flume一个复制和多路复用的配置文件记录

Flume-1：flume-file-flume.conf：

a1.sources = r1
a1.channels = c1 c2
a1.sinks = k1 k2

# 配置一个选择器为复制
a1.sources.r1.selector.type = replicating



#配置sources
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /opt/module/hive/logs/hive.log
a1.sources.r1.shell = /bin/bash -c


#配置c1
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

#配置c2
a1.channels.c2.type = memory
a1.channels.c2.capacity = 1000
a1.channels.c2.transactionCapacity = 100


#配置k1
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = hadoop102
a1.sinks.k1.port = 4141

#配置k2
a1.sinks.k2.type = avro
a1.sinks.k2.hostname = hadoop102
a1.sinks.k2.port = 4142

#连接
a1.sources.r1.channels = c1 c2

a1.sinks.k2.channel = c2
a1.sinks.k1.channel = c1

Flime2：flume-flume-hdfs.conf

a2.sources = r1
a2.channels = c1
a2.sinks = k1




#配置r1
a2.sources.r1.type = avro
a2.sources.r1.bind = hadoop102
a2.sources.r1.port = 4141


#配置c1
a2.channels.c1.type = memory
a2.channels.c1.capacity = 1000
a2.channels.c1.transactionCapacity = 100


#配置k1
a2.sinks.k1.type = hdfs
#路径使用滚动路径
a2.sinks.k1.hdfs.path = hdfs://hadoop102:9820/flume2/%Y%m%d/%H
#上传文件的前缀
a2.sinks.k1.hdfs.filePrefix = logs-
#是否按照时间滚动文件夹
a2.sinks.k1.hdfs.round = true
#多少时间单位创建一个新的文件夹，配合下面的使用表示一个小时
a2.sinks.k1.hdfs.roundValue = 1
#重新定义时间单位
a2.sinks.k1.hdfs.roundUnit = hour
#是否使用本地时间戳，如果使用时间滚动的目录，需要改为true默认是false
a2.sinks.k1.hdfs.useLocalTimeStamp = true
#积攒多少个Event才flush到HDFS一次
a2.sinks.k1.hdfs.batchSize = 100
#设置文件类型，可支持压缩
a2.sinks.k1.hdfs.fileType = DataStream
#多久生成一个新的文件
a2.sinks.k1.hdfs.rollInterval = 60
#设置每个文件的滚动大小，设置一个略小于hdfs块大小的值
a2.sinks.k1.hdfs.rollSize = 134217700
#文件的滚动与Event数量无关，值为0表示无关
a2.sinks.k1.hdfs.rollCount = 0


#连接
a2.sources.r1.channels = c1 
a2.sinks.k1.channel = c1

Flume3：flume-flume-dir.conf

a3.sources = r1
a3.channels = c1
a3.sinks = k1




#配置r1
a3.sources.r1.type = avro
a3.sources.r1.bind = hadoop102
a3.sources.r1.port = 4142


#配置c1
a3.channels.c1.type = memory
a3.channels.c1.capacity = 1000
a3.channels.c1.transactionCapacity = 100


#配置k1
a3.sinks.k1.type = file_roll
a3.sinks.k1.sink.directory = /opt/module/data/flume3


#连接
a3.sources.r1.channels = c1 
a3.sinks.k1.channel = c1