https://github.com/apache/spark/tree/master/core/src/main/scala/org/apache/spark/network

https://github.com/apache/spark/blob/master/core/src/main/scala/org/apache/spark/network/BlockTransferService.scala

https://github.com/apache/spark/blob/master/core/src/main/scala/org/apache/spark/network/BlockDataManager.scala

package org.apache.spark.network

import scala.reflect.ClassTag

import org.apache.spark.network.buffer.ManagedBuffer
import org.apache.spark.storage.{BlockId, StorageLevel} private[spark]
trait BlockDataManager { /**
* Interface to get local block data. Throws an exception if the block cannot be found or
* cannot be read successfully.
*/
def getBlockData(blockId: BlockId): ManagedBuffer /**
* Put the block locally, using the given storage level.
*
* Returns true if the block was stored and false if the put operation failed or the block
* already existed.
*/
def putBlockData(
blockId: BlockId,
data: ManagedBuffer,
level: StorageLevel,
classTag: ClassTag[_]): Boolean /**
* Release locks acquired by [[putBlockData()]] and [[getBlockData()]].
*/
def releaseLock(blockId: BlockId, taskAttemptId: Option[Long]): Unit
}
package org.apache.spark.network

import java.io.Closeable
import java.nio.ByteBuffer import scala.concurrent.{Future, Promise}
import scala.concurrent.duration.Duration
import scala.reflect.ClassTag import org.apache.spark.internal.Logging
import org.apache.spark.network.buffer.{FileSegmentManagedBuffer, ManagedBuffer, NioManagedBuffer}
import org.apache.spark.network.shuffle.{BlockFetchingListener, ShuffleClient, TempFileManager}
import org.apache.spark.storage.{BlockId, StorageLevel}
import org.apache.spark.util.ThreadUtils private[spark]
abstract class BlockTransferService extends ShuffleClient with Closeable with Logging { /**
* Initialize the transfer service by giving it the BlockDataManager that can be used to fetch
* local blocks or put local blocks.
*/
def init(blockDataManager: BlockDataManager): Unit /**
* Tear down the transfer service.
*/
def close(): Unit /**
* Port number the service is listening on, available only after [[init]] is invoked.
*/
def port: Int /**
* Host name the service is listening on, available only after [[init]] is invoked.
*/
def hostName: String /**
* Fetch a sequence of blocks from a remote node asynchronously,
* available only after [[init]] is invoked.
*
* Note that this API takes a sequence so the implementation can batch requests, and does not
* return a future so the underlying implementation can invoke onBlockFetchSuccess as soon as
* the data of a block is fetched, rather than waiting for all blocks to be fetched.
*/
override def fetchBlocks(
host: String,
port: Int,
execId: String,
blockIds: Array[String],
listener: BlockFetchingListener,
tempFileManager: TempFileManager): Unit /**
* Upload a single block to a remote node, available only after [[init]] is invoked.
*/
def uploadBlock(
hostname: String,
port: Int,
execId: String,
blockId: BlockId,
blockData: ManagedBuffer,
level: StorageLevel,
classTag: ClassTag[_]): Future[Unit] /**
* A special case of [[fetchBlocks]], as it fetches only one block and is blocking.
*
* It is also only available after [[init]] is invoked.
*/
def fetchBlockSync(
host: String,
port: Int,
execId: String,
blockId: String,
tempFileManager: TempFileManager): ManagedBuffer = {
// A monitor for the thread to wait on.
val result = Promise[ManagedBuffer]()
fetchBlocks(host, port, execId, Array(blockId),
new BlockFetchingListener {
override def onBlockFetchFailure(blockId: String, exception: Throwable): Unit = {
result.failure(exception)
}
override def onBlockFetchSuccess(blockId: String, data: ManagedBuffer): Unit = {
data match {
case f: FileSegmentManagedBuffer =>
result.success(f)
case _ =>
val ret = ByteBuffer.allocate(data.size.toInt)
ret.put(data.nioByteBuffer())
ret.flip()
result.success(new NioManagedBuffer(ret))
}
}
}, tempFileManager)
ThreadUtils.awaitResult(result.future, Duration.Inf)
} /**
* Upload a single block to a remote node, available only after [[init]] is invoked.
*
* This method is similar to [[uploadBlock]], except this one blocks the thread
* until the upload finishes.
*/
def uploadBlockSync(
hostname: String,
port: Int,
execId: String,
blockId: BlockId,
blockData: ManagedBuffer,
level: StorageLevel,
classTag: ClassTag[_]): Unit = {
val future = uploadBlock(hostname, port, execId, blockId, blockData, level, classTag)
ThreadUtils.awaitResult(future, Duration.Inf)
}
}

spark通信原理的更多相关文章

  1. Spark Shuffle 堆外内存溢出问题与解决(Shuffle通信原理)

    Spark Shuffle 堆外内存溢出问题与解决(Shuffle通信原理) http://xiguada.org/spark-shuffle-direct-buffer-oom/ 问题描述 Spar ...

