1. 写在前面

flume-ng高可用长在大数据处理环节第一个出现，对于处理日志文件有很好的作用，本篇博客将详细介绍flume-ng的高可用负载均衡搭建

2. flume-ng高可用负载均衡描述

在一般情况下，Flume-ng高可用采用server和client模式，client主要负责数据源source及数据流向端的sink指向配置，server主要负责数据流向sink详细配置，client需要将server的信息统一管理，server和sink之间数据连接通过channels

3. 配置server，这里配置三个server

flume-server1.properties

#set Agent name

agent.sources = r1

agent.channels = c1

agent.sinks = k1

#set channel

agent.channels.c1.type = memory

agent.channels.c1.capacity = 1024000

agent.channels.c1.transactionCapacity = 10000

agent.channels.c1.byteCapacity=134217728

agent.channels.c1.byteCapacityBufferPercentage=80

# other node,nna to nns

agent.sources.r1.type = avro

agent.sources.r1.bind = ynjz003

agent.sources.r1.port = 52020

agent.sources.r1.interceptors = i1

agent.sources.r1.interceptors.i1.type = static

agent.sources.r1.interceptors.i1.key = Collector

agent.sources.r1.interceptors.i1.value = ynjz003

agent.sources.r1.channels = c1

#set sink to hdfs

agent.sinks.k1.channel = c1

agent.sinks.k1.type = org.apache.flume.sink.kafka.KafkaSink

agent.sinks.k1.brokerList = ynjz003:9092,ynjz004:9092,ynjz005:9092,ynjz006:9092,ynjz007:9092,ynjz008:9092,ynjz009:9092

agent.sinks.k1.topic = flume-kafka-meijs33

agent.sinks.k1.serializer.class = kafka.serializer.StringEncoder

flume-server2.properties

#set Agent name

agent.sources = r1

agent.channels = c1

agent.sinks = k1

#set channel

agent.channels.c1.type = memory

agent.channels.c1.capacity = 1024000

agent.channels.c1.transactionCapacity = 10000

agent.channels.c1.byteCapacity=134217728

agent.channels.c1.byteCapacityBufferPercentage=80

# other node,nna to nns

agent.sources.r1.type = avro

agent.sources.r1.bind = ynjz004

agent.sources.r1.port = 52020

agent.sources.r1.interceptors = i1

agent.sources.r1.interceptors.i1.type = static

agent.sources.r1.interceptors.i1.key = Collector

agent.sources.r1.interceptors.i1.value = ynjz004

agent.sources.r1.channels = c1

#set sink to hdfs

agent.sinks.k1.channel = c1

agent.sinks.k1.type = org.apache.flume.sink.kafka.KafkaSink

agent.sinks.k1.brokerList = ynjz003:9092,ynjz004:9092,ynjz005:9092,ynjz006:9092,ynjz007:9092,ynjz008:9092,ynjz009:9092

agent.sinks.k1.topic = flume-kafka-meijs33

agent.sinks.k1.serializer.class = kafka.serializer.StringEncoder

flume-server3.properties

#set Agent name

agent.sources = r1

agent.channels = c1

agent.sinks = k1

#set channel

agent.channels.c1.type = memory

agent.channels.c1.capacity = 1024000

agent.channels.c1.transactionCapacity = 10000

agent.channels.c1.byteCapacity=134217728

agent.channels.c1.byteCapacityBufferPercentage=80

# other node,nna to nns

agent.sources.r1.type = avro

agent.sources.r1.bind = ynjz005

agent.sources.r1.port = 52020

agent.sources.r1.interceptors = i1

agent.sources.r1.interceptors.i1.type = static

agent.sources.r1.interceptors.i1.key = Collector

agent.sources.r1.interceptors.i1.value = ynjz005

agent.sources.r1.channels = c1

#set sink to hdfs

agent.sinks.k1.channel = c1

agent.sinks.k1.type = org.apache.flume.sink.kafka.KafkaSink

agent.sinks.k1.brokerList = ynjz003:9092,ynjz004:9092,ynjz005:9092,ynjz006:9092,ynjz007:9092,ynjz008:9092,ynjz009:9092

