新建一个flume的.properties文件 vim flume-conf-kafka2hdfs.properties
# ------------------- 定义数据流----------------------# source的名字
flume2HDFS_agent.sources = source_from_kafka
# channels的名字,建议按照type来命名
flume2HDFS_agent.channels = mem_channel
# sink的名字,建议按照目标来命名
flume2HDFS_agent.sinks = hdfs_sink
#auto.commit.enable = true ## kerberos config ## #flume2HDFS_agent.sinks.hdfs_sink.hdfs.kerberosPrincipal = flume/datanode2.hdfs.alpha.com@OMGHADOOP.COM #flume2HDFS_agent.sinks.hdfs_sink.hdfs.kerberosKeytab = /root/apache-flume-1.6.0-bin/conf/flume.keytab #-------- kafkaSource相关配置-----------------# 定义消息源类型# For each one of the sources, the type is defined
flume2HDFS_agent.sources.source_from_kafka.type = org.apache.flume.source.kafka.KafkaSource
flume2HDFS_agent.sources.source_from_kafka.channels = mem_channel
flume2HDFS_agent.sources.source_from_kafka.batchSize = 5000# 定义kafka所在的地址 #flume2HDFS_agent.sources.source_from_kafka.zookeeperConnect = 10.129.142.46:2181,10.166.141.46:2181,10.166.141.47:2181/testkafka
flume2HDFS_agent.sources.source_from_kafka.kafka.bootstrap.servers = 192.168.2.86:9092,192.168.2.87:9092# 配置消费的kafka topic#flume2HDFS_agent.sources.source_from_kafka.topic = itil_topic_4097
flume2HDFS_agent.sources.source_from_kafka.kafka.topics = mtopic
# 配置消费的kafka groupid#flume2HDFS_agent.sources.source_from_kafka.groupId = flume4097
flume2HDFS_agent.sources.source_from_kafka.kafka.consumer.group.id = flumetest
#---------hdfsSink 相关配置------------------# The channel can be defined as follows.
flume2HDFS_agent.sinks.hdfs_sink.type = hdfs
# 指定sink需要使用的channel的名字,注意这里是channel#Specify the channel the sink should use
flume2HDFS_agent.sinks.hdfs_sink.channel = mem_channel
#flume2HDFS_agent.sinks.hdfs_sink.filePrefix = %{host}
flume2HDFS_agent.sinks.hdfs_sink.hdfs.path = hdfs://192.168.2.xx:8020/tmp/ds=%Y%m%d
#File size to trigger roll, in bytes (0: never roll based on file size)
flume2HDFS_agent.sinks.hdfs_sink.hdfs.rollSize = 0#Number of events written to file before it rolled (0 = never roll based on number of events)
flume2HDFS_agent.sinks.hdfs_sink.hdfs.rollCount = 0
flume2HDFS_agent.sinks.hdfs_sink.hdfs.rollInterval = 3600
flume2HDFS_agent.sinks.hdfs_sink.hdfs.threadsPoolSize = 30#flume2HDFS_agent.sinks.hdfs_sink.hdfs.codeC = gzip #flume2HDFS_agent.sinks.hdfs_sink.hdfs.fileType = CompressedStream
flume2HDFS_agent.sinks.hdfs_sink.hdfs.fileType=DataStream
flume2HDFS_agent.sinks.hdfs_sink.hdfs.writeFormat=Text
#------- memoryChannel相关配置-------------------------# channel类型# Each channel's type is defined.
flume2HDFS_agent.channels.mem_channel.type = memory
# Other config values specific to each type of channel(sink or source) # can be defined as well # channel存储的事件容量# In this case, it specifies the capacity of the memory channel
flume2HDFS_agent.channels.mem_channel.capacity = 100000# 事务容量
flume2HDFS_agent.channels.mem_channel.transactionCapacity = 10000