flume的使用：扇入-flume與flume之間數據傳遞，多flume彙總數據到單flume

1.圖示

2.新建配置文件：
(1)flume-1.conf

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

# 2 source
a1.sources.r1.type = netcat
a1.sources.r1.bind = hadoop2
a1.sources.r1.port = 55555

#3 sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = hadoop4
a1.sinks.k1.port = 4141

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

# 5 Bind
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

(2)flume-2.conf

# 1 agent
a2.sources = r1
a2.sinks = k1
a2.channels = c1

# 2 source
a2.sources.r1.type = exec
a2.sources.r1.command = tail -F /opt/plus
a2.sources.r1.shell = /bin/bash -c

# 3 sink
a2.sinks.k1.type = avro
a2.sinks.k1.hostname = hadoop4
a2.sinks.k1.port = 4141

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

# 5. Bind
a2.sources.tail-file.channels = c1
a2.sinks.avro4.channel = c1

(3)flume-3.conf

# 1 agent
a3.sources = r1
a3.sinks = k1
a3.channels = c1

# 2 source
a3.sources.r1.type = avro
a3.sources.r1.bind = hadoop4
a3.sources.r1.port = 4141

# 3 sink
a3.sinks.k1.type = hdfs
a3.sinks.k1.hdfs.path = hdfs://hadoop2:9000/flume3/%H
#上傳文件的前綴
a3.sinks.k1.hdfs.filePrefix = flume3-
#是否按照時間滾動文件夾
a3.sinks.k1.hdfs.round = true
#多少時間單位創建一個新的文件夾
a3.sinks.k1.hdfs.roundValue = 1
#重新定義時間單位
a3.sinks.k1.hdfs.roundUnit = hour
#是否使用本地時間戳
a3.sinks.k1.hdfs.useLocalTimeStamp = true
#積攢多少個Event才flush到HDFS一次
a3.sinks.k1.hdfs.batchSize = 100
#設置文件類型，可支持壓縮
a3.sinks.k1.hdfs.fileType = DataStream
#多久生成一個新的文件
a3.sinks.k1.hdfs.rollInterval = 600
#設置每個文件的滾動大小大概是128M
a3.sinks.k1.hdfs.rollSize = 134217700
#文件的滾動與Event數量無關
a3.sinks.k1.hdfs.rollCount = 0
#最小冗餘數
a3.sinks.k1.hdfs.minBlockReplicas = 1

# 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

3.測試

(1)依次啓動flume-3.conf,flume-2.conf,flume-1.conf
(2)改變文件，查看結果