Flume使用案例之实时读取目录到HDFS

#1 Agent

a3.sources = r3

a3.sinks = k3

a3.channels = c3

#2 source

a3.sources.r3.type = spooldir

a3.sources.r3.spoolDir = /opt/module/flume1.8.0/upload

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)

# 3 sink

a3.sinks.k3.type = hdfs

a3.sinks.k3.hdfs.path = hdfs://dtstack_hdfs:9000/flume/%H

#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

#最小副本数

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

/opt/module/flume1.8.0/bin/flume-ng agent \

--conf /opt/module/flume1.8.0/conf/ \

--name a3 \

--conf-file /opt/module/flume1.8.0/jobconf/flume-dir.conf