// scalastyle:off println

package org.apache.spark.examples

import scala.math.random

import org.apache.spark._

/** Computes an approximation to pi */

object SparkPi {

  def main(args: Array[String]) {

    val conf = new SparkConf().setAppName("Spark Pi")

    val spark = new SparkContext(conf)

    val slices = if (args.length > ) args().toInt else

    val n = math.min(100000L * slices, Int.MaxValue).toInt // avoid overflow

    val count = spark.parallelize( until n, slices).map { i =>

      val x = random *  -

      val y = random *  -

      if (x*x + y*y < )  else

    }.reduce(_ + _)

    println("Pi is roughly " + 4.0 * count / n)

    spark.stop()

  }

}

[abc@search-engine---dev4 spark]$ ./bin/run-example SparkPi

Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties

// :: INFO SparkContext: Running Spark version 1.6.

// :: WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable

#进行acls用户权限认证

// :: INFO SecurityManager: Changing view acls to: abc

// :: INFO SecurityManager: Changing modify acls to: abc

// :: INFO SecurityManager: SecurityManager: authentication disabled; ui acls disabled; users with view permissions: Set(abc); users with modify permissions: Set(abc)

// :: INFO Utils: Successfully started service 'sparkDriver' on port .

// :: INFO Slf4jLogger: Slf4jLogger started

#启动远程监听服务，端口是36739，Spark的通信工作由akka来实现

// :: INFO Remoting: Starting remoting

// :: INFO Remoting: Remoting started; listening on addresses :[akka.tcp://sparkDriverActorSystem@127.0.0.1:36739]

// :: INFO Utils: Successfully started service 'sparkDriverActorSystem' on port .

#注册MapOutputTracker，BlockManagerMaster，BlockManager

// :: INFO SparkEnv: Registering MapOutputTracker

// :: INFO SparkEnv: Registering BlockManagerMaster

#分配存储空间，包括磁盘空间和内存空间

// :: INFO DiskBlockManager: Created local directory at /tmp/blockmgr-8a68c39e-40e5-43ca-b21e-081ef8d278e2

// :: INFO MemoryStore: MemoryStore started with capacity 511.1 MB

// :: INFO SparkEnv: Registering OutputCommitCoordinator

// :: INFO Utils: Successfully started service 'SparkUI' on port .

// :: INFO SparkUI: Started SparkUI at http://127.0.0.1:4040

// :: INFO HttpFileServer: HTTP File server directory is /tmp/spark-3ef0b16c-fe81-482e--30571da062e7/httpd-796af3e2-122c---f4aa7d32bb04

#启动HTTP服务，可以通过界面查看服务和任务运行情况

// :: INFO HttpServer: Starting HTTP Server

// :: INFO Utils: Successfully started service 'HTTP file server' on port .

#启动SparkContext，并上传本地运行的jar包到http://127.0.0.1:54315

// :: INFO SparkContext: Added JAR file:/usr/local/spark/lib/spark-examples-1.6.-hadoop2.6.0.jar at http://127.0.0.1:54315/jars/spark-examples-1.6.1-hadoop2.6.0.jar with timestamp 1465285404966

// :: INFO Executor: Starting executor ID driver on host localhost

// :: INFO Utils: Successfully started service 'org.apache.spark.network.netty.NettyBlockTransferService' on port .

// :: INFO NettyBlockTransferService: Server created on 

// :: INFO BlockManagerMaster: Trying to register BlockManager

// :: INFO BlockManagerMasterEndpoint: Registering block manager localhost: with 511.1 MB RAM, BlockManagerId(driver, localhost, )

// :: INFO BlockManagerMaster: Registered BlockManager

#Spark提交了一个job给DAGScheduler

// :: INFO SparkContext: Starting job: reduce at SparkPi.scala:

#DAGScheduler收到一个编号为0的含有2个partitions分区的job

// :: INFO DAGScheduler: Got job  (reduce at SparkPi.scala:) with  output partitions

#将job转换为编号为0的stage

// :: INFO DAGScheduler: Final stage: ResultStage  (reduce at SparkPi.scala:)

#DAGScheduler在submitting stage之前，首先寻找本次stage的parents，如果missing parents为空，则submitting stage；

#如果有，会对parents stage进行递归submit stage，随之又将stage 0分成了2个task，提交给TaskScheduler的submitTasks方法。

#对于某些简单的job，如果它没有依赖关系，并且只有一个partition，这样的job会使用local thread处理而并不会提交到TaskScheduler上处理。

// :: INFO DAGScheduler: Parents of final stage: List()

