何瑞龙的专栏

private[storage] class BlockManagerSlaveActor(blockManager: BlockManager) extends Actor {   override def receive = {     case RemoveBlock(blockId) =>       blockManager.removeBlock(blockId)  

每次rdd调用iterator方法时，都先会从 final def iterator(split: Partition, context: TaskContext): Iterator[T] = {     if (storageLevel != StorageLevel.NONE) {       SparkEnv.get.cacheManager.getOrCom

override def preStart() {     if (!BlockManager.getDisableHeartBeatsForTesting(conf)) {       import context.dispatcher       timeoutCheckingTask = context.system.scheduler.schedule(0.seconds, chec