spark Job 源码

2022-10-20
浏览 (310)

spark Job 代码

文件路径：/streaming/src/main/scala/org/apache/spark/streaming/scheduler/Job.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.streaming.scheduler

import scala.util.{Failure, Try}

import org.apache.spark.streaming.Time
import org.apache.spark.util.{CallSite, Utils}

/**
 * Class representing a Spark computation. It may contain multiple Spark jobs.
 */
private[streaming]
class Job(val time: Time, func: () => _) {
  private var _id: String = _
  private var _outputOpId: Int = _
  private var isSet = false
  private var _result: Try[_] = null
  private var _callSite: CallSite = null
  private var _startTime: Option[Long] = None
  private var _endTime: Option[Long] = None

  def run(): Unit = {
    _result = Try(func())
  }

  def result: Try[_] = {
    if (_result == null) {
      throw new IllegalStateException("Cannot access result before job finishes")
    }
    _result
  }

  /**
   * @return the global unique id of this Job.
   */
  def id: String = {
    if (!isSet) {
      throw new IllegalStateException("Cannot access id before calling setId")
    }
    _id
  }

  /**
   * @return the output op id of this Job. Each Job has a unique output op id in the same JobSet.
   */
  def outputOpId: Int = {
    if (!isSet) {
      throw new IllegalStateException("Cannot access number before calling setId")
    }
    _outputOpId
  }

  def setOutputOpId(outputOpId: Int): Unit = {
    if (isSet) {
      throw new IllegalStateException("Cannot call setOutputOpId more than once")
    }
    isSet = true
    _id = s"streaming job $time.$outputOpId"
    _outputOpId = outputOpId
  }

  def setCallSite(callSite: CallSite): Unit = {
    _callSite = callSite
  }

  def callSite: CallSite = _callSite

  def setStartTime(startTime: Long): Unit = {
    _startTime = Some(startTime)
  }

  def setEndTime(endTime: Long): Unit = {
    _endTime = Some(endTime)
  }

  def toOutputOperationInfo: OutputOperationInfo = {
    val failureReason = if (_result != null && _result.isFailure) {
      Some(Utils.exceptionString(_result.asInstanceOf[Failure[_]].exception))
    } else {
      None
    }
    OutputOperationInfo(
      time, outputOpId, callSite.shortForm, callSite.longForm, _startTime, _endTime, failureReason)
  }

  override def toString: String = id
}

相关信息

spark 源码目录

相关文章

spark BatchInfo 源码

spark ExecutorAllocationManager 源码

spark InputInfoTracker 源码

spark JobGenerator 源码

spark JobScheduler 源码

spark JobSet 源码

spark OutputOperationInfo 源码

spark RateController 源码

spark ReceivedBlockInfo 源码

spark ReceivedBlockTracker 源码

0 赞

所属分类： 前端技术
本文标签：
版权声明： 原创文章如转载，请注明本文链接: https://m.seaxiang.com/blog/9a32eb26333849479b03de2badc4402e

热门推荐

1、直接访问google.com
2、 - 优质文章
3、 gate.io
4、 harmony 鸿蒙hdc使用指导
5、 harmony 鸿蒙初识ArkTS语言
6、 harmony 鸿蒙ArkUI组件（ArkTS）开发常见问题
7、 flink kafka connector scan.startup.mode 的几个选项
8、 golang
9、 openharmony
10、 Vue中input框自动聚焦

Loading...