spark streaming程序因集群kafka版本不一致造成ZkUtils类无法更新offset解决方案

问题：

因为CDH集群环境问题，我spark streaming程序的依赖就依照其版本来进行，但这就遇到一个问题，集群spark2支持的kafka版本是0.9.0，而我们程序操作zookeeper的ZkUtils类就不兼容了。

解决方案：

重新KafkaCluster类，兼容集群版本。

原程序单个topic的zk更新offset的方法：

val stream = createCustomDirectKafkaStream(ssc,kafkaParams,"advertidshadoop161v14taiji.cdn.ifengidc.com","/kafka", topics)

/*
   * createDirectStream() method overloaded
   */
  def createCustomDirectKafkaStream(ssc: StreamingContext, kafkaParams: Map[String, String], zkHosts: String
                                    , zkPath: String, topics: Set[String]): InputDStream[(String, String)] = {
    val topic = topics.last //TODO only for single kafka topic right now
    val zkClient = new ZkClient(zkHosts, 30000, 30000)
    val storedOffsets = readOffsets(zkClient,zkHosts, zkPath, topic)
    val kafkaStream = storedOffsets match {
      case None => // start from the latest offsets
        KafkaUtils.createDirectStream[String, String, StringDecoder, StringDecoder](ssc, kafkaParams, topics)
      case Some(fromOffsets) => // start from previously saved offsets
        val messageHandler = (mmd: MessageAndMetadata[String, String]) => (mmd.key, mmd.message)
        KafkaUtils.createDirectStream[String, String, StringDecoder, StringDecoder
          , (String, String)](ssc, kafkaParams, fromOffsets, messageHandler)
    }
    // save the offsets
    kafkaStream.foreachRDD(rdd => saveOffsets(zkClient,zkHosts, zkPath, rdd))
    kafkaStream
  }

  /*
   * Read the previously saved offsets from Zookeeper
   */
  private def readOffsets(zkClient: ZkClient,zkHosts:String, zkPath: String, topic: String):
  Option[Map[TopicAndPartition, Long]] = {
    logger.info("Reading offsets from Zookeeper")
    val stopwatch = new Stopwatch()
    val (offsetsRangesStrOpt, _) = ZkUtils.readDataMaybeNull(zkClient, zkPath)
    offsetsRangesStrOpt match {
      case Some(offsetsRangesStr) =>
        logger.info(s"Read offset ranges: ${offsetsRangesStr}")
        val offsets = offsetsRangesStr.split(",")
          .map(s => s.split(":"))
          .map { case Array(partitionStr, offsetStr) => (TopicAndPartition(topic, partitionStr.toInt) -> offsetStr.toLong) }
          .toMap
        logger.info("Done reading offsets from Zookeeper. Took " + stopwatch)
        Some(offsets)
      case None =>
        logger.info("No offsets found in Zookeeper. Took " + stopwatch)
        None
    }
  }

  private def saveOffsets(zkClient: ZkClient,zkHosts:String, zkPath: String, rdd: RDD[_]): Unit = {
    logger.info("Saving offsets to Zookeeper")
    val stopwatch = new Stopwatch()
    val offsetsRanges = rdd.asInstanceOf[HasOffsetRanges].offsetRanges
    offsetsRanges.foreach(offsetRange => logger.debug(s"Using ${offsetRange}"))
    val offsetsRangesStr = offsetsRanges.map(offsetRange => s"${offsetRange.partition}:${offsetRange.fromOffset}")
      .mkString(",")
    logger.info("Writing offsets to Zookeeper zkClient="+zkClient+"  zkHosts="+zkHosts+"zkPath="+zkPath+"  offsetsRangesStr:"+ offsetsRangesStr)
    ZkUtils.updatePersistentPath(zkClient, zkPath, offsetsRangesStr)
    logger.info("Done updating offsets in Zookeeper. Took " + stopwatch)
  }

  class Stopwatch {
    private val start = System.currentTimeMillis()
    override def toString() = (System.currentTimeMillis() - start) + " ms"
  }

重写方法操作zk：

参考的github项目：https://github.com/xlturing/spark-journey/tree/master/SparkStreamingKafka