1 配置tail-hdfs.conf文件
a1.sources = r1
a1.sinks = k1
a1.channels = c1
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /root/logs/test.log
a1.sinks.k1.type = hdfs
a1.sinks.k1.channel = c1
a1.sinks.k1.hdfs.path = /flume/tailout/%y-%m-%d/%H-%M/
a1.sinks.k1.hdfs.filePrefix = itcast-
a1.sinks.k1.hdfs.round = true
a1.sinks.k1.hdfs.roundValue = 10
a1.sinks.k1.hdfs.roundUnit = minute
a1.sinks.k1.hdfs.rollInterval = 5
a1.sinks.k1.hdfs.rollSize = 1014
a1.sinks.k1.hdfs.rollCount = 3
a1.sinks.k1.hdfs.batchSize = 1
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
2 启动flume
bin/flume-ng agent -c conf -f conf/tail-hdfs.conf -n a1 -Dflume.root.logger= INFO,console
3 创建要监控的文件夹
mkdir -p /root/logs
4 创建要监控的文件
touch /root/logs/test.log
5 使用shell模拟数据源源不断产生
while true ; do date >> /root/logs/test.log; sleep 0.5; done
或者:
while true
do
date >> /root/logs/test.log
sleep 0.5
done
6 测试
2020-06-23 04:53:02,932 ( SinkRunner-PollingRunner-DefaultSinkProcessor) [ INFO - org.apache.flume.sink.hdfs.HDFSDataStream.configure( HDFSDataStream.java:57) ] Serializer = TEXT, UseRawLocalFileSystem = false
2020-06-23 04:53:02,943 ( SinkRunner-PollingRunner-DefaultSinkProcessor) [ INFO - org.apache.flume.sink.hdfs.BucketWriter.open( BucketWriter.java:251) ] Creating /flume/tailout/20-06-23/04-50//itcast-.1592859182933.tmp
2020-06-23 04:53:07,963 ( hdfs-k1-roll-timer-0) [ INFO - org.apache.flume.sink.hdfs.BucketWriter.close( BucketWriter.java:393) ] Closing /flume/tailout/20-06-23/04-50//itcast-.1592859182933.tmp
2020-06-23 04:53:07,975 ( hdfs-k1-call-runner-3) [ INFO - org.apache.flume.sink.hdfs.BucketWriter$8 .call( BucketWriter.java:655) ] Renaming /flume/tailout/20-06-23/04-50/itcast-.1592859182933.tmp to /flume/tailout/20-06-23/04-50/itcast-.1592859182933
2020-06-23 04:53:07,977 ( hdfs-k1-roll-timer-0) [ INFO - org.apache.flume.sink.hdfs.HDFSEventSink$1 .run( HDFSEventSink.java:382) ] Writer callback called.
7 扩展 conf中配置属性解释
a1.sinks.k1.hdfs.rollInterval = 3
a1.sinks.k1.hdfs.rollSize = 20
a1.sinks.k1.hdfs.rollCount = 5
a1.sinks.k1.hdfs.round = true
a1.sinks.k1.hdfs.roundValue = 10
a1.sinks.k1.hdfs.roundUnit = minute