ok that is good Yours is basically simple streaming with Kafka (publishing topic) and your Spark streaming. use the following as blueprint
// Create a local StreamingContext with two working thread and batch interval of 2 seconds. val sparkConf = new SparkConf(). setAppName("CEP_streaming"). setMaster("local[2]"). set("spark.executor.memory", "4G"). set("spark.cores.max", "2"). set("spark.streaming.concurrentJobs", "2"). set("spark.driver.allowMultipleContexts", "true"). set("spark.hadoop.validateOutputSpecs", "false") val ssc = new StreamingContext(sparkConf, Seconds(2)) ssc.checkpoint("checkpoint") val kafkaParams = Map[String, String]("bootstrap.servers" -> "rhes564:9092", "schema.registry.url" -> "http://rhes564:8081", "zookeeper.connect" -> "rhes564:2181", "group.id" -> "CEP_streaming" ) val topics = Set("newtopic") val dstream = KafkaUtils.createDirectStream[String, String, StringDecoder, StringDecoder](ssc, kafkaParams, topics) dstream.cache() val lines = dstream.map(_._2) val price = lines.map(_.split(',').view(2)).map(_.toFloat) // window length - The duration of the window below that must be multiple of batch interval n in = > StreamingContext(sparkConf, Seconds(n)) val windowLength = 4 // sliding interval - The interval at which the window operation is performed in other words data is collected within this "previous interval' val slidingInterval = 2 // keep this the same as batch window for continuous streaming. You are aggregating data that you are collecting over the batch Window val countByValueAndWindow = price.filter(_ > 95.0).countByValueAndWindow(Seconds(windowLength), Seconds(slidingInterval)) countByValueAndWindow.print() // ssc.start() ssc.awaitTermination() HTH Dr Mich Talebzadeh LinkedIn * https://www.linkedin.com/profile/view?id=AAEAAAAWh2gBxianrbJd6zP6AcPCCdOABUrV8Pw <https://www.linkedin.com/profile/view?id=AAEAAAAWh2gBxianrbJd6zP6AcPCCdOABUrV8Pw>* http://talebzadehmich.wordpress.com On 7 June 2016 at 10:58, Dominik Safaric <dominiksafa...@gmail.com> wrote: > Dear Mich, > > Thank you for the reply. > > By running the following command in the command line: > > bin/kafka-console-consumer.sh --zookeeper localhost:2181 --topic > <topic_name> --from-beginning > > I do indeed retrieve all messages of a topic. > > Any indication onto what might cause the issue? > > An important note to make, I’m using the default configuration of both > Kafka and Zookeeper. > > On 07 Jun 2016, at 11:39, Mich Talebzadeh <mich.talebza...@gmail.com> > wrote: > > I assume you zookeeper is up and running > > can you confirm that you are getting topics from kafka independently for > example on the command line > > ${KAFKA_HOME}/bin/kafka-console-consumer.sh --zookeeper rhes564:2181 > --from-beginning --topic newtopic > > > > > > Dr Mich Talebzadeh > > > LinkedIn * > https://www.linkedin.com/profile/view?id=AAEAAAAWh2gBxianrbJd6zP6AcPCCdOABUrV8Pw > <https://www.linkedin.com/profile/view?id=AAEAAAAWh2gBxianrbJd6zP6AcPCCdOABUrV8Pw>* > > > http://talebzadehmich.wordpress.com > > > > On 7 June 2016 at 10:06, Dominik Safaric <dominiksafa...@gmail.com> wrote: > >> As I am trying to integrate Kafka into Spark, the following exception >> occurs: >> >> org.apache.spark.SparkException: java.nio.channels.ClosedChannelException >> org.apache.spark.SparkException: Couldn't find leader offsets for >> Set([*<topicName>*,0]) >> at >> >> org.apache.spark.streaming.kafka.KafkaCluster$$anonfun$checkErrors$1.apply(KafkaCluster.scala:366) >> at >> >> org.apache.spark.streaming.kafka.KafkaCluster$$anonfun$checkErrors$1.apply(KafkaCluster.scala:366) >> at scala.util.Either.fold(Either.scala:97) >> at >> >> org.apache.spark.streaming.kafka.KafkaCluster$.checkErrors(KafkaCluster.scala:365) >> at >> >> org.apache.spark.streaming.kafka.KafkaUtils$.getFromOffsets(KafkaUtils.scala:222) >> at >> >> org.apache.spark.streaming.kafka.KafkaUtils$.createDirectStream(KafkaUtils.scala:484) >> at org.mediasoft.spark.Driver$.main(Driver.scala:42) >> at .