Flume 收集Nginx日志到Hdfs Tail-to-hdfs sink

andyyuduo

nginx，access.log日志约8000条/s，每100w条数据约253M,需要2min

agent1.sources = source1
agent1.sinks = sink1
agent1.channels = channel1
# Describe/configure spooldir source1
#agent1.sources.source1.type = spooldir
#agent1.sources.source1.spoolDir = /var/log/apache/flumeSpool1
#agent1.sources.source1.fileHeader = true
# Describe/configure tail -F source1
agent1.sources.source1.type = exec
agent1.sources.source1.command = tail -F /tmp/log.log
agent1.sources.source1.channels = channel1
# Describe/configure nc source1
#agent1.sources.source1.type = netcat
#agent1.sources.source1.bind = localhost
#agent1.sources.source1.port = 44444
#configure host for source
agent1.sources.source1.interceptors = i1
agent1.sources.source1.interceptors.i1.type = host
agent1.sources.source1.interceptors.i1.hostHeader = hostname
# Describe sink1
#agent1.sinks.sink1.type = logger
agent1.sinks.sink1.type = hdfs
#a1.sinks.k1.channel = c1
#agent1.sinks.sink1.hdfs.path =hdfs://xxx:9000/tmp/tail/%y-%m-%d/%H%M%S
agent1.sinks.sink1.hdfs.path =hdfs://xxx:9000/tmp/tail/%y-%m-%d/%H
agent1.sinks.sink1.hdfs.filePrefix = %{hostname}/events-
agent1.sinks.sink1.hdfs.maxOpenFiles = 5000
agent1.sinks.sink1.hdfs.batchSize= 500
agent1.sinks.sink1.hdfs.fileType = DataStream
agent1.sinks.sink1.hdfs.writeFormat =Text
agent1.sinks.sink1.hdfs.rollSize = 0
agent1.sinks.sink1.hdfs.rollCount = 1000000
agent1.sinks.sink1.hdfs.rollInterval = 600
#agent1.sinks.sink1.hdfs.round = true
#agent1.sinks.sink1.hdfs.roundValue = 10
#agent1.sinks.sink1.hdfs.roundUnit = minute
agent1.sinks.sink1.hdfs.useLocalTimeStamp = true
# Use a channel which buffers events in memory
agent1.channels.channel1.type = memory
agent1.channels.channel1.keep-alive = 120
agent1.channels.channel1.capacity = 500000
agent1.channels.channel1.transactionCapacity = 600
# Bind the source and sink to the channel
agent1.sources.source1.channels = channel1
agent1.sinks.sink1.channel = channel1