Flume使用案例之Flume与Flume之间数据传递(单Flume多Channel、Sink)

# 1.agent

a1.sources = r1

a1.sinks = k1 k2

a1.channels = c1 c2

# 将数据流复制给多个channel

a1.sources.r1.selector.type = replicating

# 2.source

a1.sources.r1.type = exec

a1.sources.r1.command = tail -F /opt/Andy

a1.sources.r1.shell = /bin/bash -c

# 3.sink1

a1.sinks.k1.type = avro

a1.sinks.k1.hostname = dtstack_hdfs

a1.sinks.k1.port = 4141

# sink2

a1.sinks.k2.type = avro

a1.sinks.k2.hostname = dtstack_hdfs

a1.sinks.k2.port = 4142

# 4.channel—1

a1.channels.c1.type = memory

a1.channels.c1.capacity = 1000

a1.channels.c1.transactionCapacity = 100

# 4.channel—2

a1.channels.c2.type = memory

a1.channels.c2.capacity = 1000

a1.channels.c2.transactionCapacity = 100

# Bind the source and sink to the channel

a1.sources.r1.channels = c1 c2

a1.sinks.k1.channel = c1

a1.sinks.k2.channel = c2

# 1 agent

a2.sources = r1

a2.sinks = k1

a2.channels = c1

# 2 source

a2.sources.r1.type = avro

a2.sources.r1.bind = dtstack_hdfs

a2.sources.r1.port = 4141

# 3 sink

a2.sinks.k1.type = hdfs

a2.sinks.k1.hdfs.path = hdfs://dtstack_hdfs:9000/flume2/%H

#上传文件的前缀

a2.sinks.k1.hdfs.filePrefix = flume2-

#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

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

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 = 600

#设置每个文件的滚动大小大概是128M

a2.sinks.k1.hdfs.rollSize = 134217700

#文件的滚动与Event数量无关

a2.sinks.k1.hdfs.rollCount = 0

#最小副本数

a2.sinks.k1.hdfs.minBlockReplicas = 1

# 4 channel

a2.channels.c1.type = memory

a2.channels.c1.capacity = 1000

a2.channels.c1.transactionCapacity = 100

#5 Bind

a2.sources.r1.channels = c1

a2.sinks.k1.channel = c1

#1 agent

a3.sources = r1

a3.sinks = k1

a3.channels = c1

# 2 source

a3.sources.r1.type = avro

a3.sources.r1.bind = dtstack_hdfs

a3.sources.r1.port = 4142

#3 sink

a3.sinks.k1.type = file_roll

#备注：此处的文件夹需要先创建好

a3.sinks.k1.sink.directory = /opt/flume3

# 4 channel

a3.channels.c1.type = memory

a3.channels.c1.capacity = 1000

a3.channels.c1.transactionCapacity = 100

# 5 Bind

a3.sources.r1.channels = c1

a3.sinks.k1.channel = c1

$ bin/flume-ng agent --conf conf/ --name a1 --conf-file jobconf/flume1.conf

$ bin/flume-ng agent --conf conf/ --name a2 --conf-file jobconf/flume2.conf

$ bin/flume-ng agent --conf conf/ --name a3 --conf-file jobconf/flume3.conf