私がやろうとしていること: 64 MB のデータごとに 1 つのファイルだけを書き込みたいと思います。
Flume が行っていること: 10 イベントごとに新しいファイルを作成する
私の設定:
a1.sources = r1
a1.sinks = k1
a1.channels = c1
# Describe/configure the source
a1.sources.r1.type = netcat
a1.sources.r1.bind = localhost
a1.sources.r1.port = 44444
# Describe the sink
a1.sinks.k1.type = hdfs
a1.sinks.k1.channel = c1
a1.sinks.k1.hdfs.path = hdfs://lawn-128-61-47-216.lawn.gatech.edu:9000/flume/events/
a1.sinks.k1.hdfs.filePrefix = events-
a1.sinks.k1.hdfs.round = true
a1.sinks.k1.hdfs.roundValue = 10
a1.sinks.k1.hdfs.roundUnit = minute
a1.sinks.k1.hdfs.fileType = DataStream
a1.sinks.k1.hdfs.writeFormat = Text
a1.sinks.k1.hdfs.hdfs.rollInterval = 0
a1.sinks.k1.hdfs.hdfs.rollSize = 67108864
a1.sinks.k1.hdfs.hdfs.rollCount = 0
a1.sinks.k1.hdfs.idleTimeout = 0
a1.sinks.k1.hdfs.batchSize = 1000
a1.sinks.k1.hdfs.serializer = text
a1.sinks.k1.sink.serializer.appendNewline = true
# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 1000
# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1