Flume汇入数据到Hive
方法一:汇入到Hive指定的HDFS路径中:
1.在hive中创建数据库
create database flume;
2.创建flume_into_hive表
create external table flume_into_hive(name string,age int) partitioned by (dt string) row format delimited fields terminated by ' ' location '/user/hive/warehouse/flume.db/flume_into_hive';
3.在root/flume_hive目录下创建hive.log
mkdir root/flume_hive
Vi hive.log
写入数据
4.在flume conf/路径下创建配置文件 flume-into-hive-1.conf
cd /opt/software/flume
agent.sources=r1
agent.channels=c1
agent.sinks=s1
agent.sources.r1.type=exec
agent.sources.r1.command=tail -F /root/flume_hive/hive.log
agent.channels.c1.type=memory
agent.channels.capacity=1000
agent.channels.c1.transactionCapacity=100
agent.sinks.s1.type=hdfs
agent.sinks.s1.hdfs.path= hdfs://node01:9000/user/hive/warehouse/flume.db/flume_into_hive/dt=%Y%m%d
agent.sinks.s1.hdfs.filePrefix = upload-
agent.sinks.s1.hdfs.fileSuffix=.txt
#是否按照时间滚动文件夹
agent.sinks.s1.hdfs.round = true
#多少时间单位创建一个新的文件夹
agent.sinks.s1.hdfs.roundValue = 1
#重新定义时间单位
agent.sinks.s1.hdfs.roundUnit = hour
#是否使用本地时间戳
agent.sinks.s1.hdfs.useLocalTimeStamp = true
#积攒多少个 Event 才 flush 到 HDFS 一次
agent.sinks.s1.hdfs.batchSize = 100
#设置文件类型,可支持压缩
agent.sinks.s1.hdfs.fileType = DataStream
agent.sinks.s1.hdfs.writeFormat=Text
#多久生成一个新的文件
agent.sinks.s1.hdfs.rollInterval = 60
#设置每个文件的滚动大小大概是 128M
agent.sinks.s1.hdfs.rollSize =