Hadoop2.7实战v1.0之Flume1.6.0搭建(Http Source-->Memory Chanel --> Hdfs Sink)
1.查看系统是否已经配置jdk1.7.0
点击(此处)折叠或打开
[root@xxx-01 jdk1.7.0_25]# bin/java -version
java version "1.7.0_25"
Java(TM) SE Runtime Environment (build 1.7.0_25-b15)
Java HotSpot(TM) 64-Bit Server VM (build 23.25-b01, mixed mode)
[root@xxx-01 jdk1.7.0_25]# pwd
/usr/java/jdk1.7.0_25
[root@xxx-01 jdk1.7.0_25]
java version "1.7.0_25"
Java(TM) SE Runtime Environment (build 1.7.0_25-b15)
Java HotSpot(TM) 64-Bit Server VM (build 23.25-b01, mixed mode)
[root@xxx-01 jdk1.7.0_25]# pwd
/usr/java/jdk1.7.0_25
[root@xxx-01 jdk1.7.0_25]
##假如没有配置jdk1.7以上的版本,请参考 http://blog.itpub.net/30089851/viewspace-1994585/ 的 "安装JDK"
2.下载和解压flume1.6.0
点击(此处)折叠或打开
- [root@xxx-01 local]# wget http://ftp.cuhk.edu.hk/pub/packages/apache.org/flume/1.6.0/apache-flume-1.6.0-bin.tar.gz
- [root@xxx-01 local]# tar zxvf apache-flume-1.6.0-bin.tar.gz
- [root@xxx-01 local]# cd apache-flume-1.6.0-bin
- [root@xxx-01 apache-flume-1.6.0-bin]# ll
- total 140
- drwxr-xr-x 2 template games 4096 May 21 17:32 bin
- -rw-r--r-- 1 template games 69856 May 9 2015 CHANGELOG
- drwxr-xr-x 2 template games 4096 May 21 17:32 conf
- -rw-r--r-- 1 template games 6172 May 9 2015 DEVNOTES
- drwxr-xr-x 10 template games 4096 May 12 2015 docs
- drwxr-xr-x 2 root root 4096 May 21 17:32 lib
- -rw-r--r-- 1 template games 25903 May 9 2015 LICENSE
- -rw-r--r-- 1 template games 249 May 9 2015 NOTICE
- -rw-r--r-- 1 template games 1779 May 9 2015 README
- -rw-r--r-- 1 template games 1585 May 9 2015 RELEASE-NOTES
- drwxr-xr-x 2 root root 4096 May 21 17:32 tools
- [root@xxx-01 apache-flume-1.6.0-bin]#
- [root@xxx-01 apache-flume-1.6.0-bin]# cd conf
- [root@xxx-01 conf]# ls -l
- total 16
- -rw-r--r-- 1 template games 1661 May 9 2015 flume-conf.properties.template
- -rw-r--r-- 1 template games 1110 May 9 2015 flume-env.ps1.template
- -rw-r--r-- 1 template games 1214 May 9 2015 flume-env.sh.template
- -rw-r--r-- 1 template games 3107 May 9 2015 log4j.properties
- [root@xxx-01 conf]#
- [root@xxx-01 conf]# cp flume-env.sh.template flume-env.sh
- [root@xxx-01 conf]# cp flume-conf.properties.template flume-conf.properties
- [root@xxx-01 conf]#
3.配置flume-env.sh 和环境变量
点击(此处)折叠或打开
- [root@xxx-01 conf]# vi flume-env.sh
- export JAVA_HOME=/usr/java/jdk1.7.0_25
- export HADOOP_HOME=/opt/cloudera/parcels/CDH/lib/hadoop
- [root@xxx-01 ~]# vi /etc/profile
- export JAVA_HOME="/usr/java/jdk1.7.0_25"
- export FLUME_HOME=/usr/local/apache-flume-1.6.0-bin
- export FLUME_CONF_DIR=$FLUME_HOME/conf
-
- export PATH=$FLUME_HOME/bin:$JAVA_HOME/bin:$PATH
-
- [root@xxx-01 ~]# source /etc/profile
- [root@xxx-01 ~]# echo $FLUME_HOME
- /usr/local/apache-flume-1.6.0-bin
4.配置flume-conf.properties
点击(此处)折叠或打开
- [root@xxx-01 conf]# vi flume-conf.properties
- # Name the components on this agent
- a1.sources = r1
- a1.sinks = k1
- a1.channels = c1
-
- # Describe/configure the source
###默认http handle的格式是json - a1.sources.r1.type = http
- a1.sources.r1.bind = 本机ip
- a1.sources.r1.port = 5140
-
- a1.sources.r1.fileHeader = false
- #a1.sources.r1.deserializer.outputCharset=UTF-8
-
- a1.sources.r1.interceptors =i1
- a1.sources.r1.interceptors.i1.type = timestamp
-
- # Describe the sink
- a1.sinks.k1.type = hdfs
- a1.sinks.k1.channel = c1
- # 可以指定hdfs ha的fs.defaultFS配置信息,而不是指定其中一台master的,关键是当前flume机器要有hadoop环境(因为要加载hadoop jar包)
- #和在flume机器上这三个hadoop-env.sh hdfs-site.xml core-site.xml文件要与 日志存储的hdfs配置一致.
