Iterator

DAGScheduler.scala

def submitJob[T, U](
      rdd: RDD[T],
      func: (TaskContext, Iterator[T]) => U,
      partitions: Seq[Int],
      callSite: CallSite,
      allowLocal: Boolean,
      resultHandler: (Int, U) => Unit,
      properties: Properties = null): JobWaiter[U] =
  {

    partitions.find(p => p >= maxPartitions || p < 0).foreach { p =>
      throw new IllegalArgumentException(
        "Attempting to access a non-existent partition: " + p + ". " +
          "Total number of partitions: " + maxPartitions)
    }

dropWhile

//RDDOperationScope.withScope
val callerMethodName = Thread.currentThread.getStackTrace()
      .dropWhile(_.getMethodName != ourMethodName)
      .find(_.getMethodName != ourMethodName)
      .map(_.getMethodName)
      .getOrElse {
        // Log a warning just in case, but this should almost certainly never happen
        logWarning("No valid method name for this RDD operation scope!")
        "N/A"
      }

dropWhile(p)表示如果集合元素符合条件则略过 如

val it = Iterator("a", "number", "of", "words")
//定义了小于2的忽略
 it dropWhile (_.length < 2)
 it.next()

当执行it.next到达"a"时忽略，直接到达"number"