Question

我有一个流式消费程序，正在阅读一个主题，并希望保存在本地系统中。我正在将spark master提交为local [*]，但是问题是输出没有保存。程序运行时，我可以在_temporary文件夹中看到输出，但是当我停止程序时，文件夹消失了。可以请任何人让我知道为什么会这样以及如何解决吗？

谢谢

这是我的代码：

package com.org.spark

import org.apache.spark.SparkConf
import org.apache.spark.streaming.StreamingContext
import org.apache.spark.streaming.Seconds
import org.apache.spark.streaming.kafka010.KafkaUtils
import org.apache.spark.sql.SparkSession
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.streaming.kafka010.HasOffsetRanges
import org.apache.spark.streaming.kafka010.OffsetRange
import org.apache.kafka.clients.consumer.ConsumerConfig
import org.apache.spark.sql.SaveMode
import org.apache.spark.SparkContext
import java.util.Date
import java.text.SimpleDateFormat

//import org.apache.spark.TaskContext

object SparkKafkaDemo {
  def main(args: Array[String]) = {
    val kafkaParams = Map[String, Object](
      "bootstrap.servers" -> “kafka-broker1:9094,kafka-broker2:9094",
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer],
      "security.protocol" -> "SASL_SSL",
      "sasl.mechanism" -> "PLAIN",
      "group.id" -> "test-consumer-group",
      "auto.offset.reset" -> "earliest",
      "enable.auto.commit" -> (false: java.lang.Boolean),
      "ssl.truststore.location" -> “/path/to/truststore/file.truststore",
      "ssl.truststore.password" -> “xxxxxxxx”,
      "ssl.keystore.location" -> “/path/to/keystore/file.keystore",
      "ssl.keystore.password" -> “xxxxxxxx”,
      "ssl.key.password" -> “xxxxxxxxx”
    )

    val topics = Array(“topic-name”)

    val sparkConf = new SparkConf().setAppName("KafkaTest")
    val sc=new SparkContext(sparkConf)
    sc.setLogLevel("ERROR")
    val streamingContext = new StreamingContext(sc, Seconds(30))

    val kafkaStream = KafkaUtils.createDirectStream[String, String](
      streamingContext,
      PreferConsistent,
      Subscribe[String, String](topics, kafkaParams)
    )
    val sqlContext = new org.apache.spark.sql.SQLContext(sc)
    import sqlContext.implicits._
    val result = kafkaStream.map(record => (record.topic(), record.value(), record.offset(), record.key()))
    result.print()
    result.foreachRDD(
      rdd => {
        val rdd1 = rdd.map(line => (line._3,line._2))
        val today = new Date()
        val date = new SimpleDateFormat("dd-MM-yyyy").format(today)
        rdd1.saveAsTextFile("file:///path/to/output/"+"/"+date+"/")
      }
        )

    streamingContext.start()
    streamingContext.awaitTermination()
}
}

Spark流的输出未永久保存在本地

0 个答案: