spark 笔记 14: spark中的delay scheduling实现
// Figure out which locality levels we have in our TaskSet, so we can do delay scheduling
var myLocalityLevels = computeValidLocalityLevels()
var localityWaits = myLocalityLevels.map(getLocalityWait) // Time to wait at each level
// Delay scheduling variables: we keep track of our current locality level and the time we
// last launched a task at that level, and move up a level when localityWaits[curLevel] expires.
// We then move down if we manage to launch a "more local" task.
var currentLocalityIndex = 0 // Index of our current locality level in validLocalityLevels
// Set of pending tasks for each executor. These collections are actually
// treated as stacks, in which new tasks are added to the end of the
// ArrayBuffer and removed from the end. This makes it faster to detect
// tasks that repeatedly fail because whenever a task failed, it is put
// back at the head of the stack. They are also only cleaned up lazily;
// when a task is launched, it remains in all the pending lists except
// the one that it was launched from, but gets removed from them later.
private val pendingTasksForExecutor = new HashMap[String, ArrayBuffer[Int]]
// Set of pending tasks for each host. Similar to pendingTasksForExecutor,
// but at host level.
private val pendingTasksForHost = new HashMap[String, ArrayBuffer[Int]]
// Set of pending tasks for each rack -- similar to the above.
private val pendingTasksForRack = new HashMap[String, ArrayBuffer[Int]]
// Set containing pending tasks with no locality preferences.
var pendingTasksWithNoPrefs = new ArrayBuffer[Int]
var lastLaunchTime = clock.getTime() // Time we last launched a task at this level/**
* Compute the locality levels used in this TaskSet. Assumes that all tasks have already been
* added to queues using addPendingTask.
*
*/
private def computeValidLocalityLevels(): Array[TaskLocality.TaskLocality] = {
import TaskLocality.{PROCESS_LOCAL, NODE_LOCAL, NO_PREF, RACK_LOCAL, ANY}
val levels = new ArrayBuffer[TaskLocality.TaskLocality]
if (!pendingTasksForExecutor.isEmpty && getLocalityWait(PROCESS_LOCAL) != 0 &&
pendingTasksForExecutor.keySet.exists(sched.isExecutorAlive(_))) {
levels += PROCESS_LOCAL
}
if (!pendingTasksForHost.isEmpty && getLocalityWait(NODE_LOCAL) != 0 &&
pendingTasksForHost.keySet.exists(sched.hasExecutorsAliveOnHost(_))) {
levels += NODE_LOCAL
}
if (!pendingTasksWithNoPrefs.isEmpty) {
levels += NO_PREF
}
if (!pendingTasksForRack.isEmpty && getLocalityWait(RACK_LOCAL) != 0 &&
pendingTasksForRack.keySet.exists(sched.hasHostAliveOnRack(_))) {
levels += RACK_LOCAL
}
levels += ANY
logDebug("Valid locality levels for " + taskSet + ": " + levels.mkString(", "))
levels.toArray
}
private def getLocalityWait(level: TaskLocality.TaskLocality): Long = {
val defaultWait = conf.get("spark.locality.wait", "3000")
level match {
case TaskLocality.PROCESS_LOCAL =>
conf.get("spark.locality.wait.process", defaultWait).toLong
case TaskLocality.NODE_LOCAL =>
conf.get("spark.locality.wait.node", defaultWait).toLong
case TaskLocality.RACK_LOCAL =>
conf.get("spark.locality.wait.rack", defaultWait).toLong
case _ => 0L
}
}
@DeveloperApi
object TaskLocality extends Enumeration {
// Process local is expected to be used ONLY within TaskSetManager for now.
val PROCESS_LOCAL, NODE_LOCAL, NO_PREF, RACK_LOCAL, ANY = Value
type TaskLocality = Value
def isAllowed(constraint: TaskLocality, condition: TaskLocality): Boolean = {
condition <= constraint
}
}
/**
* Find the index in myLocalityLevels for a given locality. This is also designed to work with
* localities that are not in myLocalityLevels (in case we somehow get those) by returning the
* next-biggest level we have. Uses the fact that the last value in myLocalityLevels is ANY.
