diff options
3 files changed, 18 insertions, 23 deletions
diff --git a/examples/src/main/scala/spark/streaming/examples/KafkaWordCount.scala b/examples/src/main/scala/spark/streaming/examples/KafkaWordCount.scala index fe55db6e2c..65d5da82fc 100644 --- a/examples/src/main/scala/spark/streaming/examples/KafkaWordCount.scala +++ b/examples/src/main/scala/spark/streaming/examples/KafkaWordCount.scala @@ -13,19 +13,19 @@ import spark.streaming.util.RawTextHelper._ object KafkaWordCount { def main(args: Array[String]) { - if (args.length < 6) { - System.err.println("Usage: KafkaWordCount <master> <hostname> <port> <group> <topics> <numThreads>") + if (args.length < 5) { + System.err.println("Usage: KafkaWordCount <master> <zkQuorum> <group> <topics> <numThreads>") System.exit(1) } - val Array(master, hostname, port, group, topics, numThreads) = args + val Array(master, zkQuorum, group, topics, numThreads) = args val sc = new SparkContext(master, "KafkaWordCount") val ssc = new StreamingContext(sc, Seconds(2)) ssc.checkpoint("checkpoint") val topicpMap = topics.split(",").map((_,numThreads.toInt)).toMap - val lines = ssc.kafkaStream[String](hostname, port.toInt, group, topicpMap) + val lines = ssc.kafkaStream[String](zkQuorum, group, topicpMap) val words = lines.flatMap(_.split(" ")) val wordCounts = words.map(x => (x, 1l)).reduceByKeyAndWindow(add _, subtract _, Minutes(10), Seconds(2), 2) wordCounts.print() @@ -38,16 +38,16 @@ object KafkaWordCount { object KafkaWordCountProducer { def main(args: Array[String]) { - if (args.length < 3) { - System.err.println("Usage: KafkaWordCountProducer <hostname> <port> <topic> <messagesPerSec> <wordsPerMessage>") + if (args.length < 2) { + System.err.println("Usage: KafkaWordCountProducer <zkQuorum> <topic> <messagesPerSec> <wordsPerMessage>") System.exit(1) } - val Array(hostname, port, topic, messagesPerSec, wordsPerMessage) = args + val Array(zkQuorum, topic, messagesPerSec, wordsPerMessage) = args // Zookeper connection properties val props = new Properties() - props.put("zk.connect", hostname + ":" + port) + props.put("zk.connect", zkQuorum) props.put("serializer.class", "kafka.serializer.StringEncoder") val config = new ProducerConfig(props) diff --git a/streaming/src/main/scala/spark/streaming/StreamingContext.scala b/streaming/src/main/scala/spark/streaming/StreamingContext.scala index 14500bdcb1..06cf7a06ed 100644 --- a/streaming/src/main/scala/spark/streaming/StreamingContext.scala +++ b/streaming/src/main/scala/spark/streaming/StreamingContext.scala @@ -136,8 +136,7 @@ class StreamingContext private ( /** * Create an input stream that pulls messages form a Kafka Broker. - * @param hostname Zookeper hostname. - * @param port Zookeper port. + * @param zkQuorum Zookeper quorum (hostname:port,hostname:port,..). * @param groupId The group id for this consumer. * @param topics Map of (topic_name -> numPartitions) to consume. Each partition is consumed * in its own thread. @@ -146,14 +145,13 @@ class StreamingContext private ( * @param storageLevel RDD storage level. Defaults to memory-only. */ def kafkaStream[T: ClassManifest]( - hostname: String, - port: Int, + zkQuorum: String, groupId: String, topics: Map[String, Int], initialOffsets: Map[KafkaPartitionKey, Long] = Map[KafkaPartitionKey, Long](), storageLevel: StorageLevel = StorageLevel.MEMORY_ONLY_SER_2 ): DStream[T] = { - val inputStream = new KafkaInputDStream[T](this, hostname, port, groupId, topics, initialOffsets, storageLevel) + val inputStream = new KafkaInputDStream[T](this, zkQuorum, groupId, topics, initialOffsets, storageLevel) registerInputStream(inputStream) inputStream } diff --git a/streaming/src/main/scala/spark/streaming/dstream/KafkaInputDStream.scala b/streaming/src/main/scala/spark/streaming/dstream/KafkaInputDStream.scala index 533c91ee95..4f8c8b9d10 100644 --- a/streaming/src/main/scala/spark/streaming/dstream/KafkaInputDStream.scala +++ b/streaming/src/main/scala/spark/streaming/dstream/KafkaInputDStream.scala @@ -23,8 +23,7 @@ case class KafkaPartitionKey(brokerId: Int, topic: String, groupId: String, part /** * Input stream that pulls messages from a Kafka Broker. * - * @param host Zookeper hostname. - * @param port Zookeper port. + * @param zkQuorum Zookeper quorum (hostname:port,hostname:port,..). * @param groupId The group id for this consumer. * @param topics Map of (topic_name -> numPartitions) to consume. Each partition is consumed * in its own thread. @@ -35,8 +34,7 @@ case class KafkaPartitionKey(brokerId: Int, topic: String, groupId: String, part private[streaming] class KafkaInputDStream[T: ClassManifest]( @transient ssc_ : StreamingContext, - host: String, - port: Int, + zkQuorum: String, groupId: String, topics: Map[String, Int], initialOffsets: Map[KafkaPartitionKey, Long], @@ -44,13 +42,13 @@ class KafkaInputDStream[T: ClassManifest]( ) extends NetworkInputDStream[T](ssc_ ) with Logging { def createReceiver(): NetworkReceiver[T] = { - new KafkaReceiver(host, port, groupId, topics, initialOffsets, storageLevel) + new KafkaReceiver(zkQuorum, groupId, topics, initialOffsets, storageLevel) .asInstanceOf[NetworkReceiver[T]] } } private[streaming] -class KafkaReceiver(host: String, port: Int, groupId: String, +class KafkaReceiver(zkQuorum: String, groupId: String, topics: Map[String, Int], initialOffsets: Map[KafkaPartitionKey, Long], storageLevel: StorageLevel) extends NetworkReceiver[Any] { @@ -73,21 +71,20 @@ class KafkaReceiver(host: String, port: Int, groupId: String, // In case we are using multiple Threads to handle Kafka Messages val executorPool = Executors.newFixedThreadPool(topics.values.reduce(_ + _)) - val zooKeeperEndPoint = host + ":" + port logInfo("Starting Kafka Consumer Stream with group: " + groupId) logInfo("Initial offsets: " + initialOffsets.toString) // Zookeper connection properties val props = new Properties() - props.put("zk.connect", zooKeeperEndPoint) + props.put("zk.connect", zkQuorum) props.put("zk.connectiontimeout.ms", ZK_TIMEOUT.toString) props.put("groupid", groupId) // Create the connection to the cluster - logInfo("Connecting to Zookeper: " + zooKeeperEndPoint) + logInfo("Connecting to Zookeper: " + zkQuorum) val consumerConfig = new ConsumerConfig(props) consumerConnector = Consumer.create(consumerConfig).asInstanceOf[ZookeeperConsumerConnector] - logInfo("Connected to " + zooKeeperEndPoint) + logInfo("Connected to " + zkQuorum) // If specified, set the topic offset setOffsets(initialOffsets) |