import com.robinspark.utils.ConnectionPool
import org.apache.spark.SparkConf
import org.apache.spark.sql.Row
import org.apache.spark.sql.hive.HiveContext
import org.apache.spark.sql.types.{IntegerType, StringType, StructField, StructType}
import org.apache.spark.streaming.{Seconds, StreamingContext}
/**
* 使用Spark Streaming+Spark SQL來在線動態計算電商中不同類別中最熱門的商品排名,例如手機這個類別下面最熱門的三種手機、電視這個類別
* 下最熱門的三種電視,該實例在實際生產環境下具有非常重大的意義;
*
* @author DT大數據夢工廠
* 新浪微博:http://weibo.com/ilovepains/
*
*
* 實現技術:Spark Streaming+Spark SQL,之所以Spark Streaming能夠使用ML、sql、graphx等功能是因爲有foreachRDD和Transform
* 等接口,這些接口中其實是基於RDD進行操作,所以以RDD爲基石,就可以直接使用Spark其它所有的功能,就像直接調用API一樣簡單。
* 假設說這裏的數據的格式:user item category,例如Rocky Samsung Android
*/
object OnlineTheTop3ItemForEachCategory2DB {
def main(args: Array[String]){
/**
* 第1步:創建Spark的配置對象SparkConf,設置Spark程序的運行時的配置信息,
* 例如說通過setMaster來設置程序要鏈接的Spark集羣的Master的URL,如果設置
* 爲local,則代表Spark程序在本地運行,特別適合於機器配置條件非常差(例如
* 只有1G的內存)的初學者 *
*/
val conf = new SparkConf() //創建SparkConf對象
conf.setAppName("OnlineTheTop3ItemForEachCategory2DB") //設置應用程序的名稱,在程序運行的監控界面可以看到名稱
conf.setMaster("spark://Master:7077") //此時,程序在Spark集羣
//conf.setMaster("local[2]")
//設置batchDuration時間間隔來控制Job生成的頻率並且創建Spark Streaming執行的入口
val ssc = new StreamingContext(conf, Seconds(5))
ssc.checkpoint("/root/Documents/SparkApps/checkpoint")
val userClickLogsDStream = ssc.socketTextStream("Master", 9999)
val formattedUserClickLogsDStream = userClickLogsDStream.map(clickLog =>
(clickLog.split(" ")(2) + "_" + clickLog.split(" ")(1), 1))
// val categoryUserClickLogsDStream = formattedUserClickLogsDStream.reduceByKeyAndWindow((v1:Int, v2: Int) => v1 + v2,
// (v1:Int, v2: Int) => v1 - v2, Seconds(60), Seconds(20))
val categoryUserClickLogsDStream = formattedUserClickLogsDStream.reduceByKeyAndWindow(_+_,
_-_, Seconds(60), Seconds(20))
categoryUserClickLogsDStream.foreachRDD { rdd => {
if (rdd.isEmpty()) {
println("No data inputted!!!")
} else {
val categoryItemRow = rdd.map(reducedItem => {
val category = reducedItem._1.split("_")(0)
val item = reducedItem._1.split("_")(1)
val click_count = reducedItem._2
Row(category, item, click_count)
})
val structType = StructType(Array(
StructField("category", StringType, true),
StructField("item", StringType, true),
StructField("click_count", IntegerType, true)
))
val hiveContext = new HiveContext(rdd.context)
val categoryItemDF = hiveContext.createDataFrame(categoryItemRow, structType)
categoryItemDF.registerTempTable("categoryItemTable")
val reseltDataFram = hiveContext.sql("SELECT category,item,click_count FROM (SELECT category,item,click_count,row_number()" +
" OVER (PARTITION BY category ORDER BY click_count DESC) rank FROM categoryItemTable) subquery " +
" WHERE rank <= 3")
reseltDataFram.show()
val resultRowRDD = reseltDataFram.rdd
resultRowRDD.foreachPartition { partitionOfRecords => {
if (partitionOfRecords.isEmpty){
println("This RDD is not null but partition is null")
} else {
// ConnectionPool is a static, lazily initialized pool of connections
val connection = ConnectionPool.getConnection()
