1.数据流向
日志系统=>flume=>kafka=>storm
2.安装flume
1.我们在storm01上安装flume1.6.0,上传安装包
2.解压到 /export/servers/flume,首先创建文件夹flume
命令: sudo tar -zxvf apache-flume-1.6.0-bin.tar.gz -C /export/servers/flume/
3.配置采集文件,在conf目录下创建一个myconf文件夹
4.继续在myconf文件夹下创建配置文件
配置文件的内容:主要是监听日志文件
agent.sinks = k1
agent.sources = s1
agent.sources = s1
agent.channels = c1
agent.sinks = k1
agent.sources.s1.type=exec
agent.sources.s1.command=tail -F /export/data/flume_source/click_log/1.log
agent.sources.s1.channels=c1
agent.channels.c1.type=memory
agent.channels.c1.capacity=10000
agent.channels.c1.transactionCapacity=100
#设置Kafka接收器
agent.sinks.k1.type= org.apache.flume.sink.kafka.KafkaSink
#设置Kafka的broker地址和端口
agent.sinks.k1.brokerList=kafka01:9092
#设置Kafka的Topic
agent.sinks.k1.topic=orderMq
#设置序列化方式
agent.sinks.k1.serializer.class=kafka.serializer.StringEncoder
agent.sinks.k1.channel=c1
准备监听的目录:
/export/data/flume_source/click_log
5.启动命令:
bin/flume-ng agent -n agent -c ./conf -f ./conf/myconf/exec.conf -Dflume.root.logger=INFO,console
6. 测试数据从flume到kafka是否正确:
Kafka的shell消费:
bin/kafka-console-consumer.sh --zookeeper zk01:2181 --from-beginning --topic orderMq 不从开始消费而是从最大开始消费:
编写模拟生产日志数据的脚本文件:
vi click_log_out.sh
for((i=0;i<50000;i++));
do echo "message-"+$i >>/export/data/flume_source/click_log/1.log;
done
Sudo chmod u+x click_log_out.sh
执行脚本:sh click_log_out.sh 另外一边的customer就在开始采集数据了:
说明数据从flume到kafka是没有问题的
3.数据从kafka到Storm
新建maven工程:添加依赖
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.wx</groupId>
<artifactId>stormkafka</artifactId>
<version>1.0-SNAPSHOT</version>
<dependencies>
<!--storm的以来包-->
<dependency>
<groupId>org.apache.storm</groupId>
<artifactId>storm-core</artifactId>
<version>0.9.5</version>
<!--<scope>provided</scope>-->
</dependency>
<!--KafkaSpout的依赖包,这个就可以把kafka的数据流到storm-->
<dependency>
<groupId>org.apache.storm</groupId>
<artifactId>storm-kafka</artifactId>
<version>0.9.5</version>
<!-- <exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</exclusion>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
</exclusion>
</exclusions>-->
</dependency>
<dependency>
<groupId>org.clojure</groupId>
<artifactId>clojure</artifactId>
<version>1.5.1</version>
</dependency>
<!--kafka的依赖包-->
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka_2.8.2</artifactId>
<version>0.8.1</version>
<exclusions>
<exclusion>
<artifactId>jmxtools</artifactId>
<groupId>com.sun.jdmk</groupId>
</exclusion>
<exclusion>
<artifactId>jmxri</artifactId>
<groupId>com.sun.jmx</groupId>
</exclusion>
<exclusion>
<artifactId>jms</artifactId>
<groupId>javax.jms</groupId>
</exclusion>
<exclusion>
<groupId>org.apache.zookeeper</groupId>
<artifactId>zookeeper</artifactId>
</exclusion>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</exclusion>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
</exclusion>
</exclusions>
</dependency>
<!-- <dependency>
<groupId>com.google.code.gson</groupId>
<artifactId>gson</artifactId>
<version>2.4</version>
</dependency>
<dependency>
<groupId>redis.clients</groupId>
<artifactId>jedis</artifactId>
<version>2.7.3</version>
</dependency>-->
</dependencies>
<build>
<plugins>
<plugin>
<!--打包的时候把项目其他依赖的一些jar,一些类打成一个整体-->
<artifactId>maven-assembly-plugin</artifactId>
<configuration>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
<archive>
<manifest>
<mainClass>cn.itcast.bigdata.hadoop.mapreduce.wordcount.WordCount</mainClass>
</manifest>
</archive>
</configuration>
<executions>
<execution>
<id>make-assembly</id>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>1.7</source>
<target>1.7</target>
</configuration>
</plugin>
</plugins>
</build>
</project>
编写一个topology:
package com.wx.kafkaandstorm;
import backtype.storm.Config;
import backtype.storm.LocalCluster;
import backtype.storm.StormSubmitter;
import backtype.storm.topology.TopologyBuilder;
import storm.kafka.KafkaSpout;
import storm.kafka.SpoutConfig;
import storm.kafka.ZkHosts;
public class KafkaAndStormTopologyMain {
