Flume与kafka集成

tailDir   启动: 

bin/flume-ng agent --conf conf --conf-file job/taildirSource-kafka.conf   --name a1 -Dflume.root.logger=INFO,console

flume#

taildirSource-kafka.conf

#taildir source   http://flume.apache.org/releases/content/1.9.0/FlumeUserGuide.html#kafka-channel
#为各个组件命名
a1.sources = r1
a1.channels = c1

#声明source
a1.sources.r1.type = TAILDIR
a1.sources.r1.filegroups = f1
#监控的目录 /log/app.*
a1.sources.r1.filegroups.f1 = /home/sea/Desktop/xx/log/.*log.*
#开启断点续传，不配置 默认开启
a1.sources.r1.positionFile= /home/sea/Desktop/xx/history/taildir_position.json
a1.sources.r1.fileHeader = true



#kafka channel 
#channels
a1.channels.c1.type = org.apache.flume.channel.kafka.KafkaChannel
a1.channels.c1.kafka.bootstrap.servers = hadoop001:9092,hadoop004:9092,hadoop005:9092
a1.channels.c1.kafka.topic = topic_log
a1.channels.c1.parseAsFlumeEvent = false
# 配置生产者的ack为1
a1.channels.c1.kafka.producer.acks = 1
# 配置生产者的批大小为1000
a1.channels.c1.kafka.producer.batch.size = 1000
a1.channels.c1.kafka.producer.linger.ms = 5000


#绑定source和channel以及sink和channel的关系
a1.sources.r1.channels = c1

 

 

 

 

tail -f

1）配置flume(flume-kafka.conf)
# define
a1.sources = r1
a1.sinks = k1
a1.channels = c1

# source
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F -c +0 /opt/module/datas/flume.log
a1.sources.r1.shell = /bin/bash -c

# sink
a1.sinks.k1.type = org.apache.flume.sink.kafka.KafkaSink
a1.sinks.k1.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
a1.sinks.k1.kafka.topic = first
a1.sinks.k1.kafka.flumeBatchSize = 20
a1.sinks.k1.kafka.producer.acks = 1
a1.sinks.k1.kafka.producer.linger.ms = 1

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

# bind
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1




2） 启动kafkaIDEA消费者

3） 进入flume根目录下，启动flume

$ bin/flume-ng agent -c conf/ -n a1 -f jobs/flume-kafka.conf

4） 向 /opt/module/datas/flume.log里追加数据，查看kafka消费者消费情况

$ echo hello > /opt/module/datas/flume.log