2)Flume的具體配置如下:
(1)在CM管理頁面hadoop102上flume的配置中找到代理名稱改爲a1
a1
102 103
a1.sources=r1
a1.channels=c1 c2
a1.sinks=k1 k2
configure source
a1.sources.r1.type = TAILDIR
a1.sources.r1.positionFile = /opt/module/flume/log_position.json
a1.sources.r1.filegroups = f1
a1.sources.r1.filegroups.f1 = /tmp/logs/app.+
a1.sources.r1.fileHeader = true
a1.sources.r1.channels = c1 c2
#interceptor
a1.sources.r1.interceptors = i1 i2
a1.sources.r1.interceptors.i1.type = com.atguigu.flume.interceptor.LogETLInterceptorBuilder
selector
a1.sources.r1.selector.type = multiplexing
a1.sources.r1.selector.header = topic
a1.sources.r1.selector.mapping.topic_start = c1
a1.sources.r1.selector.mapping.topic_event = c2
configure channel
a1.channels.c1.type = memory
a1.channels.c1.capacity=10000
a1.channels.c1.byteCapacityBufferPercentage=20
a1.channels.c2.type = memory
a1.channels.c2.capacity=10000
a1.channels.c2.byteCapacityBufferPercentage=20
configure sink
start-sink
a1.sinks.k1.type = org.apache.flume.sink.kafka.KafkaSink
a1.sinks.k1.kafka.topic = topic_start
a1.sinks.k1.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
a1.sinks.k1.kafka.flumeBatchSize = 2000
a1.sinks.k1.kafka.producer.acks = 1
a1.sinks.k1.channel = c1
event-sink
a1.sinks.k2.type = org.apache.flume.sink.kafka.KafkaSink
a1.sinks.k2.kafka.topic = topic_event
a1.sinks.k2.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
a1.sinks.k2.kafka.flumeBatchSize = 2000
a1.sinks.k2.kafka.producer.acks = 1
a1.sinks.k2.channel = c2