1 搭建
1.1 解压
tar -zxf /opt/software/apache-flume-1.9.0-bin.tar.gz -C /opt/module/ mv /opt/module/apache-flume-1.9.0-bin /opt/module/flume
1.2 删除不兼容包
rm /opt/module/flume/lib/guava-11.0.2.jar
1.3 测试
1.3.1、安装nc
yum install -y nc
1.3.2、创建agent配置文件
cd /opt/module/flume/job vim flume-netcat-logger.conf
# Name the components on this agent a1.sources = r1 a1.sinks = k1 a1.channels = c1 # Describe/configure the source a1.sources.r1.type = netcat a1.sources.r1.bind = localhost a1.sources.r1.port = 44444 # Describe the sink a1.sinks.k1.type = logger # Use a channel which buffers events in memory a1.channels.c1.type = memory a1.channels.c1.capacity = 1000 a1.channels.c1.transactionCapacity = 100 # Bind the source and sink to the channel a1.sources.r1.channels = c1 a1.sinks.k1.channel = c1
1.3.3、启动
vi flume.sh
/opt/module/flume/bin/flume-ng agent --conf /opt/module/flume/conf/ --name a1 --conf-file /opt/module/flume/job/flume-netcat-logger.conf -Dflume.root.logger=INFO,console
sh flume.sh
参数说明:
--conf/-c:表示配置文件存储在conf/目录
--name/-n:表示给agent起名为a1
--conf-file/-f:flume本次启动读取的配置文件是在job文件夹下的flume-telnet.conf文件。
-Dflume.root.logger=INFO,console :-D表示flume运行时动态修改flume.root.logger参数属性值,并将控制台日志打印级别设置为INFO级别。日志级别包括:log、info、warn、error。
1.3.4、启动nc输入数据
nc localhost 44444
1.3.5、检查数据
2 使用
2.1、Flume数据输出到HDFS
2.1.1、flume文本
vim flume-file-hdfs.conf
# Name the components on this agent a2.sources = r2 a2.sinks = k2 a2.channels = c2 # Describe/configure the source a2.sources.r2.type = exec a2.sources.r2.command = tail -F /opt/module/hive/logs/hive.log # Describe the sink a2.sinks.k2.type = hdfs a2.sinks.k2.hdfs.path = hdfs://bigdata:9820/flume/%Y%m%d/%H #上传文件的前缀 a2.sinks.k2.hdfs.filePrefix = logs- #是否按照时间滚动文件夹 a2.sinks.k2.hdfs.round = true #多少时间单位创建一个新的文件夹 a2.sinks.k2.hdfs.roundValue = 1 #重新定义时间单位 a2.sinks.k2.hdfs.roundUnit = hour #是否使用本地时间戳 a2.sinks.k2.hdfs.useLocalTimeStamp = true #积攒多少个Event才flush到HDFS一次 a2.sinks.k2.hdfs.batchSize = 100 #设置文件类型,可支持压缩 a2.sinks.k2.hdfs.fileType = DataStream #多久生成一个新的文件 a2.sinks.k2.hdfs.rollInterval = 60 #设置每个文件的滚动大小 a2.sinks.k2.hdfs.rollSize = 134217700 #文件的滚动与Event数量无关 a2.sinks.k2.hdfs.rollCount = 0 # Use a channel which buffers events in memory a2.channels.c2.type = memory a2.channels.c2.capacity = 1000 a2.channels.c2.transactionCapacity = 100 # Bind the source and sink to the channel a2.sources.r2.channels = c2 a2.sinks.k2.channel = c2
2.1.2、启动脚本
vim flume-file-hdfs.sh
/opt/module/flume/bin/flume-ng agent --conf /opt/module/flume/conf/ --name a2 --conf-file /opt/module/flume/job/flume-file-hdfs.conf -Dflume.root.logger=INFO,console
sh flume-file-hdfs.sh
2.1.3、hdfs页面验证数据
2.2、Flume监听整个目录的实时追加文件,并上传至HDFS
2.2.1、flume文本
vim flume-taildir-hdfs.conf
a3.sources = r3 a3.sinks = k3 a3.channels = c3 # Describe/configure the source a3.sources.r3.type = TAILDIR a3.sources.r3.positionFile = /opt/module/flume/tail_dir.json a3.sources.r3.filegroups = f1 f2 a3.sources.r3.filegroups.f1 = /opt/module/flume/files/.*file.* a3.sources.r3.filegroups.f2 = /opt/module/flume/files2/.*log.* # Describe the sink a3.sinks.k3.type = hdfs a3.sinks.k3.hdfs.path = hdfs://bigdata:9820/flume/upload2/%Y%m%d/%H #上传文件的前缀 a3.sinks.k3.hdfs.filePrefix = upload- #是否按照时间滚动文件夹 a3.sinks.k3.hdfs.round = true #多少时间单位创建一个新的文件夹 a3.sinks.k3.hdfs.roundValue = 1 #重新定义时间单位 a3.sinks.k3.hdfs.roundUnit = hour #是否使用本地时间戳 a3.sinks.k3.hdfs.useLocalTimeStamp = true #积攒多少个Event才flush到HDFS一次 a3.sinks.k3.hdfs.batchSize = 100 #设置文件类型,可支持压缩 a3.sinks.k3.hdfs.fileType = DataStream #多久生成一个新的文件 a3.sinks.k3.hdfs.rollInterval = 60 #设置每个文件的滚动大小大概是128M a3.sinks.k3.hdfs.rollSize = 134217700 #文件的滚动与Event数量无关 a3.sinks.k3.hdfs.rollCount = 0 # Use a channel which buffers events in memory a3.channels.c3.type = memory a3.channels.c3.capacity = 1000 a3.channels.c3.transactionCapacity = 100 # Bind the source and sink to the channel a3.sources.r3.channels = c3 a3.sinks.k3.channel = c3
2.2.2、启动脚本
vi flume-taildir-hdfs.sh
/opt/module/flume/bin/flume-ng agent --conf /opt/module/flume/conf/ --name a3 --conf-file /opt/module/flume/job/flume-taildir-hdfs.conf -Dflume.root.logger=INFO,console
sh flume-taildir-hdfs.sh
2.2.3、测试验证数据
在/opt/module/flume目录下创建files和files2文件夹
在files下
echo hello >> file1.txt echo hello >> file2.txt
在files2下
echo hello >> log1.txt echo hello >> log2.txt