用flume从日志服务器中实时抽数据的案例

日志服务器flume配置文件

# example.conf: A single-node Flume configuration

# Name the components on this agent
# The name of the agent is defined as a1.
a1.sources = r1
a1.sinks = k1
a1.channels = c1

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

#a1.sources.r1.type= spooldir
#a1.sources.r1.spoolDir= /opt/flume

# Describe the sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = 172.21.16.28
a1.sinks.k1.port =44444

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000000
a1.channels.c1.transactionCapacity = 1000000

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

 

cdh flume-hdfs配置文件

#agent命名
a1.sources = r1
a1.sinks = k1
a1.channels = c1

#sources配置
a1.sources.r1.type = avro
a1.sources.r1.bind = 172.21.16.28
a1.sources.r1.port = 44444

#channels配置
a1.channels.c1.type = memory
a1.channels.c1.capacity = 20000
a1.channels.c1.transactionCapacity = 20000
a1.channels.c1.byteCapacityBufferPercentage = 40
a1.channels.c1.byteCapacity = 8000000000

#sinks配置
#hdfs
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path = hdfs://172.21.16.28:8020/flume/fenjilog-%Y%m%d
a1.sinks.k1.hdfs.filePrefix=%H
a1.sinks.k1.hdfs.fileSuffix=.log
a1.sinks.k1.hdfs.rollInterval = 3600
a1.sinks.k1.hdfs.rollSize = 0
a1.sinks.k1.hdfs.rollCount = 0
a1.sinks.k1.hdfs.batchSize = 5000
a1.sinks.k1.hdfs.useLocalTimeStamp = true
a1.sinks.k1.hdfs.fileType = DataStream
a1.sinks.k1.hdfs.inUsePrefix = .

#进行绑定
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1