血缘

package com.atguigu

import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}

object Lineage {
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf().setMaster("local[*]").setAppName("Spark01_Partition")
    //构建spark上下文对象
    val sc = new SparkContext(conf)

    val rdd: RDD[Int] = sc.makeRDD(List(1,2,3,4,5,6))

    val rdd1: RDD[(Int, Int)] = rdd.map((_,1)).reduceByKey(_+_)

    println(rdd1.toDebugString)
    
  }
}

(4) ShuffledRDD[2] at reduceByKey at Lineage.scala:14 []
+-(4) MapPartitionsRDD[1] at map at Lineage.scala:14 []
| ParallelCollectionRDD[0] at makeRDD at Lineage.scala:12 []