【大数据架构】大数据数据仓库与数据中台架构

a1.sources=r1
a1.channels=c1 c2

# 配置 source
a1.sources.r1.type = TAILDIR
a1.sources.r1.positionFile = /opt/module/flume/test/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.gupao.flume.interceptor.LogETLInterceptor$Builder
a1.sources.r1.interceptors.i2.type = com.gupao.flume.interceptor.LogTypeInterceptor$Builder

# 多路复用选择器，replicating（复制选择器）
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

# 配置 channel
a1.channels.c1.type = org.apache.flume.channel.kafka.KafkaChannel
a1.channels.c1.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
a1.channels.c1.kafka.topic = topic_start
a1.channels.c1.parseAsFlumeEvent = false
a1.channels.c1.kafka.consumer.group.id = flume-consumer

a1.channels.c2.type = org.apache.flume.channel.kafka.KafkaChannel
a1.channels.c2.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
a1.channels.c2.kafka.topic = topic_event
a1.channels.c2.parseAsFlumeEvent = false
a1.channels.c2.kafka.consumer.group.id = flume-consumer

# 组件
a1.sources=r1 r2
a1.channels=c1 c2
a1.sinks=k1 k2

# source1
a1.sources.r1.type = org.apache.flume.source.kafka.KafkaSource
a1.sources.r1.batchSize = 5000
a1.sources.r1.batchDurationMillis = 2000
a1.sources.r1.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
a1.sources.r1.kafka.topics=topic_start

# source2
a1.sources.r2.type = org.apache.flume.source.kafka.KafkaSource
a1.sources.r2.batchSize = 5000
a1.sources.r2.batchDurationMillis = 2000
a1.sources.r2.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
a1.sources.r2.kafka.topics=topic_event

# channel1
a1.channels.c1.type = file
a1.channels.c1.checkpointDir = /opt/module/flume/checkpoint/behavior1
a1.channels.c1.dataDirs = /opt/module/flume/data/behavior1/
a1.channels.c1.maxFileSize = 2146435071
a1.channels.c1.capacity = 1000000
a1.channels.c1.keep-alive = 6

# channel2
a1.channels.c2.type = file
a1.channels.c2.checkpointDir = /opt/module/flume/checkpoint/behavior2
a1.channels.c2.dataDirs = /opt/module/flume/data/behavior2/
a1.channels.c2.maxFileSize = 2146435071
a1.channels.c2.capacity = 1000000
a1.channels.c2.keep-alive = 6

# sink1
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path = /origin_data/gmall/log/topic_start/%Y-%m-%d
a1.sinks.k1.hdfs.filePrefix = logstart-
a1.sinks.k1.hdfs.round = true
a1.sinks.k1.hdfs.roundValue = 10
a1.sinks.k1.hdfs.roundUnit = second

# sink2
a1.sinks.k2.type = hdfs
a1.sinks.k2.hdfs.path = /origin_data/gmall/log/topic_event/%Y-%m-%d
a1.sinks.k2.hdfs.filePrefix = logevent-
a1.sinks.k2.hdfs.round = true
a1.sinks.k2.hdfs.roundValue = 10
a1.sinks.k2.hdfs.roundUnit = second

# 不要产生大量小文件（默认128M）
a1.sinks.k1.hdfs.rollInterval = 10
a1.sinks.k1.hdfs.rollSize = 134217728
# 写入文件的events数量
a1.sinks.k1.hdfs.rollCount = 0

a1.sinks.k2.hdfs.rollInterval = 10
a1.sinks.k2.hdfs.rollSize = 134217728
a1.sinks.k2.hdfs.rollCount = 0

# 控制输出文件是原始文件还是压缩文件
a1.sinks.k1.hdfs.fileType = CompressedStream 
a1.sinks.k2.hdfs.fileType = CompressedStream 

a1.sinks.k1.hdfs.codeC = lzop
a1.sinks.k2.hdfs.codeC = lzop

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

a1.sources.r2.channels = c2
a1.sinks.k2.channel= c2