public static void main(String[] args) throws Exception{
TopologyBuilder topologyBuilder = new TopologyBuilder();
topologyBuilder.setSpout("kafkaSpout",
new KafkaSpout(new SpoutConfig(
new ZkHosts("192.168.25.130:2181,192.168.25.131:2181,192.168.25.132:2181"),
"orderMq",
"/myKafka",
"kafkaSpout")),1);
topologyBuilder.setBolt("mybolt1",new ParserOrderMqBolt(),1).shuffleGrouping("kafkaSpout");
Config config = new Config();
config.setNumWorkers(1);
//3、提交任务 -----两种模式 本地模式和集群模式
if (args.length>0) {
StormSubmitter.submitTopology(args[0], config, topologyBuilder.createTopology());
}else {
LocalCluster localCluster = new LocalCluster();
localCluster.submitTopology("storm2kafka", config, topologyBuilder.createTopology());
}
}
}
编写一个Bolt接收来自kafka的数据
package com.wx.kafkaandstorm;
import backtype.storm.task.OutputCollector;
import backtype.storm.task.TopologyContext;
import backtype.storm.topology.OutputFieldsDeclarer;
import backtype.storm.topology.base.BaseRichBolt;
import backtype.storm.tuple.Tuple;
import java.util.Map;
public class ParserOrderMqBolt extends BaseRichBolt {
@Override
public void prepare(Map map, TopologyContext topologyContext, OutputCollector outputCollector) {
}
@Override
public void execute(Tuple tuple) {
Object o=tuple.getValue(0);
System.out.printf(new String((byte[]) tuple.getValue(0))+"\n\t");
}
@Override
public void declareOutputFields(OutputFieldsDeclarer outputFieldsDeclarer) {
}
}
启动:
4.联合测试:
启动日志生产脚本:
kafka可以消费到数据:
数据也可以从kafka流到storm:
本地运行没有问题,但是把他打包上传到集群上去跑就出现问题了,报了个错:backtype.storm.topology.IRichSpout
这个错表示要么少包要么包冲突,本地能运行成功,应该不可能少包,应该是包冲突,到底是哪个包冲突了呢?集群的storm版本是1.0.6而本地运行的storm jar的版本是0.9.5,所以果断把本地的storm包换成1.0.6版本的,但是还是运行不成功,原因是clojure包的版本太低,storm1.0以上的需要clojure包的版本是1.7,所以改变包的版本,本地测试能通过,集群测试也能通过
贴出最终pom文件:
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.wx</groupId>
<artifactId>stormkafka</artifactId>
<version>1.0-SNAPSHOT</version>
<dependencies>
<!--storm的以来包-->
<dependency>
<groupId>org.apache.storm</groupId>
<artifactId>storm-core</artifactId>
<version>1.0.6</version>
<scope>provided</scope>
</dependency>
<!--KafkaSpout的依赖包,这个就可以把kafka的数据流到storm-->
<dependency>
<groupId>org.apache.storm</groupId>
<artifactId>storm-kafka</artifactId>
<version>1.0.6</version>
<!-- <exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</exclusion>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
</exclusion>
</exclusions>-->
</dependency>
<dependency>
<groupId>org.clojure</groupId>
<artifactId>clojure</artifactId>
<version>1.7.0</version>
</dependency>
<!--kafka的依赖包-->
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka_2.8.2</artifactId>
<version>0.8.1</version>
<exclusions>
<exclusion>
<artifactId>jmxtools</artifactId>
<groupId>com.sun.jdmk</groupId>
</exclusion>
<exclusion>
<artifactId>jmxri</artifactId>
<groupId>com.sun.jmx</groupId>
</exclusion>
<exclusion>
<artifactId>jms</artifactId>
<groupId>javax.jms</groupId>
</exclusion>
<exclusion>
<groupId>org.apache.zookeeper</groupId>
<artifactId>zookeeper</artifactId>
</exclusion>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</exclusion>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
</exclusion>
</exclusions>
</dependency>
<!-- <dependency>
<groupId>com.google.code.gson</groupId>
<artifactId>gson</artifactId>
<version>2.4</version>
</dependency>
<dependency>
<groupId>redis.clients</groupId>
<artifactId>jedis</artifactId>
<version>2.7.3</version>
</dependency>-->
</dependencies>
<build>
<plugins>
<plugin>
<!--打包的时候把项目其他依赖的一些jar,一些类打成一个整体-->
<artifactId>maven-assembly-plugin</artifactId>
<configuration>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
<archive>
<manifest>
<mainClass>com.wx.kafkaandstorm.KafkaAndStormTopologyMain</mainClass>
</manifest>
</archive>
</configuration>
<executions>
<execution>
<id>make-assembly</id>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>1.7</source>
<target>1.7</target>
</configuration>
</plugin>
</plugins>
</build>
</project>
打包上传运行:
启动生产数据的脚本: