sh cca175-problem-07-step-02-flume.sh

Posted 2021-05-07

mkdir flume-logs
cd flume-logs

// create flume configuration file

# Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /opt/gen_logs/logs/access.log


# Describe the sink
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path = /user/cloudera/problem7/step2
a1.sinks.k1.hdfs.fileSuffix = .log
a1.sinks.k1.hdfs.writeFormat = Text
a1.sinks.k1.hdfs.fileType = DataStream

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 200

# Bind the source and sink to the channel
a1.sources.r1.channels = c1

a1.sinks.k1.channel = c1

// create hdfs sink directory
hadoop fs -mkdir /user/cloudera/problem7/sink

// Run the flume-agent
flume-ng agent --name a1 --conf . --conf-file f.config