<init>(<console>:11) >> at .<clinit>(<console>) >> at .<init>(<console>:7) >> at .<clinit>(<console>) >> at $print(<console>) >> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) >> at >> >> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) >> at >> >> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) >> at java.lang.reflect.Method.invoke(Method.java:483) >> at >> scala.tools.nsc.interpreter.IMain$ReadEvalPrint.call(IMain.scala:734) >> at >> scala.tools.nsc.interpreter.IMain$Request.loadAndRun(IMain.scala:983) >> at >> scala.tools.nsc.interpreter.IMain.loadAndRunReq$1(IMain.scala:573) >> at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:604) >> at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:568) >> at >> scala.tools.nsc.interpreter.ILoop.reallyInterpret$1(ILoop.scala:760) >> at >> scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:805) >> at scala.tools.nsc.interpreter.ILoop.command(ILoop.scala:717) >> at >> scala.tools.nsc.interpreter.ILoop.processLine$1(ILoop.scala:581) >> at scala.tools.nsc.interpreter.ILoop.innerLoop$1(ILoop.scala:588) >> at scala.tools.nsc.interpreter.ILoop.loop(ILoop.scala:591) >> at >> >> scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply$mcZ$sp(ILoop.scala:882) >> at >> >> scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply(ILoop.scala:837) >> at >> >> scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply(ILoop.scala:837) >> at >> >> scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135) >> at scala.tools.nsc.interpreter.ILoop.process(ILoop.scala:837) >> at scala.tools.nsc.interpreter.ILoop.main(ILoop.scala:904) >> at >> >> org.jetbrains.plugins.scala.compiler.rt.ConsoleRunner.main(ConsoleRunner.java:64) >> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) >> at >> >> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) >> at >> >> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) >> at java.lang.reflect.Method.invoke(Method.java:483) >> at >> com.intellij.rt.execution.application.AppMain.main(AppMain.java:144) >> >> As for the Spark configuration: >> >> val conf: SparkConf = new >> SparkConf().setAppName("AppName").setMaster("local[2]") >> >> val confParams: Map[String, String] = Map( >> "metadata.broker.list" -> "<IP_ADDRESS>:9092", >> "auto.offset.reset" -> "largest" >> ) >> >> val topics: Set[String] = Set("<topic_name>") >> >> val context: StreamingContext = new StreamingContext(conf, Seconds(1)) >> val kafkaStream = KafkaUtils.createDirectStream(context,confParams, >> topics) >> >> kafkaStream.foreachRDD(rdd => { >> rdd.collect().foreach(println) >> }) >> >> context.awaitTermination() >> context.start() >> >> The Kafka topic does exist, Kafka server is up and running and I am able >> to >> produce messages to that particular topic using the Confluent REST API. >> >> What might the problem actually be? >> >> >> >> >> -- >> View this message in context: >> http://apache-spark-user-list.1001560.n3.nabble.com/Apache-Spark-Kafka-Integration-org-apache-spark-SparkException-Couldn-t-find-leader-offsets-for-Set-tp27103.html >> Sent from the Apache Spark User List mailing list archive at Nabble.com >> <http://nabble.com>. >> >> --------------------------------------------------------------------- >> To unsubscribe, e-mail: user-unsubscr...@spark.apache.org >> For additional commands, e-mail: user-h...@spark.apache.org >> >> > >