三、 Flume-案例二：实时读取本地文件到HDFS

1、 配置文件

# 1 agent
a2.sources = r2
a2.sinks = k2
a2.channels = c2

# 2 source
a2.sources.r2.type = exec
a2.sources.r2.command = tail -F /opt/tmp
a2.sources.r2.shell = /bin/bash -c

# 3 sink
a2.sinks.k2.type = hdfs
a2.sinks.k2.hdfs.path = hdfs://bigdata111:9000/flume/%Y%m%d/%H

#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 = 2
#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 = 1000

# Bind the source and sink to the channel
a2.sources.r2.channels = c2
a2.sinks.k2.channel = c2

2、 结果

image.png

image.png

image.png