1.安装配置

1.1.解压安装

tar-zxvfapache-flume-1.6.0-bin.tar.gz-C/opt

mvapache-flume-1.6.0-binflume

1.2.配置环境变量

vim/etc/profile

exportFLUME_HOME=/opt/flume

exportPATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$FLUME_HOME/bin:

保存退出后，刷新profile

source/etc/profile

1.3.验证

#查看flume版本：

[root@aloneopt]#flume-ngversion

Flume1.8.0

Sourcecoderepository:https://git-wip-us.apache.org/repos/asf/flume.git

Revision:99f591994468633fc6f8701c5fc53e0214b6da4f

CompiledbydenesonFriSep1514:58:00CEST2017

Fromsourcewithchecksumfbb44c8c8fb63a49be0a59e27316833d

#出现上面的信息，表示安装成功了

2.实时采集案例---参见官网，对每种类型的source、channel、sink有详细的解释和示例

agent2.sources = s1
agent2.channels = c1 c2
agent2.sinks = k1 k2

# 定义source

#监控文件
#agent2.sources.s1.type=exec 
#agent2.sources.s1.command=tail -F /test/data/test.log
#agent2.sources.s1.channels = c1 c2
agent2.sources.s1.type = avro
agent2.sources.s1.bind=172.16.90.62
agent2.sources.s1.port=4141
agent2.sources.s1.channels = c1 c2

# 定义channels

#------- c1-------------------------
agent2.channels.c1.type = memory
agent2.channels.c1.capacity = 100000
agent2.channels.c1.transactionCapacity = 100000
#------- c2-------------------------
agent2.channels.c2.type = memory
agent2.channels.c2.capacity=10000
agent2.channels.c2.transactionCapacity=1000

# 定义sinks

#---------k1 ------------------
agent2.sinks.k1.type=org.apache.flume.sink.kafka.KafkaSink
agent2.sinks.k1.brokerList=app1:6667,app2:6667
agent2.sinks.k1.topic=kafkatest2
agent2.sinks.k1.serializer.class=kafka.serializer.StringEncoder
agent2.sinks.k1.channel=c1

#---------k2 ------------------
agent2.sinks.k2.type = hdfs
agent2.sinks.k2.channel = c2
agent2.sinks.k2.hdfs.path = /flume/events/%y-%m-%d/%H%M/
agent2.sinks.k2.hdfs.filePrefix = events-
agent2.sinks.k2.hdfs.round = true

#集合roundUnit可以按时间生成文件夹，单位分钟
agent2.sinks.k2.hdfs.roundValue = 10
agent2.sinks.k2.hdfs.roundUnit = minute
#hdfs sink间隔多长将临时文件滚动成最终目标文件，单位：秒；
agent2.sinks.k2.hdfs.rollInterval = 300
#当临时文件达到该大小（单位：bytes）时，滚动成目标文件
agent2.sinks.k2.hdfs.rollSize = 0
#当events数据达到该数量时候，将临时文件滚动成目标文件；
#agent2.sinks.k2.hdfs.rollCount = 300
#每个批次刷新到HDFS上的events数量；
agent2.sinks.k2.hdfs.batchSize = 10
agent2.sinks.k2.hdfs.useLocalTimeStamp = true
#生成的文件类型，默认是Sequencefile，可用DataStream，则为普通文本
agent2.sinks.k2.hdfs.fileType = DataStream

Flume除了以上介绍的内容，还支持定义各种拦截器，用来做一些简单的数据清洗，可以自己去官网学习