[大数据]Flume实践案例

目录

安装flume：http://t.csdn.cn/J1Pnn

一、采集目录中的新文件到HDFS中

1.Flume要想将数据输出到HDFS，必须持有Hadoop相关jar包

2.创建flume-file-hdfs.conf文件

二、采集文件新增内容到HDFS中

1.需求分析

2.实现

?三、多级agent串联

1.配置hadoop02监听服务端

2.在其它节点配置监听客户端

安装flume：http://t.csdn.cn/J1Pnn

一、采集目录中的新文件到HDFS中

文档对应说明： Flume 1.7.0 User Guide — Apache Flume

?采集需求：使用flume监听整个目录的文件

1.Flume要想将数据输出到HDFS，必须持有Hadoop相关jar包

将commons-configuration-1.6.jar、hadoop-auth-2.7.3.jar、hadoop-common-2.7.3.jar、hadoop-hdfs-2.7.3.jar、commons-io-2.4.jar、htrace-core-3.1.0-incubating.jar拷贝到/opt/module/flume/lib文件夹下。

1.上面jar包的地址

[root@hadoop01 hadoop]# pwd
/opt/module/hadoop-2.7.3/share/hadoop    #上面jar包的地址

2.commons-configuration-1.6.jar，commons-io-2.4.jar，htrace-core-3.1.0-incubating.jar，hadoop-auth-2.7.3.jar

[root@hadoop01 lib]# pwd
/opt/module/hadoop-2.7.3/share/hadoop/tools/lib
[root@hadoop01 lib]# cp commons-configuration-1.6.jar /opt/module/flume/lib/
[root@hadoop01 lib]# cp commons-io-2.4.jar /opt/module/flume/lib/
[root@hadoop01 lib]# cp htrace-core-3.1.0-incubating.jar /opt/module/flume/lib/
[root@hadoop01 lib]# cp hadoop-auth-2.7.3.jar /opt/module/flume/lib/

3.hadoop-common-2.7.3.jar

[root@hadoop01 common]# pwd
/opt/module/hadoop-2.7.3/share/hadoop/common
[root@hadoop01 common]# cp hadoop-common-2.7.3.jar /opt/module/flume/lib/

4.hadoop-hdfs-2.7.3.jar

[root@hadoop01 hdfs]# pwd
/opt/module/hadoop-2.7.3/share/hadoop/hdfs
[root@hadoop01 hdfs]# cp hadoop-hdfs-2.7.3.jar /opt/module/flume/lib/

2.创建flume-file-hdfs.conf文件

1.创建文件

[root@hadoop01 flume]# touch dir-hdfs.conf

2.编辑文件?

[root@hadoop01 flume]# vim dir-hdfs.conf 

#定义三大组件的名称
ag1.sources = source1
ag1.sinks = sink1
ag1.channels = channel1

# 配置source组件
ag1.sources.source1.type = spooldir
ag1.sources.source1.spoolDir = /root/log/
ag1.sources.source1.fileSuffix=.FINISHED
#ag1.sources.source1.deserializer.maxLineLength=5120

# 配置sink组件
ag1.sinks.sink1.type = hdfs
ag1.sinks.sink1.hdfs.path =hdfs://hadoop01:9000/access_log/%y-%m-%d/%H-%M
ag1.sinks.sink1.hdfs.filePrefix = app_log
ag1.sinks.sink1.hdfs.fileSuffix = .log
ag1.sinks.sink1.hdfs.batchSize= 100
ag1.sinks.sink1.hdfs.fileType = DataStream
ag1.sinks.sink1.hdfs.writeFormat =Text

## roll：滚动切换：控制写文件的切换规则
## 按文件体积（字节）来切
ag1.sinks.sink1.hdfs.rollSize = 512000
## 按event条数切     
ag1.sinks.sink1.hdfs.rollCount = 1000000
## 按时间间隔切换文件
ag1.sinks.sink1.hdfs.rollInterval = 60

## 控制生成目录的规则
ag1.sinks.sink1.hdfs.round = true
ag1.sinks.sink1.hdfs.roundValue = 10
ag1.sinks.sink1.hdfs.roundUnit = minute

ag1.sinks.sink1.hdfs.useLocalTimeStamp = true

# channel组件配置
ag1.channels.channel1.type = memory
## event条数
ag1.channels.channel1.capacity = 500000
##flume事务控制所需要的缓存容量600条event
ag1.channels.channel1.transactionCapacity = 600

# 绑定source、channel和sink之间的连接
ag1.sources.source1.channels = channel1
ag1.sinks.sink1.channel = channel1

3.启动Flume采集命令(测试阶段下使用)

[root@hadoop01 flume]# bin/flume-ng agent -c conf -f dir-hdfs.conf -n ag1 -Dflume.root.logger=INFO,console

重要说明： 在使用Spooling Directory Source时

1)??? 不要在监控目录中创建并持续修改文件

2)??? 采集完成的文件会以.FINISHED结尾

3)??? 被监控文件夹每600毫秒扫描一次文件变动

二、采集文件新增内容到HDFS中

采集需求:比如业务系统使用log4j生成日志,日志内容不断添加,需要把追加的日志实时采集到hdfs存储.

1.需求分析

根据需求首先定义以下3大要素:

采集源: 即是source--监控文件内容的更新: exec 'tail -F file'

下沉目标: 即是sink --HDFS文件系统 : hdfs sink

source与sink的传递通道-- channel, 可用file channel 也可以用内存channel.

