
          }
          socket.close()
        }
      }.start()
    }
  }
}

运行：java -cp week5.jar week5.SaleSimulation /home/mmicky/data/spark/people.txt 9999 1000 //从people文件随机读取，发送端口9999，间隔1秒

2）sparkStream 监控端

import org.apache.spark.{SparkContext, SparkConf}
import org.apache.spark.streaming.{Milliseconds, Seconds, StreamingContext}
import org.apache.spark.streaming.StreamingContext._
import org.apache.spark.storage.StorageLevel

object NetworkWordCount {
  def main(args: Array[String]) {
    val conf = new SparkConf().setAppName("NetworkWordCount").setMaster("local[2]")
    val sc = new SparkContext(conf)
    val ssc = new StreamingContext(sc, Seconds(5))//5秒间隔
 
    val lines = ssc.socketTextStream(args(0), args(1).toInt, StorageLevel.MEMORY_AND_DISK_SER)// 服务器地址，端口，序列化方案
    val words = lines.flatMap(_.split(","))
    val wordCounts = words.map(x => (x, 1)).reduceByKey(_ + _)

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

3、监控有状态（stateful）

import org.apache.spark.{SparkContext, SparkConf}
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.StreamingContext._

object StatefulWordCount {
  def main(args: Array[String]) {

    val updateFunc = (values: Seq[Int], state: Option[Int]) => { //StateFul需要定义的处理函数，第一个参数是本次进来的值，第二个是过去处理后保存的值
      val currentCount = values.foldLeft(0)(_ + _)	//求和
      val previousCount = state.getOrElse(0)	// 如果过去没有 即取0
      Some(currentCount + previousCount)// 求和<span style="white-space:pre">	</span>
    }

    val conf = new SparkConf().setAppName("StatefulWordCount").setMaster("local[2]")
    val sc = new SparkContext(conf)

    //创建StreamingContext
    val ssc = new StreamingContext(sc, Seconds(5))
    ssc.checkpoint(".")//因为是有状态的，需要保存之前的信息，所以这里设定了 checkpoint的目录，以防断电后内存数据丢失。
//这里因为没有设置checkpoint的时间间隔，所以会发现每一次数据块过来 即切分一次，产生一个 .checkpoint 文件
    //获取数据
    val lines = ssc.socketTextStream(args(0), args(1).toInt)
    val words = lines.flatMap(_.split(","))
    val wordCounts = words.map(x => (x, 1))

    //使用updateStateByKey来更新状态
    val stateDstream = wordCounts.updateStateByKey[Int](updateFunc)//调用 处理函数 updateFunc
    stateDstream.print()
    ssc.start()
    ssc.awaitTermination()
  }
}

4、windows操作

import org.apache.spark.{SparkContext, SparkConf}
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming._
import org.apache.spark.streaming.StreamingContext._

object WindowWordCount {
  def main(args: Array[String]) {

    val conf = new SparkConf().setAppName("WindowWordCount").setMaster("local[2]")
    val sc = new SparkContext(conf)

    //创建StreamingContext
    val ssc = new StreamingContext(sc, Seconds(5))
    ssc.checkpoint(".")

    // //获取数据
    val lines = ssc.socketTextStream(args(0), args(1).toInt, StorageLevel.MEMORY_ONLY_SER)
    val words = lines.flatMap(_.split(","))

    //windows操作
    val wordCounts = words.map(x => (x , 1)).reduceByKeyAndWindow((a:Int,b:Int) => (a + b), Seconds(args(2).toInt), Seconds(args(3).toInt))
//第二个参数是 windows的窗口时间间隔，比如是 监听间隔的 倍数，上面是 5秒，这里必须是5的倍数。eg :30
//第三个参数是 windows的滑动时间间隔，也必须是监听间隔的倍数。eg :10
//那么这里的作用是， 每隔10秒钟，对前30秒的数据， 进行一次处理，这里的处理就是 word count。
    //val wordCounts = words.map(x => (x , 1)).reduceByKeyAndWindow(_+_, _-_,Seconds(args(2).toInt), Seconds(args(3).toInt))
//这个是优化方法， 即加上上一次的结果，减去 上一次存在又不在这一次的数据块的部分。

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