//提交stage，为stage创建一批task，task数量和partition数量相同
创新互联是一家
网站设计制作、网站设计，提供网页设计，网站设计，网站制作，建网站，按需求定制网站，网站开发公司，于2013年成立是互联行业建设者，服务者。以提升客户品牌价值为核心业务，全程参与项目的网站策划设计制作，前端开发，后台程序制作以及后期项目运营并提出专业建议和思路。
private def submitMissingTasks(stage: Stage, jobId: Int) {
logDebug("submitMissingTasks(" + stage + ")")
// Get our pending tasks and remember them in our pendingTasks entry
stage.pendingTasks.clear()
// First figure out the indexes of partition ids to compute.
//获取要创建的task的数量
val partitionsToCompute: Seq[Int] = {
if (stage.isShuffleMap) {
(0 until stage.numPartitions).filter(id => stage.outputLocs(id) == Nil)
} else {
val job = stage.resultOfJob.get
(0 until job.numPartitions).filter(id => !job.finished(id))
}
}
val properties = if (jobIdToActiveJob.contains(jobId)) {
jobIdToActiveJob(stage.jobId).properties
} else {
// this stage will be assigned to "default" pool
null
}
//将stage加入runningstage队列
runningStages += stage
// SparkListenerStageSubmitted should be posted before testing whether tasks are
// serializable. If tasks are not serializable, a SparkListenerStageCompleted event
// will be posted, which should always come after a corresponding SparkListenerStageSubmitted
// event.
stage.latestInfo = StageInfo.fromStage(stage, Some(partitionsToCompute.size))
outputCommitCoordinator.stageStart(stage.id)
listenerBus.post(SparkListenerStageSubmitted(stage.latestInfo, properties))
// TODO: Maybe we can keep the taskBinary in Stage to avoid serializing it multiple times.
// Broadcasted binary for the task, used to dispatch tasks to executors. Note that we broadcast
// the serialized copy of the RDD and for each task we will deserialize it, which means each
// task gets a different copy of the RDD. This provides stronger isolation between tasks that
// might modify state of objects referenced in their closures. This is necessary in Hadoop
// where the JobConf/Configuration object is not thread-safe.
var taskBinary: Broadcast[Array[Byte]] = null
try {
// For ShuffleMapTask, serialize and broadcast (rdd, shuffleDep).
// For ResultTask, serialize and broadcast (rdd, func).
val taskBinaryBytes: Array[Byte] =
if (stage.isShuffleMap) {
closureSerializer.serialize((stage.rdd, stage.shuffleDep.get) : AnyRef).array()
} else {
closureSerializer.serialize((stage.rdd, stage.resultOfJob.get.func) : AnyRef).array()
}
taskBinary = sc.broadcast(taskBinaryBytes)
} catch {
// In the case of a failure during serialization, abort the stage.
case e: NotSerializableException =>
abortStage(stage, "Task not serializable: " + e.toString)
runningStages -= stage
return
case NonFatal(e) =>
abortStage(stage, s"Task serialization failed: $e\n${e.getStackTraceString}")
runningStages -= stage
return
}
//为stage创建指定数量的task
val tasks: Seq[Task[_]] = if (stage.isShuffleMap) {
partitionsToCompute.map { id =>
//给每个partition创建一个task
//给每个task计算最佳位置
val locs = getPreferredLocs(stage.rdd, id)
val part = stage.rdd.partitions(id)
//对于finalstage之外的stage的isShuffleMap都是true
//所以会创建ShuffleMapTask
new ShuffleMapTask(stage.id, taskBinary, part, locs)
}
} else {
//如果不是ShuffleMap，就会创建finalstage
//finalstage是穿件resultTask
val job = stage.resultOfJob.get
partitionsToCompute.map { id =>
val p: Int = job.partitions(id)
val part = stage.rdd.partitions(p)
//获取task计算的最佳位置的方法 getPreferredLocs
val locs = getPreferredLocs(stage.rdd, p)
new ResultTask(stage.id, taskBinary, part, locs, id)
}
}
if (tasks.size > 0) {
logInfo("Submitting " + tasks.size + " missing tasks from " + stage + " (" + stage.rdd + ")")
stage.pendingTasks ++= tasks
logDebug("New pending tasks: " + stage.pendingTasks)
taskScheduler.submitTasks(
new TaskSet(tasks.toArray, stage.id, stage.newAttemptId(), stage.jobId, properties))
stage.latestInfo.submissionTime = Some(clock.getTimeMillis())
} else {
// Because we posted SparkListenerStageSubmitted earlier, we should post
// SparkListenerStageCompleted here in case there are no tasks to run.
outputCommitCoordinator.stageEnd(stage.id)
listenerBus.post(SparkListenerStageCompleted(stage.latestInfo))
logDebug("Stage " + stage + " is actually done; %b %d %d".format(
stage.isAvailable, stage.numAvailableOutputs, stage.numPartitions))
runningStages -= stage
}
}
def getPreferredLocs(rdd: RDD[_], partition: Int): Seq[TaskLocation] = {
getPreferredLocsInternal(rdd, partition, new HashSet)
}
//task对应partition的最佳位置
//就是从stage的最后一个RDD开始，找哪个RDD是被持久化了或者checkpoint
//那么task的最佳位置就是缓存的/checkpoint 的 partition的位置
//因为这样的话，task就在那个节点上执行，不需要计算之前的RDD
private def getPreferredLocsInternal(
rdd: RDD[_],
partition: Int,
visited: HashSet[(RDD[_],Int)])
: Seq[TaskLocation] =
{
// If the partition has already been visited, no need to re-visit.
// This avoids exponential path exploration. SPARK-695
if (!visited.add((rdd,partition))) {
// Nil has already been returned for previously visited partitions.
return Nil
}
// If the partition is cached, return the cache locations
//寻找当前RDD是否缓存了
val cached = getCacheLocs(rdd)(partition)
if (!cached.isEmpty) {
return cached
}
// If the RDD has some placement preferences (as is the case for input RDDs), get those
//寻找当前RDD是否checkpoint了
val rddPrefs = rdd.preferredLocations(rdd.partitions(partition)).toList
if (!rddPrefs.isEmpty) {
return rddPrefs.map(TaskLocation(_))
}
// If the RDD has narrow dependencies, pick the first partition of the first narrow dep
// that has any placement preferences. Ideally we would choose based on transfer sizes,
// but this will do for now.
//递归调用，看看父RDD是否缓存或者checkpoint
rdd.dependencies.foreach {
case n: NarrowDependency[_] =>
for (inPart <- n.getParents(partition)) {
val locs = getPreferredLocsInternal(n.rdd, inPart, visited)
if (locs != Nil) {
return locs
}
}
case _ =>
}
//如果从第一个RDD到最后一个RDD都没有缓存或者checkpoint，那最佳位置就是Nil，也就是没有最佳位置
//那他的位置就要由taskscheduler来分配
Nil
}
另外有需要云服务器可以了解下创新互联scvps.cn，海内外云服务器15元起步，三天无理由+7*72小时售后在线，公司持有idc许可证，提供“云服务器、裸金属服务器、高防服务器、香港服务器、美国服务器、虚拟主机、免备案服务器”等云主机租用服务以及企业上云的综合解决方案，具有“安全稳定、简单易用、服务可用性高、性价比高”等特点与优势，专为企业上云打造定制，能够满足用户丰富、多元化的应用场景需求。
网站题目：提交stage-创新互联
当前URL：
http://cdkjz.cn/article/icjpg.html