agent.sinks.k1.topic = flume-kafka-meijs33

agent.sinks.k1.serializer.class = kafka.serializer.StringEncoder

可以看出多个server配置的规律

3. 配置client，这里也配置一个client示例

flume-client.properties

#agent1 name

agent.channels = c1

agent.sources = r1

agent.sinks = k1 k2 k3 k4 k5 k6 k7

#set gruop

agent.sinkgroups = g1

#set channel

agent.channels.c1.type = memory

agent.channels.c1.capacity = 102400

agent.channels.c1.transactionCapacity = 1000

agent.channels.c1.byteCapacity=134217728

agent.channels.c1.byteCapacityBufferPercentage=80

agent.sources.r1.type = com.cbo.flume.source.zip.SpoolDirectorySource

agent.sources.r1.channels = c1

agent.sources.r1.spoolDir = /data/ynjz/workspace/zip

agent.sources.r1.fileHeader = true

agent.sources.r1.channels = c1

agent.sources.r1.flumeBatchSize=1000

agent.sources.r1.useFlumeEventFormat=false

agent.sources.r1.restart=true

agent.sources.r1.batchSize=1000

agent.sources.r1.batchTimeout=3000

agent.sources.r1.channels=c1

# set sink1

agent.sinks.k1.channel = c1

agent.sinks.k1.type = avro

agent.sinks.k1.hostname = ynjz003

agent.sinks.k1.port = 52020

# set sink2

agent.sinks.k2.channel = c1

agent.sinks.k2.type = avro

agent.sinks.k2.hostname = ynjz004

agent.sinks.k2.port = 52020

# set sink3

agent.sinks.k3.channel = c1

agent.sinks.k3.type = avro

agent.sinks.k3.hostname = ynjz005

agent.sinks.k3.port = 52020

# set sink4

agent.sinks.k1.channel = c1

agent.sinks.k1.type = avro

agent.sinks.k1.hostname = ynjz006

agent.sinks.k1.port = 52020

# set sink5

agent.sinks.k2.channel = c1

agent.sinks.k2.type = avro

agent.sinks.k2.hostname = ynjz007

agent.sinks.k2.port = 52020

# set sink6

agent.sinks.k3.channel = c1

agent.sinks.k3.type = avro

agent.sinks.k3.hostname = ynjz008

agent.sinks.k3.port = 52020

# set sink7

agent.sinks.k3.channel = c1

agent.sinks.k3.type = avro

agent.sinks.k3.hostname = ynjz009

agent.sinks.k3.port = 52020

#set sink group

agent.sinkgroups.g1.sinks = k1 k2 k3 k4 k5 k6 k7

#set failover

agent.sinkgroups.g1.processor.type = failover

agent.sinkgroups.g1.processor.priority.k1 = 10

agent.sinkgroups.g1.processor.priority.k2 = 10

agent.sinkgroups.g1.processor.priority.k3 = 10

agent.sinkgroups.g1.processor.priority.k4 = 10

agent.sinkgroups.g1.processor.priority.k5 = 10

agent.sinkgroups.g1.processor.priority.k6 = 10

agent.sinkgroups.g1.processor.priority.k7 = 10

agent.sinkgroups.g1.processor.maxpenalty = 10000

这里需要注意sinkgroups配置，flume sinkgroups在常用的应用中有两种方式failover和load_balance,failover可以理解为容错机制，在上面的配置中sink只会往一个kafka写入数据，但一个kafka挂了，failover机制会立马选举一个出来，所以这里的容错机制很完善，但是应对大数据量会影响数据写入的能力，所以建议在大数据量的时候采用load_balance配置，下面时配置示例