partitionOfRecords.foreach(record => {
val sql = "insert into categorytop3(category,item,client_count) values('" + record.getAs("category") + "','" +
record.getAs("item") + "'," + record.getAs("click_count") + ")"
val stmt = connection.createStatement();
stmt.executeUpdate(sql);
})
ConnectionPool.returnConnection(connection) // return to the pool for future reuse
}
}
}
}
}
}
/**
* 在StreamingContext調用start方法的內部其實是會啓動JobScheduler的Start方法,進行消息循環,在JobScheduler
* 的start內部會構造JobGenerator和ReceiverTacker,並且調用JobGenerator和ReceiverTacker的start方法:
* 1,JobGenerator啓動後會不斷的根據batchDuration生成一個個的Job
* 2,ReceiverTracker啓動後首先在Spark Cluster中啓動Receiver(其實是在Executor中先啓動ReceiverSupervisor),在Receiver收到
* 數據後會通過ReceiverSupervisor存儲到Executor並且把數據的Metadata信息發送給Driver中的ReceiverTracker,在ReceiverTracker
* 內部會通過ReceivedBlockTracker來管理接受到的元數據信息
* 每個BatchInterval會產生一個具體的Job,其實這裏的Job不是Spark Core中所指的Job,它只是基於DStreamGraph而生成的RDD
* 的DAG而已,從Java角度講,相當於Runnable接口實例,此時要想運行Job需要提交給JobScheduler,在JobScheduler中通過線程池的方式找到一個
* 單獨的線程來提交Job到集羣運行(其實是在線程中基於RDD的Action觸發真正的作業的運行),爲什麼使用線程池呢?
* 1,作業不斷生成,所以爲了提升效率,我們需要線程池;這和在Executor中通過線程池執行Task有異曲同工之妙;
* 2,有可能設置了Job的FAIR公平調度的方式,這個時候也需要多線程的支持;
*
*/
ssc.start()
ssc.awaitTermination()
}
}
this(StreamingContext.createNewSparkContext(conf), null, batchDuration)
}
new SparkContext(conf)
}
port: Int,
storageLevel: StorageLevel = StorageLevel.MEMORY_AND_DISK_SER_2
): ReceiverInputDStream[String] = withNamedScope("socket text stream") {
socketStream[String](hostname, port, SocketReceiver.bytesToLines, storageLevel)
}
hostname: String,
port: Int,
converter: (InputStream) => Iterator[T],
storageLevel: StorageLevel
): ReceiverInputDStream[T] = {
new SocketInputDStream[T](this, hostname, port, converter, storageLevel)
}
class SocketInputDStream[T: ClassTag](
ssc_ : StreamingContext,
host: String,
port: Int,
bytesToObjects: InputStream => Iterator[T],
storageLevel: StorageLevel
) extends ReceiverInputDStream[T](ssc_) {
def getReceiver(): Receiver[T] = {
new SocketReceiver(host, port, bytesToObjects, storageLevel)
}
}
extends InputDStream[T](ssc_) {
extends DStream[T](ssc_) {
* DStreams internally is characterized by a few basic properties:
* - A list of other DStreams that the DStream depends on
* - A time interval at which the DStream generates an RDD
* - A function that is used to generate an RDD after each time interval
*/
@transient private[streaming] var ssc: StreamingContext
// Start the thread that receives data over a connection
new Thread("Socket Receiver") {
setDaemon(true)
override def run() { receive() }
}.start()
}
def receive() {
var socket: Socket = null
try {
logInfo("Connecting to " + host + ":" + port)
socket = new Socket(host, port)
logInfo("Connected to " + host + ":" + port)
val iterator = bytesToObjects(socket.getInputStream())
while(!isStopped && iterator.hasNext) {
store(iterator.next)
}
if (!isStopped()) {
restart("Socket data stream had no more data")
} else {
logInfo("Stopped receiving")
}
// like call sites and job groups can be reset without affecting those of the
// current thread.
