sparkstreaming+kafka

环境配置：
----kafka------server.properties-----------start----------------------------
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# see kafka.server.KafkaConfig for additional details and defaults
############################# Server Basics #############################
# The id of the broker. This must be set to a unique integer for each broker.
broker.id=0
port=9092
host.name=master
# Switch to enable topic deletion or not, default value is false
#delete.topic.enable=true
############################# Socket Server Settings #############################
# The address the socket server listens on. It will get the value returned from 
# java.net.InetAddress.getCanonicalHostName() if not configured.
#   FORMAT:
#     listeners = security_protocol://host_name:port
#   EXAMPLE:
#     listeners = PLAINTEXT://your.host.name:9092
#listeners=PLAINTEXT://:9092
# Hostname and port the broker will advertise to producers and consumers. If not set, 
# it uses the value for "listeners" if configured.  Otherwise, it will use the value
# returned from java.net.InetAddress.getCanonicalHostName().
#advertised.listeners=PLAINTEXT://your.host.name:9092
# The number of threads handling network requests
num.network.threads=3
# The number of threads doing disk I/O
num.io.threads=8
# The send buffer (SO_SNDBUF) used by the socket server
socket.send.buffer.bytes=102400
# The receive buffer (SO_RCVBUF) used by the socket server
socket.receive.buffer.bytes=102400
# The maximum size of a request that the socket server will accept (protection against OOM)
socket.request.max.bytes=104857600
############################# Log Basics #############################
# A comma seperated list of directories under which to store log files
log.dirs=/tmp/kafka-logs
# The default number of log partitions per topic. More partitions allow greater
# parallelism for consumption, but this will also result in more files across
# the brokers.
num.partitions=2
# The number of threads per data directory to be used for log recovery at startup and flushing at shutdown.
# This value is recommended to be increased for installations with data dirs located in RAID array.
num.recovery.threads.per.data.dir=1
############################# Log Flush Policy #############################
# Messages are immediately written to the filesystem but by default we only fsync() to sync
# the OS cache lazily. The following configurations control the flush of data to disk.
# There are a few important trade-offs here:
#    1. Durability: Unflushed data may be lost if you are not using replication.
#    2. Latency: Very large flush intervals may lead to latency spikes when the flush does occur as there will be a lot of data to flush.
#    3. Throughput: The flush is generally the most expensive operation, and a small flush interval may lead to exceessive seeks.
# The settings below allow one to configure the flush policy to flush data after a period of time or
# every N messages (or both). This can be done globally and overridden on a per-topic basis.
# The number of messages to accept before forcing a flush of data to disk
#log.flush.interval.messages=10000
# The maximum amount of time a message can sit in a log before we force a flush
#log.flush.interval.ms=1000
############################# Log Retention Policy #############################
# The following configurations control the disposal of log segments. The policy can
# be set to delete segments after a period of time, or after a given size has accumulated.
# A segment will be deleted whenever *either* of these criteria are met. Deletion always happens
# from the end of the log.
# The minimum age of a log file to be eligible for deletion
log.retention.hours=168
# A size-based retention policy for logs. Segments are pruned from the log as long as the remaining
# segments don't drop below log.retention.bytes.
#log.retention.bytes=1073741824
# The maximum size of a log segment file. When this size is reached a new log segment will be created.
log.segment.bytes=1073741824
# The interval at which log segments are checked to see if they can be deleted according
# to the retention policies
log.retention.check.interval.ms=300000
############################# Zookeeper #############################
# Zookeeper connection string (see zookeeper docs for details).
# This is a comma separated host:port pairs, each corresponding to a zk
# server. e.g. "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002".
# You can also append an optional chroot string to the urls to specify the
# root directory for all kafka znodes.
zookeeper.connect=master:2181,slave1:2181,slave2:2181
# Timeout in ms for connecting to zookeeper
zookeeper.connection.timeout.ms=6000
-------------------end---------------------------------------
------------------zookeeper-------------zoo.cfg------------------


