blob: 8e4c2b6229755f9243468e79200ee0408880c83d (
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
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
|
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
// scalastyle:off println
package org.apache.spark.examples
import java.util.Random
import org.apache.spark.{SparkConf, SparkContext}
/**
* Usage: GroupByTest [numMappers] [numKVPairs] [KeySize] [numReducers]
*/
object SkewedGroupByTest {
def main(args: Array[String]) {
val sparkConf = new SparkConf().setAppName("GroupBy Test")
var numMappers = if (args.length > 0) args(0).toInt else 2
var numKVPairs = if (args.length > 1) args(1).toInt else 1000
var valSize = if (args.length > 2) args(2).toInt else 1000
var numReducers = if (args.length > 3) args(3).toInt else numMappers
val sc = new SparkContext(sparkConf)
val pairs1 = sc.parallelize(0 until numMappers, numMappers).flatMap { p =>
val ranGen = new Random
// map output sizes linearly increase from the 1st to the last
numKVPairs = (1.0 * (p + 1) / numMappers * numKVPairs).toInt
var arr1 = new Array[(Int, Array[Byte])](numKVPairs)
for (i <- 0 until numKVPairs) {
val byteArr = new Array[Byte](valSize)
ranGen.nextBytes(byteArr)
arr1(i) = (ranGen.nextInt(Int.MaxValue), byteArr)
}
arr1
}.cache()
// Enforce that everything has been calculated and in cache
pairs1.count()
println(pairs1.groupByKey(numReducers).count())
sc.stop()
}
}
// scalastyle:on println
|