本篇内容从ReceiverTracker消息通讯的角度来研究ReceiverTracker的源码
在第10篇中介绍过Receiver的启动、注册、数据汇报，接着第10篇的内容看。从ReceiverSupervisorImpl的pushAndReportBlock方法开始，代码如下
def pushAndReportBlock(
receivedBlock: ReceivedBlock,
metadataOption: Option[Any],
blockIdOption: Option[StreamBlockId]
) {
val blockId = blockIdOption.getOrElse(nextBlockId)
val time = System.currentTimeMillis
val blockStoreResult = receivedBlockHandler.storeBlock(blockId, receivedBlock)
logDebug(s"Pushed block $blockId in ${(System.currentTimeMillis - time)} ms")
val numRecords = blockStoreResult.numRecords
val blockInfo = ReceivedBlockInfo(streamId, numRecords, metadataOption, blockStoreResult)
trackerEndpoint.askWithRetry[Boolean](AddBlock(blockInfo))
logDebug(s"Reported block $blockId")
}向trackerEndpoint汇报AddBlock消息，blockInfo只是一个简单的case class，代码如下
private[streaming] case class ReceivedBlockInfo(
streamId: Int,
numRecords: Option[Long],
metadataOption: Option[Any],
blockStoreResult: ReceivedBlockStoreResult
) {
require(numRecords.isEmpty || numRecords.get >= 0, "numRecords must not be negative")
@volatile private var _isBlockIdValid = true
def blockId: StreamBlockId = blockStoreResult.blockId
def walRecordHandleOption: Option[WriteAheadLogRecordHandle] = {
blockStoreResult match { case walStoreResult: WriteAheadLogBasedStoreResult => Some(walStoreResult.walRecordHandle) case _ => None
}
}
/** Is the block ID valid, that is, is the block present in the Spark executors. */
def isBlockIdValid(): Boolean = _isBlockIdValid
/**
* Set the block ID as invalid. This is useful when it is known that the block is not present
* in the Spark executors.
* 当block在Executors中不存在时，将block ID 设置为无效的
*/
def setBlockIdInvalid(): Unit = {
_isBlockIdValid = false
}
}里面没什么信息，看ReceivedBlockStoreResult，代码如下
private[streaming] trait ReceivedBlockStoreResult { // Any implementation of this trait will store a block id
def blockId: StreamBlockId // Any implementation of this trait will have to return the number of records
def numRecords: Option[Long]
}他只是一个接口，看他的两个子类，分别是WriteAheadLogBasedStoreResult和BlockManagerBasedStoreResult。在WriteAheadLogBasedStoreResult类中多了一个WriteAheadLogRecordHandle。
看ReceiverTrackerEndpoint中的receiveAndReply是怎样接收AddBlock消息的，代码如下
case AddBlock(receivedBlockInfo) => if (WriteAheadLogUtils.isBatchingEnabled(ssc.conf, isDriver = true)) {
walBatchingThreadPool.execute(new Runnable { override def run(): Unit = Utils.tryLogNonFatalError { if (active) {
context.reply(addBlock(receivedBlockInfo))
} else { throw new IllegalStateException("ReceiverTracker RpcEndpoint shut down.")
}
}
})
} else {
context.reply(addBlock(receivedBlockInfo))
}首先判断是否采用WAL的方法保存元数据，默认为true。如果是WAL的方式存储，WAL采用了一个线程池来处理操作。两种方法最终都是调用addBlock(receivedBlockInfo)方法，addBlock的代码如下
private def addBlock(receivedBlockInfo: ReceivedBlockInfo): Boolean = {
receivedBlockTracker.addBlock(receivedBlockInfo)
}这里什么也没做就把任务交给了receivedBlockTracker，ReceivedBlockTracker在ReceiverTrack实例化的时候被创建。看他的addBlock方法，代码如下
def addBlock(receivedBlockInfo: ReceivedBlockInfo): Boolean = {
try {
val writeResult = writeToLog(BlockAdditionEvent(receivedBlockInfo)) if (writeResult) {
synchronized {
getReceivedBlockQueue(receivedBlockInfo.streamId) += receivedBlockInfo
}
logDebug(s"Stream ${receivedBlockInfo.streamId} received " +
s"block ${receivedBlockInfo.blockStoreResult.blockId}")
} else {
logDebug(s"Failed to acknowledge stream ${receivedBlockInfo.streamId} receiving " +
s"block ${receivedBlockInfo.blockStoreResult.blockId} in the Write Ahead Log.")
