#
# Source: Loghub
# Sink: HDFS
#
agent.sources = slssource
agent.sinks = hdfssink
agent.channels = memoryChannel
# Configure the source:
agent.sources.slssource.type = com.aliyun.loghub.flume.source.LoghubSource
agent.sources.slssource.endpoint = https://us-west-1.log.aliyuncs.com
agent.sources.slssource.project = XXXXXX
agent.sources.slssource.logstore = XXXXXXX
agent.sources.slssource.accessKeyId =XXXXXXX
agent.sources.slssource.accessKey = XXXXXXX
agent.sources.slssource.consumerGroup =log_test_group_1
agent.sources.slssource.columns = @timestamp,client_ip,country,document_id,duration,fields,geoip,input,isNewUser,language,log,meta,method,offset,params,params_2,prospector,request_query,responseCode,source,spm,system,system_version,tags,trace_id,url_path,user_id
agent.sources.slssource.deserializer = DELIMITED
agent.sources.slssource.separatorChar = ;
agent.sources.slssource.initialPosition = end
# Describe the sink:
agent.sinks.hdfssink.type = hdfs
agent.sinks.hdfssink.hdfs.path = hdfs://ip:port/flume/20%y-%m-%d
agent.sinks.hdfssink.hdfs.writeFormat = Text
#agent.sinks.hdfssink.hdfs.round = true
#agent.sinks.hdfssink.hdfs.roundValue = 10
#agent.sinks.hdfssink.hdfs.roundUnit = minute
agent.sinks.hdfssink.hdfs.rollSize = 10485760
agent.sinks.hdfssink.hdfs.rollCount = 0
agent.sinks.hdfssink.hdfs.fileType = DataStream
agent.sinks.hdfssink.hdfs.useLocalTimeStamp = true
agent.sinks.hdfssink.hdfs.minBlockReplicas = 1
agent.sinks.hdfssink.hdfs.rollInterval = 0
agent.sinks.hdfssink.hdfs.idleTimeout = 1000
# Configure a channel that buffers events in memory:
agent.channels.memoryChannel.type = memory
agent.channels.memoryChannel.capacity = 40000
agent.channels.memoryChannel.transactionCapacity = 2000
# Bind the source and sink to the channel:
agent.sources.slssource.channels = memoryChannel
agent.sinks.hdfssink.channel = memoryChannel
flume配置文件:消费阿里云loghub落地到hdfs,按100M滚动
最新推荐文章于 2024-01-09 22:07:52 发布