各配置文件信息如下：
一、Flume监控Hive日志信息并上传到Hdfs：
# Name the components on this agent a2.sources = r2
a2.sinks = k2 a2.channels = c2
# Describe/configure the source a2.sources.r2.type = exec
a2.sources.r2.command = tail -F /hive安装路径/hive.log
a2.sources.r2.shell = /bin/bash -c
# Describe the sink a2.sinks.k2.type = hdfs
a2.sinks.k2.hdfs.path = hdfs://namenodeIP:8020/指定存储路径
#上传文件的前缀
a2.sinks.k2.hdfs.filePrefix = logs-
#是否按照时间滚动文件夹
a2.sinks.k2.hdfs.round = true
#多少时间单位创建一个新的文件夹
a2.sinks.k2.hdfs.roundValue = 1
#重新定义时间单位
a2.sinks.k2.hdfs.roundUnit = hour
#是否使用本地时间戳
a2.sinks.k2.hdfs.useLocalTimeStamp = true
#积攒多少个Event 才 flush 到 HDFS 一次
a2.sinks.k2.hdfs.batchSize = 1000
#设置文件类型，可支持压缩
a2.sinks.k2.hdfs.fileType = DataStream
#多久生成一个新的文件
a2.sinks.k2.hdfs.rollInterval = 600
#设置每个文件的滚动大小
a2.sinks.k2.hdfs.rollSize = 134217700
#文件的滚动与 Event 数量无关
a2.sinks.k2.hdfs.rollCount = 0
#最小副本数
a2.sinks.k2.hdfs.minBlockReplicas = 1
# Use a channel which buffers events in memory
a2.channels.c2.type = memory
a2.channels.c2.capacity = 1000
a2.channels.c2.transactionCapacity = 100
# Bind the source and sink to the channel
a2.sources.r2.channels = c2
a2.sinks.k2.channel = c2
二、Flume监听整个目录的文件并保存到hdfs
a3.sources = r3
a3.sinks = k3
a3.channels = c3
# Describe/configure the source
a3.sources.r3.type = spooldir
a3.sources.r3.spoolDir = 想要监听的目录
a3.sources.r3.fileSuffix = .COMPLETED
a3.sources.r3.fileHeader = true
#忽略所有以.tmp 结尾的文件，不上传
a3.sources.r3.ignorePattern = ([^ ]*\.tmp)
# Describe the sink
a3.sinks.k3.type = hdfs
a3.sinks.k3.hdfs.path = hdfs://NameNodeIP:8020/存储目录
#上传文件的前缀
a3.sinks.k3.hdfs.filePrefix = upload-
#是否按照时间滚动文件夹
a3.sinks.k3.hdfs.round = true
#多少时间单位创建一个新的文件夹
a3.sinks.k3.hdfs.roundValue = 1
#重新定义时间单位
a3.sinks.k3.hdfs.roundUnit = hour
#是否使用本地时间戳
a3.sinks.k3.hdfs.useLocalTimeStamp = true
#积攒多少个Event 才 flush 到 HDFS 一次
a3.sinks.k3.hdfs.batchSize = 100
#设置文件类型，可支持压缩
a3.sinks.k3.hdfs.fileType = DataStream
#多久生成一个新的文件
a3.sinks.k3.hdfs.rollInterval = 600
#设置每个文件的滚动大小大概是 128M
a3.sinks.k3.hdfs.rollSize = 134217700
#文件的滚动与 Event 数量无关
a3.sinks.k3.hdfs.rollCount = 0
#最小冗余数
a3.sinks.k3.hdfs.minBlockReplicas = 1
# Use a channel which buffers events in memory
a3.channels.c3.type = memory
a3.channels.c3.capacity = 1000
a3.channels.c3.transactionCapacity = 100
# Bind the source and sink to the channel
a3.sources.r3.channels = c3
a3.sinks.k3.channel = c3