Flume监听文件目录sink至hdfs按照每天切割

采用的channels为file,sink为hdfs,此处往hdfs写的策略是当时间达到3600s或者文件大小达到128M。可以自己调整

agent1.sources = source1
agent1.sinks = sink1
agent1.channels = channel1

# Describe/configure spooldir source1
#agent1.sources.source1.type = spooldir
#agent1.sources.source1.spoolDir = /var/log/apache/flumeSpool1
#agent1.sources.source1.fileHeader = true

# Describe/configure tail -F source1
agent1.sources.source1.type = exec 
agent1.sources.source1.command = tail -n 0 -F /tmp/log.log
agent1.sources.source1.channels = channel1

# Describe/configure nc source1
#agent1.sources.source1.type = netcat
#agent1.sources.source1.bind = localhost
#agent1.sources.source1.port = 44444

#configure host for source
agent1.sources.source1.interceptors = i1 i2
agent1.sources.source1.interceptors.i1.type = host
agent1.sources.source1.interceptors.i1.hostHeader = hostname
agent1.sources.source1.interceptors.i2.type = timestamp
# Describe sink1
#agent1.sinks.sink1.type = logger

agent1.sinks.sink1.type = hdfs
#a1.sinks.k1.channel = c1
#agent1.sinks.sink1.hdfs.path =hdfs://xxx:9000/tmp/tail/%Y-%m-%d/%H%M%S
agent1.sinks.sink1.hdfs.path =hdfs://xxx:9000/tmp/tail/%Y-%m-%d/%H
agent1.sinks.sink1.hdfs.filePrefix = %{hostname}/events-
agent1.sinks.sink1.hdfs.inUsePrefix = .
agent1.sinks.sink1.hdfs.maxOpenFiles = 5000 
agent1.sinks.sink1.hdfs.batchSize= 1000
agent1.sinks.sink1.hdfs.fileType = DataStream
agent1.sinks.sink1.hdfs.writeFormat =Text
agent1.sinks.sink1.hdfs.rollSize = 128000000
agent1.sinks.sink1.hdfs.rollCount = 0
agent1.sinks.sink1.hdfs.rollInterval = 3600
#agent1.sinks.sink1.hdfs.round = true
#agent1.sinks.sink1.hdfs.roundValue = 10
#agent1.sinks.sink1.hdfs.roundUnit = minute
agent1.sinks.sink1.hdfs.useLocalTimeStamp = true

# Use a channel which buffers events in memory
agent1.channels.channel1.type = memory
agent1.channels.channel1.keep-alive = 120
agent1.channels.channel1.capacity = 500000
agent1.channels.channel1.transactionCapacity = 600

# Bind the source and sink to the channel
agent1.sources.source1.channels = channel1
agent1.sinks.sink1.channel = channel1

生产实例:

# The configuration file needs to define the sources, 
# the channels and the sinks.
# Sources, channels and sinks are defined per agent, 
# in this case called 'a
#agent section  
producer.sources = s 
producer.channels = c
producer.sinks = r

#producer.sources.s.type = seq
producer.sources.s.channels = c
producer.sources.s.type = exec
producer.sources.s.command=tail -n 0 -F /usr/local/nginx/nginxlog/access.log
producer.sources.s.deletePolicy=never
#producer.sources.s.type = avro
#producer.sources.s.bind = localhost
#producer.sources.s.port = 10000
# Each sink's type must be defined(给谁了)
#producer.sinks.r.type = avro
#producer.sinks.r.hostname = 10.1.1.100
#producer.sinks.r.port = 20000
producer.sources.source1.interceptors = i1
producer.sources.source1.interceptors.i1.type = timestamp

producer.sinks.r.type = hdfs
producer.sinks.r.hdfs.path = hdfs://localhost:8010/user/hive/warehouse/tail/%Y-%m-%d
producer.sinks.r.hdfs.inUsePrefix = .
producer.sinks.r.hdfs.maxOpenFiles = 5000
producer.sinks.r.hdfs.batchSize= 1000
producer.sinks.r.hdfs.fileType = DataStream
producer.sinks.r.hdfs.writeFormat =Text
producer.sinks.r.hdfs.rollSize = 128000000
producer.sinks.r.hdfs.rollCount = 0
producer.sinks.r.hdfs.rollInterval = 3600
producer.sinks.r.hdfs.useLocalTimeStamp = true
producer.sinks.r.request.required.acks=1
producer.sinks.r.max.message.size=1000000
producer.sinks.r.producer.type=sync
producer.sinks.r.custom.encoding=UTF-8
#Specify the channel the sink should use
producer.sinks.r.channel = c
# Each channel's type is defined.
producer.channels.c.type = memory  
producer.channels.c.capacity = 1000000
producer.channels.c.transactionCapacity = 1000
#producer.channels.c.type=file
#producer.channels.c.checkpointDir=/usr/local/flumeng/checkpointdir/tcpdir/example_agent
#producer.channels.c.dataDirs=/usr/local/flumeng/datadirs/tddirs/example_agen

实例启动脚本:

#发送到hdfs
#./flume-ng agent -c /usr/local/flumeng/apache-flume-1.5.2-bin/conf/ -f /usr/local/flumeng/apache-flume-1.5.2-bin/conf/flume-hdfs.properties -n producer -Dflume.root.logger=INFO,console

相关推荐