【发布时间】:2016-08-24 02:17:29
【问题描述】:
我正在尝试使用 Flume-ng 获取 128MB 的日志信息并将其放入 HDFS 中的文件中。但是 HDFS 滚动选项不起作用。 Flume-ng 每秒发送日志文件。如何修复 flume.conf 文件?
agent01.sources = avroGenSrc
agent01.channels = memoryChannel hdfsChannel
agent01.sinks = fileSink hadoopSink
# For each one of the sources, the type is defined
agent01.sources.avroGenSrc.type = avro
agent01.sources.avroGenSrc.bind = dev-hadoop03.ncl
agent01.sources.avroGenSrc.port = 3333
# The channel can be defined as follows.
agent01.sources.avroGenSrc.channels = memoryChannel hdfsChannel
# Each sink's type must be defined
agent01.sinks.fileSink.type = file_roll
agent01.sinks.fileSink.sink.directory = /home1/irteam/flume/data
agent01.sinks.fileSink.sink.rollInterval = 3600
agent01.sinks.fileSink.sink.batchSize = 100
#Specify the channel the sink should use
agent01.sinks.fileSink.channel = memoryChannel
agent01.sinks.hadoopSink.type = hdfs
agent01.sinks.hadoopSink.hdfs.useLocalTimeStamp = true
agent01.sinks.hadoopSink.hdfs.path = hdfs://dev-hadoop04.ncl:9000/user/hive/warehouse/raw_logs/year=%Y/month=%m/day=%d
agent01.sinks.hadoopSink.hdfs.filePrefix = AccessLog.%Y-%m-%d.%Hh
agent01.sinks.hadoopSink.hdfs.fileType = DataStream
agent01.sinks.hadoopSink.hdfs.writeFormat = Text
agent01.sinks.hadoopSink.hdfs.rollInterval = 0
agent01.sinks.hadoopSink.hdfs.rollSize = 134217728
agent01.sinks.hadoopSink.hdfs.rollCount = 0
#Specify the channel the sink should use
agent01.sinks.hadoopSink.channel = hdfsChannel
# Each channel's type is defined.
agent01.channels.memoryChannel.type = memory
agent01.channels.hdfsChannel.type = memory
# Other config values specific to each type of channel(sink or source)
# can be defined as well
# In this case, it specifies the capacity of the memory channel
agent01.channels.memoryChannel.capacity = 100000
agent01.channels.memoryChannel.transactionCapacity = 10000
agent01.channels.hdfsChannel.capacity = 100000
agent01.channels.hdfsChannel.transactionCapacity = 10000
【问题讨论】: