blob: 145e419c53b508e4a76a8eb53595ea55b77075de (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
|
package spark.rdd
import spark.Partitioner
import spark.RDD
import spark.ShuffleDependency
import spark.SparkEnv
import spark.Split
private[spark] class ShuffledRDDSplit(val idx: Int) extends Split {
override val index = idx
override def hashCode(): Int = idx
}
/**
* The resulting RDD from a shuffle (e.g. repartitioning of data).
* @param parent the parent RDD.
* @param part the partitioner used to partition the RDD
* @tparam K the key class.
* @tparam V the value class.
*/
class ShuffledRDD[K, V](
@transient parent: RDD[(K, V)],
part: Partitioner) extends RDD[(K, V)](parent.context) {
override val partitioner = Some(part)
@transient
val splits_ = Array.tabulate[Split](part.numPartitions)(i => new ShuffledRDDSplit(i))
override def splits = splits_
override def preferredLocations(split: Split) = Nil
val dep = new ShuffleDependency(parent, part)
override val dependencies = List(dep)
override def compute(split: Split): Iterator[(K, V)] = {
SparkEnv.get.shuffleFetcher.fetch[K, V](dep.shuffleId, split.index)
}
}
|
