RDD的依赖内部解密_list(partitionid - outstart + instart)

RDD的依赖内部解密

视频学习来源：DT-大数据梦工厂 IMF传奇行动视频（后附王家林老师联系方式）

DAG逻辑图：

  /**
   * Generic function to combine the elements for each key using a custom set of aggregation聚合
   * functions. This method is here for backward compatibility. It does not provide combiner
   * classtag information to the shuffle.
   *
   * @see [[combineByKeyWithClassTag]]
   */
  def combineByKey[C](
      createCombiner: V => C,
      mergeValue: (C, V) => C,
      mergeCombiners: (C, C) => C,
      partitioner: Partitioner,
      mapSideCombine: Boolean = true,
      serializer: Serializer = null): RDD[(K, C)] = self.withScope {
    combineByKeyWithClassTag(createCombiner, mergeValue, mergeCombiners,
      partitioner, mapSideCombine, serializer)(null)
  }
  /**
   * Simplified version of combineByKeyWithClassTag that hash-partitions the output RDD.
   * This method is here for backward compatibility. It does not provide combiner
   * classtag information to the shuffle.
   *
   * @see [[combineByKeyWithClassTag]]
   */
  def combineByKey[C](
      createCombiner: V => C,
      mergeValue: (C, V) => C,
      mergeCombiners: (C, C) => C,
      numPartitions: Int): RDD[(K, C)] = self.withScope {
    combineByKeyWithClassTag(createCombiner, mergeValue, mergeCombiners, numPartitions)(null)
  }

@DeveloperApi
abstract class Dependency[T] extends Serializable {
  def rdd: RDD[T]
}
 
/**
 * :: DeveloperApi ::
 * Base class for dependencies where each partition of the child RDD depends on a small number
 * of partitions of the parent RDD. Narrow dependencies allow for pipelined execution.
 */
@DeveloperApi
abstract class NarrowDependency[T](_rdd: RDD[T]) extends Dependency[T] {
  /**
   * Get the parent partitions for a child partition.
   * @param partitionId a partition of the child RDD
   * @return the partitions of the parent RDD that the child partition depends upon
   */
  def getParents(partitionId: Int): Seq[Int]
  override def rdd: RDD[T] = _rdd
}

/**
 * :: DeveloperApi ::
 * Represents a one-to-one dependency between partitions of the parent and child RDDs.
 */
@DeveloperApi
class OneToOneDependency[T](rdd: RDD[T]) extends NarrowDependency[T](rdd) {
  override def getParents(partitionId: Int): List[Int] = List(partitionId)
}
/**
 * :: DeveloperApi ::
 * Represents a one-to-one dependency between ranges of partitions in the parent and child RDDs.
 * @param rdd the parent RDD
 * @param inStart the start of the range in the parent RDD
 * @param outStart the start of the range in the child RDD
 * @param length the length of the range
 */
@DeveloperApi
class RangeDependency[T](rdd: RDD[T], inStart: Int, outStart: Int, length: Int)
  extends NarrowDependency[T](rdd) {
  override def getParents(partitionId: Int): List[Int] = {
    if (partitionId >= outStart && partitionId < outStart + length) {
      List(partitionId - outStart + inStart)
    } else {
      Nil
    }
  }
}

class ShuffleDependency[K: ClassTag, V: ClassTag, C: ClassTag](
    @transient private val _rdd: RDD[_ <: Product2[K, V]],
    val partitioner: Partitioner,
    val serializer: Option[Serializer] = None,
    val keyOrdering: Option[Ordering[K]] = None,
    val aggregator: Option[Aggregator[K, V, C]] = None,
    val mapSideCombine: Boolean = false)
  extends Dependency[Product2[K, V]] {