 #agent1 name

agent.channels = c1

agent.sources = r1

agent.sinks = k1 k2 k3 k4 k5 k6 k7

#set gruop

agent.sinkgroups = g1

#set channel

agent.channels.c1.type = memory

agent.channels.c1.capacity = 102400

agent.channels.c1.transactionCapacity = 24000

agent.channels.c1.byteCapacity=134217728

agent.channels.c1.byteCapacityBufferPercentage=80

agent.sources.r1.type = com.cbo.flume.source.zip.SpoolDirectorySource

agent.sources.r1.channels = c1

agent.sources.r1.spoolDir = /data/4G

agent.sources.r1.includePattern = ([^ ]*\.zip$)

agent.sources.r1.fileHeader = true

agent.sources.r1.channels = c1

agent.sources.r1.flumeBatchSize=10000

agent.sources.r1.useFlumeEventFormat=false

agent.sources.r1.restart=true

agent.sources.r1.batchSize=10000

agent.sources.r1.batchTimeout=3000

agent.sources.r1.channels=c1

# set sink1

agent.sinks.k1.channel = c1

agent.sinks.k1.type = avro

agent.sinks.k1.hostname = ynjz003

agent.sinks.k1.port = 52020

# set sink2

agent.sinks.k2.channel = c1

agent.sinks.k2.type = avro

agent.sinks.k2.hostname = ynjz004

agent.sinks.k2.port = 52020

# set sink3

agent.sinks.k3.channel = c1

agent.sinks.k3.type = avro

agent.sinks.k3.hostname = ynjz005

agent.sinks.k3.port = 52020

# set sink4

agent.sinks.k4.channel = c1

agent.sinks.k4.type = avro

agent.sinks.k4.hostname = ynjz006

agent.sinks.k4.port = 52020

# set sink5

agent.sinks.k5.channel = c1

agent.sinks.k5.type = avro

agent.sinks.k5.hostname = ynjz007

agent.sinks.k5.port = 52020

# set sink6

agent.sinks.k6.channel = c1

agent.sinks.k6.type = avro

agent.sinks.k6.hostname = ynjz008

agent.sinks.k6.port = 52020

# set sink7

agent.sinks.k7.channel = c1

agent.sinks.k7.type = avro

agent.sinks.k7.hostname = ynjz009

agent.sinks.k7.port = 52020

#set sink group

agent.sinkgroups.g1.sinks = k1 k2 k3 k4 k5 k6 k7

#set load_balance

agent.sinkgroups.g1.processor.type=load_balance

agent.sinkgroups.g1.processor.backoff=true

agent.sinkgroups.g1.processor.selector=random

在实际应用中多个client基本上一直，只有监控文件目录的配置不同即可agent.sources.r1.spoolDir = /data/4G

4. 启动flume-ng高可用集群

首先启动每个server,每个server只是配置文件flume-server-data.properties不同:

./bin/flume-ng agent --name agent --conf conf --conf-file conf/flume-server-data.properties -Dflume.root.logger=INFO,console > /data/ynjz/workspace/flume-server-data.log 2>&1 &

启动每个client,,每个server只是配置文件flume-client-data.properties不同:

./bin/flume-ng agent --name agent --conf conf --conf-file conf/flume-client-data.properties -Dflume.root.logger=INFO,console > /data/ynjz/workspace/flume-client-data.log 2>&1 &

在平时应用中，可以随时停止client，但停止了server没起而启动client会导致报错

Flume-ng高可用集群负载安装与配置的更多相关文章

  1. Flume 学习笔记之 Flume NG高可用集群搭建

    Flume NG高可用集群搭建: 架构总图: 架构分配: 角色 Host 端口 agent1 hadoop3 52020 collector1 hadoop1 52020 collector2 had ...

  2. 大数据高可用集群环境安装与配置（09）——安装Spark高可用集群

    1. 获取spark下载链接 登录官网:http://spark.apache.org/downloads.html 选择要下载的版本 2. 执行命令下载并安装 cd /usr/local/src/ ...

  3. Flume NG高可用集群搭建详解

    .Flume NG简述 Flume NG是一个分布式,高可用,可靠的系统,它能将不同的海量数据收集,移动并存储到一个数据存储系统中.轻量,配置简单,适用于各种日志收集,并支持 Failover和负载均 ...

  4. 大数据高可用集群环境安装与配置（06）——安装Hadoop高可用集群

    下载Hadoop安装包 登录 https://mirrors.tuna.tsinghua.edu.cn/apache/hadoop/common/ 镜像站,找到我们要安装的版本,点击进去复制下载链接 ...