  2. [Spark内核] 第32课:Spark Worker原理和源码剖析解密:Worker工作流程图、Worker启动Driver源码解密、Worker启动Executor源码解密等

    本課主題 Spark Worker 原理 Worker 启动 Driver 源码鉴赏 Worker 启动 Executor 源码鉴赏 Worker 与 Master 的交互关系 [引言部份:你希望读者 ...

  3. Spark核心技术原理透视一(Spark运行原理)

    在大数据领域,只有深挖数据科学领域,走在学术前沿,才能在底层算法和模型方面走在前面,从而占据领先地位. Spark的这种学术基因,使得它从一开始就在大数据领域建立了一定优势.无论是性能,还是方案的统一 ...

  4. spark核心原理

    spark运行结构图如下: spark基本概念 应用程序(application):用户编写的spark应用程序,包含驱动程序(Driver)和分布在集群中多个节点上运行的Executor代码,在执行 ...

  5. Spark集群基础概念 与 spark架构原理

    一.Spark集群基础概念 将DAG划分为多个stage阶段,遵循以下原则: 1.将尽可能多的窄依赖关系的RDD划为同一个stage阶段. 2.当遇到shuffle操作,就意味着上一个stage阶段结 ...

  6. Spark Worker原理和源码剖析解密:Worker工作流程图、Worker启动Driver源码解密、Worker启动Executor源码解密等

    本课主题 Spark Worker 原理 Worker 启动 Driver 源码鉴赏 Worker 启动 Executor 源码鉴赏 Worker 与 Master 的交互关系 Spark Worke ...

  7. 基于web的IM软件通信原理分析

    关于IM(InstantMessaging)即时通信类软件(如微信,QQ),大多数都是桌面应用程序或者native应用较为流行,而网上关于原生IM或桌面IM软件类的通信原理介绍也较多,此处不再赘述.而 ...

  8. Socket 通信原理(Android客户端和服务器以TCP&&UDP方式互通)

    转载地址:http://blog.csdn.net/mad1989/article/details/9147661 ZERO.前言 有关通信原理内容是在网上或百科整理得到,代码部分为本人所写,如果不当 ...

  9. SSL 通信原理及Tomcat SSL 配置

    SSL 通信原理及Tomcat SSL 双向配置 目录1 参考资料 .................................................................. ...

随机推荐

  1. Python之虚拟机操作:利用VIX二次开发,实现自己的pyvix(系列一)成果展示和python实例

    在日常工作中,需要使用python脚本去自动化控制VMware虚拟机,现有的pyvix功能较少,而且不适合个人编程习惯,故萌发了开发一个berlin版本pyvix的想法,暂且叫其OpenPyVix.O ...

  2. 算法复习——差分约束(ssoi种树)

    题目: 题目描述 为了绿化乡村,H 村积极响应号召,开始种树了. H 村里有 n 幢房屋,这些屋子的排列顺序很有特点,在一条直线上.于是方便起见,我们给它们标上 1-n .树就种在房子前面的空地上. ...

  3. P1681 最大正方形II (动态规划)

    题目背景 忙完了学校的事,v神终于可以做他的"正事":陪女朋友散步.一天,他和女朋友走着走着,不知不觉就来到了一个千里无烟的地方.v神正要往回走,如发现了一块牌子,牌子上有有一行小 ...

  4. Snoop resynchronization mechanism to preserve read ordering

    A processor employing a post-cache (LS2) buffer. Loads are stored into the LS2buffer after probing t ...

  5. 标准C程序设计七---04

    Linux应用             编程深入            语言编程 标准C程序设计七---经典C11程序设计    以下内容为阅读:    <标准C程序设计>(第7版) 作者 ...

  6. Mongodb报错:ERROR: child process failed, exited with error number 1

    Mongodb在启动时报错: 2018-10-16T11:18:54.533+0800 I CONTROL [main] Automatically disabling TLS 1.0, to for ...

  7. android Paint属性

    **       * Paint类介绍       *        * Paint即画笔,在绘图过程中起到了极其重要的作用,画笔主要保存了颜色,     * 样式等绘制信息,指定了如何绘制文本和图形 ...

  8. MySQL与MSSQL的一些语法差异(持续更新中)

    分号不能少:分号不能少:分号不能少:重要的事情说3遍 Insert或者Update的数据包含反斜杠\的时候需要进行转义\\,例:insert into tablename(id,name) value ...

  9. 让win7任务条上的文件夹打开是c,d,e,f而不是库

    如果资源管理器是打开的,则右键点击资源管理器的图标,在跳出的菜单中,右键点击“Windows资源管理器”,选择“属性”. 在“快捷方式’选项卡,“目标”一栏,默认的是 %windir%\explore ...

  10. sklearn 特征选择

    1.移除低方差的特征(Removing features with low variance) VarianceThreshold 是特征选择中的一项基本方法.它会移除所有方差不满足阈值的特征.默认设 ...