flume实时采集数据+Kafka+shell脚本+定时任务crontab

1.flume实时采集数据

修改 Flume agent config 文件

#cd 到flume的conf目录
[root@localhost conf]# cd /usr/hdp/2.6.4.0-91/flume/conf
# 编辑配置文件
[root@localhost conf]# vim flume-Aerospace.conf

a1.sources = r1
a1.sinks = k1
a1.channels = c1
 
a1.sources.r1.type = exec
a1.sources.r1.command = tail -f /usr/local/dataaccess.log

a1.sources.r1.channels = c1
a1.sinks.k1.type = org.apache.flume.sink.kafka.KafkaSink
#设置Kafka的Topic 
a1.sinks.k1.kafka.topic = AerospaceBigBigData
#根据具体的情况进行调整
a1.sinks.k1.kafka.bootstrap.servers = slave2:6667,slave1:6667,master:6667
a1.sinks.k1.kafka.flumeBatchSize = 10
a1.sinks.k1.kafka.batchSize=10
a1.sinks.k1.kafka.producer.acks = -1
a1.sinks.k1.kafka.producer.linger.ms = 1000

a1.channels.c1.type = memory
agent.channels.c1.capacity=100000 
agent.channels.c1.transactionCapacity=100

a1.sinks.k1.channel = c1

启动flume命令

#启动flum