12 Spark on RDD 分区器

12 Spark on RDD 分区器

RDD 分区器

Spark 目前支持 Hash 分区和 Range 分区，和用户自定义分区。Hash 分区为当前的默认分区。分区器直接决定了 RDD 中分区的个数、RDD 中每条数据经过 Shuffle 后进入哪个分区，进而决定了 Reduce 的个数。只有 Key-Value 类型的 RDD 才有分区器，非 Key-Value 类型的 RDD 分区的值是 None每个 RDD 的分区 ID 范围：0 ~ (numPartitions - 1)，决定这个值是属于那个分区的。

Hash 分区：对于给定的 key，计算其 hashCode,并除以分区个数取余。

class HashPartitioner(partitions: Int) extends Partitioner {
require(partitions >= 0, s"Number of partitions ($partitions) cannot be 
negative.")
def numPartitions: Int = partitions
def getPartition(key: Any): Int = key match {
case null => 0
case _ => Utils.nonNegativeMod(key.hashCode, numPartitions)
}
override def equals(other: Any): Boolean = other match {
case h: HashPartitioner =>
h.numPartitions == numPartitions
case _ =>
false
}
override def hashCode: Int = numPartitions
}

Range 分区：将一定范围内的数据映射到一个分区中，尽量保证每个分区数据均匀，而且分区间有序

class RangePartitioner[K : Ordering : ClassTag, V](
partitions: Int,
rdd: RDD[_ <: Product2[K, V]],
private var ascending: Boolean = true)
extends Partitioner {
// We allow partitions = 0, which happens when sorting an empty RDD under the 
default settings.
require(partitions >= 0, s"Number of partitions cannot be negative but found 
$partitions.")
private var ordering = implicitly[Ordering[K]]
// An array of upper bounds for the first (partitions - 1) partitions
private var rangeBounds: Array[K] = {
...
}
def numPartitions: Int = rangeBounds.length + 1
private var binarySearch: ((Array[K], K) => Int) = 
CollectionsUtils.makeBinarySearch[K]
def getPartition(key: Any): Int = {
val k = key.asInstanceOf[K]
var partition = 0
if (rangeBounds.length <= 128) {
// If we have less than 128 partitions naive search
while (partition < rangeBounds.length && ordering.gt(k, 
rangeBounds(partition))) {
partition += 1
}
} else {
// Determine which binary search method to use only once.
partition = binarySearch(rangeBounds, k)
// binarySearch either returns the match location or -[insertion point]-1
if (partition < 0) {
partition = -partition-1 }
if (partition > rangeBounds.length) {
partition = rangeBounds.length
} }
if (ascending) {
partition
} else {
rangeBounds.length - partition
} }
override def equals(other: Any): Boolean = other match {
...
}
override def hashCode(): Int = {
...
}
@throws(classOf[IOException])
private def writeObject(out: ObjectOutputStream): Unit = 
Utils.tryOrIOException {
...
}
@throws(classOf[IOException])
private def readObject(in: ObjectInputStream): Unit = Utils.tryOrIOException 
{
...
} }