spark ActiveJob 源码
spark ActiveJob 代码
文件路径：/core/src/main/scala/org/apache/spark/scheduler/ActiveJob.scala
/*
* 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 java.util.Properties
import org.apache.spark.util.CallSite
/**
* A running job in the DAGScheduler. Jobs can be of two types: a result job, which computes a
* ResultStage to execute an action, or a map-stage job, which computes the map outputs for a
* ShuffleMapStage before any downstream stages are submitted. The latter is used for adaptive
* query planning, to look at map output statistics before submitting later stages. We distinguish
* between these two types of jobs using the finalStage field of this class.
*
* Jobs are only tracked for "leaf" stages that clients directly submitted, through DAGScheduler's
* submitJob or submitMapStage methods. However, either type of job may cause the execution of
* other earlier stages (for RDDs in the DAG it depends on), and multiple jobs may share some of
* these previous stages. These dependencies are managed inside DAGScheduler.
*
* @param jobId A unique ID for this job.
* @param finalStage The stage that this job computes (either a ResultStage for an action or a
* ShuffleMapStage for submitMapStage).
* @param callSite Where this job was initiated in the user's program (shown on UI).
* @param listener A listener to notify if tasks in this job finish or the job fails.
* @param properties Scheduling properties attached to the job, such as fair scheduler pool name.
*/
private[spark] class ActiveJob(
val jobId: Int,
val finalStage: Stage,
val callSite: CallSite,
val listener: JobListener,
val properties: Properties) {
/**
* Number of partitions we need to compute for this job. Note that result stages may not need
* to compute all partitions in their target RDD, for actions like first() and lookup().
*/
val numPartitions = finalStage match {
case r: ResultStage => r.partitions.length
case m: ShuffleMapStage => m.numPartitions
}
/** Which partitions of the stage have finished */
val finished = Array.fill[Boolean](numPartitions)(false)
var numFinished = 0
/** Resets the status of all partitions in this stage so they are marked as not finished. */
def resetAllPartitions(): Unit = {
(0 until numPartitions).foreach(finished.update(_, false))
numFinished = 0
}
}
相关信息
相关文章
spark BarrierJobAllocationFailed 源码
spark ExecutorDecommissionInfo 源码
0
赞
- 所属分类： 前端技术
- 本文标签：
热门推荐
-
2、 - 优质文章
-
3、 gate.io
-
8、 golang
-
9、 openharmony
-
10、 Vue中input框自动聚焦