Spark-Streaming缓存计算结果，Wordcount累加求和

依赖

<dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>2.1.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
            <version>2.1.1</version>
        </dependency>
        <dependency>
            <groupId>redis.clients</groupId>
            <artifactId>jedis</artifactId>
            <version>2.9.0</version>
        </dependency>
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.27</version>
        </dependency>
    </dependencies>

一 updateStateByKey

函数声明：

def updateStateByKey[S: ClassTag](
                 updateFunc: (Seq[V], Option[S]) => Option[S]): DStream[(K, S)]

getActiveOrCreate 函数声明

def getActiveOrCreate(
      checkpointPath: String,
      creatingFunc: () => StreamingContext,
      hadoopConf: Configuration = SparkHadoopUtil.get.conf,
      createOnError: Boolean = false
    ): StreamingContext = {
    ACTIVATION_LOCK.synchronized {
      getActive().getOrElse { getOrCreate(checkpointPath, creatingFunc, hadoopConf, createOnError) }
    }
  }

需求：对上次计算的结果进行缓存，在应用重启后，加载上次计算的结果，这里从scoket中读取流数据

package com.gc.sparkStreaming.day01.transform

import org.apache.spark.streaming.dstream.{DStream, ReceiverInputDStream}
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.streaming.{Seconds, StreamingContext}

object RddToDStream {
  //定义状态改变函数 seq:Seq[Int] 当前批次的数据  option:Option[Int] 累加值
  val updateFun=(seq:Seq[Int],option:Option[Int])=>{
    Some(seq.sum+option.getOrElse(0))
  }
  val checkPoint:String="./ssss" // checkpoint 目录 默认取的是core-default.xml中fs.defaultFS 的文件历经

  // 创建StreamingContext 函数
  val createStream: () => StreamingContext = ()=>{
    val conf = new SparkConf().setAppName("rdd").setMaster("local[*]")
    val spark: StreamingContext = new StreamingContext(conf,Seconds(2))
    val dStrem: ReceiverInputDStream[String] = spark.socketTextStream("hadoop103",9999)
    val ds: DStream[(String, Int)] = dStrem.flatMap(_.split("\\W+")).map((_,1))
    val res: DStream[(String, Int)] = ds.updateStateByKey(updateFun)
    res.print() // 调用行动算子
    spark
  }
  def main(args: Array[String]): Unit = {
    val spark = StreamingContext.getActiveOrCreate(checkPoint,createStream)
    spark.checkpoint("./ssss")
    spark.start()
    spark.awaitTermination()
  }
}

注意点：

• 使用updateBykey 必须设置定checkpoint
• 要想在应用重启后保留上次计算的结果，需使用这种方式创建StreamingContext对象StreamingContext.getActiveOrCreate(checkPoint,createStream)
• 使用上述方式创建StreamingContext后，必须将业务逻辑全部放在createStream函数内，否则会报错

二 中间数据存储到Mysql

累加的本质就是获取之前运算的结果和本次新传入的数据进行汇总，要做的就是将之前累加后的数据缓存起来

import java.sql.{Connection, DriverManager, PreparedStatement}
import java.util.Properties

import org.apache.spark.SparkConf
import org.apache.spark.streaming.dstream.DStream
import org.apache.spark.streaming.{Seconds, StreamingContext}

object UseMysqlToChecpoint {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setMaster("local[*]").setAppName("UseMysqlToChecpoint")
    val spark = new StreamingContext(conf,Seconds(2))
    //业务逻辑
    // 从scoket
    val sourceDstream = spark.socketTextStream("hadoop102",9999)
    val wordCount: DStream[(String, Int)] = sourceDstream.flatMap(_.split("\\W+")).map((_,1)).reduceByKey(_+_)
     //将本次计算的结果写入mysql
    wordCount.foreachRDD(rdd=>{

    rdd.foreachPartition(it=>{
      val conn = getConnection() // 一个分区创建一个连接
      conn.setAutoCommit(false) //取消自动提交事务
      val sql:String="insert into  wordcount values(?,?) on duplicate key update wcount=if(wcount is not null ,wcount+?,wcount)" //设置wordcount 表中对应的work为主键，不允许重复，当key存在的时候进行修改，if(wcount is not null ,wcount+?,wcount) 判断统计结果是否存在，存在则加上本次计算的结果，不存在则直接修改
      val ps: PreparedStatement = conn.prepareStatement(sql)
      it.foreach(result=>{
          ps.setString(1,result._1);
          ps.setInt(2,result._2);
           ps.setInt(3,result._2);
          ps.addBatch() // 一批
        })
      ps.executeBatch() // 批量执行
      conn.commit() // 提交事务
      ps.close() // 关闭连接
      conn.close()
    })

    })
    spark.start()
    spark.awaitTermination()
  }

def getConnection():Connection={
  Class.forName("com.mysql.jdbc.Driver")
  val pro = new Properties()
  pro.setProperty("user","root")
  pro.setProperty("password","root")
  val conn = DriverManager.getConnection("jdbc:mysql://hadoop102:3306/sparkdemo",pro)
  conn
}
}

• 连接外部存储应该放在foreachPartition中，一个分区创建一个连接
• 在这为方便起见，将单词的word作为mysql表中的主键
• 可以使用ps.addBatch() 和 ps.executeBatch()对一个分区的数据进行批量执行

三 中间数据存到Redis中

import org.apache.spark.SparkConf
import org.apache.spark.streaming.dstream.DStream
import org.apache.spark.streaming.{Seconds, StreamingContext}
import redis.clients.jedis.{JedisPool, JedisPoolConfig}

object UseRedisToChecpoint {
  private val jedisPoolConfig: JedisPoolConfig = new JedisPoolConfig()
  jedisPoolConfig.setMaxTotal(100) //最大连接数
  jedisPoolConfig.setMaxIdle(20) //最大空闲
  jedisPoolConfig.setMinIdle(20) //最小空闲
  jedisPoolConfig.setBlockWhenExhausted(true) //忙碌时是否等待
  jedisPoolConfig.setMaxWaitMillis(500) //忙碌时等待时长 毫秒
  jedisPoolConfig.setTestOnBorrow(false) //每次获得连接的进行测试
  private val jedisPool: JedisPool = new JedisPool(jedisPoolConfig, "hadoop102", 6379)


  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setMaster("local[*]").setAppName("UseRedisToChecpoint")
    val spark = new StreamingContext(conf,Seconds(2))
    //业务逻辑
    val sourceDstream = spark.socketTextStream("hadoop102",9999)
    val wordCount: DStream[(String, Int)] = sourceDstream.flatMap(_.split("\\W+")).map((_,1)).reduceByKey(_+_)
     //将本次计算的结果写入redis
    wordCount.foreachRDD(rdd=>{
    rdd.foreachPartition(it=>{
      val jedis = getJedis()
      it.foreach(result=>{
        jedis.hincrBy("wordcount",result._1,result._2); //hincrBy 存在累加 不存在则写入1
      })
      jedis.close()
    })

    })
    spark.start()
    spark.awaitTermination()
  }
  def getJedis()={
    jedisPool.getResource
  }

}