*/
def getLocalityIndex(locality: TaskLocality.TaskLocality): Int = {
var index = 0
while (locality > myLocalityLevels(index)) {
index += 1
}
index
}
/**
* Get the level we can launch tasks according to delay scheduling, based on current wait time.
*/
private def getAllowedLocalityLevel(curTime: Long): TaskLocality.TaskLocality = {
while (curTime - lastLaunchTime >= localityWaits(currentLocalityIndex) &&
currentLocalityIndex < myLocalityLevels.length - 1)
{
// Jump to the next locality level, and remove our waiting time for the current one since
// we don't want to count it again on the next one
lastLaunchTime += localityWaits(currentLocalityIndex)
currentLocalityIndex += 1
}
myLocalityLevels(currentLocalityIndex)
}
def recomputeLocality() {
val previousLocalityLevel = myLocalityLevels(currentLocalityIndex)
myLocalityLevels = computeValidLocalityLevels()
localityWaits = myLocalityLevels.map(getLocalityWait)
currentLocalityIndex = getLocalityIndex(previousLocalityLevel)
}
/**
* Compute the locality levels used in this TaskSet. Assumes that all tasks have already been
* added to queues using addPendingTask.
*
*/
private def computeValidLocalityLevels(): Array[TaskLocality.TaskLocality] = {
import TaskLocality.{PROCESS_LOCAL, NODE_LOCAL, NO_PREF, RACK_LOCAL, ANY}
val levels = new ArrayBuffer[TaskLocality.TaskLocality]
if (!pendingTasksForExecutor.isEmpty && getLocalityWait(PROCESS_LOCAL) != 0 &&
pendingTasksForExecutor.keySet.exists(sched.isExecutorAlive(_))) {
levels += PROCESS_LOCAL
}
if (!pendingTasksForHost.isEmpty && getLocalityWait(NODE_LOCAL) != 0 &&
pendingTasksForHost.keySet.exists(sched.hasExecutorsAliveOnHost(_))) {
levels += NODE_LOCAL
}
if (!pendingTasksWithNoPrefs.isEmpty) {
levels += NO_PREF
}
if (!pendingTasksForRack.isEmpty && getLocalityWait(RACK_LOCAL) != 0 &&
pendingTasksForRack.keySet.exists(sched.hasHostAliveOnRack(_))) {
levels += RACK_LOCAL
}
levels += ANY
logDebug("Valid locality levels for " + taskSet + ": " + levels.mkString(", "))
levels.toArray
}
/**
* Dequeue a pending task for a given node and return its index and locality level.
* Only search for tasks matching the given locality constraint.
*
* @return An option containing (task index within the task set, locality, is speculative?)
*/
private def findTask(execId: String, host: String, maxLocality: TaskLocality.Value)
: Option[(Int, TaskLocality.Value, Boolean)] =
{
for (index <- findTaskFromList(execId, getPendingTasksForExecutor(execId))) {
return Some((index, TaskLocality.PROCESS_LOCAL, false))
}
。。。
// find a speculative task if all others tasks have been scheduled
findSpeculativeTask(execId, host, maxLocality).map {
case (taskIndex, allowedLocality) => (taskIndex, allowedLocality, true)}
}
spark 笔记 14: spark中的delay scheduling实现的更多相关文章
- spark 笔记 3:Delay Scheduling: A Simple Technique for Achieving Locality and Fairness in Cluster Scheduling
spark论文中说他使用了延迟调度算法,源于这篇论文:http://people.csail.mit.edu/matei/papers/2010/eurosys_delay_scheduling.pd ...
- spark 笔记 2: Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing
http://www.cs.berkeley.edu/~matei/papers/2012/nsdi_spark.pdf ucb关于spark的论文,对spark中核心组件RDD最原始.本质的理解, ...
- Apache Spark 2.2.0 中文文档 - Spark RDD(Resilient Distributed Datasets)论文 | ApacheCN
Spark RDD(Resilient Distributed Datasets)论文 概要 1: 介绍 2: Resilient Distributed Datasets(RDDs) 2.1 RDD ...
