flume到hdfs和kafka


flume-conf.properties的配置

a1.sources = r1
a1.sinks = k1 sink-hdfs
a1.channels = c1 chn-hdfs

a1.sources.r1.type = exec
a1.sources.r1.command = tail -f /home/abc/robotResume/jupiter/jupiter_http_log/logback.log
a1.sources.r1.inputCharset = UTF-8
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = timestamp

a1.sinks.k1.type=org.apache.flume.sink.kafka.KafkaSink
a1.sinks.k1.kafka.topic=nginx-resume
a1.sinks.k1.kafka.bootstrap.servers=localhost:9092
a1.sinks.k1.kafka.flumeBatchSize=100
a1.sinks.k1.kafka.producer.acks=1

a1.sinks.sink-hdfs.type=hdfs
a1.sinks.sink-hdfs.hdfs.fileType=DataStream
a1.sinks.sink-hdfs.hdfs.writeFormat=Text
a1.sinks.sink-hdfs.hdfs.path=hdfs://localhost:7000/flumeResume/data/%Y-%m-%d
a1.sinks.sink-hdfs.hdfs.rollInterval=0
a1.sinks.sink-hdfs.hdfs.rollSize=10240000
a1.sinks.sink-hdfs.hdfs.rollCount=0
a1.sinks.sink-hdfs.hdfs.idleTimeout=60

a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100
a1.channels.chn-hdfs.type=memory
a1.channels.chn-hdfs.capacity=1000
a1.channels.chn-hdfs.transactionCapacity=100

a1.sources.r1.channels = c1 chn-hdfs
a1.sinks.k1.channel = c1
a1.sinks.sink-hdfs.channel=chn-hdfs