1、将flume-ng-1.5.0-cdh5.3.6.tar.gz使用WinSCP拷贝到sparkproject1的/usr/local目录下。
2、对flume进行解压缩:tar -zxvf flume-ng-1.5.0-cdh5.3.6.tar.gz
3、对flume目录进行重命名:mv apache-flume-1.5.0-cdh5.3.6-bin flume
4、配置scala相关的环境变量
vi ~/.bashrc
export FLUME_HOME=/usr/local/flume
export FLUME_CONF_DIR=$FLUME_HOME/conf
export PATH=$FLUME_HOME/bin
source ~/.bashrc
vi /usr/local/flume/conf/flume-conf.properties #agent1表示代理名称 agent1.sources=source1 agent1.sinks=sink1 agent1.channels=channel1 #配置source1 agent1.sources.source1.type=spooldir agent1.sources.source1.spoolDir=/usr/local/logs //设置监控的文件夹 agent1.sources.source1.channels=channel1 agent1.sources.source1.fileHeader = false agent1.sources.source1.interceptors = i1 agent1.sources.source1.interceptors.i1.type = timestamp #配置channel1 agent1.channels.channel1.type=file agent1.channels.channel1.checkpointDir=/usr/local/logs_tmp_cp agent1.channels.channel1.dataDirs=/usr/local/logs_tmp #配置sink1 agent1.sinks.sink1.type=hdfs agent1.sinks.sink1.hdfs.path=hdfs://sparkproject1:9000/logs //监控日志写入到hdfs agent1.sinks.sink1.hdfs.fileType=DataStream agent1.sinks.sink1.hdfs.writeFormat=TEXT agent1.sinks.sink1.hdfs.rollInterval=1 agent1.sinks.sink1.channel=channel1 agent1.sinks.sink1.hdfs.filePrefix=%Y-%m-%d
|