案例代码:
package com.dt.spark.sparkstreaming
import org.apache.spark.SparkConf
import org.apache.spark.sql.Row
import org.apache.spark.sql.hive.HiveContext
import org.apache.spark.sql.types.{IntegerType, StringType, StructField, StructType}
import org.apache.spark.streaming.{Seconds, StreamingContext}
/**
* 使用Spark Streaming+Spark SQL来在线动态计算电商中不同类别中最热门的商品排名,例如手机这个类别下面最热门的三种手机、电视这个类别
* 下最热门的三种电视,该实例在实际生产环境下具有非常重大的意义;
*
* @author DT大数据梦工厂
* 新浪微博:http://weibo.com/ilovepains/
*
*
* 实现技术:Spark Streaming+Spark SQL,之所以Spark Streaming能够使用ML、sql、graphx等功能是因为有foreachRDD和Transform
* 等接口,这些接口中其实是基于RDD进行操作,所以以RDD为基石,就可以直接使用Spark其它所有的功能,就像直接调用API一样简单。
* 假设说这里的数据的格式:user item category,例如Rocky Samsung Android
*/
object OnlineTheTop3ItemForEachCategory2DB {
def main(args: Array[String]){
val conf = new SparkConf() //创建SparkConf对象
conf.setAppName("OnlineTheTop3ItemForEachCategory2DB") //设置应用程序的名称,在程序运行的监控界面可以看到名称
// conf.setMaster("spark://Master:7077") //此时,程序在Spark集群
conf.setMaster("local[6]")
//设置batchDuration时间间隔来控制Job生成的频率并且创建Spark Streaming执行的入口
val ssc = new StreamingContext(conf, Seconds(5))
ssc.checkpoint("/root/Documents/SparkApps/checkpoint")
val userClickLogsDStream = ssc.socketTextStream("Master", 9999)
val formattedUserClickLogsDStream = userClickLogsDStream.map(clickLog =>
(clickLog.split(" ")(2) + "_" + clickLog.split(" ")(1), 1))
// val categoryUserClickLogsDStream = formattedUserClickLogsDStream.reduceByKeyAndWindow((v1:Int, v2: Int) => v1 + v2,
// (v1:Int, v2: Int) => v1 - v2, Seconds(60), Seconds(20))
val categoryUserClickLogsDStream = formattedUserClickLogsDStream.reduceByKeyAndWindow(_+_,
_-_, Seconds(60), Seconds(20))
categoryUserClickLogsDStream.foreachRDD { rdd => {
if (rdd.isEmpty()) {
println("No data inputted!!!")
} else {
val categoryItemRow = rdd.map(reducedItem => {
val category = reducedItem._1.split("_")(0)
val item = reducedItem._1.split("_")(1)
val click_count = reducedItem._2
Row(category, item, click_count)
})
val structType = StructType(Array(
StructField("category", StringType, true),
StructField("item", StringType, true),
StructField("click_count", IntegerType, true)
))
val hiveContext = new HiveContext(rdd.context)
val categoryItemDF = hiveContext.createDataFrame(categoryItemRow, structType)
categoryItemDF.registerTempTable("categoryItemTable")
val reseltDataFram = hiveContext.sql("SELECT category,item,click_count FROM (SELECT category,item,click_count,row_number()" +
" OVER (PARTITION BY category ORDER BY click_count DESC) rank FROM categoryItemTable) subquery " +
" WHERE rank <= 3")
reseltDataFram.show()
val resultRowRDD = reseltDataFram.rdd
resultRowRDD.foreachPartition { partitionOfRecords => {
if (partitionOfRecords.isEmpty){
println("This RDD is not null but partition is null")
} else {
// ConnectionPool is a static, lazily initialized pool of connections
val connection = ConnectionPool.getConnection()
partitionOfRecords.foreach(record => {
val sql = "insert into categorytop3(category,item,client_count) values('" + record.getAs("category") + "','" +
record.getAs("item") + "'," + record.getAs("click_count") + ")"
val stmt = connection.createStatement();
stmt.executeUpdate(sql);
})
ConnectionPool.returnConnection(connection) // return to the pool for future reuse
}
}
}
}
}
}
ssc.start()
ssc.awaitTermination()
}
}
代码分析:
1. 创建StreamingContext
val ssc = new StreamingContext(conf, Seconds(5))
/**
* Create a StreamingContext by providing the details necessary for creating a new SparkContext.