}
writeResult
} catch { case NonFatal(e) =>
logError(s"Error adding block $receivedBlockInfo", e) false
}
}首先调用writeToLog方法，将receivedBlockInfo放到BlockAdditionEvent类中，传递进去 ，writeToLog的代码如下
private def writeToLog(record: ReceivedBlockTrackerLogEvent): Boolean = { if (isWriteAheadLogEnabled) {
logTrace(s"Writing record: $record") try {
writeAheadLogOption.get.write(ByteBuffer.wrap(Utils.serialize(record)),
clock.getTimeMillis()) true
} catch { case NonFatal(e) =>
logWarning(s"Exception thrown while writing record: $record to the WriteAheadLog.", e) false
}
} else { true
}
}如果是WAL的方式，就是把record序列化后存储，返回操作结果true,否则直接返回true。
回到上面的判断if (writeResult)，将receivedBlockInfo放入到getReceivedBlockQueue队列中，看一下getReceivedBlockQueue的代码
private def getReceivedBlockQueue(streamId: Int): ReceivedBlockQueue = {
streamIdToUnallocatedBlockQueues.getOrElseUpdate(streamId, new ReceivedBlockQueue)
}先从streamIdToUnallocatedBlockQueues中获取ReceivedBlockQueue队列，如果没有放一个新的ReceivedBlockQueue，取到队列后将receivedBlockInfo放入队列。每一个receiver对应一个自己的队列，streamIdToUnallocatedBlockQueues的代码如下
private type ReceivedBlockQueue = mutable.Queue[ReceivedBlockInfo]private val streamIdToUnallocatedBlockQueues = new mutable.HashMap[Int, ReceivedBlockQueue]
将receivedBlockInfo放入队列后，返回writeResult(就是true或false),代表元数据被接收成功或失败。
receivedBlockInfo已经被放入到队列中了，那么在什么时候被使用了呢？我们在job的动态生成的时候好像看到过，看JobGenerator的generateJobs方法里有这样一行代码，代码如下
// allocate received blocks to batch// 分配接收到的数据给batchjobScheduler.receiverTracker.allocateBlocksToBatch(time)
看receiverTracker的allocateBlocksToBatch方法，代码如下
def allocateBlocksToBatch(batchTime: Time): Unit = { if (receiverInputStreams.nonEmpty) {
receivedBlockTracker.allocateBlocksToBatch(batchTime)
}
}这里调用了receivedBlockTracker的allocateBlocksToBatch(batchTime)方法，接着看allocateBlocksToBatch的代码
/**
* Allocate all unallocated blocks to the given batch.
* This event will get written to the write ahead log (if enabled).
* 分配所有示分配的blocks给batch
*/def allocateBlocksToBatch(batchTime: Time): Unit = synchronized { if (lastAllocatedBatchTime == null || batchTime > lastAllocatedBatchTime) {
val streamIdToBlocks = streamIds.map { streamId =>
(streamId, getReceivedBlockQueue(streamId).dequeueAll(x => true))
}.toMap
val allocatedBlocks = AllocatedBlocks(streamIdToBlocks) if (writeToLog(BatchAllocationEvent(batchTime, allocatedBlocks))) {
timeToAllocatedBlocks.put(batchTime, allocatedBlocks)
lastAllocatedBatchTime = batchTime
} else {
logInfo(s"Possibly processed batch $batchTime need to be processed again in WAL recovery")
}
} else { // This situation occurs when:
// 1. WAL is ended with BatchAllocationEvent, but without BatchCleanupEvent,
// possibly processed batch job or half-processed batch job need to be processed again,
// so the batchTime will be equal to lastAllocatedBatchTime.
