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
|
/*
* 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
import org.apache.spark.scheduler.SchedulingMode.SchedulingMode
import org.apache.spark.storage.BlockManagerId
/**
* Low-level task scheduler interface, currently implemented exclusively by
* [[org.apache.spark.scheduler.TaskSchedulerImpl]].
* This interface allows plugging in different task schedulers. Each TaskScheduler schedules tasks
* for a single SparkContext. These schedulers get sets of tasks submitted to them from the
* DAGScheduler for each stage, and are responsible for sending the tasks to the cluster, running
* them, retrying if there are failures, and mitigating stragglers. They return events to the
* DAGScheduler.
*/
private[spark] trait TaskScheduler {
private val appId = "spark-application-" + System.currentTimeMillis
def rootPool: Pool
def schedulingMode: SchedulingMode
def start(): Unit
// Invoked after system has successfully initialized (typically in spark context).
// Yarn uses this to bootstrap allocation of resources based on preferred locations,
// wait for slave registrations, etc.
def postStartHook() { }
// Disconnect from the cluster.
def stop(): Unit
// Submit a sequence of tasks to run.
def submitTasks(taskSet: TaskSet): Unit
// Cancel a stage.
def cancelTasks(stageId: Int, interruptThread: Boolean): Unit
// Set the DAG scheduler for upcalls. This is guaranteed to be set before submitTasks is called.
def setDAGScheduler(dagScheduler: DAGScheduler): Unit
// Get the default level of parallelism to use in the cluster, as a hint for sizing jobs.
def defaultParallelism(): Int
/**
* Update metrics for in-progress tasks and let the master know that the BlockManager is still
* alive. Return true if the driver knows about the given block manager. Otherwise, return false,
* indicating that the block manager should re-register.
*/
def executorHeartbeatReceived(
execId: String,
accumUpdates: Array[(Long, Seq[AccumulableInfo])],
blockManagerId: BlockManagerId): Boolean
/**
* Get an application ID associated with the job.
*
* @return An application ID
*/
def applicationId(): String = appId
/**
* Process a lost executor
*/
def executorLost(executorId: String, reason: ExecutorLossReason): Unit
/**
* Get an application's attempt ID associated with the job.
*
* @return An application's Attempt ID
*/
def applicationAttemptId(): Option[String]
}
|
