解压安装包
tar -zvxf apache-flume-1.6.0-bin.tar.gz
添加配置文件
#定义三大组件的名称 ag1.sources = source1 ag1.sinks = sink1 ag1.channels = channel1 # 配置source组件 ag1.sources.source1.type = spooldir ag1.sources.source1.spoolDir = /root/log/ ag1.sources.source1.fileSuffix=.FINISHED ag1.sources.source1.deserializer.maxLineLength=5120 # 配置sink组件 ag1.sinks.sink1.type = hdfs ag1.sinks.sink1.hdfs.path =hdfs://hdp-01:9000/access_log/%y-%m-%d/%H-%M ag1.sinks.sink1.hdfs.filePrefix = app_log ag1.sinks.sink1.hdfs.fileSuffix = .log ag1.sinks.sink1.hdfs.batchSize= 100 ag1.sinks.sink1.hdfs.fileType = DataStream ag1.sinks.sink1.hdfs.writeFormat =Text ## roll：滚动切换：控制写文件的切换规则 ## 按文件体积（字节）来切 ag1.sinks.sink1.hdfs.rollSize = 512000 ## 按event条数切 ag1.sinks.sink1.hdfs.rollCount = 1000000 ## 按时间间隔切换文件 ag1.sinks.sink1.hdfs.rollInterval = 60 ## 控制生成目录的规则 ag1.sinks.sink1.hdfs.round = true ag1.sinks.sink1.hdfs.roundValue = 10 ag1.sinks.sink1.hdfs.roundUnit = minute ag1.sinks.sink1.hdfs.useLocalTimeStamp = true # channel组件配置 ag1.channels.channel1.type = memory ## event条数 ag1.channels.channel1.capacity = 500000 ##flume事务控制所需要的缓存容量600条event ag1.channels.channel1.transactionCapacity = 600 # 绑定source、channel和sink之间的连接 ag1.sources.source1.channels = channel1 ag1.sinks.sink1.channel = channel1
启动flume
# -c conf：指定自带配置文件-f conf/tail-hdfs.conf:自定义配置文件 -n ag1：agent名称
bin/flume-ng agent -c conf -f conf/tail-hdfs.conf -n ag1