mkdir /data/UnifiedLog/;
cd /data/UnifiedLog/;
wget http://mirror.bit.edu.cn/apache/flume/1.8.0/apache-flume-1.8.0-bin.tar.gz;
tar -xvf apache-flume-1.8.0-bin.tar.gz;
ln -s apache-flume-1.8.0-bin flume;
export FlumeHome=/data/UnifiedLog/flume;

[root@d ~]# cat /data/UnifiedLog/flume/conf/httpSourceApp.conf
a1.sources=r1
a1.sinks=k1
a1.channels=c1

a1.sources.r1.type=http
a1.sources.r1.bind=0.0.0.0
a1.sources.r1.port=50000
a1.sources.r1.channels=c1

a1.sinks.k1.channel=c1
#a1.sinks.k1.type = com.product.FlumeApp #自己打包jar
a1.sinks.k1.type = file_roll # 无自定义jar
a1.sinks.k1.sink.directory = /data/UnifiedLog/log
a1.sinks.k1.batchSize=1
#a1.sinks.k1.pathManager=%y%m%d%H%M%S
a1.sinks.k1.pathManager.extension=log
a1.sinks.k1.pathManager.prefix=webTrack
a1.sinks.k1.rollInterval=0
a1.sinks.k1.sink.serializer = text

a1.channels.c1.type=memory
#a1.channels.c1.capacity=1000
#a1.channels.c1.transactionCapacity=100
a1.channels.c1.capacity=8
a1.channels.c1.transactionCapacity=4

[root@d ~]#

成功启动进程;
$FlumeHome/bin/flume-ng agent -c $FlumeHome/conf/ -f $FlumeHome/conf/httpSourceApp.conf -n a1 -Dflume.root.logger=INFO,console;

