blob: 3da5236745b51b238c420909f450b47244633975 (
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
|
/*
* 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 org.apache.spark.{SparkConf, SparkContext}
/**
* Usage: BroadcastTest [slices] [numElem] [blockSize]
*/
object BroadcastTest {
def main(args: Array[String]) {
val blockSize = if (args.length > 2) args(2) else "4096"
val sparkConf = new SparkConf().setAppName("Broadcast Test")
.set("spark.broadcast.blockSize", blockSize)
val sc = new SparkContext(sparkConf)
val slices = if (args.length > 0) args(0).toInt else 2
val num = if (args.length > 1) args(1).toInt else 1000000
val arr1 = (0 until num).toArray
for (i <- 0 until 3) {
println("Iteration " + i)
println("===========")
val startTime = System.nanoTime
val barr1 = sc.broadcast(arr1)
val observedSizes = sc.parallelize(1 to 10, slices).map(_ => barr1.value.length)
// Collect the small RDD so we can print the observed sizes locally.
observedSizes.collect().foreach(i => println(i))
println("Iteration %d took %.0f milliseconds".format(i, (System.nanoTime - startTime) / 1E6))
}
sc.stop()
}
}
// scalastyle:on println
|