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
|
/*
* 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
/**
* A client that communicates with the cluster manager to request or kill executors.
* This is currently supported only in YARN mode.
*/
private[spark] trait ExecutorAllocationClient {
/** Get the list of currently active executors */
private[spark] def getExecutorIds(): Seq[String]
/**
* Update the cluster manager on our scheduling needs. Three bits of information are included
* to help it make decisions.
* @param numExecutors The total number of executors we'd like to have. The cluster manager
* shouldn't kill any running executor to reach this number, but,
* if all existing executors were to die, this is the number of executors
* we'd want to be allocated.
* @param localityAwareTasks The number of tasks in all active stages that have a locality
* preferences. This includes running, pending, and completed tasks.
* @param hostToLocalTaskCount A map of hosts to the number of tasks from all active stages
* that would like to like to run on that host.
* This includes running, pending, and completed tasks.
* @return whether the request is acknowledged by the cluster manager.
*/
private[spark] def requestTotalExecutors(
numExecutors: Int,
localityAwareTasks: Int,
hostToLocalTaskCount: Map[String, Int]): Boolean
/**
* Request an additional number of executors from the cluster manager.
* @return whether the request is acknowledged by the cluster manager.
*/
def requestExecutors(numAdditionalExecutors: Int): Boolean
/**
* Request that the cluster manager kill the specified executors.
*
* When asking the executor to be replaced, the executor loss is considered a failure, and
* killed tasks that are running on the executor will count towards the failure limits. If no
* replacement is being requested, then the tasks will not count towards the limit.
*
* @param executorIds identifiers of executors to kill
* @param replace whether to replace the killed executors with new ones, default false
* @param force whether to force kill busy executors, default false
* @return the ids of the executors acknowledged by the cluster manager to be removed.
*/
def killExecutors(
executorIds: Seq[String],
replace: Boolean = false,
force: Boolean = false): Seq[String]
/**
* Request that the cluster manager kill every executor on the specified host.
*
* @return whether the request is acknowledged by the cluster manager.
*/
def killExecutorsOnHost(host: String): Boolean
/**
* Request that the cluster manager kill the specified executor.
* @return whether the request is acknowledged by the cluster manager.
*/
def killExecutor(executorId: String): Boolean = {
val killedExecutors = killExecutors(Seq(executorId))
killedExecutors.nonEmpty && killedExecutors(0).equals(executorId)
}
}
|