Spark-Dependency/Aggregator
@(spark)[Dependency|Aggregator]
RDD的核心之一:依赖关系
/**
* :: DeveloperApi ::
* Base class for dependencies.
*/
@DeveloperApi
abstract class Dependency[T] extends Serializable {
def rdd: RDD[T]
}
Product2 是scala的类
Product2 is a cartesian product of 2 components.
NarrowDependency
比较简单的一类依赖,
/**
* :: 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
}
OneToOneDependency
1:1 的mapping
/**
* :: 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(partitionId)
}
RangeDependency
根据range确定依赖关系,每个range一个dependency?
/**
* :: 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)
ShuffleDependency
/**
* :: DeveloperApi ::
* Represents a dependency on the output of a shuffle stage. Note that in the case of shuffle,
* the RDD is transient since we don't need it on the executor side.
*
* @param _rdd the parent RDD
* @param partitioner partitioner used to partition the shuffle output
* @param serializer [[org.apache.spark.serializer.Serializer Serializer]] to use. If set to None,
* the default serializer, as specified by `spark.serializer` config option, will
* be used.
* @param keyOrdering key ordering for RDD's shuffles
* @param aggregator map/reduce-side aggregator for RDD's shuffle
* @param mapSideCombine whether to perform partial aggregation (also known as map-side combine)
*/
@DeveloperApi
class ShuffleDependency[K, V, C](
@transient _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]] {
Aggregator
/**
* :: DeveloperApi ::
* A set of functions used to aggregate data.
*
* @param createCombiner function to create the initial value of the aggregation.
* @param mergeValue function to merge a new value into the aggregation result.
* @param mergeCombiners function to merge outputs from multiple mergeValue function.
*/
@DeveloperApi
case class Aggregator[K, V, C] (
createCombiner: V => C,
mergeValue: (C, V) => C,
mergeCombiners: (C, C) => C) {