ThreadUtils.runInNewThread("streaming-start") {
sparkContext.setCallSite(startSite.get)
sparkContext.clearJobGroup()
sparkContext.setLocalProperty(SparkContext.SPARK_JOB_INTERRUPT_ON_CANCEL, "false")
scheduler.start()
}
if (eventLoop != null) return // scheduler has already been started
logDebug("Starting JobScheduler")
eventLoop = new EventLoop[JobSchedulerEvent]("JobScheduler") {
override protected def onReceive(event: JobSchedulerEvent): Unit = processEvent(event)
override protected def onError(e: Throwable): Unit = reportError("Error in job scheduler", e)
}
eventLoop.start()
private val eventQueue: BlockingQueue[E] = new LinkedBlockingDeque[E]()
private val stopped = new AtomicBoolean(false)
private val eventThread = new Thread(name) {
setDaemon(true)
override def run(): Unit = {
try {
while (!stopped.get) {
val event = eventQueue.take()
try {
onReceive(event)
} catch {
try {
event match {
case JobStarted(job, startTime) => handleJobStart(job, startTime)
case JobCompleted(job, completedTime) => handleJobCompletion(job, completedTime)
case ErrorReported(m, e) => handleError(m, e)
}
} catch {
for {
inputDStream <- ssc.graph.getInputStreams
rateController <- inputDStream.rateController
} ssc.addStreamingListener(rateController)
protected[streaming] val rateController: Option[RateController] = None
receiverTracker = new ReceiverTracker(ssc)
inputInfoTracker = new InputInfoTracker(ssc)
receiverTracker.start()
jobGenerator.start()
event match {
case receiverStarted: StreamingListenerReceiverStarted =>
listener.onReceiverStarted(receiverStarted)
case receiverError: StreamingListenerReceiverError =>
listener.onReceiverError(receiverError)
case receiverStopped: StreamingListenerReceiverStopped =>
listener.onReceiverStopped(receiverStopped)
case batchSubmitted: StreamingListenerBatchSubmitted =>
listener.onBatchSubmitted(batchSubmitted)
case batchStarted: StreamingListenerBatchStarted =>
listener.onBatchStarted(batchStarted)
case batchCompleted: StreamingListenerBatchCompleted =>
listener.onBatchCompleted(batchCompleted)
case outputOperationStarted: StreamingListenerOutputOperationStarted =>
listener.onOutputOperationStarted(outputOperationStarted)
case outputOperationCompleted: StreamingListenerOutputOperationCompleted =>
listener.onOutputOperationCompleted(outputOperationCompleted)
case _ =>
}
}
def start(): Unit = synchronized {
if (isTrackerStarted) {
throw new SparkException("ReceiverTracker already started")
}
if (!receiverInputStreams.isEmpty) {
endpoint = ssc.env.rpcEnv.setupEndpoint(
"ReceiverTracker", new ReceiverTrackerEndpoint(ssc.env.rpcEnv))
if (!skipReceiverLaunch) launchReceivers()
logInfo("ReceiverTracker started")
trackerState = Started
}
}
// Local messages
case StartAllReceivers(receivers) =>
val scheduledLocations = schedulingPolicy.scheduleReceivers(receivers, getExecutors)
for (receiver <- receivers) {
val executors = scheduledLocations(receiver.streamId)
updateReceiverScheduledExecutors(receiver.streamId, executors)
receiverPreferredLocations(receiver.streamId) = receiver.preferredLocation
startReceiver(receiver, executors)
}
case RestartReceiver(receiver) =>
// Old scheduled executors minus the ones that are not active any more
val oldScheduledExecutors = getStoredScheduledExecutors(receiver.streamId)
val scheduledLocations = if (oldScheduledExecutors.nonEmpty) {
// Try global scheduling again
oldScheduledExecutors
} else {
val oldReceiverInfo = receiverTrackingInfos(receiver.streamId)
// Clear "scheduledLocations" to indicate we are going to do local scheduling
val newReceiverInfo = oldReceiverInfo.copy(
state = ReceiverState.INACTIVE, scheduledLocations = None)
receiverTrackingInfos(receiver.streamId) = newReceiverInfo
schedulingPolicy.rescheduleReceiver(
receiver.streamId,
receiver.preferredLocation,
receiverTrackingInfos,
getExecutors)
}
// Assume there is one receiver restarting at one time, so we don't need to update
// receiverTrackingInfos
startReceiver(receiver, scheduledLocations)
// we need to make sure the "preferredLocation" is in the candidate scheduled executor list.
for (i <- 0 until receivers.length) {
// Note: preferredLocation is host but executors are host_executorId
receivers(i).preferredLocation.foreach { host =>
hostToExecutors.get(host) match {
case Some(executorsOnHost) =>
// preferredLocation is a known host. Select an executor that has the least receivers in
// this host
val leastScheduledExecutor =
executorsOnHost.minBy(executor => numReceiversOnExecutor(executor))
scheduledLocations(i) += leastScheduledExecutor
numReceiversOnExecutor(leastScheduledExecutor) =
numReceiversOnExecutor(leastScheduledExecutor) + 1
case None =>
// preferredLocation is an unknown host.
// Note: There are two cases:
// 1. This executor is not up. But it may be up later.