// 2. Slow checkpointing makes recovered batch time older than WAL recovered
// lastAllocatedBatchTime.
// This situation will only occurs in recovery time.
logInfo(s"Possibly processed batch $batchTime need to be processed again in WAL recovery")
}
}获取streamIdToBlocks:Map[Int,Seq[ReceiverBlockInfo]],从streamIdToUnallocatedBlockQueues中获取每一个receiver对应的ReceiverBlockInfo列表。
在writeToLog方法，判断如果是WAL方式，就写日志，否则直接返回true。
timeToAllocatedBlocks.put(batchTime, allocatedBlocks)这行代码将allocatedBlocks所有receiver接收的元数据按时间保存到timeToAllocatedBlocks中，然后更新lastAllocatedBatchTime
那么timeToAllocatedBlocks中的数据在什么时候被获取的，我们想一下，timeToAllocatedBlocks在job生成的时候需要填充数据，数据是在RDD中被使用的，所以猜想是在创建RDD的时候用到了timeToAllocatedBlocks。
找第一个RDD,就是BlockRDD，在ReceiverInputDStream的compute方法中找到了timeToAllocatedBlocks的使用，代码如下
override def compute(validTime: Time): Option[RDD[T]] = {
val blockRDD = { if (validTime < graph.startTime) { // If this is called for any time before the start time of the context,
// then this returns an empty RDD. This may happen when recovering from a
// driver failure without any write ahead log to recover pre-failure data.
new BlockRDD[T](ssc.sc, Array.empty)
} else { // Otherwise, ask the tracker for all the blocks that have been allocated to this stream
// for this batch
val receiverTracker = ssc.scheduler.receiverTracker // 根据时间获取所有receiver接收数据的元数据列表
val blockInfos = receiverTracker.getBlocksOfBatch(validTime).getOrElse(id, Seq.empty) // Register the input blocks information into InputInfoTracker
val inputInfo = StreamInputInfo(id, blockInfos.flatMap(_.numRecords).sum)
ssc.scheduler.inputInfoTracker.reportInfo(validTime, inputInfo) // Create the BlockRDD
createBlockRDD(validTime, blockInfos)
}
}
Some(blockRDD)
}跟踪receiverTracker.getBlocksOfBatch这个方法，代码如下
def getBlocksOfBatch(batchTime: Time): Map[Int, Seq[ReceivedBlockInfo]] = {
receivedBlockTracker.getBlocksOfBatch(batchTime)
}接着看getBlocksOfBatch方法
def getBlocksOfBatch(batchTime: Time): Map[Int, Seq[ReceivedBlockInfo]] = synchronized {
timeToAllocatedBlocks.get(batchTime).map { _.streamIdToAllocatedBlocks }.getOrElse(Map.empty)
}终于看到了timeToAllocatedBlocks被使用
再看一个ReceiverTracker的stop方法
代码如下
def stop(graceful: Boolean): Unit = synchronized { if (isTrackerStarted) { // First, stop the receivers
trackerState = Stopping if (!skipReceiverLaunch) { // Send the stop signal to all the receivers
endpoint.askWithRetry[Boolean](StopAllReceivers) // Wait for the Spark job that runs the receivers to be over
// That is, for the receivers to quit gracefully.
