•  
很多知识星球球友问过浪尖一个问题:
就是spark streaming经过窗口的聚合操作之后,再去管理offset呢?

 

对于spark streaming来说窗口操作之后,是无法管理offset的,因为offset的存储于HasOffsetRanges。只有kafkaRDD继承了他,所以假如我们对KafkaRDD进行了转化之后就无法再获取offset了。

 

还有窗口之后的offset的管理,也是很麻烦的,主要原因就是窗口操作会包含若干批次的RDD数据,那么提交offset我们只需要提交最近的那个批次的kafkaRDD的offset即可。如何获取呢?

 

对于spark 来说代码执行位置分为driver和executor,我们希望再driver端获取到offset,在处理完结果提交offset,或者直接与结果一起管理offset。

 

说到driver端执行,其实我们只需要使用transform获取到offset信息,然后在输出操作foreachrdd里面使用提交即可。

  •  
package bigdata.spark.SparkStreaming.kafka010
import java.util.Properties
import org.apache.kafka.clients.consumer.{Consumer, ConsumerRecord, KafkaConsumer}import org.apache.kafka.common.TopicPartitionimport org.apache.kafka.common.serialization.StringDeserializerimport org.apache.spark.rdd.RDDimport org.apache.spark.streaming.kafka010._import org.apache.spark.streaming.{Seconds, StreamingContext}import org.apache.spark.{SparkConf, TaskContext}
import scala.collection.JavaConverters._import scala.collection.mutable
object kafka010NamedRDD { def main(args: Array[String]) { // 创建一个批处理时间是2s的context 要增加环境变量 val sparkConf = new SparkConf().setAppName("DirectKafkaWordCount").setMaster("local[*]") val ssc = new StreamingContext(sparkConf, Seconds(5))
ssc.checkpoint("/opt/checkpoint")
// 使用broker和topic创建DirectStream val topicsSet = "test".split(",").toSet val kafkaParams = Map[String, Object]("bootstrap.servers" -> "mt-mdh.local:9093", "key.deserializer"->classOf[StringDeserializer], "value.deserializer"-> classOf[StringDeserializer], "group.id"->"test4", "auto.offset.reset" -> "latest", "enable.auto.commit"->(false: java.lang.Boolean))
// 没有接口提供 offset val messages = KafkaUtils.createDirectStream[String, String]( ssc, LocationStrategies.PreferConsistent, ConsumerStrategies.Subscribe[String, String](topicsSet, kafkaParams,getLastOffsets(kafkaParams ,topicsSet)))// var A:mutable.HashMap[String,Array[OffsetRange]] = new mutable.HashMap()
val trans = messages.transform(r =>{ val offsetRanges = r.asInstanceOf[HasOffsetRanges].offsetRanges A += ("rdd1"->offsetRanges) r }).countByWindow(Seconds(10), Seconds(5)) trans.foreachRDD(rdd=>{
if(!rdd.isEmpty()){ val offsetRanges = A.get("rdd1").get//.asInstanceOf[HasOffsetRanges].offsetRanges
rdd.foreachPartition { iter => val o: OffsetRange = offsetRanges(TaskContext.get.partitionId) println(s"${o.topic} ${o.partition} ${o.fromOffset} ${o.untilOffset}") }
println(rdd.count()) println(offsetRanges) // 手动提交offset ,前提是禁止自动提交 messages.asInstanceOf[CanCommitOffsets].commitAsync(offsetRanges)
}// A.-("rdd1") }) // 启动流 ssc.start() ssc.awaitTermination() } def getLastOffsets(kafkaParams : Map[String, Object],topics:Set[String]): Map[TopicPartition, Long] ={ val props = new Properties() props.putAll(kafkaParams.asJava) val consumer = new KafkaConsumer[String, String](props) consumer.subscribe(topics.asJavaCollection) paranoidPoll(consumer) val map = consumer.assignment().asScala.map { tp => println(tp+"---" +consumer.position(tp)) tp -> (consumer.position(tp)) }.toMap println(map) consumer.close() map } def paranoidPoll(c: Consumer[String, String]): Unit = { val msgs = c.poll(0) if (!msgs.isEmpty) { // position should be minimum offset per topicpartition msgs.asScala.foldLeft(Map[TopicPartition, Long]()) { (acc, m) => val tp = new TopicPartition(m.topic, m.partition) val off = acc.get(tp).map(o => Math.min(o, m.offset)).getOrElse(m.offset) acc + (tp -> off) }.foreach { case (tp, off) => c.seek(tp, off) } } }}