[root@d ~]# $FlumeHome/bin/flume-ng agent -c $FlumeHome/conf/ -f $FlumeHome/conf/httpSourceApp.conf -n a1 -Dflume.root.logger=INFO,console;
Info: Including Hive libraries found via () for Hive access
+ exec /usr/java/jdk1.8.0_101/bin/java -Xmx20m -Dflume.root.logger=INFO,console -cp '/data/UnifiedLog/flume/conf:/data/UnifiedLog/flume/lib/*:/lib/*' -Djava.library.path= org.apache.flume.node.Application -f /data/UnifiedLog/flume/conf/httpSourceApp.conf -n a1
2018-10-30 16:35:30,092 (lifecycleSupervisor-1-0) [INFO - org.apache.flume.node.PollingPropertiesFileConfigurationProvider.start(PollingPropertiesFileConfigurationProvider.java:62)] Configuration provider starting
2018-10-30 16:35:30,097 (conf-file-poller-0) [INFO - org.apache.flume.node.PollingPropertiesFileConfigurationProvider$FileWatcherRunnable.run(PollingPropertiesFileConfigurationProvider.java:134)] Reloading configuration file:/data/UnifiedLog/flume/conf/httpSourceApp.conf
2018-10-30 16:35:30,106 (conf-file-poller-0) [INFO - org.apache.flume.conf.FlumeConfiguration$AgentConfiguration.addProperty(FlumeConfiguration.java:1016)] Processing:k1
2018-10-30 16:35:30,107 (conf-file-poller-0) [INFO - org.apache.flume.conf.FlumeConfiguration$AgentConfiguration.addProperty(FlumeConfiguration.java:930)] Added sinks: k1 Agent: a1
2018-10-30 16:35:30,107 (conf-file-poller-0) [INFO - org.apache.flume.conf.FlumeConfiguration$AgentConfiguration.addProperty(FlumeConfiguration.java:1016)] Processing:k1
2018-10-30 16:35:30,107 (conf-file-poller-0) [INFO - org.apache.flume.conf.FlumeConfiguration$AgentConfiguration.addProperty(FlumeConfiguration.java:1016)] Processing:k1
2018-10-30 16:35:30,107 (conf-file-poller-0) [INFO - org.apache.flume.conf.FlumeConfiguration$AgentConfiguration.addProperty(FlumeConfiguration.java:1016)] Processing:k1
2018-10-30 16:35:30,107 (conf-file-poller-0) [INFO - org.apache.flume.conf.FlumeConfiguration$AgentConfiguration.addProperty(FlumeConfiguration.java:1016)] Processing:k1
2018-10-30 16:35:30,107 (conf-file-poller-0) [INFO - org.apache.flume.conf.FlumeConfiguration$AgentConfiguration.addProperty(FlumeConfiguration.java:1016)] Processing:k1
2018-10-30 16:35:30,107 (conf-file-poller-0) [INFO - org.apache.flume.conf.FlumeConfiguration$AgentConfiguration.addProperty(FlumeConfiguration.java:1016)] Processing:k1
2018-10-30 16:35:30,108 (conf-file-poller-0) [INFO - org.apache.flume.conf.FlumeConfiguration$AgentConfiguration.addProperty(FlumeConfiguration.java:1016)] Processing:k1
2018-10-30 16:35:30,124 (conf-file-poller-0) [INFO - org.apache.flume.conf.FlumeConfiguration.validateConfiguration(FlumeConfiguration.java:140)] Post-validation flume configuration contains configuration for agents: [a1]
2018-10-30 16:35:30,124 (conf-file-poller-0) [INFO - org.apache.flume.node.AbstractConfigurationProvider.loadChannels(AbstractConfigurationProvider.java:147)] Creating channels
2018-10-30 16:35:30,131 (conf-file-poller-0) [INFO - org.apache.flume.channel.DefaultChannelFactory.create(DefaultChannelFactory.java:42)] Creating instance of channel c1 type memory
2018-10-30 16:35:30,136 (conf-file-poller-0) [INFO - org.apache.flume.node.AbstractConfigurationProvider.loadChannels(AbstractConfigurationProvider.java:201)] Created channel c1
2018-10-30 16:35:30,137 (conf-file-poller-0) [INFO - org.apache.flume.source.DefaultSourceFactory.create(DefaultSourceFactory.java:41)] Creating instance of source r1, type http
2018-10-30 16:35:30,201 (conf-file-poller-0) [INFO - org.apache.flume.sink.DefaultSinkFactory.create(DefaultSinkFactory.java:42)] Creating instance of sink: k1, type: file_roll
2018-10-30 16:35:30,208 (conf-file-poller-0) [INFO - org.apache.flume.node.AbstractConfigurationProvider.getConfiguration(AbstractConfigurationProvider.java:116)] Channel c1 connected to [r1, k1]
2018-10-30 16:35:30,216 (conf-file-poller-0) [INFO - org.apache.flume.node.Application.startAllComponents(Application.java:137)] Starting new configuration:{ sourceRunners:{r1=EventDrivenSourceRunner: { source:org.apache.flume.source.http.HTTPSource{name:r1,state:IDLE} }} sinkRunners:{k1=SinkRunner: { policy:org.apache.flume.sink.DefaultSinkProcessor@6918ccb0 counterGroup:{ name:null counters:{} } }} channels:{c1=org.apache.flume.channel.MemoryChannel{name: c1}} }
2018-10-30 16:35:30,227 (conf-file-poller-0) [INFO - org.apache.flume.node.Application.startAllComponents(Application.java:144)] Starting Channel c1
2018-10-30 16:35:30,279 (lifecycleSupervisor-1-0) [INFO - org.apache.flume.instrumentation.MonitoredCounterGroup.register(MonitoredCounterGroup.java:119)] Monitored counter group for type: CHANNEL, name: c1: Successfully registered new MBean.
2018-10-30 16:35:30,279 (lifecycleSupervisor-1-0) [INFO - org.apache.flume.instrumentation.MonitoredCounterGroup.start(MonitoredCounterGroup.java:95)] Component type: CHANNEL, name: c1 started
2018-10-30 16:35:30,280 (conf-file-poller-0) [INFO - org.apache.flume.node.Application.startAllComponents(Application.java:171)] Starting Sink k1
2018-10-30 16:35:30,280 (lifecycleSupervisor-1-1) [INFO - org.apache.flume.sink.RollingFileSink.start(RollingFileSink.java:110)] Starting org.apache.flume.sink.RollingFileSink{name:k1, channel:c1}...
2018-10-30 16:35:30,280 (conf-file-poller-0) [INFO - org.apache.flume.node.Application.startAllComponents(Application.java:182)] Starting Source r1
2018-10-30 16:35:30,281 (lifecycleSupervisor-1-1) [INFO - org.apache.flume.instrumentation.MonitoredCounterGroup.register(MonitoredCounterGroup.java:119)] Monitored counter group for type: SINK, name: k1: Successfully registered new MBean.
2018-10-30 16:35:30,281 (lifecycleSupervisor-1-1) [INFO - org.apache.flume.instrumentation.MonitoredCounterGroup.start(MonitoredCounterGroup.java:95)] Component type: SINK, name: k1 started
2018-10-30 16:35:30,282 (lifecycleSupervisor-1-1) [INFO - org.apache.flume.sink.RollingFileSink.start(RollingFileSink.java:142)] RollingFileSink k1 started.
2018-10-30 16:35:30,301 (lifecycleSupervisor-1-0) [INFO - org.mortbay.log.Slf4jLog.info(Slf4jLog.java:67)] Logging to org.slf4j.impl.Log4jLoggerAdapter(org.mortbay.log) via org.mortbay.log.Slf4jLog
2018-10-30 16:35:30,338 (lifecycleSupervisor-1-0) [INFO - org.mortbay.log.Slf4jLog.info(Slf4jLog.java:67)] jetty-6.1.26
2018-10-30 16:35:30,391 (lifecycleSupervisor-1-0) [INFO - org.mortbay.log.Slf4jLog.info(Slf4jLog.java:67)] Started SelectChannelConnector@0.0.0.0:50000
2018-10-30 16:35:30,392 (lifecycleSupervisor-1-0) [INFO - org.apache.flume.instrumentation.MonitoredCounterGroup.register(MonitoredCounterGroup.java:119)] Monitored counter group for type: SOURCE, name: r1: Successfully registered new MBean.
2018-10-30 16:35:30,392 (lifecycleSupervisor-1-0) [INFO - org.apache.flume.instrumentation.MonitoredCounterGroup.start(MonitoredCounterGroup.java:95)] Component type: SOURCE, name: r1 started