receiverJobExitLatch.await(10, TimeUnit.SECONDS) if (graceful) {
logInfo("Waiting for receiver job to terminate gracefully")
receiverJobExitLatch.await()
logInfo("Waited for receiver job to terminate gracefully")
} // Check if all the receivers have been deregistered or not
val receivers = endpoint.askWithRetry[Seq[Int]](AllReceiverIds) if (receivers.nonEmpty) {
logWarning("Not all of the receivers have deregistered, " + receivers)
} else {
logInfo("All of the receivers have deregistered successfully")
}
} // Finally, stop the endpoint
ssc.env.rpcEnv.stop(endpoint)
endpoint = null
receivedBlockTracker.stop()
logInfo("ReceiverTracker stopped")
trackerState = Stopped
}
}向endpoint发送一条停止所有receiver的消息StopAllReceivers，看接收到消息是怎样处理的，代码如下
case StopAllReceivers => assert(isTrackerStopping || isTrackerStopped) stopReceivers() context.reply(true)
接着看stopReceivers()方法，代码如下
private def stopReceivers() {
receiverTrackingInfos.values.flatMap(_.endpoint).foreach { _.send(StopReceiver) }
logInfo("Sent stop signal to all " + receiverTrackingInfos.size + " receivers")
}向每一个receiver发送一条StopReceiver消息，看ReceiverSupervisorImpl中的endpoint接收消息后的逻辑代码
case StopReceiver =>
logInfo("Received stop signal")
ReceiverSupervisorImpl.this.stop("Stopped by driver", None)调用了ReceiverSupervisorImpl的stop方法，stop方法代码如下
def stop(message: String, error: Option[Throwable]) {
stoppingError = error.orNull
stopReceiver(message, error)
onStop(message, error)
futureExecutionContext.shutdownNow()
stopLatch.countDown()
}先看stopReceiver方法，代码如下
def stopReceiver(message: String, error: Option[Throwable]): Unit = synchronized { try {
logInfo("Stopping receiver with message: " + message + ": " + error.getOrElse(""))
receiverState match { case Initialized =>
logWarning("Skip stopping receiver because it has not yet stared") case Started =>
receiverState = Stopped
receiver.onStop()
logInfo("Called receiver onStop")
onReceiverStop(message, error) case Stopped =>
logWarning("Receiver has been stopped")
}
} catch { case NonFatal(t) =>
logError("Error stopping receiver " + streamId + t.getStackTraceString)
}
}第一调用了receiver的stop方法receiver.onStop()，看一下KafkaReceiver的onStop()方法，代码如下
def onStop() { if (consumerConnector != null) {
consumerConnector.shutdown()
consumerConnector = null
}
}关闭了consumer的连接，就是停止接收数据
第二调用onReceiverStop，看ReceiverSupervisor的子类ReceiverSupervisorImpl的onReceiverStop方法，代码如下
override protected def onReceiverStop(message: String, error: Option[Throwable]) {
logInfo("Deregistering receiver " + streamId)
val errorString = error.map(Throwables.getStackTraceAsString).getOrElse("")
trackerEndpoint.askWithRetry[Boolean](DeregisterReceiver(streamId, message, errorString))
logInfo("Stopped receiver " + streamId)
}向trackerEndpoint发送了一条 注销receiver的消息DeregisterReceiver。
再看onStop()方法，在ReceiverSupervisor的子类ReceiverSupervisorImpl的onReceiverStop方法，代码如下
override protected def onStop(message: String, error: Option[Throwable]) {
registeredBlockGenerators.foreach { _.stop() }
env.rpcEnv.stop(endpoint)
}调用了每一个BlockGenerator的stop方法，stop方法代码如下
def stop(): Unit = { // Set the state to stop adding data
synchronized { if (state == Active) {
state = StoppedAddingData
} else {
logWarning(s"Cannot stop BlockGenerator as its not in the Active state [state = $state]") return
}
} // Stop generating blocks and set the state for block pushing thread to start draining the queue
logInfo("Stopping BlockGenerator")
blockIntervalTimer.stop(interruptTimer = false) synchronized { state = StoppedGeneratingBlocks } // Wait for the queue to drain and mark generated as stopped
logInfo("Waiting for block pushing thread to terminate")
blockPushingThread.join() synchronized { state = StoppedAll }
logInfo("Stopped BlockGenerator")
}主要是定时器的停止blockIntervalTimer.stop，blockIntervalTimer在上一讲有具体的作用讲解
ReceiverTracker的其他消息，以后再继
作者：海纳百川_spark
链接：https://www.jianshu.com/p/43c890d623e2
共同学习，写下你的评论
评论加载中...
作者其他优质文章
