first、top 原理-源码(spark3.0)

first  

     底层调用的take(1)

/**
   * Return the first element in this RDD.
   */
  def first(): T = withScope {
    take(1) match {
      case Array(t) => t
      case _ => throw new UnsupportedOperationException("empty collection")
    }
  }

top

     底层调用的takeOrdered(num)(ord.reverse)

 /**
   * Returns the top k (largest) elements from this RDD as defined by the specified
   * implicit Ordering[T] and maintains the ordering. This does the opposite of
   * [[takeOrdered]]. For example:
   * {{{
   *   sc.parallelize(Seq(10, 4, 2, 12, 3)).top(1)
   *   // returns Array(12)
   *
   *   sc.parallelize(Seq(2, 3, 4, 5, 6)).top(2)
   *   // returns Array(6, 5)
   * }}}
   *
   * @note This method should only be used if the resulting array is expected to be small, as
   * all the data is loaded into the driver's memory.
   *
   * @param num k, the number of top elements to return
   * @param ord the implicit ordering for T
   * @return an array of top elements
   */
  def top(num: Int)(implicit ord: Ordering[T]): Array[T] = withScope {
    takeOrdered(num)(ord.reverse)
  }