blob: 4943d58e254034f43c2f4ce6b305455b5cf40e1a (
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
|
/*
* 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 spark.scheduler
import spark.scheduler.cluster.Pool
import spark.scheduler.cluster.SchedulingMode.SchedulingMode
/**
* Low-level task scheduler interface, implemented by both ClusterScheduler and LocalScheduler.
* 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 through
* the TaskSchedulerListener interface.
*/
private[spark] trait TaskScheduler {
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 registerations, etc.
def postStartHook() { }
// Disconnect from the cluster.
def stop(): Unit
// Submit a sequence of tasks to run.
def submitTasks(taskSet: TaskSet): Unit
// Set a listener for upcalls. This is guaranteed to be set before submitTasks is called.
def setListener(listener: TaskSchedulerListener): Unit
// Get the default level of parallelism to use in the cluster, as a hint for sizing jobs.
def defaultParallelism(): Int
}
|