Question

假设我基本上希望Stream.from(0)为InputDStream。我该怎么做？我能看到的唯一方法是使用StreamingContext#queueStream，但是我必须将来自另一个线程或子类Queue的元素排队以创建一个行为类似于无限流的队列，两者都是感觉就像一个黑客。

这样做的正确方法是什么？

Answer 1

我不认为默认情况下它可以在Spark中使用，但使用ReceiverInputDStream可以很容易地实现它。

import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.StreamingContext
import org.apache.spark.streaming.dstream.ReceiverInputDStream
import org.apache.spark.streaming.receiver.Receiver

class InfiniteStreamInputDStream[T](
       @transient ssc_ : StreamingContext,
       stream: Stream[T],
       storageLevel: StorageLevel
      ) extends ReceiverInputDStream[T](ssc_)  {

  override def getReceiver(): Receiver[T] = {
    new InfiniteStreamReceiver(stream, storageLevel)
  }
}

class InfiniteStreamReceiver[T](stream: Stream[T], storageLevel: StorageLevel) extends Receiver[T](storageLevel) {

  // Stateful iterator
  private val streamIterator = stream.iterator

  private class ReadAndStore extends Runnable {
    def run(): Unit = {
      while (streamIterator.hasNext) {
        val next = streamIterator.next()
        store(next)
      }
    }
  }

  override def onStart(): Unit = {
    new Thread(new ReadAndStore).run()    
  }

  override def onStop(): Unit = { }
}

Answer 2

稍微修改过的代码与Spark 2.0一起使用：

import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.StreamingContext
import org.apache.spark.streaming.dstream.ReceiverInputDStream
import org.apache.spark.streaming.receiver.Receiver
import scala.reflect.ClassTag

class InfiniteDStream[T: ClassTag](
                                    @transient ssc_ : StreamingContext,
                                    stream: Stream[T],
                                    storageLevel: StorageLevel
                                  ) extends ReceiverInputDStream[T](ssc_) {

  override def getReceiver(): Receiver[T] = {
    new InfiniteStreamReceiver(stream, storageLevel)
  }
}

class InfiniteStreamReceiver[T](stream: Stream[T], storageLevel: StorageLevel) extends Receiver[T](storageLevel) {

  private class ReadAndStore extends Runnable {
    def run(): Unit = {
      stream.foreach(store)
    }
  }

  override def onStart(): Unit = {
    val t = new Thread(new ReadAndStore)
    t.setDaemon(true)
    t.run()
  }

  override def onStop(): Unit = {}
}

如何在Spark Streaming中使用无限的Scala流作为源？

2 个答案: