sparkStream重启后获取checkpoint数据的使用问题

学习checkpoint使用是重启时总是获取不到重启之前的值，后来才发现用法不对

最开始都是直接创建对象用new 的方式创建对象，代码如下

def main(args: Array[String]): Unit = {
val conf: SparkConf = new SparkConf().setMaster("local[4]").setAppName("SparkStreamingSocketTotal")
    // 2创建csaprkcontext
    val sc = new SparkContext(conf)
    sc.setLogLevel("warn")
    // 创建streamcontext
    val ssc = new StreamingContext(sc,Seconds(5))
    //设置checkpoint目录用于保存每一个单词在之气那的所有单词出翔的总次数
    ssc.checkpoint("./socket")

    // 接受socket 出现的次数
    val scokettext: ReceiverInputDStream[String] = ssc.socketTextStream(ip ,9999)
    // 切 分每一行数据
    val words: DStream[String] = scokettext.flatMap(_.split(" "))
    // m每个单词记为1
    val wordone: DStream[(String, Int)] = words.map(x=>(x,1))

    val result: DStream[(String, Int)] = wordone.updateStateByKey(updateFunc)
    result.print()
  ssc.start()
    ssc.awaitTermination()
}

程序执行是数据也保存到scoket目录，显示结果累加正确，但是数据重启后总是重0开始，重启之前的数据获取不到

证据方法应该是StreamingContext.getOrCreate来获取StreamContext对象,getOrCreate先检查给定的checkpoint路径是否存在，然后读取checkpoint路径的数据，具体代码如下

 def updateFunc(currentValues:Seq[Int],historyValues:Option[Int]):Option[Int] = {
    val newValue: Int = currentValues.sum + historyValues.getOrElse(0)
    Some(newValue)
  } 
  var checkpointDirectory ="./socket"
def functionToCreateContext(): StreamingContext = {
    val conf: SparkConf = new SparkConf().setMaster("local[4]").setAppName("SparkStreamingSocketTotal")
    // 2创建csaprkcontext
    val sc = new SparkContext(conf)
    sc.setLogLevel("warn")
    // 创建streamcontext
    val ssc = new StreamingContext(sc,Seconds(5))
    //设置checkpoint目录用于保存每一个单词在之气那的所有单词出翔的总次数
    ssc.checkpoint("./socket")

    // 接受socket 出现的次数
    val scokettext: ReceiverInputDStream[String] = ssc.socketTextStream("xx.xx.xx.xx" ,9999)
    // 切 分每一行数据
    val words: DStream[String] = scokettext.flatMap(_.split(" "))
    // m每个单词记为1
    val wordone: DStream[(String, Int)] = words.map(x=>(x,1))

    val result: DStream[(String, Int)] = wordone.updateStateByKey(updateFunc)
    result.print()
    ssc
  }
def main(args: Array[String]): Unit = {
    //val conf: SparkConf = new SparkConf().setMaster("local[4]").setAppName("SparkStreamingSocketTotal")
    val ssc = StreamingContext.getOrCreate(checkpointDirectory, functionToCreateContext _)

    ssc.start()
    ssc.awaitTermination()


  }

无论是本地还是集群，重启后都会获取到之前的累加数据

下面是源码Streamcontext中getOrCreate源码

def getOrCreate(
    checkpointPath: String,
    creatingFunc: () => StreamingContext,
    hadoopConf: Configuration = SparkHadoopUtil.get.conf,
    createOnError: Boolean = false
  ): StreamingContext = {
​​​​​​​//调用 CheckpointReader来读取数据
  val checkpointOption = CheckpointReader.read(
    checkpointPath, new SparkConf(), hadoopConf, createOnError)
  checkpointOption.map(new StreamingContext(null, _, null)).getOrElse(creatingFunc())
}