// 2. This executor is dead, or it's not a host in the cluster.
// Currently, simply add host to the scheduled executors.
// Note: host could be `HDFSCacheTaskLocation`, so use `TaskLocation.apply` to handle
// this case
scheduledLocations(i) += TaskLocation(host)
}
}
}
* Get the receivers from the ReceiverInputDStreams, distributes them to the
* worker nodes as a parallel collection, and runs them.
*/
private def launchReceivers(): Unit = {
val receivers = receiverInputStreams.map(nis => {
val rcvr = nis.getReceiver()
rcvr.setReceiverId(nis.id)
rcvr
})
runDummySparkJob()
logInfo("Starting " + receivers.length + " receivers")
endpoint.send(StartAllReceivers(receivers))
}
* Run the dummy Spark job to ensure that all slaves have registered. This avoids all the
* receivers to be scheduled on the same node.
*
* TODO Should poll the executor number and wait for executors according to
* "spark.scheduler.minRegisteredResourcesRatio" and
* "spark.scheduler.maxRegisteredResourcesWaitingTime" rather than running a dummy job.
*/
private def runDummySparkJob(): Unit = {
if (!ssc.sparkContext.isLocal) {
ssc.sparkContext.makeRDD(1 to 50, 50).map(x => (x, 1)).reduceByKey(_ + _, 20).collect()
}
assert(getExecutors.nonEmpty)
}
// This not being null means the tracker has been started and not stopped
private var endpoint: RpcEndpointRef = null
"ReceiverTracker", new ReceiverTrackerEndpoint(ssc.env.rpcEnv))
// Local messages
case StartAllReceivers(receivers) =>
val scheduledLocations = schedulingPolicy.scheduleReceivers(receivers, getExecutors)
for (receiver <- receivers) {
val executors = scheduledLocations(receiver.streamId)
updateReceiverScheduledExecutors(receiver.streamId, executors)
receiverPreferredLocations(receiver.streamId) = receiver.preferredLocation
startReceiver(receiver, executors)
}
val startReceiverFunc: Iterator[Receiver[_]] => Unit =
(iterator: Iterator[Receiver[_]]) => {
if (!iterator.hasNext) {
throw new SparkException(
"Could not start receiver as object not found.")
}
if (TaskContext.get().attemptNumber() == 0) {
val receiver = iterator.next()
assert(iterator.hasNext == false)
val supervisor = new ReceiverSupervisorImpl(
receiver, SparkEnv.get, serializableHadoopConf.value, checkpointDirOption)
supervisor.start()
supervisor.awaitTermination()
} else {
// It's restarted by TaskScheduler, but we want to reschedule it again. So exit it.
}
}
val receiverRDD: RDD[Receiver[_]] =
if (scheduledLocations.isEmpty) {
ssc.sc.makeRDD(Seq(receiver), 1)
} else {
val preferredLocations = scheduledLocations.map(_.toString).distinct
ssc.sc.makeRDD(Seq(receiver -> preferredLocations))
}
receiverRDD.setName(s"Receiver $receiverId")
ssc.sparkContext.setJobDescription(s"Streaming job running receiver $receiverId")
ssc.sparkContext.setCallSite(Option(ssc.getStartSite()).getOrElse(Utils.getCallSite()))
val future = ssc.sparkContext.submitJob[Receiver[_], Unit, Unit](
receiverRDD, startReceiverFunc, Seq(0), (_, _) => Unit, ())
// We will keep restarting the receiver job until ReceiverTracker is stopped
future.onComplete {
case Success(_) =>
if (!shouldStartReceiver) {
onReceiverJobFinish(receiverId)
} else {
logInfo(s"Restarting Receiver $receiverId")
self.send(RestartReceiver(receiver))
}
case Failure(e) =>
if (!shouldStartReceiver) {
onReceiverJobFinish(receiverId)
} else {
logError("Receiver has been stopped. Try to restart it.", e)
logInfo(s"Restarting Receiver $receiverId")
self.send(RestartReceiver(receiver))
}
}(submitJobThreadPool)
logInfo(s"Receiver ${receiver.streamId} started")
}
def startReceiver(): Unit = synchronized {
try {
if (onReceiverStart()) {
logInfo("Starting receiver")
receiverState = Started
receiver.onStart()
logInfo("Called receiver onStart")
} else {
// The driver refused us
stop("Registered unsuccessfully because Driver refused to start receiver " + streamId, None)
}
val msg = RegisterReceiver(
streamId, receiver.getClass.getSimpleName, host, executorId, endpoint)
trackerEndpoint.askWithRetry[Boolean](msg)
}
def start(): Unit = synchronized {
if (eventLoop != null) return // generator has already been started
// Call checkpointWriter here to initialize it before eventLoop uses it to avoid a deadlock.
