forked from apache/spark
/
LocalSparkCluster.scala
83 lines (71 loc) · 3.18 KB
/
LocalSparkCluster.scala
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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
/*
* 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.
*/
package org.apache.spark.deploy
import scala.collection.mutable.ArrayBuffer
import akka.actor.ActorSystem
import org.apache.spark.{Logging, SparkConf}
import org.apache.spark.deploy.worker.Worker
import org.apache.spark.deploy.master.Master
import org.apache.spark.util.Utils
/**
* Testing class that creates a Spark standalone process in-cluster (that is, running the
* spark.deploy.master.Master and spark.deploy.worker.Workers in the same JVMs). Executors launched
* by the Workers still run in separate JVMs. This can be used to test distributed operation and
* fault recovery without spinning up a lot of processes.
*/
private[spark]
class LocalSparkCluster(
numWorkers: Int,
coresPerWorker: Int,
memoryPerWorker: Int,
conf: SparkConf)
extends Logging {
private val localHostname = Utils.localHostName()
private val masterActorSystems = ArrayBuffer[ActorSystem]()
private val workerActorSystems = ArrayBuffer[ActorSystem]()
def start(): Array[String] = {
logInfo("Starting a local Spark cluster with " + numWorkers + " workers.")
// Disable REST server on Master in this mode unless otherwise specified
val _conf = conf.clone()
.setIfMissing("spark.master.rest.enabled", "false")
.set("spark.shuffle.service.enabled", "false")
/* Start the Master */
val (masterSystem, masterPort, _, _) = Master.startSystemAndActor(localHostname, 0, 0, _conf)
masterActorSystems += masterSystem
val masterUrl = "spark://" + Utils.localHostNameForURI() + ":" + masterPort
val masters = Array(masterUrl)
/* Start the Workers */
for (workerNum <- 1 to numWorkers) {
val (workerSystem, _) = Worker.startSystemAndActor(localHostname, 0, 0, coresPerWorker,
memoryPerWorker, masters, null, Some(workerNum), _conf)
workerActorSystems += workerSystem
}
masters
}
def stop() {
logInfo("Shutting down local Spark cluster.")
// Stop the workers before the master so they don't get upset that it disconnected
// TODO: In Akka 2.1.x, ActorSystem.awaitTermination hangs when you have remote actors!
// This is unfortunate, but for now we just comment it out.
workerActorSystems.foreach(_.shutdown())
// workerActorSystems.foreach(_.awaitTermination())
masterActorSystems.foreach(_.shutdown())
// masterActorSystems.foreach(_.awaitTermination())
masterActorSystems.clear()
workerActorSystems.clear()
}
}