- spark学习笔记总结-spark入门资料精化
Spark学习笔记 Spark简介 spark 可以很容易和yarn结合,直接调用HDFS.Hbase上面的数据,和hadoop结合.配置很容易. spark发展迅猛,框架比hadoop更加灵活实用. ...
- Apache Spark 2.2.0 中文文档 - Spark Streaming 编程指南 | ApacheCN
Spark Streaming 编程指南 概述 一个入门示例 基础概念 依赖 初始化 StreamingContext Discretized Streams (DStreams)(离散化流) Inp ...
- Apache Spark 2.2.0 中文文档
Apache Spark 2.2.0 中文文档 - 快速入门 | ApacheCN Geekhoo 关注 2017.09.20 13:55* 字数 2062 阅读 13评论 0喜欢 1 快速入门 使用 ...
- spark 笔记 7: DAGScheduler
在前面的sparkContex和RDD都可以看到,真正的计算工作都是同过调用DAGScheduler的runjob方法来实现的.这是一个很重要的类.在看这个类实现之前,需要对actor模式有一点了解: ...
- Apache Spark 2.2.0 中文文档 - Spark Streaming 编程指南
Spark Streaming 编程指南 概述 一个入门示例 基础概念 依赖 初始化 StreamingContext Discretized Streams (DStreams)(离散化流) Inp ...
- 二、spark入门之spark shell:文本中发现5个最常用的word
scala> val textFile = sc.textFile("/Users/admin/spark-1.5.1-bin-hadoop2.4/README.md") s ...
随机推荐
- arcgisJs之底图切换插件
arcgisJs之底图切换插件 底图切换插件在arcgis中有两种表现,如下: 1.两张底图切换 2.多张底图切换 一.两张地图切换 let basemapToggle = new BasemapTo ...
- 4.(基础)tornado应用安全与认证
这一节我们介绍应用安全与认证,其实中间省略了一个数据库.对于tornado来说,读取数据库的数据,性能的瓶颈还是在数据库上面.关于数据库,我在<>中介绍了sqlalchemy,这是一个工业 ...
- Linux系统吃“内存”现象
而当我们使用free命令查看Linux系统内存使用情况时,会发现内存使用一直处于较高的水平,即使此时系统并没有运行多少软件.这正是Windows和Linux在内存管理上的区别,乍一看,Linux系统吃 ...
- zabbix-server、proxy、agent的分布式部署步骤
1.准备工作 关闭防火墙和SELinux防火墙,因为他们会限制一些访问权限,如果服务器不能关闭就需要手动设置规则,这里测试用就直接关闭了 service firewalld stop; setenfo ...
- maven地址配置为阿里maven仓库,附ali maven官方指南链接
一.参考链接 官方指南 链接地址:https://help.aliyun.com/document_detail/102512.html?spm=a2c40.aliyun_maven_repo.0.0 ...
- MongoDB的优势应用场景和配置
一:MongoDB的简介: MongoDB是一个基于分布式文件存储的数据库.由C++语言编写.旨在为WEB应用提供可扩展的高性能数据存储解决方案 MongoDB是一个介于关系数据库和非关系数据库之间的 ...
- SELinux 对nginx访问目录的影响
centos新装的系统,用yum 安装的nginx . 因用yum 安装的nginx 默认目录在/usr下面. 当SELinux开启时,将会禁止访问设置在其他路径下的地址.比如我设置server 中 ...
- k8sJob控制器
Job控制器用于调配pod对象运行一次性任务,容器中的进程在正常运行结束后不会对其进行重启,而是将pod对象置于completed状态.若容器中的进程因错误而终止,则需要依据配置确定重启与否,未运行完 ...
- uniapp引用iconfont图标
不得不说uniapp引入iconfont确实比较坑.下面方法可行: 引入方法: 1.在confont官网找好图标,然后点击复制代码, 2.点击红圈的复制代码后在网页打开,出现如下: 3.然后再unia ...
- linux运维、架构之路-MongoDB单机部署
一.MongoDB介绍 MongoDB 是一个基于分布式文件存储的数据库.由 C++ 语言编写.旨在为 WEB 应用提供可扩展的高性能数据存储解决方案. MongoDB 是一个介于关系型数据库和非关系 ...