2.实现

[root@hadoop01 ~]# cd /root/log/
[root@hadoop01 log]# touch access.log
[root@hadoop01 flume]# touch file-hdfs.conf 
[root@hadoop01 flume]# vim file-hdfs.conf 

#定义三大组件的名称
ag1.sources = source1
ag1.sinks = sink1
ag1.channels = channel1

# 配置source组件
ag1.sources.source1.type = exec
ag1.sources.source1.command = tail -F /root/log/access.log

# 配置sink组件
ag1.sinks.sink1.type = hdfs
ag1.sinks.sink1.hdfs.path =hdfs://hadoop01:9000/access_log/%y-%m-%d
ag1.sinks.sink1.hdfs.filePrefix = app_log
ag1.sinks.sink1.hdfs.fileSuffix = .log
ag1.sinks.sink1.hdfs.batchSize= 100
ag1.sinks.sink1.hdfs.fileType = DataStream
ag1.sinks.sink1.hdfs.writeFormat =Text

## roll：滚动切换：控制写文件的切换规则
## 按文件体积（字节）来切   
ag1.sinks.sink1.hdfs.rollSize = 512000
## 按event条数切
ag1.sinks.sink1.hdfs.rollCount = 1000000
## 按时间间隔切换文件
ag1.sinks.sink1.hdfs.rollInterval = 60

## 控制生成目录的规则
ag1.sinks.sink1.hdfs.round = true
ag1.sinks.sink1.hdfs.roundValue = 10
ag1.sinks.sink1.hdfs.roundUnit = minute
ag1.sinks.sink1.hdfs.useLocalTimeStamp = true

# channel组件配置
ag1.channels.channel1.type = memory
## event条数
ag1.channels.channel1.capacity = 500000
##flume事务控制所需要的缓存容量600条event
ag1.channels.channel1.transactionCapacity = 600

# 绑定source、channel和sink之间的连接
ag1.sources.source1.channels = channel1
ag1.sinks.sink1.channel = channel1

3.写入数据测试

??

?三、多级agent串联

1.配置hadoop02监听服务端

1.配置文件avro-hdfs.conf

[root@hadoop02 flume]# vim avro-hdfs.conf 

#定义三大组件的名称
ag1.sources = source1
ag1.sinks = sink1
ag1.channels = channel1

# 配置source组件,该source的avro组件是一个接收者的服务
ag1.sources.source1.type = avro
ag1.sources.source1.bind = hadoop02
ag1.sources.source1.port = 4141

# 配置sink组件
ag1.sinks.sink1.type = hdfs
ag1.sinks.sink1.hdfs.path =hdfs://hadoop01:9000/flume/taildata/%y-%m-%d/
ag1.sinks.sink1.hdfs.filePrefix = tail-
ag1.sinks.sink1.hdfs.round = true
ag1.sinks.sink1.hdfs.roundValue = 24
ag1.sinks.sink1.hdfs.roundUnit = hour
ag1.sinks.sink1.hdfs.rollInterval = 0
ag1.sinks.sink1.hdfs.rollSize = 0
ag1.sinks.sink1.hdfs.rollCount = 50
ag1.sinks.sink1.hdfs.batchSize = 10
ag1.sinks.sink1.hdfs.useLocalTimeStamp = true
#生成的文件类型，默认是Sequencefile，可用DataStream，则为普通文本
ag1.sinks.sink1.hdfs.fileType = DataStream

# channel组件配置
ag1.channels.channel1.type = memory
## event条数
ag1.channels.channel1.capacity = 1000
##flume事务控制所需要的缓存容量100条event
ag1.channels.channel1.transactionCapacity = 100

# 绑定source、channel和sink之间的连接
ag1.sources.source1.channels = channel1
ag1.sinks.sink1.channel = channel1

2.启动

[root@hadoop02 flume]# bin/flume-ng agent -c conf -f avro-hdfs.conf -n ag1 -Dflume.root.logger=INFO,console 

3.查看是否启动监听

[root@hadoop02 ~]# netstat -nltp

4.查看flume进程详情

[root@hadoop02 ~]# jps -m

2.在其它节点配置监听客户端

1.配置文件tail-avro.conf

[root@hadoop01 flume]# vim tail-avro.conf 

#定义三大组件的名称
ag1.sources = source1
ag1.sinks = sink1
ag1.channels = channel1

# 配置source组件
ag1.sources.source1.type = exec
ag1.sources.source1.command = tail -F /root/log/access.log

# 配置sink组件
ag1.sinks.sink1.type = avro
ag1.sinks.sink1.hostname = hadoop02
ag1.sinks.sink1.port = 4141
ag1.sinks.sink1.batch-size = 2

# channel组件配置
ag1.channels.channel1.type = memory
## event条数
ag1.channels.channel1.capacity = 1000
##flume事务控制所需要的缓存容量100条event
ag1.channels.channel1.transactionCapacity = 100

# 绑定source、channel和sink之间的连接
ag1.sources.source1.channels = channel1
ag1.sinks.sink1.channel = channel1

2.启动进行测试

[root@hadoop01 flume]#  bin/flume-ng agent -c conf -f tail-avro.conf -n ag1 -Dflume.root.logger=INFO,console

3.发送数据测试

[root@hadoop01 flume]# while true; do echo `date` >> access.log; sleep 0.1; done

4.查看数据