- a1.sinks.k1.hdfs.path = hdfs://nameservice1/testwjp/%Y-%m-%d/%H
- #a1.sinks.k1.hdfs.path = hdfs://xxx-01:8022/testwjp/%Y-%m-%d/%H
- a1.sinks.k1.hdfs.filePrefix = logs
- a1.sinks.k1.hdfs.inUsePrefix = .
-
- a1.sinks.k1.hdfs.rollInterval = 0
- ### roll 16 m = 16777216 bytes
- a1.sinks.k1.hdfs.rollSize = 16777216
- a1.sinks.k1.hdfs.rollCount = 0
- a1.sinks.k1.hdfs.batchSize = 1000
- a1.sinks.k1.hdfs.writeFormat = text
-
- ###A. plain text format 普通文本格式
- a1.sinks.k1.hdfs.fileType = DataStream
-
- ###B. compressed plain text to zip format 压缩格式
- #a1.sinks.k1.hdfs.fileType = CompressedStream
- #a1.sinks.k1.hdfs.codeC = bzip2
-
- # Use a channel which buffers events in memory
- a1.channels.c1.type = memory
- a1.channels.c1.keep-alive = 30
- a1.channels.c1.capacity = 100000
- a1.channels.c1.transactionCapacity = 1000
- # Bind the source and sink to the channel
- a1.sources.r1.channels = c1
- a1.sinks.k1.channel = c1
5.启动agent
[root@xxx-01 apache-flume-1.6.0-bin]#bin/flume-ng agent -c conf -f conf/http-memory-hdfs.properties -n a1 -Dflume.root.logger=INFO,console
###后台启动
nohup bin/flume-ng agent -c conf -f conf/http-memory-hdfs.properties -n a1 -Dflume.root.logger=INFO,console &
6.测试端A
[root@xxx-01 bin]# curl -X POST -d'[{"headers":{"h1":"v1","h2":"v2"},"body":"hello body"}]' http://10.168.11.13:5140
7.测试端B Fox浏览器+HttpRequester工具
URL:http://本机ip:5140
Type:POST
Content Type: application/json
Content:
点击(此处)折叠或打开
[{
"headers" : {
"timestamp" : "1",
"host" : "random_host1.example.com"
},
"body" : "random_body1"
},
{
"headers" : {
"timestamp" : "2",
"host" : "random_host2.example.com"
},
"body" : "random_body2"
}]
"headers" : {
"timestamp" : "1",
"host" : "random_host1.example.com"
},
"body" : "random_body1"
},
{
"headers" : {
"timestamp" : "2",
"host" : "random_host2.example.com"
},
"body" : "random_body2"
}]
###单击"Submit"按钮,返回状态 200,标识内容post成功.
8.验证数据是否sink到hdfs上
命令行:hadoop fs -ls hdfs://nameservice1/testwjp/
Web:http://x.x.x.x:50070/
官方文档: http://flume.apache.org/FlumeUserGuide.html
