无法序列化foreachRDD中的SparkContext

Question

我正试图将流数据从Kafka保存到卡桑德拉。我能够读取和解析数据，但是当我调用下面的行来保存数据时，我会得到一个任务不序列化异常。我的类正在扩展序列化，但不确定为什么我会看到这个错误，在谷歌搜索了3个小时后没有得到多少帮助，有没有人能给出任何指示？

val collection = sc.parallelize(Seq((obj.id, obj.data)))
collection.saveToCassandra("testKS", "testTable ", SomeColumns("id", "data"))` 


import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.sql.SaveMode
import org.apache.spark.streaming.Seconds
import org.apache.spark.streaming.StreamingContext
import org.apache.spark.streaming.kafka.KafkaUtils
import com.datastax.spark.connector._

import kafka.serializer.StringDecoder
import org.apache.spark.rdd.RDD
import com.datastax.spark.connector.SomeColumns
import java.util.Formatter.DateTime

object StreamProcessor extends Serializable {
  def main(args: Array[String]): Unit = {
    val sparkConf = new SparkConf().setMaster("local[2]").setAppName("StreamProcessor")
      .set("spark.cassandra.connection.host", "127.0.0.1")

    val sc = new SparkContext(sparkConf)

    val ssc = new StreamingContext(sc, Seconds(2))

    val sqlContext = new SQLContext(sc)

    val kafkaParams = Map("metadata.broker.list" -> "localhost:9092")

    val topics = args.toSet

    val stream = KafkaUtils.createDirectStream[String, String, StringDecoder, StringDecoder](
      ssc, kafkaParams, topics)

    stream.foreachRDD { rdd =>

      if (!rdd.isEmpty()) {
        try {

          rdd.foreachPartition { iter =>
            iter.foreach {
              case (key, msg) =>

                val obj = msgParseMaster(msg)

                val collection = sc.parallelize(Seq((obj.id, obj.data)))
                collection.saveToCassandra("testKS", "testTable ", SomeColumns("id", "data"))

            }
          }

        }

      }
    }

    ssc.start()
    ssc.awaitTermination()

  }

  import org.json4s._
  import org.json4s.native.JsonMethods._
  case class wordCount(id: Long, data: String) extends serializable
  implicit val formats = DefaultFormats
  def msgParseMaster(msg: String): wordCount = {
    val m = parse(msg).extract[wordCount]
    return m

  }

}

我得到了

sparkException：任务不可序列化

下面是完整的日志

16/08/06 10:24:52错误JobScheduler：运行作业流作业1470504292000 MS.0 org.apache.spark.util.closurecleaner$.ensureclealizable（closurecleaner.scala:304)在org.apache.spark.util.closurecleaner$.org.apache.spark.util.closurecleaner$$clean（closurecleaner.scala:294)在org.apache.spark.util.closurecleaner$.clean（closurecleaner.scala:122)上任务不可序列化sparkcontext.clean（sparkcontext.scala：2055）在org.apache.spark.rdd.rdd$$anonfun$foreachpartition$1。apply（rdd.scala：919）在org.apache.spark.rdd.rdd$$anonfun$foreachpartition$1。apply（rdd.scala：918）在org.apache.spark.rdd.rddoperationscope$.withscope（rddoperationscope.scala：150）在org.apache.spark.rdd.rddoperationscope$.withscope（rddoperationscope.scala：111）在org.apache.spark.rdd.rdd.withscope（在org.apache.spark.rdd.rdd.foreachpartition(rdd.scala:918)上

Answer 1

sparkcontext不可序列化，您不能在foreachrdd中使用它，而且从使用您的图来看，您不需要它。相反,您可以简单地映射每个RDD,解析出相关数据并将新RDD保存到Cassandra：

stream
  .map { 
    case (_, msg) => 
      val result = msgParseMaster(msg)
      (result.id, result.data)
   }
  .foreachRDD(rdd => if (!rdd.isEmpty)
                       rdd.saveToCassandra("testKS",
                                           "testTable",
                                            SomeColumns("id", "data")))