优雅的停止SparkStreaming

背景：流式任务需要7*24小时执行，但是有时涉及到升级代码需要主动停止程序，但是分布式程序，没办法做到一个个进程去杀死，所有配置优雅的关闭就显得至关重要了。可以考虑使用外部文件存储或者关系型数据库、缓存等来控制内部程序关闭。

此例子使用hdfs创建指定文件来控制程序的关闭，想要更好的在前端进行控制，可以在注册程序中修改标志源。

package com.smothclose

import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FileSystem, Path}
import org.apache.spark.streaming.{StreamingContext, StreamingContextState}

class MonitorStop(ssc: StreamingContext) extends Runnable {

  override def run(): Unit = {

    val configuration = new Configuration()
    configuration.set("fs.defaultFS","hdfs://node01:8020")
    configuration.set("user","hadoop")
    val fs: FileSystem = FileSystem.get(configuration )

    while (true) {
      try
        Thread.sleep(5000)
      catch {
        case e: InterruptedException =>
          e.printStackTrace()
      }
      val state: StreamingContextState = ssc.getState

      val bool: Boolean = fs.exists(new Path("/stopSparkTest"))

      if (bool) {
        if (state == StreamingContextState.ACTIVE) {
          ssc.stop(stopSparkContext = true, stopGracefully = true)
          System.exit(0)
        }
      }
    }
  }
}

package com.smothclose

import org.apache.log4j.{Level, Logger}
import org.apache.spark.SparkConf
import org.apache.spark.streaming.dstream.{DStream, ReceiverInputDStream}
import org.apache.spark.streaming.{Seconds, StreamingContext}

object SparkTest {

  def createSSC(): _root_.org.apache.spark.streaming.StreamingContext = {
    val update: (Seq[Int], Option[Int]) => Some[Int] = (values: Seq[Int], status: Option[Int]) => {

      //当前批次内容的计算
      val sum: Int = values.sum

      //取出状态信息中上一次状态
      val lastStatu: Int = status.getOrElse(0)

      Some(sum + lastStatu)
    }

    val sparkConf: SparkConf = new SparkConf().setMaster("local[4]").setAppName("SparkTest")
    //	如果为true，Spark会StreamingContext在JVM关闭时正常关闭，而不是立即关闭。
    sparkConf.set("spark.streaming.stopGracefullyOnShutdown", "true")

    val ssc = new StreamingContext(sparkConf, Seconds(5))

    ssc.checkpoint("./ck1111")

    val line: ReceiverInputDStream[String] = ssc.socketTextStream("node01", 9999)

    val word: DStream[String] = line.flatMap(_.split(" "))

    val wordAndOne: DStream[(String, Int)] = word.map((_, 1))

    val wordAndCount: DStream[(String, Int)] = wordAndOne.updateStateByKey(update)

    wordAndCount.print()

    ssc
  }

  def main(args: Array[String]): Unit = {

    val ssc: StreamingContext = StreamingContext.getActiveOrCreate("./ck", () => createSSC())

    new Thread(new MonitorStop(ssc)).start()

    ssc.start()
    ssc.awaitTermination()
  }
}

会有一个常驻线程来监控标志位文件是否存在，若存在检查该ssc(StreamingContext)的状态是否为活跃，若是活跃状态进行停职该线程。

注：需要开启优雅关闭配置（默认是false）