注意分析控制台输出,修改配置信息;
$FlumeHome/conf/httpSourceApp.conf

POST json

[{
"headers" : {
"timestamp" : "434324343",
"host" : "random_host.example.com"
},
"body" : 'str'
}]

[{
"headers" : {
"timestamp" : "434324343",
"host" : "random_host.example.com"
},
"body" : '{
"timestamp" : "434324343",
"host" : "random_host.example.com"
}'
}]

记录的是body的字符串

[root@d log]# cat 1540888530206-7
{
"timestamp" : "434324343",
"host" : "random_host.example.com"
}
[root@d log]# ll -as
total 16
4 drwxr-xr-x 2 root root 4096 Oct 30 16:40 .
4 drwxr-xr-x 5 root root 4096 Oct 30 12:06 ..
0 -rw-r--r-- 1 root root 0 Oct 30 16:40 1540888530206-10
4 -rw-r--r-- 1 root root 108 Oct 30 16:38 1540888530206-7
0 -rw-r--r-- 1 root root 0 Oct 30 16:39 1540888530206-8
4 -rw-r--r-- 1 root root 4 Oct 30 16:39 1540888530206-9
[root@d log]# cat 1540888530206-9
str
[root@d log]#

自定义sink

关键点 event事件获取body后的byte转string

String body = new String(event.getBody());
System.out.println("body-----" + body);
txn.commit();
package com.product;

import org.apache.flume.Channel;
import org.apache.flume.Context;
import org.apache.flume.Event;
import org.apache.flume.EventDeliveryException;
import org.apache.flume.Transaction;
import org.apache.flume.conf.Configurable;
import org.apache.flume.sink.AbstractSink; public class FlumeApp extends AbstractSink implements Configurable {
@Override
public void configure(Context context) {
// TODO Auto-generated method stub
} @Override
public Status process() throws EventDeliveryException {
// TODO Auto-generated method stub
Channel ch = getChannel();
Transaction txn = ch.getTransaction();
Event event = null;
txn.begin();
while (true) {
event = ch.take();
if (event != null) {
break;
}
}
try {
String body = new String(event.getBody());
System.out.println("body-----" + body);
txn.commit();
return Status.READY;
} catch (Throwable th) {
txn.rollback();
if (th instanceof Error) {
throw (Error) th;
} else {
throw new EventDeliveryException(th);
}
} finally {
txn.close();
}
}
}

  

A handler is provided out of the box which can handle events represented in JSON format, and supports UTF-8, UTF-16 and UTF-32 character sets. The handler accepts an array of events (even if there is only one event, the event has to be sent in an array) and converts them to a Flume event based on the encoding specified in the request. If no encoding is specified, UTF-8 is assumed. The JSON handler supports UTF-8, UTF-16 and UTF-32. Events are represented as follows.

[{
"headers" : {
"timestamp" : "434324343",
"host" : "random_host.example.com"
},
"body" : "random_body"
},
{
"headers" : {
"namenode" : "namenode.example.com",
"datanode" : "random_datanode.example.com"
},
"body" : "really_random_body"
}]

To set the charset, the request must have content type specified as application/json; charset=UTF-8 (replace UTF-8 with UTF-16 or UTF-32 as required).

One way to create an event in the format expected by this handler is to use JSONEvent provided in the Flume SDK and use Google Gson to create the JSON string using the Gson#fromJson(Object, Type) method. The type token to pass as the 2nd argument of this method for list of events can be created by:

Type type = new TypeToken<List<JSONEvent>>() {}.getType();

flume sink两种类型 file_rool 自定义sing com.mycomm.MySink even if there is only one event, the event has to be sent in an array的更多相关文章

  1. .NET环境下导出Excel表格的两种方式和导入两种类型的Excel表格

    一.导出Excel表格的两种方式,其中两种方式指的是导出XML数据类型的Excel(即保存的时候可以只需要修改扩展名为.xls)和真正的Excel这两种. using System; using Sy ...

