Flume 收集Nginx日志 tail-to-avro avro-to-file

gaoke

nginx，access.log日志约1.6w条/s，每1000w条数据约2000M,需要10min


tail-to-avro

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 logger  sink1
#agent1.sinks.sink1.type = logger
# Describe avro  sink1
agent1.sinks.sink1.type = avro
agent1.sinks.sink1.hostname = 172.16.10.175
agent1.sinks.sink1.port = 4545
# 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
avro-to-rollfile
agent1.sources = source1
agent1.sinks = sink1
agent1.channels = channel1
# Describe/configure avro source
agent1.sources.source1.type = avro
agent1.sources.source1.bind = 0.0.0.0
agent1.sources.source1.port = 4545

# Describe logger sink1
#agent1.sinks.sink1.type = logger
# Describe file sink1
agent1.sinks.sink1.type = file_roll
agent1.sinks.sink1.sink.directory = /var/log/flume
# 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