// See SPARK-10125
checkpointWriter
eventLoop = new EventLoop[JobGeneratorEvent]("JobGenerator") {
override protected def onReceive(event: JobGeneratorEvent): Unit = processEvent(event)
override protected def onError(e: Throwable): Unit = {
jobScheduler.reportError("Error in job generator", e)
}
}
eventLoop.start()
if (ssc.isCheckpointPresent) {
restart()
} else {
startFirstTime()
}
}
private def processEvent(event: JobGeneratorEvent) {
logDebug("Got event " + event)
event match {
case GenerateJobs(time) => generateJobs(time)
case ClearMetadata(time) => clearMetadata(time)
case DoCheckpoint(time, clearCheckpointDataLater) =>
doCheckpoint(time, clearCheckpointDataLater)
case ClearCheckpointData(time) => clearCheckpointData(time)
}
}
private def generateJobs(time: Time) {
// Set the SparkEnv in this thread, so that job generation code can access the environment
// Example: BlockRDDs are created in this thread, and it needs to access BlockManager
// Update: This is probably redundant after threadlocal stuff in SparkEnv has been removed.
SparkEnv.set(ssc.env)
Try {
jobScheduler.receiverTracker.allocateBlocksToBatch(time) // allocate received blocks to batch
graph.generateJobs(time) // generate jobs using allocated block
} match {
case Success(jobs) =>
val streamIdToInputInfos = jobScheduler.inputInfoTracker.getInfo(time)
jobScheduler.submitJobSet(JobSet(time, jobs, streamIdToInputInfos))
case Failure(e) =>
jobScheduler.reportError("Error generating jobs for time " + time, e)
}
eventLoop.post(DoCheckpoint(time, clearCheckpointDataLater = false))
}
if (jobSet.jobs.isEmpty) {
logInfo("No jobs added for time " + jobSet.time)
} else {
listenerBus.post(StreamingListenerBatchSubmitted(jobSet.toBatchInfo))
jobSets.put(jobSet.time, jobSet)
jobSet.jobs.foreach(job => jobExecutor.execute(new JobHandler(job)))
logInfo("Added jobs for time " + jobSet.time)
}
}
* Executes the given task sometime in the future. The task
* may execute in a new thread or in an existing pooled thread.
*
* If the task cannot be submitted for execution, either because this
* executor has been shutdown or because its capacity has been reached,
* the task is handled by the current {@code RejectedExecutionHandler}.
*
* @param command the task to execute
* @throws RejectedExecutionException at discretion of
* {@code RejectedExecutionHandler}, if the task
* cannot be accepted for execution
* @throws NullPointerException if {@code command} is null
*/
public void execute(Runnable command) {
if (command == null)
throw new NullPointerException();
/*
* Proceed in 3 steps:
*
* 1. If fewer than corePoolSize threads are running, try to
* start a new thread with the given command as its first
* task. The call to addWorker atomically checks runState and
* workerCount, and so prevents false alarms that would add
* threads when it shouldn't, by returning false.
*
* 2. If a task can be successfully queued, then we still need
* to double-check whether we should have added a thread
* (because existing ones died since last checking) or that
* the pool shut down since entry into this method. So we
* recheck state and if necessary roll back the enqueuing if
* stopped, or start a new thread if there are none.
*
* 3. If we cannot queue task, then we try to add a new
* thread. If it fails, we know we are shut down or saturated
* and so reject the task.
*/
int c = ctl.get();
if (workerCountOf(c) < corePoolSize) {
if (addWorker(command, true))
return;
c = ctl.get();
}
if (isRunning(c) && workQueue.offer(command)) {
int recheck = ctl.get();
if (! isRunning(recheck) && remove(command))
reject(command);
else if (workerCountOf(recheck) == 0)
addWorker(null, false);
}
else if (!addWorker(command, false))
reject(command);
}
import JobScheduler._
def run() {
try {
val formattedTime = UIUtils.formatBatchTime(
job.time.milliseconds, ssc.graph.batchDuration.milliseconds, showYYYYMMSS = false)
val batchUrl = s"/streaming/batch/?id=${job.time.milliseconds}"
val batchLinkText = s"[output operation ${job.outputOpId}, batch time ${formattedTime}]"
ssc.sc.setJobDescription(
s"""Streaming job from <a href="$batchUrl">$batchLinkText</a>""")
ssc.sc.setLocalProperty(BATCH_TIME_PROPERTY_KEY, job.time.milliseconds.toString)
ssc.sc.setLocalProperty(OUTPUT_OP_ID_PROPERTY_KEY, job.outputOpId.toString)
// We need to assign `eventLoop` to a temp variable. Otherwise, because
// `JobScheduler.stop(false)` may set `eventLoop` to null when this method is running, then
// it's possible that when `post` is called, `eventLoop` happens to null.