// :: INFO DAGScheduler: Missing parents: List()

// :: INFO DAGScheduler: Submitting ResultStage  (MapPartitionsRDD[] at map at SparkPi.scala:), which has no missing parents

// :: INFO MemoryStore: Block broadcast_0 stored as values in memory (estimated size 1904.0 B, free 1904.0 B)

// :: INFO MemoryStore: Block broadcast_0_piece0 stored as bytes in memory (estimated size 1218.0 B, free 3.0 KB)

// :: INFO BlockManagerInfo: Added broadcast_0_piece0 in memory on localhost: (size: 1218.0 B, free: 511.1 MB)

// :: INFO SparkContext: Created broadcast  from broadcast at DAGScheduler.scala:

// :: INFO DAGScheduler: Submitting  missing tasks from ResultStage  (MapPartitionsRDD[] at map at SparkPi.scala:)

#TaskSchedulerImpl是TaskScheduler的实现类，接收了DAGScheduler提交的2个task

// :: INFO TaskSchedulerImpl: Adding task set 0.0 with  tasks

// :: INFO TaskSetManager: Starting task 0.0 in stage 0.0 (TID , localhost, partition ,PROCESS_LOCAL,  bytes)

// :: INFO TaskSetManager: Starting task 1.0 in stage 0.0 (TID , localhost, partition ,PROCESS_LOCAL,  bytes)

#Executor接收任务后则从远程的服务器中将运行jar包存放到本地，然后进行计算，并各自汇报了任务执行状态

// :: INFO Executor: Running task 1.0 in stage 0.0 (TID )

// :: INFO Executor: Running task 0.0 in stage 0.0 (TID )

// :: INFO Executor: Fetching http://127.0.0.1:54315/jars/spark-examples-1.6.1-hadoop2.6.0.jar with timestamp 1465285404966

// :: INFO Utils: Fetching http://127.0.0.1:54315/jars/spark-examples-1.6.1-hadoop2.6.0.jar to /tmp/spark-3ef0b16c-fe81-482e-8446-30571da062e7/userFiles-b021b090-3024-421c-b4b0-73fc9f723f44/fetchFileTemp4760324069006875921.tmp

// :: INFO Executor: Adding file:/tmp/spark-3ef0b16c-fe81-482e--30571da062e7/userFiles-b021b090--421c-b4b0-73fc9f723f44/spark-examples-1.6.-hadoop2.6.0.jar to class loader

// :: INFO Executor: Finished task 1.0 in stage 0.0 (TID ).  bytes result sent to driver

// :: INFO Executor: Finished task 0.0 in stage 0.0 (TID ).  bytes result sent to driver

#TaskSetManager、SparkContent各自收到任务完成报告

// :: INFO TaskSetManager: Finished task 1.0 in stage 0.0 (TID ) in  ms on localhost (/)

// :: INFO TaskSetManager: Finished task 0.0 in stage 0.0 (TID ) in  ms on localhost (/)

// :: INFO TaskSchedulerImpl: Removed TaskSet 0.0, whose tasks have all completed, from pool

// :: INFO DAGScheduler: ResultStage  (reduce at SparkPi.scala:) finished in 2.217 s

// :: INFO DAGScheduler: Job  finished: reduce at SparkPi.scala:, took 2.877995 s

#打印程序执行结果

Pi is roughly 3.14282

#Spark服务关闭

// :: INFO SparkUI: Stopped Spark web UI at http://127.0.0.1:4040

// :: INFO MapOutputTrackerMasterEndpoint: MapOutputTrackerMasterEndpoint stopped!

// :: INFO MemoryStore: MemoryStore cleared

// :: INFO BlockManager: BlockManager stopped

// :: INFO BlockManagerMaster: BlockManagerMaster stopped

// :: INFO OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: OutputCommitCoordinator stopped!

// :: INFO RemoteActorRefProvider$RemotingTerminator: Shutting down remote daemon.

// :: INFO RemoteActorRefProvider$RemotingTerminator: Remote daemon shut down; proceeding with flushing remote transports.

// :: INFO SparkContext: Successfully stopped SparkContext

// :: INFO RemoteActorRefProvider$RemotingTerminator: Remoting shut down.

// :: INFO ShutdownHookManager: Shutdown hook called

// :: INFO ShutdownHookManager: Deleting directory /tmp/spark-3ef0b16c-fe81-482e--30571da062e7/httpd-796af3e2-122c---f4aa7d32bb04

// :: INFO ShutdownHookManager: Deleting directory /tmp/spark-3ef0b16c-fe81-482e--30571da062e7