  2. AspNetWebApi管线中如果定义两种类型的消息处理程序(全局/路由)

    AspNetWebApi管线中如果定义两种类型的消息处理程序(全局/路由) 在AspNetWebApi管线中存在两种类型的消息处理程序(Message Handler) 1.全局消息处理程序,所有的请 ...

  3. apache软件no_ssl和openssl两种类型的区别

    apache软件同一版本有两种类型:no_ssl和openssl: openssl多了个ssl安全认证模式,它的协议是HTTPS而不是HTTP,这就是带有SSL的服务器与一般网页服务器的区别了. 一般 ...

  4. 从上面的集合框架图可以看到,Java 集合框架主要包括两种类型的容器,一种是集合(Collection),存储一个元素集合,另一种是图(Map),存储键/值对映射

    从上面的集合框架图可以看到,Java 集合框架主要包括两种类型的容器,一种是集合(Collection),存储一个元素集合,另一种是图(Map),存储键/值对映射.Collection 接口又有 3 ...

  5. JavaScript中两种类型的全局对象/函数【转】

    Snandy Stop, thinking is the essence of progress. JavaScript中两种类型的全局对象/函数 这里所说的JavaScript指浏览器环境中的包括宿 ...

  6. Spring 让 LOB 数据操作变得简单易行,LOB 代表大对象数据,包括 BLOB 和 CLOB 两种类型

    转自:https://www.ibm.com/developerworks/cn/java/j-lo-spring-lob/index.html 概述 LOB 代表大对象数据,包括 BLOB 和 CL ...

  7. 块级标签与预格式化文本标签----------大多数XHTML可以表示为两种类型的标签:块标签(block tag)和内联标签(inline tag)

    <html> <head> <meta charset="utf-8"> <title>块级标签</title> < ...

  8. github page的两种类型

    1. 什么是Github ? Github 官方主页 简单说,Github是一个基于git的社会化代码分享社区. 你可以在Github上创建免费的远程仓库(remote repository),分享你 ...

  9. TouTiao开源项目 分析笔记15 新闻详情之两种类型的实现

    1.预览效果 1.1.首先看一下需要实现的效果. 第一种,文字类型新闻. 第二种,图片类型新闻. 1.2.在NewsArticleTextViewBinder中设置了点击事件 RxView.click ...

随机推荐

  1. Mongodb更新数组$sort操作符

    db.students.update( { _id: 1 }, { $push: { quizzes: { $each: [ { id: 3, score: 8 }, { id: 4, score:  ...

  2. Bash编程的难点

    Bash作为一个编程语言,有很多奇怪的表达字符,有时候会让人感到很费解,其实,只要我们弄清楚bash面临的问题 就能够理解为啥要这么搞了,举个例子: 1.比较字符串"ab"和&qu ...

  3. securtCRT右键复制功能配置

    Options->Global Options->Terminal 在右边选择或者取消“Copy on select”和“Paste on right button”的勾选即可打开或者关闭 ...

  4. matplotlib之极坐标系的极径网格线(rgrids)的显示刻度

    matplotlib之极坐标系的极径网格线(rgrids)的显示刻度 #!/usr/bin/env python3 #-*- coding:utf-8 -*- #################### ...

  5. nyoj 975 Distinct Count

    Distinct Count 时间限制:3000 ms  |  内存限制:65535 KB 难度:3 描述 给一个长度为 n 的数列 {an} ,找出有多少个长度为 m 的区间,使区间中不含有重复的数 ...

  6. Monotone Chain Convex Hull(单调链凸包)

    Monotone Chain Convex Hull(单调链凸包)算法伪代码: //输入:一个在平面上的点集P //点集 P 按 先x后y 的递增排序 //m 表示共a[i=0...m]个点,ans为 ...

  7. oracle9i 精简版客户端界面没有显示实例名

    1.右击"我的电脑",选择"属性"菜单项 2.在弹出的窗口中,点击"高级系统设置" 3.在弹出的窗口中,选择"环境变量" ...

  8. Ubuntu下修改tomcat6默认的8080端口

    $ sudo vi /etc/tomcat6/server.xml   将 <Connector port="8080" protocol="HTTP/1.1&qu ...

  9. python+fastcgi+flup获取请求的数据和环境变量

    关于nginx+python+fastcgi+flup搭建fastcgi环境没问题了,可是如何处理POST/GET的请求数据呢,这个问题着实纠结了没久,通过尝试和阅读flup的源代码,终于明白了.先上 ...

  10. Tensorflow之计算tensor平均值

    https://www.tensorflow.org/versions/r0.12/api_docs/python/math_ops.html#reduce_mean tf.reduce_mean(i ...