a1.sources = r1
a1.sinks = k1
a1.channels = c1

a1.sources.r1.type = spooldir
a1.sources.r1.spoolDir =/home/hadoop/log
a1.sources.r1.fileHeader = true


a1.sinks.k1.type = hdfs
a1.sinks.k1.channel = c1
a1.sinks.k1.hdfs.path = /flume/events/%Y-%m-%d/
a1.sinks.k1.hdfs.filePrefix = events-
a1.sinks.k1.hdfs.round = true
a1.sinks.k1.hdfs.roundValue = 10
a1.sinks.k1.hdfs.roundUnit = second
a1.sinks.k1.hdfs.rollInterval = 2
a1.sinks.k1.hdfs.rollSize = 10240
a1.sinks.k1.hdfs.rollCount = 256
a1.sinks.k1.hdfs.batchSize = 50
a1.sinks.k1.hdfs.useLocalTimeStamp = true

a1.sinks.k1.hdfs.fileType = DataStream

a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

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

是監控資料夾，看一下寫在hdfs之後的樣子，速度很快。

需要注意的是：我監控的是整個資料夾，寫完之後，flume會將這個資料夾的名字在後面加上一個.COMPLMETED
加上了這個字尾之後，下次就不會監控這個檔案夾了。我之前測試的時候，沒注意到這一點，發現一直都沒往hdfs上寫檔案，我還傻傻等半天。

後面我又修改了配置檔案，如果不修改的話，那麼生成太多的檔案，執行MapReduce程式會非常地卡。

a1.sources = r1
a1.sinks = k1
a1.channels = c1

a1.sources.r1.type = spooldir
a1.sources.r1.spoolDir =/home/hadoop/log
a1.sources.r1.fileHeader = true


a1.sinks.k1.type = hdfs
a1.sinks.k1.channel = c1
a1.sinks.k1.hdfs.path = /flume/events/%Y-%m-%d/
a1.sinks.k1.hdfs.filePrefix = events-
a1.sinks.k1.hdfs.round = true
a1.sinks.k1.hdfs.roundValue = 10
a1.sinks.k1.hdfs.roundUnit = second
a1.sinks.k1.hdfs.rollInterval = 3
a1.sinks.k1.hdfs.rollSize = 1048576
a1.sinks.k1.hdfs.rollCount = 0
a1.sinks.k1.hdfs.batchSize = 50
a1.sinks.k1.hdfs.useLocalTimeStamp = true

a1.sinks.k1.hdfs.fileType = DataStream

a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

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