  5. 大数据高可用集群环境安装与配置（07）——安装HBase高可用集群

    1. 下载安装包 登录官网获取HBase安装包下载地址 https://hbase.apache.org/downloads.html 2. 执行命令下载并安装 cd /usr/local/src/ ...

  6. 大数据高可用集群环境安装与配置（03）——设置SSH免密登录

    Hadoop的NameNode需要启动集群中所有机器的Hadoop守护进程,这个过程需要通过SSH登录来实现 Hadoop并没有提供SSH输入密码登录的形式,因此,为了能够顺利登录每台机器,需要将所有 ...

  7. 大数据高可用集群环境安装与配置（08）——安装Ganglia监控集群

    1. 安装依赖包和软件 在所有服务器上输入命令进行安装操作 yum install epel-release -y yum install ganglia-web ganglia-gmetad gan ...

  8. 大数据高可用集群环境安装与配置（02）——配置ntp服务

    NTP服务概述 NTP服务器[Network Time Protocol(NTP)]是用来使计算机时间同步化的一种协议,它可以使计算机对其服务器或时钟源(如石英钟,GPS等等)做同步化,它可以提供高精 ...

  9. 大数据高可用集群环境安装与配置（10）——安装Kafka高可用集群

    1. 获取安装包下载链接 访问https://kafka.apache.org/downloads 找到kafka对应版本 需要与服务器安装的scala版本一致(运行spark-shell可以看到当前 ...

随机推荐

  1. 数论ex

    数论ex 数学学得太差了补补知识点or复习 Miller-Rabin 和 Pollard Rho Miller-Rabin 前置知识: 费马小定理 \[ a^{p-1}\equiv 1\pmod p, ...

  2. PHP7 中 ？？ 与？ ：的区别

    ??是PHP7版本的新特性,它与?:的区别在哪里呢 ?? $b = $a?? $c ;相当于$b= isset($a)?$a:$c; ?: $b = $a?$a: $c 则是 $b = !empty( ...

  3. （十四）QFile操作，QByteArray，文件流操作,QTextStream，QDataStream，QFileInfo, QIODevice

    QFile f 1.readall #include "widget.h" #include "ui_widget.h" #include <QFileD ...

  4. STL迭代器iterator

    一:迭代器原理 迭代器是一个“可遍历STL容器内全部或部分元素”的对象. 迭代器指出容器中的一个特定位置. 迭代器就如同一个指针. 迭代器提供对一个容器中的对象的访问方法,并且可以定义了容器中对象的范 ...

  5. 自定义 ThreadPoolExecutor 处理线程运行时异常

    自定义 ThreadPoolExecutor 处理线程运行时异常 最近看完了ElasticSearch线程池模块的源码,感触颇深,然后也自不量力地借鉴ES的 EsThreadPoolExecutor ...

  6. 你们都在用IntelliJ IDEA吗？或许你们需要看一下这篇博文

    写在前面 以前一直用的elipce,如今入坑IntelliJ IDEA,没想到啊.深深的爱上了它,强大到无所不能: "工欲善其事必先利其器",IntelliJ IDEA作为一个非常 ...

  7. C# 学习之路--百度网盘爬虫设计与实现（一）

    百度网盘爬虫 现在市面上出现了很多网盘搜索引擎,写这系列博文及爬虫程序的初衷: 更方面的查找资源 学习C# 学习爬虫的设计与实现 记录学习历程 自我监督 能力有限,如有不妥之处,还请各位看官点评.同在 ...

  8. module.ngdoc

    译自Angular's module docs 1.模块 大部分的应用都有一个主要的方法来实例化,链接,引导.angular应用没有这个方法,而是用模块声明来替代. 这种方式的优点: *程序的声明越详 ...

  9. Docker-----仓库

    安装registry 安装并启动docker yum -y install docker systemctl enable docker systemctl start docker 下载regist ...

  10. 2018-2019-2 《网络对抗技术》 Exp0 Kali安装 20165221 Week1

    2018-2019-2 <网络对抗技术> Exp0 Kali安装 20165221 Week1 安装Vmware 上学期已经安装过,不再赘述. 如需安装,可参考如何安装vmware 下载v ...