实战步骤

1. node1中进入/opt/flume-1.9.0/jobs/

   xxxxxxxxxx
   [root@node1 ~]# cd /opt/flume-1.9.0/jobs/
   

2. 在node1上创建配置文件agg1.conf，配置Source用于监控access.log文件，配置Sink输出数据到下一级Flume,配置内容如下：

   xxxxxxxxxx
   [root@node1 jobs]# vim agg1.conf
   # Name the components on this agent
   a1.sources = r1
   a1.sinks = k1
   a1.channels = c1
   
   # Describe/configure the source
   a1.sources.r1.type = exec
   a1.sources.r1.command = tail -F /usr/local/nginx/logs/access.log
   a1.sources.r1.shell = /bin/bash -c
   
   # Describe the sink
   # sink端的avro是一个数据发送者
   a1.sinks.k1.type = avro
   a1.sinks.k1.hostname = node3 
   a1.sinks.k1.port = 10000
   
   # Describe the channel
   a1.channels.c1.type = memory
   a1.channels.c1.capacity = 1000
   a1.channels.c1.transactionCapacity = 100
   
   # Bind the source and sink to the channel
   a1.sources.r1.channels = c1
   a1.sinks.k1.channel = c1
   

3. node2中进入/opt/flume-1.9.0/jobs/

   xxxxxxxxxx
   [root@node2 ~]# cd /opt/flume-1.9.0/jobs/
   

4. 在node2上创建配置文件agg2.conf，内容如下：

   xxxxxxxxxx
   [root@node2 jobs]# vim agg2.conf
   # Name the components on this agent
   a2.sources = r1
   a2.sinks = k1
   a2.channels = c1
   
   # Describe/configure the source
   # source端的netcat是一个数据接收服务
   a2.sources.r1.type = netcat
   a2.sources.r1.bind = node2
   a2.sources.r1.port = 10000
   
   # Describe the sink
   a2.sinks.k1.type = avro
   a2.sinks.k1.hostname = node3
   a2.sinks.k1.port = 10000
   
   
   # Describe the channel
   a2.channels.c1.type = memory
   a2.channels.c1.capacity = 1000
   a2.channels.c1.transactionCapacity = 100
   
   # Bind the source and sink to the channel
   a2.sources.r1.channels = c1
   a2.sinks.k1.channel = c1
   

5. node3中进入/opt/flume-1.9.0/jobs/

   xxxxxxxxxx
   [root@node3 ~]# cd /opt/flume-1.9.0/jobs/
   

6. node3上创建agg3.conf，内容如下

   xxxxxxxxxx
   [root@node3 jobs]# vim agg3.conf
   # Name the components on this agent
   a3.sources = r3
   a3.sinks = k3
   a3.channels = c3
   
   # Describe/configure the source
   a3.sources.r3.type = avro
   a3.sources.r3.bind = node3
   a3.sources.r3.port = 10000
   
   # Describe the sink
   a3.sinks.k3.type = logger
   
   # Describe the channel
   a3.channels.c3.type = memory
   a3.channels.c3.capacity = 1000
   a3.channels.c3.transactionCapacity = 100
   
   # Bind the source and sink to the channel
   a3.sources.r3.channels = c3
   a3.sinks.k3.channel = c3
   

7. 先启动node3的flume

   xxxxxxxxxx
   [root@node3 jobs]# flume-ng agent -c ./ -n a3 -f agg3.conf -Dflume.root.logger=INFO,console
   

8. 启动node1和node2上上的flume

   xxxxxxxxxx
   [root@node1 jobs]# flume-ng agent -c ./ -n a1 -f agg1.conf -Dflume.root.logger=INFO,console
   [root@node2 jobs]# flume-ng agent -c ./ -n a2 -f agg2.conf -Dflume.root.logger=INFO,console
   

9. 如果Nginx没有启动，则启动nginx。

10. 打开浏览器不断访问nginx页面

11. 在node4上安装telnet包

xxxxxxxxxx
[root@node4 ~]# yum install -y telnet

12. 在node4上向node2的10000端口发送数据

xxxxxxxxxx
[root@node4 ~]# telnet node2 10000

13. 查看node3上的logger输出