Hadoop离线_flume静态拦截器

---

1.需求

把A、B 机器中的access.log、nginx.log、web.log 采集汇总到C机器上然后统一收集到hdfs指定的目录中：
/source/logs/access/20180101/**
/source/logs/nginx/20180101/**
/source/logs/web/20180101/**

2.画图分析

3.配置文件的开发

1.将node01、node02分别分配为采集端服务器A和服务器B，node03为服务端的服务器C
2.分别在node01、node02执行以下命令
cd /export/servers/apache-flume-1.6.0-cdh5.14.0-bin/conf
vim exec_source_avro_sink.conf

# Name the components on this agent
a1.sources = r1 r2 r3
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /export/servers/taillogs/access.log
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = static
##  static拦截器的功能就是往采集到的数据的header中插入自己定## 义的key-value对
a1.sources.r1.interceptors.i1.key = type
a1.sources.r1.interceptors.i1.value = access

a1.sources.r2.type = exec
a1.sources.r2.command = tail -F /export/servers/taillogs/nginx.log
a1.sources.r2.interceptors = i2
a1.sources.r2.interceptors.i2.type = static
a1.sources.r2.interceptors.i2.key = type
a1.sources.r2.interceptors.i2.value = nginx

a1.sources.r3.type = exec
a1.sources.r3.command = tail -F /export/servers/taillogs/web.log
a1.sources.r3.interceptors = i3
a1.sources.r3.interceptors.i3.type = static
a1.sources.r3.interceptors.i3.key = type
a1.sources.r3.interceptors.i3.value = web

# Describe the sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = node03
a1.sinks.k1.port = 41414

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 20000
a1.channels.c1.transactionCapacity = 10000

# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sources.r2.channels = c1
a1.sources.r3.channels = c1
a1.sinks.k1.channel = c1

3.在node03上面开发flume配置文件
cd /export/servers/apache-flume-1.6.0-cdh5.14.0-bin/conf
vim avro_source_hdfs_sink.conf

a1.sources = r1
a1.sinks = k1
a1.channels = c1
#定义source
a1.sources.r1.type = avro
a1.sources.r1.bind = 192.168.52.120
a1.sources.r1.port =41414

#添加时间拦截器
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = org.apache.flume.interceptor.TimestampInterceptor$Builder


#定义channels
a1.channels.c1.type = memory
a1.channels.c1.capacity = 20000
a1.channels.c1.transactionCapacity = 10000

#定义sink
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path=hdfs://192.168.52.100:8020/source/logs/%{type}/%Y%m%d
a1.sinks.k1.hdfs.filePrefix =events
a1.sinks.k1.hdfs.fileType = DataStream
a1.sinks.k1.hdfs.writeFormat = Text
#时间类型
a1.sinks.k1.hdfs.useLocalTimeStamp = true
#生成的文件不按条数生成
a1.sinks.k1.hdfs.rollCount = 0
#生成的文件按时间生成
a1.sinks.k1.hdfs.rollInterval = 30
#生成的文件按大小生成
a1.sinks.k1.hdfs.rollSize  = 10485760
#批量写入hdfs的个数
a1.sinks.k1.hdfs.batchSize = 10000
#flume操作hdfs的线程数（包括新建，写入等）
a1.sinks.k1.hdfs.threadsPoolSize=10
#操作hdfs超时时间
a1.sinks.k1.hdfs.callTimeout=30000

#组装source、channel、sink
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

3.在node01与node02上面开发shell脚本，模拟数据生成
cd /export/servers/shells
vim server.sh

#!/bin/bash
while true
do  
 date >> /export/servers/taillogs/access.log; 
 date >> /export/servers/taillogs/web.log;
 date >> /export/servers/taillogs/nginx.log;
  sleep 0.5;
done

4.顺序启动

启动node03的flume实现数据收集
bin/flume-ng agent -c conf -f conf/avro_source_hdfs_sink.conf -n a1 -Dflume.root.logger=DEBUG,console
启动node01和node02实现数据监控
bin/flume-ng agent -c conf -f conf/exec_source_avro_sink.conf -n a1 -Dflume.root.logger=DEBUG,console
启动node01和node02生成脚本文件
sh /export/servers/shells/server.sh