# The number of milliseconds of each tick
tickTime=2000
# The number of ticks that the initial 
# synchronization phase can take
initLimit=10
# The number of ticks that can pass between 
# sending a request and getting an acknowledgement
syncLimit=5
# the directory where the snapshot is stored.
# do not use /tmp for storage, /tmp here is just 
# example sakes.
dataDir=/usr/hadoop/zookeeper-3.4.5/data
dataLogDir=/usr/hadoop/zookeeper-3.4.5/logs
server.0=master:2888:3888
server.1=slave1:2888:3888
server.2=slave2:2888:3888
# the port at which the clients will connect
clientPort=2181
#
# Be sure to read the maintenance section of the 
# administrator guide before turning on autopurge.
#
# http://zookeeper.apache.org/doc/current/zookeeperAdmin.html#sc_maintenance
#
# The number of snapshots to retain in dataDir
#autopurge.snapRetainCount=3
# Purge task interval in hours
# Set to "0" to disable auto purge feature
#autopurge.purgeInterval=1




-------------------------------------------------------------------------------


shell：
启动zookeeper：zkServe
r.sh start
启动kafka：./bin/kafka-server-start.sh ./config/server.properties


创建test
/bin/kafka-topics.sh --create --zookeeper localhost:2181 --replication-factor 1 --partitions 1 --topic test
查看：
/usr/hadoop/kafka_2.10-0.10.1.0/bin/kafka-topics.sh --describe --zookeeper master:2181,slave1:2181,slave2:2181 --topic test
生产：
/usr/hadoop/kafka_2.10-0.10.1.0/bin/kafka-console-producer.sh --broker-list slave1:9092 --sync --topic test
消费：
/usr/hadoop/kafka_2.10-0.10.1.0/bin/kafka-console-consumer.sh --zookeeper master:2181,slave1:2181,slave2:2181 --topic test --from-beginning






生产数据：
参数：master:9092,slave1:9092,slave2:9092 test 5 8
package sparkStreaming.stream1
import java.util._
import org.apache.kafka.clients.producer.{KafkaProducer, ProducerConfig, ProducerRecord}


/**
 * Created by zyf on 2016/10/29.
 */
object KafkaWordCountProducer {
  def main(args: Array[String]) {
    if (args.length < 4) {
      System.err.println("Usage: KafkaWordCountProducer <metadataBrokerList> <topic> " +
        "<messagesPerSec> <wordsPerMessage>")
      System.exit(1)
    }


    val Array(brokers, topic, messagesPerSec, wordsPerMessage) = args


    // Zookeeper连接属性配置
    val props = new HashMap[String, Object]()


    props.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, brokers)
    props.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG,"org.apache.kafka.common.serialization.StringSerializer")
    props.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG,"org.apache.kafka.common.serialization.StringSerializer")
    //创建KafkaProducer
    val producer = new KafkaProducer[String, String](props)


    // 向kafka集群发送消息
    while(true) {
      (1 to messagesPerSec.toInt).foreach { messageNum =>
        val str = (1 to wordsPerMessage.toInt).map(x => scala.util.Random.nextInt(10).toString).mkString(" ")


        val message = new ProducerRecord[String, String](topic, null, str)
        producer.send(message)
      }
      Thread.sleep(1000)
    }
  }


}


消费数据：
参数：master:2181  test-consumer-group test 1
package sparkStreaming.stream1


/**
 * Created by zyf on 2016/10/28.
 */
import org.apache.spark.SparkConf
import org.apache.spark.streaming._
import org.apache.spark.streaming.kafka._


object KafkaWordCount {
  def main(args: Array[String]) {
    if (args.length < 4) {
      System.err.println("Usage: KafkaWordCount <zkQuorum> <group> <topics> <numThreads>")
      System.exit(1)
    }
    //StreamingExamples.setStreamingLogLevels()


    val Array(zkQuorum, group, topics, numThreads) = args
    val sparkConf = new SparkConf().setAppName("KafkaWordCount")
      //.setMaster("spark://master:7077")
       .setMaster("local[4]")
    val ssc = new StreamingContext(sparkConf, Seconds(2))
    ssc.checkpoint("checkpoint")


    val topicMap = topics.split(",").map((_, numThreads.toInt)).toMap
    //创建ReceiverInputDStream
    val lines = KafkaUtils.createStream(ssc, zkQuorum, group, topicMap).map(_._2)
    val words = lines.flatMap(_.split(" "))
    val wordCounts = words.map(x => (x, 1L))
      .reduceByKeyAndWindow(_ + _, _ - _, Minutes(10), Seconds(2), 2)
    wordCounts.print()


    ssc.start()
    ssc.awaitTermination()
  }
}