var _eventLoop = eventLoop
if (_eventLoop != null) {
_eventLoop.post(JobStarted(job, clock.getTimeMillis()))
// Disable checks for existing output directories in jobs launched by the streaming
// scheduler, since we may need to write output to an existing directory during checkpoint
// recovery; see SPARK-4835 for more details.
PairRDDFunctions.disableOutputSpecValidation.withValue(true) {
job.run()
}
_eventLoop = eventLoop
if (_eventLoop != null) {
_eventLoop.post(JobCompleted(job, clock.getTimeMillis()))
}
} else {
// JobScheduler has been stopped.
}
} finally {
ssc.sc.setLocalProperty(JobScheduler.BATCH_TIME_PROPERTY_KEY, null)
ssc.sc.setLocalProperty(JobScheduler.OUTPUT_OP_ID_PROPERTY_KEY, null)
}
}
}
}
try {
event match {
case JobStarted(job, startTime) => handleJobStart(job, startTime)
case JobCompleted(job, completedTime) => handleJobCompletion(job, completedTime)
case ErrorReported(m, e) => handleError(m, e)
}
} catch {
case e: Throwable =>
reportError("Error in job scheduler", e)
}
}
val jobSet = jobSets.get(job.time)
val isFirstJobOfJobSet = !jobSet.hasStarted
jobSet.handleJobStart(job)
if (isFirstJobOfJobSet) {
// "StreamingListenerBatchStarted" should be posted after calling "handleJobStart" to get the
// correct "jobSet.processingStartTime".
listenerBus.post(StreamingListenerBatchStarted(jobSet.toBatchInfo))
}
job.setStartTime(startTime)
listenerBus.post(StreamingListenerOutputOperationStarted(job.toOutputOperationInfo))
logInfo("Starting job " + job.id + " from job set of time " + jobSet.time)
}
import JobScheduler._
def run() {
try {
val formattedTime = UIUtils.formatBatchTime(
job.time.milliseconds, ssc.graph.batchDuration.milliseconds, showYYYYMMSS = false)
val batchUrl = s"/streaming/batch/?id=${job.time.milliseconds}"
val batchLinkText = s"[output operation ${job.outputOpId}, batch time ${formattedTime}]"
ssc.sc.setJobDescription(
s"""Streaming job from <a href="$batchUrl">$batchLinkText</a>""")
ssc.sc.setLocalProperty(BATCH_TIME_PROPERTY_KEY, job.time.milliseconds.toString)
ssc.sc.setLocalProperty(OUTPUT_OP_ID_PROPERTY_KEY, job.outputOpId.toString)
// We need to assign `eventLoop` to a temp variable. Otherwise, because
// `JobScheduler.stop(false)` may set `eventLoop` to null when this method is running, then
// it's possible that when `post` is called, `eventLoop` happens to null.
var _eventLoop = eventLoop
if (_eventLoop != null) {
_eventLoop.post(JobStarted(job, clock.getTimeMillis()))
// Disable checks for existing output directories in jobs launched by the streaming
// scheduler, since we may need to write output to an existing directory during checkpoint
// recovery; see SPARK-4835 for more details.
PairRDDFunctions.disableOutputSpecValidation.withValue(true) {
job.run()
}
_eventLoop = eventLoop
if (_eventLoop != null) {
_eventLoop.post(JobCompleted(job, clock.getTimeMillis()))
}
} else {
// JobScheduler has been stopped.
}
} finally {
ssc.sc.setLocalProperty(JobScheduler.BATCH_TIME_PROPERTY_KEY, null)
ssc.sc.setLocalProperty(JobScheduler.OUTPUT_OP_ID_PROPERTY_KEY, null)
}
}
}
}
新浪微博:http://www.weibo.com/ilovepains