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
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
|
/*
* 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.scheduler.cluster
import scala.collection.mutable.HashMap
import org.apache.spark.{Logging, SparkContext}
import org.apache.spark.deploy.client.{Client, ClientListener}
import org.apache.spark.deploy.{Command, ApplicationDescription}
import org.apache.spark.scheduler.{ExecutorExited, ExecutorLossReason, SlaveLost, ClusterScheduler}
import org.apache.spark.util.Utils
private[spark] class SparkDeploySchedulerBackend(
scheduler: ClusterScheduler,
sc: SparkContext,
masters: Array[String],
appName: String)
extends CoarseGrainedSchedulerBackend(scheduler, sc.env.actorSystem)
with ClientListener
with Logging {
var client: Client = null
var stopping = false
var shutdownCallback : (SparkDeploySchedulerBackend) => Unit = _
val maxCores = System.getProperty("spark.cores.max", Int.MaxValue.toString).toInt
override def start() {
super.start()
// The endpoint for executors to talk to us
val driverUrl = "akka://spark@%s:%s/user/%s".format(
System.getProperty("spark.driver.host"), System.getProperty("spark.driver.port"),
CoarseGrainedSchedulerBackend.ACTOR_NAME)
val args = Seq(driverUrl, "{{EXECUTOR_ID}}", "{{HOSTNAME}}", "{{CORES}}")
val command = Command(
"org.apache.spark.executor.CoarseGrainedExecutorBackend", args, sc.executorEnvs)
val sparkHome = sc.getSparkHome().getOrElse(null)
val appDesc = new ApplicationDescription(appName, maxCores, executorMemory, command, sparkHome,
"http://" + sc.ui.appUIAddress)
client = new Client(sc.env.actorSystem, masters, appDesc, this)
client.start()
}
override def stop() {
stopping = true
super.stop()
client.stop()
if (shutdownCallback != null) {
shutdownCallback(this)
}
}
override def connected(appId: String) {
logInfo("Connected to Spark cluster with app ID " + appId)
}
override def disconnected() {
if (!stopping) {
logWarning("Disconnected from Spark cluster! Waiting for reconnection...")
}
}
override def dead() {
if (!stopping) {
logError("Spark cluster looks dead, giving up.")
scheduler.error("Spark cluster looks down")
}
}
override def executorAdded(fullId: String, workerId: String, hostPort: String, cores: Int, memory: Int) {
logInfo("Granted executor ID %s on hostPort %s with %d cores, %s RAM".format(
fullId, hostPort, cores, Utils.megabytesToString(memory)))
}
override def executorRemoved(fullId: String, message: String, exitStatus: Option[Int]) {
val reason: ExecutorLossReason = exitStatus match {
case Some(code) => ExecutorExited(code)
case None => SlaveLost(message)
}
logInfo("Executor %s removed: %s".format(fullId, message))
removeExecutor(fullId.split("/")(1), reason.toString)
}
}
|