* @param master cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
* @param appName a name for your job, to display on the cluster web UI
* @param batchDuration the time interval at which streaming data will be divided into batches
*/
def this(
master: String,
appName: String,
batchDuration: Duration,
sparkHome: String = null,
jars: Seq[String] = Nil,
environment: Map[String, String] = Map()) = {
this(StreamingContext.createNewSparkContext(master, appName, sparkHome, jars, environment),
null, batchDuration)
}
StreamingContext在构建的时候会通过配置conf在内部构建SparkContext,说明SparkStreaming就是Spark上的一个应用程序
class StreamingContext private[streaming] (
sc_ : SparkContext,
cp_ : Checkpoint,
batchDur_ : Duration
) extends Logging {
private[streaming] def createNewSparkContext(conf: SparkConf): SparkContext = {
new SparkContext(conf)
}
2.创建socket输入流
val userClickLogsDStream = ssc.socketTextStream("Master", 9999)
def socketTextStream(
hostname: String,
port: Int,
storageLevel: StorageLevel = StorageLevel.MEMORY_AND_DISK_SER_2
): ReceiverInputDStream[String] = withNamedScope("socket text stream") {
socketStream[String](hostname, port, SocketReceiver.bytesToLines, storageLevel)
}
创建SocketInputDStream,返回的是 ReceiverInputDStream类型
def socketStream[T: ClassTag](
hostname: String,
port: Int,
converter: (InputStream) => Iterator[T],
storageLevel: StorageLevel
): ReceiverInputDStream[T] = {
new SocketInputDStream[T](this, hostname, port, converter, storageLevel)
}
基于SocketReceiver接收数据
class SocketInputDStream[T: ClassTag](
ssc_ : StreamingContext,
host: String,
port: Int,
bytesToObjects: InputStream => Iterator[T],
storageLevel: StorageLevel
) extends ReceiverInputDStream[T](ssc_) {
def getReceiver(): Receiver[T] = {
new SocketReceiver(host, port, bytesToObjects, storageLevel)
}
}
SocketReceiver的onStart方法开启了了一个线程,在线程里面run时,调用receive方法
class SocketReceiver[T: ClassTag](
host: String,
port: Int,
bytesToObjects: InputStream => Iterator[T],
storageLevel: StorageLevel
) extends Receiver[T](storageLevel) with Logging {
def onStart() {
// Start the thread that receives data over a connection
new Thread("Socket Receiver") {
setDaemon(true)
override def run() { receive() }
}.start()
}
receive根据ip和port连接socket,不断循环接收数据,以hashmap的方式存储
def receive() {
var socket: Socket = null
try {
logInfo("Connecting to " + host + ":" + port)
socket = new Socket(host, port)
logInfo("Connected to " + host + ":" + port)
val iterator = bytesToObjects(socket.getInputStream())
while(!isStopped && iterator.hasNext) {
store(iterator.next)
}
3.继承结构
Ctrl+H查看:
Dstream–>InputDStream–>ReceiverInputDStream–>SocketInputDStream
InputDStream中有start和stop方法,具体子类SocketInputDStream中onstart方法是被回调的,ReceiverSupervisor调用的就是start方法
Dstream中有ForEachDstream,输出流,所有Dstream级别的action输出操作,都会有ForEachDStream的产生,里面会创建新job
class ForEachDStream[T: ClassTag] (
parent: DStream[T],
foreachFunc: (RDD[T], Time) => Unit,
displayInnerRDDOps: Boolean
) extends DStream[Unit](parent.ssc) {
override def generateJob(time: Time): Option[Job] = {
parent.getOrCompute(time) match {
case Some(rdd) =>
val jobFunc = () => createRDDWithLocalProperties(time, displayInnerRDDOps) {
foreachFunc(rdd, time)
}
Some(new Job(time, jobFunc))
case None => None
}
}
}
Dstream.scala中,根据时间间隔生成RDD,hashmap中key是batch duration,value是RDD
private[streaming] var generatedRDDs = new HashMap[Time, RDD[T]] ()
getOrCompute生成RDD,放在hashmap中
private[streaming] final def getOrCompute(time: Time): Option[RDD[T]] = {
...
}
4.ssc.start()
JobScheduler是在一个新的线程中启动
def start(): Unit = synchronized {
state match {
case INITIALIZED =>
startSite.set(DStream.getCreationSite())
StreamingContext.ACTIVATION_LOCK.synchronized {
StreamingContext.assertNoOtherContextIsActive()
try {
validate()
// Start the streaming scheduler in a new thread, so that thread local properties
// like call sites and job groups can be reset without affecting those of the
// current thread.
ThreadUtils.runInNewThread("streaming-start") {
sparkContext.setCallSite(startSite.get)
sparkContext.clearJobGroup()
sparkContext.setLocalProperty(SparkContext.SPARK_JOB_INTERRUPT_ON_CANCEL, "false")
scheduler.start()
}
state = StreamingContextState.ACTIVE
JobScheduler.scala
private var eventLoop: EventLoop[JobSchedulerEvent] = null
def start(): Unit = synchronized {
if (eventLoop != null) return // scheduler has already been started
logDebug("Starting JobScheduler")
eventLoop = new EventLoop[JobSchedulerEvent]("JobScheduler") {
override protected def onReceive(event: JobSchedulerEvent): Unit = processEvent(event)
override protected def onError(e: Throwable): Unit = reportError("Error in job scheduler", e)
}
eventLoop.start()
// attach rate controllers of input streams to receive batch completion updates
for {
inputDStream <- ssc.graph.getInputStreams
rateController <- inputDStream.rateController
} ssc.addStreamingListener(rateController)
listenerBus.start(ssc.sparkContext)
receiverTracker = new ReceiverTracker(ssc)
inputInfoTracker = new InputInfoTracker(ssc)
receiverTracker.start()
jobGenerator.start()
logInfo("Started JobScheduler")
}
listenerBus监听所有event
ReceiverTracker处理数据接收,数据缓存,Block生成等,以发送Job的方式到集群中的Executor去启动receiver,内部使用ReceiverTrackEndpoint接收来自Receiver的消息。
JobScheduler是job的调度器,用一个线程循环,监听不同的job:启动JobStarted,完成JobCompleted,失败ErrorReported
private def processEvent(event: JobSchedulerEvent) {
try {
event match {
case JobStarted(job, startTime) => handleJobStart(job, startTime)
case JobCompleted(job, completedTime) => handleJobCompletion(job, completedTime)
case ErrorReported(m, e) => handleError(m, e)
}
} catch {
case e: Throwable =>
reportError("Error in job scheduler", e)
}
}