The Process of Submitting a Job
来源:互联网 发布:数据恢复大师破解版 编辑:程序博客网 时间:2024/05/17 03:45
When calls the collect of a rdd, it triggers a job.
/** * Return an array that contains all of the elements in this RDD. * * @note this method should only be used if the resulting array is expected to be small, as * all the data is loaded into the driver's memory. */ def collect(): Array[T] = withScope { val results = sc.runJob(this, (iter: Iterator[T]) => iter.toArray) Array.concat(results: _*) }
/** * Run a job on all partitions in an RDD and return the results in an array. */ def runJob[T, U: ClassTag](rdd: RDD[T], func: Iterator[T] => U): Array[U] = { runJob(rdd, func, 0 until rdd.partitions.length) }
/** * Run a job on a given set of partitions of an RDD, but take a function of type * `Iterator[T] => U` instead of `(TaskContext, Iterator[T]) => U`. */ def runJob[T, U: ClassTag]( rdd: RDD[T], func: Iterator[T] => U, partitions: Seq[Int]): Array[U] = { val cleanedFunc = clean(func) runJob(rdd, (ctx: TaskContext, it: Iterator[T]) => cleanedFunc(it), partitions) }
/** * Run a function on a given set of partitions in an RDD and return the results as an array. */ def runJob[T, U: ClassTag]( rdd: RDD[T], func: (TaskContext, Iterator[T]) => U, partitions: Seq[Int]): Array[U] = { val results = new Array[U](partitions.size) runJob[T, U](rdd, func, partitions, (index, res) => results(index) = res) results }
/** * Run a function on a given set of partitions in an RDD and pass the results to the given * handler function. This is the main entry point for all actions in Spark. */ def runJob[T, U: ClassTag]( rdd: RDD[T], func: (TaskContext, Iterator[T]) => U, partitions: Seq[Int], resultHandler: (Int, U) => Unit): Unit = { if (stopped.get()) { throw new IllegalStateException("SparkContext has been shutdown") } val callSite = getCallSite val cleanedFunc = clean(func) logInfo("Starting job: " + callSite.shortForm) if (conf.getBoolean("spark.logLineage", false)) { logInfo("RDD's recursive dependencies:\n" + rdd.toDebugString) } dagScheduler.runJob(rdd, cleanedFunc, partitions, callSite, resultHandler, localProperties.get) progressBar.foreach(_.finishAll()) rdd.doCheckpoint() }
- dagScheduler.runJob
/** * Run an action job on the given RDD and pass all the results to the resultHandler function as * they arrive. * * @param rdd target RDD to run tasks on * @param func a function to run on each partition of the RDD * @param partitions set of partitions to run on; some jobs may not want to compute on all * partitions of the target RDD, e.g. for operations like first() * @param callSite where in the user program this job was called * @param resultHandler callback to pass each result to * @param properties scheduler properties to attach to this job, e.g. fair scheduler pool name * * @throws Exception when the job fails */ def runJob[T, U]( rdd: RDD[T], func: (TaskContext, Iterator[T]) => U, partitions: Seq[Int], callSite: CallSite, resultHandler: (Int, U) => Unit, properties: Properties): Unit = { val start = System.nanoTime val waiter = submitJob(rdd, func, partitions, callSite, resultHandler, properties) // Note: Do not call Await.ready(future) because that calls `scala.concurrent.blocking`, // which causes concurrent SQL executions to fail if a fork-join pool is used. Note that // due to idiosyncrasies in Scala, `awaitPermission` is not actually used anywhere so it's // safe to pass in null here. For more detail, see SPARK-13747. val awaitPermission = null.asInstanceOf[scala.concurrent.CanAwait] waiter.completionFuture.ready(Duration.Inf)(awaitPermission) waiter.completionFuture.value.get match { case scala.util.Success(_) => logInfo("Job %d finished: %s, took %f s".format (waiter.jobId, callSite.shortForm, (System.nanoTime - start) / 1e9)) case scala.util.Failure(exception) => logInfo("Job %d failed: %s, took %f s".format (waiter.jobId, callSite.shortForm, (System.nanoTime - start) / 1e9)) // SPARK-8644: Include user stack trace in exceptions coming from DAGScheduler. val callerStackTrace = Thread.currentThread().getStackTrace.tail exception.setStackTrace(exception.getStackTrace ++ callerStackTrace) throw exception } }
/** * Submit an action job to the scheduler. * * @param rdd target RDD to run tasks on * @param func a function to run on each partition of the RDD * @param partitions set of partitions to run on; some jobs may not want to compute on all * partitions of the target RDD, e.g. for operations like first() * @param callSite where in the user program this job was called * @param resultHandler callback to pass each result to * @param properties scheduler properties to attach to this job, e.g. fair scheduler pool name * * @return a JobWaiter object that can be used to block until the job finishes executing * or can be used to cancel the job. * * @throws IllegalArgumentException when partitions ids are illegal */ def submitJob[T, U]( rdd: RDD[T], func: (TaskContext, Iterator[T]) => U, partitions: Seq[Int], callSite: CallSite, resultHandler: (Int, U) => Unit, properties: Properties): JobWaiter[U] = { // Check to make sure we are not launching a task on a partition that does not exist. val maxPartitions = rdd.partitions.length partitions.find(p => p >= maxPartitions || p < 0).foreach { p => throw new IllegalArgumentException( "Attempting to access a non-existent partition: " + p + ". " + "Total number of partitions: " + maxPartitions) } val jobId = nextJobId.getAndIncrement() if (partitions.size == 0) { // Return immediately if the job is running 0 tasks return new JobWaiter[U](this, jobId, 0, resultHandler) } assert(partitions.size > 0) val func2 = func.asInstanceOf[(TaskContext, Iterator[_]) => _] val waiter = new JobWaiter(this, jobId, partitions.size, resultHandler) eventProcessLoop.post(JobSubmitted( jobId, rdd, func2, partitions.toArray, callSite, waiter, SerializationUtils.clone(properties))) waiter }
0 0
- The Process of Submitting a Job
- Submitting a Batch Job in PBS
- The life of looking for a job
- Condor手册 - 2.5 - Submitting a Job 提交任务
- ORA-31623 When Submitting a Datapump Job [ID 308388.1]
- the process of developing a program
- the limit to the amount of thread from a process
- The process of creating a socket is as follows
- Monitoring the death of a parent process (via Dispatch Sources)
- The Process of Write a File to Encryption Zone
- The process of testing
- The Process Of BFS.
- The Process Of PCI
- CGI - Submitting a Form
- Submitting a Command Buffer
- The Laws of Software Process: A New Model for the Production and Management of Software
- Describe the process of opening a file in Linux system, what actions the operating system w
- The Process of Software Architecting
- 算法15:打印中两个整数范围内的所有素数,例如:(12, 15) ->13
- 操作手机联系人
- QT修改qss文件后导致样式表不生效
- 面试被虐系列_算法分析篇_二叉树
- zookeeper小例子
- The Process of Submitting a Job
- 反向传导算法
- JAVA中的null
- 微服务技能树
- java中的synchronized(同步代码块和同步方法的区别)
- 数据源
- SmartGit 破解
- pta 5-8 表达式转换 (25分) (栈)
- 366-斐波那契数列