spark--transform算子--coalesce

import org.apache.spark.{SparkConf, SparkContext}import scala.collection.mutable.ArrayBuffer/**  * Created by yz02 on 2017/6/15.  */object T_coalesce {  System.setProperty("hadoop.home.dir","F:\\hadoop-2.6.5")  def fun_index(index : Int, iter : Iterator[String]) : Iterator[String] = {    var list  = ArrayBuffer[String]()    while (iter.hasNext)    {      val name : String = iter.next()      var fs = index + ":" + name      list += fs//      println(fs)    }    return list.iterator  }  def fun_index1(index : Int, iter : Iterator[String]) : Iterator[String] = {    var list  = ArrayBuffer[String]()    while (iter.hasNext)    {      val name : String = iter.next()      var fs = index + ":" + name      list += fs      println(fs)    }    return list.iterator  }  def main(args: Array[String]): Unit = {    val conf = new SparkConf().setAppName("coalesce_test").setMaster("local")    val sc = new SparkContext(conf)    //coalesce算子，功能是将RDD的partition的数量减缩，减少    //将一定的数据压缩到更少的partition分区中去    //使用场景！很多时候在filter算子之后会优化一下使用coalesce算子    //filter算子应用到RDD上面，说白了会应用到RDD对应的里面的每一个partition上去    //数据倾斜，换句话说就是有可能有的partition里面就剩下了一条数据！！    //建议使用coalesce算子，从而让各个partition中的数据都更加紧凑！    val nameList : List[String] = List("liupeng1", "liupeng2", "liuipeng3",      "liupeng4", "liupeng5", "liupeng6",      "liupeng7", "liupeng8", "liupeng9",      "liupeng10", "liupeng11", "liupeng12"    )    val nameRDD = sc.parallelize(nameList, 6)    val nameRDD2 = nameRDD.mapPartitionsWithIndex(fun_index)    val nameRDD3 = nameRDD2.coalesce(3)    val nameRDD4 = nameRDD3.mapPartitionsWithIndex(fun_index1)    val info : Array[String] = nameRDD4.collect()  }}

运行结果：

0:0:liupeng1
0:0:liupeng2
0:1:liuipeng3
0:1:liupeng4

1:2:liupeng5
1:2:liupeng6
1:3:liupeng7
1:3:liupeng8

2:4:liupeng9
2:4:liupeng10
2:5:liupeng11
2:5:liupeng12