flume配置案例

flume配置案例

dir-hdfs.conf：

#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://hadoop1:9000/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
ag1.sinks.sink1.hdfs.rollSize = 512000    ## 按文件体积（字节）来切   
ag1.sinks.sink1.hdfs.rollCount = 1000000  ## 按event条数切
ag1.sinks.sink1.hdfs.rollInterval = 60    ## 按时间间隔切换文件


## 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
ag1.channels.channel1.capacity = 500000   ## event条数
ag1.channels.channel1.transactionCapacity = 600  ##flume事务控制所需要的缓存容量600条event


# 绑定source、channel和sink之间的连接

ag1.sources.source1.channels = channel1
ag1.sinks.sink1.channel = channel1

tail-hdfs.conf：

tail-hdfs.conf

用tail命令获取数据，下沉到hdfs
启动命令：
bin/flume-ng agent -c conf -f conf/tail-hdfs.conf -n a1
########

# Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /root/app_weichat_login.log

# Describe the sink
agent1.sinks.sink1.type = hdfs
agent1.sinks.sink1.hdfs.path =hdfs://hdp20-01:9000/app_weichat_login_log/%y-%m-%d/%H-%M
agent1.sinks.sink1.hdfs.filePrefix = weichat_log
agent1.sinks.sink1.hdfs.fileSuffix = .dat
agent1.sinks.sink1.hdfs.batchSize= 100
agent1.sinks.sink1.hdfs.fileType = DataStream
agent1.sinks.sink1.hdfs.writeFormat =Text

agent1.sinks.sink1.hdfs.rollSize = 100
agent1.sinks.sink1.hdfs.rollCount = 1000000
agent1.sinks.sink1.hdfs.rollInterval = 60

agent1.sinks.sink1.hdfs.round = true
agent1.sinks.sink1.hdfs.roundValue = 1
agent1.sinks.sink1.hdfs.roundUnit = minute


agent1.sinks.sink1.hdfs.useLocalTimeStamp = true



# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1