在flume/bin 下 vi dir-hdfs.conf 写配置文件,作用是监听log文件夹
flume的配置文件如下:
#spooldir:flume中自带的读取目录的source,只要出现新文件就会被读走
#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=5129
# 配置sink组件 把读到的文件存放到哪个地方
ag1.sinks.sink1.type = hdfs
ag1.sinks.sink1.hdfs.path =hdfs://hdp-1:9000/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.writeForma