使用flume监听目录

# listen-dir.conf
a1.sources = r1
a1.sources.r1.type = spooldir
# 这个是要监听的目录路径
a1.sources.r1.spoolDir = /home/master/listendDir
a1.sources.r1.fileHeader = true
a1.sources.r1.fileSuffix = .COMPLETED
a1.sources.r1.basenameHeader = true
a1.sources.r1.deletePolicy = immediate
a1.sources.r1.ignorePattern = ^\.
a1.sources.r1.deserializer = org.apache.flume.sink.solr.morphline.BlobDeserializer$Builder

a1.sinks = k1
a1.sinks.k1.type = hdfs
# 这个是 hdfs 中对应的目录路径
a1.sinks.k1.hdfs.path = hdfs://master:9000/listendDir
a1.sinks.k1.hdfs.filePrefix = events-
a1.sinks.k1.hdfs.fileSuffix = .log
a1.sinks.k1.hdfs.fileType = DataStream
a1.sinks.k1.hdfs.writeFormat = Text
a1.sinks.k1.hdfs.rollInterval = 0
a1.sinks.k1.hdfs.rollSize = 0
a1.sinks.k1.hdfs.rollCount = 10000
a1.sinks.k1.hdfs.batchSize = 100
a1.sinks.k1.hdfs.useLocalTimeStamp = true

a1.channels = c1
a1.channels.c1.type = memory
a1.channels.c1.capacity = 10000
a1.channels.c1.transactionCapacity = 1000

a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

hdfs dfs -mkdir /listendDir

bin/flume-ng agent -n a1 -c conf -f job/listen-dir.conf -Dflume.log.file -Dflume.root.logger=INFO,console