a1.channels.c1.type = org.apache.flume.channel.kafka.KafkaChannel a1.channels.c1.kafka.bootstrap.servers = 10.26.22.124:8092,10.26.22.121:8092,10.26.22.120:8092,10.26.22.102:8092,10.26.22.122:8092 a1.channels.c1.kafka.topic = api_searchlog_novel a1.channels.c1.kafka.consumer.group.id = flume2kafka # Define an Avro source called r1 on a1 and tell it # to bind to 0.0.0.0:41414. Connect it to channel c1. #注意这里分出2个channel出来,一个是到k1,一个到k2 #如果这里只出一个channel c1的话,下面2个sink channel都为c1,则消息就会随机分到2个sink上,而不是2个sink都有一份 a1.sources.r1.channels = c1 a1.sources.r1.type = exec a1.sources.r1.command = tail -F /log/resin-books/words/access.log a1.sources.r1.restart = true a1.sources.r1.batchSize = 10000 a1.sources.r1.interceptors = i1 i2 i3 a1.sources.r1.interceptors.i1.type = timestamp a1.sources.r1.interceptors.i2.type = host a1.sources.r1.interceptors.i2.useIP = false a1.sources.r1.interceptors.i3.type = regex_filter a1.sources.r1.interceptors.i3.regex = ^\\s*$ a1.sources.r1.interceptors.i3.excludeEvents = true #默认是replicationg,还有multiplexer #a1.sources.r1.selector.type = replicationg # Finally, now that we've defined all of our components, tell # a1 which ones we want to activate. a1.sources = r1 r2 r3 a1.channels = c1 c2 c3 a1.sinks = #########searchrecord apirs的BI统计搜索日志 a1.channels.c2.type = org.apache.flume.channel.kafka.KafkaChannel a1.channels.c2.kafka.bootstrap.servers = 10.26.22.124:8092,10.26.22.121:8092,10.26.22.120:8092,10.26.22.102:8092,10.26.22.122:8092 a1.channels.c2.kafka.topic = api_searchrecord_bi a1.channels.c2.kafka.consumer.group.id = flume2kafka # Define an Avro source called r1 on a1 and tell it #注意这里分出2个channel出来,一个是到k1,一个到k2 #如果这里只出一个channel c1的话,下面2个sink channel都为c1,则消息就会随机分到2个sink上,而不是2个sink都有一份 a1.sources.r2.channels = c2 a1.sources.r2.type = exec a1.sources.r2.command = tail -F /log/resin-books/search/searchrecord.log a1.sources.r2.restart = true a1.sources.r2.batchSize = 10000 a1.sources.r2.interceptors = i1 i2 i3 a1.sources.r2.interceptors.i1.type = timestamp a1.sources.r2.interceptors.i2.type = host a1.sources.r2.interceptors.i2.useIP = false a1.sources.r2.interceptors.i3.type = regex_filter a1.sources.r2.interceptors.i3.regex = ^\\s*$ a1.sources.r2.interceptors.i3.excludeEvents = true #默认是replicationg,还有multiplexer #a1.sources.r1.selector.type = replicationg #####bookincharge a1.channels.c3.type = org.apache.flume.channel.kafka.KafkaChannel a1.channels.c3.kafka.bootstrap.servers = 10.26.22.124:8092,10.26.22.121:8092,10.26.22.120:8092,10.26.22.102:8092,10.26.22.122:8092 a1.channels.c3.kafka.topic = api_bookincharge_novel a1.channels.c3.kafka.consumer.group.id = flume2kafka # Define an Avro source called r1 on a1 and tell it # to bind to 0.0.0.0:41414. Connect it to channel c1. a1.sources.r3.channels = c3 a1.sources.r3.type = exec a1.sources.r3.command = tail -F /data/log/bookincharge/bookincharge.log a1.sources.r3.restart = true a1.sources.r3.batchSize = 10000 a1.sources.r3.interceptors = i1 i2 i3 a1.sources.r3.interceptors.i1.type = timestamp a1.sources.r3.interceptors.i2.type = host a1.sources.r3.interceptors.i2.useIP = false a1.sources.r3.interceptors.i3.type = regex_filter a1.sources.r3.interceptors.i3.regex = ^\\s*$ a1.sources.r3.interceptors.i3.excludeEvents = true #默认是replicationg,还有multiplexer #a1.sources.r2.selector.type = replicationg