spark学习之Lambda架构日志分析流水线

bin/kafka-server-start.sh config/server.properties

bin/kafka-topics.sh --create --zookeeper vm: 2181 --replication-factor 1 --partitions 1 --topic test

#define c1
agent1.channels.c1.type = memory
agent1.channels.c1.capacity = 2000000
agent1.channels.c1.transactionCapacity = 100
#define c1 end

#define c2
agent1.channels.c2.type = memory
agent1.channels.c2.capacity = 2000000
agent1.channels.c2.transactionCapacity = 100
#define c2 end

#define source monitor a file
agent1.sources.avro-s.type = exec
agent1.sources.avro-s.command = tail -f -n+1 /usr/local/hong/apache-tomcat-8.0.32/logs/localhost_access_log.2016-02-19.txt
agent1.sources.avro-s.channels = c1 c2
agent1.sources.avro-s.threads = 5

# send to hadoop
agent1.sinks.log-hdfs.channel = c1
agent1.sinks.log-hdfs.type = hdfs
agent1.sinks.log-hdfs.hdfs.path = hdfs://vm:9000/flume
agent1.sinks.log-hdfs.hdfs.writeFormat = Text
agent1.sinks.log-hdfs.hdfs.fileType = DataStream
agent1.sinks.log-hdfs.hdfs.rollInterval = 0
agent1.sinks.log-hdfs.hdfs.rollSize = 1000000
agent1.sinks.log-hdfs.hdfs.rollCount = 0
agent1.sinks.log-hdfs.hdfs.batchSize = 1000
agent1.sinks.log-hdfs.hdfs.txnEventMax = 1000
agent1.sinks.log-hdfs.hdfs.callTimeout = 60000
agent1.sinks.log-hdfs.hdfs.appendTimeout = 60000

#send to kafaka
agent1.sinks.log-sink2.type = org.apache.flume.sink.kafka.KafkaSink
agent1.sinks.log-sink2.topic = test
agent1.sinks.log-sink2.brokerList = vm:9092
agent1.sinks.log-sink2.requiredAcks = 1
agent1.sinks.log-sink2.batchSize = 20
agent1.sinks.log-sink2.channel = c2


# Finally, now that we‘ve defined all of our components, tell
# agent1 which ones we want to activate.
agent1.channels = c1 c2
agent1.sources = avro-s
agent1.sinks = log-hdfs log-sink2

./start-dfs.sh

./zkServer.sh start

 flume-ng agent -c conf -f dh.conf -n agent1 -Dflume.root.logger=INFO,console

bin/kafka-console-consumer.sh --zookeeper localhost:2181 --topic test --from-beginning