15、Spark Streaming源码解读之No Receivers彻底思考

trait HasOffsetRanges {
  def offsetRanges: Array[OffsetRange]
}

  override def getPartitions: Array[Partition] = {
    offsetRanges.zipWithIndex.map { case (o, i) =>
        val (host, port) = leaders(TopicAndPartition(o.topic, o.partition))
        new KafkaRDDPartition(i, o.topic, o.partition, o.fromOffset, o.untilOffset, host, port)
    }.toArray
  }

private[kafka]
class KafkaRDDPartition(
  val index: Int,
  val topic: String,
  val partition: Int,
  val fromOffset: Long,
  val untilOffset: Long,
  val host: String,
  val port: Int
) extends Partition {
  /** Number of messages this partition refers to */
  def count(): Long = untilOffset - fromOffset
}

  override def compute(thePart: Partition, context: TaskContext): Iterator[R] = {
    val part = thePart.asInstanceOf[KafkaRDDPartition]
    assert(part.fromOffset <= part.untilOffset, errBeginAfterEnd(part))
    if (part.fromOffset == part.untilOffset) {
      log.info(s"Beginning offset ${part.fromOffset} is the same as ending offset " +
        s"skipping ${part.topic} ${part.partition}")
      Iterator.empty
    } else {
      new KafkaRDDIterator(part, context)
    }
  }

 private class KafkaRDDIterator(
      part: KafkaRDDPartition,
      context: TaskContext) extends NextIterator[R] {
    context.addTaskCompletionListener{ context => closeIfNeeded() }
    log.info(s"Computing topic ${part.topic}, partition ${part.partition} " +
      s"offsets ${part.fromOffset} -> ${part.untilOffset}")
    val kc = new KafkaCluster(kafkaParams)
    val keyDecoder = classTag[U].runtimeClass.getConstructor(classOf[VerifiableProperties])
      .newInstance(kc.config.props)
      .asInstanceOf[Decoder[K]]
    val valueDecoder = classTag[T].runtimeClass.getConstructor(classOf[VerifiableProperties])
      .newInstance(kc.config.props)
      .asInstanceOf[Decoder[V]]
    val consumer = connectLeader
    var requestOffset = part.fromOffset
    var iter: Iterator[MessageAndOffset] = null
    //..................
}

    val messages = KafkaUtils.createDirectStream[String, String, StringDecoder, StringDecoder](
      ssc, kafkaParams, topicsSet)

  def createDirectStream[
    K: ClassTag,
    V: ClassTag,
    KD <: Decoder[K]: ClassTag,
    VD <: Decoder[V]: ClassTag] (
      ssc: StreamingContext,
      kafkaParams: Map[String, String],
      topics: Set[String]
  ): InputDStream[(K, V)] = {
    val messageHandler = (mmd: MessageAndMetadata[K, V]) => (mmd.key, mmd.message)
//创建KakfaCluster对象
    val kc = new KafkaCluster(kafkaParams)
//更具kc的信息获取数据偏移量
    val fromOffsets = getFromOffsets(kc, kafkaParams, topics)
    new DirectKafkaInputDStream[K, V, KD, VD, (K, V)](
      ssc, kafkaParams, fromOffsets, messageHandler)
  }

 override def compute(validTime: Time): Option[KafkaRDD[K, V, U, T, R]] = {
    //计算最近的数据终止偏移量
    val untilOffsets = clamp(latestLeaderOffsets(maxRetries))
    //利用数据的偏移量创建KafkaRDD
    val rdd = KafkaRDD[K, V, U, T, R](
      context.sparkContext, kafkaParams, currentOffsets, untilOffsets, messageHandler)
    // Report the record number and metadata of this batch interval to InputInfoTracker.
    val offsetRanges = currentOffsets.map { case (tp, fo) =>
      val uo = untilOffsets(tp)
      OffsetRange(tp.topic, tp.partition, fo, uo.offset)
    }
    val description = offsetRanges.filter { offsetRange =>
      // Don‘t display empty ranges.
      offsetRange.fromOffset != offsetRange.untilOffset
    }.map { offsetRange =>
      s"topic: ${offsetRange.topic}\tpartition: ${offsetRange.partition}\t" +
        s"offsets: ${offsetRange.fromOffset} to ${offsetRange.untilOffset}"
    }.mkString("\n")
    // Copy offsetRanges to immutable.List to prevent from being modified by the user
    val metadata = Map(
      "offsets" -> offsetRanges.toList,
      StreamInputInfo.METADATA_KEY_DESCRIPTION -> description)
    val inputInfo = StreamInputInfo(id, rdd.count, metadata)
    ssc.scheduler.inputInfoTracker.reportInfo(validTime, inputInfo)
    currentOffsets = untilOffsets.map(kv => kv._1 -> kv._2.offset)
    Some(rdd)
  }