Flume的数据收集,监控目录,监控某个文件的最新目录,两个agent级联,故障转移,负载均衡,过滤器案例

Flume 专栏收录该内容
3 篇文章 0 订阅

数据收集

  • 在flume安装包下创建一个临时文件tmpconf
mkdir tmpconf
  • 创建文件,并在文件中添加数据
vim tmpconf/a1.conf
  • 数据
a1.sources = r1
a1.channels = c1
a1.sinks = k1
a1.sources.r1.type = netcat
a1.sources.r1.bind = node01
a1.sources.r1.port = 44444 
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100 
a1.sinks.k1.type  = logger
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

执行命令

bin/flume-ng agent -c conf -f tmpconf/a1.conf -n a1  -Dflume.root.logger=INFO,console

在另一个节点执行

telnet node01 44444

监控目录

  • 创建一个目录存储数据
mkdir export/dir
  • 创建文件,添加数据
vim tmpconf/b1.conf

数据

#Name the components on this agent
a1.sources=r1
a1.channels=c1
a1.sinks=k1
#Describe/configure the source
##注意:不能往监控目中重复丢同名文件
a1.sources.r1.type=spooldir
a1.sources.r1.spoolDir=/export/dir
a1.sources.r1.fileHeader = true
#Describe the sink
a1.sinks.k1.type=hdfs
a1.sinks.k1.hdfs.path=hdfs://node01:8020/spooldir/
#Describe the channel
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
  • 执行命令
bin/flume-ng agent -c conf -f tmpconf/b1.conf -n a1  -Dflume.root.logger=INFO,console
  • 在创建好的文件中上传txt文件

11.txt

  • 执行完变成

11.txt.COMPLETED

监控某个文件的最新目录

  • 创建文件,添加数据
vim tmpconf/c1.conf

数据

a1.sources=r1
a1.channels=c1
a1.sinks=k1
#Describe/configure tail -F source1
a1.sources.r1.type=exec
a1.sources.r1.command =tail -F /export/taillogs/access_log
#Describe sink1
a1.sinks.k1.type=hdfs
a1.sinks.k1.hdfs.path=hdfs://node01:8020/spooldir/
#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
  • 执行命令
bin/flume-ng agent -c conf -f tmpconf/c1.conf -n a1  -Dflume.root.logger=INFO,console 
  • 创建脚本

mkdir /export/taillogs

touch /export/taillogs/access_log

脚本数据

#!/bin/bash
while true
do
 date >> /export/servers/taillogs/access_log;
  sleep 0.5;
done

查看效果
tail -f /export/taillogs/access_log

两个agent级联

  • node01 :
  • 创建文件,添加数据
vim tmpconf/d1.conf

数据

#Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1

#Describe/configure the source
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /export/taillogs/access_log

#Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

##sink端的avro是一个数据发送者
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = node02
a1.sinks.k1.port = 4141

#Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
  • node02 :
  • 创建文件,添加数据
vim tmpconf/d2.conf

数据

#Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1

##source中的avro组件是一个接收者服务
a1.sources.r1.type = avro
a1.sources.r1.bind = node02
a1.sources.r1.port = 4141

#Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

#Describe the sink
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path = hdfs://node01:8020/avro

#Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

执行

bin/flume-ng agent -c conf -f tmpconf/d2.conf -n a1  -Dflume.root.logger=INFO,console 
bin/flume-ng agent -c conf -f tmpconf/d1.conf -n a1  -Dflume.root.logger=INFO,console 

执行顺序不能乱

故障转移

  • node01 :
  • 创建文件,添加数据
 vim tmpconf/e1.conf

数据

#agent1 name
agent1.channels = c1
agent1.sources = r1
agent1.sinks = k1 k2
##set gruop
agent1.sinkgroups = g1
##set sink group
agent1.sinkgroups.g1.sinks = k1 k2
agent1.sources.r1.type = exec
agent1.sources.r1.command = tail -F /export/taillogs/access_log
##set channel
agent1.channels.c1.type = memory
agent1.channels.c1.capacity = 1000
agent1.channels.c1.transactionCapacity = 100
##set sink1
agent1.sinks.k1.type = avro
agent1.sinks.k1.hostname = node02
agent1.sinks.k1.port = 52020
##set sink2
agent1.sinks.k2.type = avro
agent1.sinks.k2.hostname = node03
agent1.sinks.k2.port = 52020
##set failover
agent1.sinkgroups.g1.processor.type = failover
agent1.sinkgroups.g1.processor.priority.k1 = 2
agent1.sinkgroups.g1.processor.priority.k2 = 1
agent1.sinkgroups.g1.processor.maxpenalty = 10000
agent1.sources.r1.channels = c1
agent1.sinks.k1.channel = c1
agent1.sinks.k2.channel = c1
  • node02:
  • 创建文件,添加数据
 vim tmpconf/e2.conf

数据

#set Agent name
a1.sources = r1
a1.channels = c1
a1.sinks = k1
## other node,nna to nns
a1.sources.r1.type = avro
a1.sources.r1.bind = node02
a1.sources.r1.port = 52020
##set channel
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100
##set sink to hdfs
a1.sinks.k1.type=hdfs
a1.sinks.k1.hdfs.path= hdfs://node01:8020/flume/failover/
a1.sources.r1.channels=c1
a1.sinks.k1.channel=c1
  • node03:
  • 创建文件,添加数据
 vim tmpconf/e3.conf

数据

#set Agent name
a1.sources = r1
a1.channels = c1
a1.sinks = k1
## other node,nna to nns
a1.sources.r1.type = avro
a1.sources.r1.bind = node03
a1.sources.r1.port = 52020
##set channel
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100
##set sink to hdfs
a1.sinks.k1.type=hdfs
a1.sinks.k1.hdfs.path= hdfs://node01:8020/flume/failover/
a1.sources.r1.channels=c1
a1.sinks.k1.channel=c1
  • 执行
bin/flume-ng agent -c conf -f tmpconf/e3.conf -n a1  -Dflume.root.logger=INFO,console 
bin/flume-ng agent -c conf -f tmpconf/e2.conf -n a1  -Dflume.root.logger=INFO,console 
bin/flume-ng agent -c conf -f tmpconf/e1.conf -n a1  -Dflume.root.logger=INFO,console 

负载均衡

  • node01:
  • 创建文件,添加数据
 vim tmpconf/f1.conf

数据:

#agent name
a1.channels = c1
a1.sources = r1
a1.sinks = k1 k2

#set gruop
a1.sinkgroups = g1
#set sink group
a1.sinkgroups.g1.sinks = k1 k2

#set sources
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /export/taillogs/access_log

#set channel
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

# set sink1
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = node02
a1.sinks.k1.port = 52021

# set sink2
a1.sinks.k2.type = avro
a1.sinks.k2.hostname = node03
a1.sinks.k2.port = 52021

#set failover
a1.sinkgroups.g1.processor.type = load_balance
a1.sinkgroups.g1.processor.backoff = true
a1.sinkgroups.g1.processor.selector = round_robin
a1.sinkgroups.g1.processor.selector.maxTimeOut=10000

a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
a1.sinks.k2.channel = c1
  • node02:
  • 创建文件,添加数据
 vim tmpconf/f2.conf

数据

# Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
a1.sources.r1.type = avro
a1.sources.r1.bind = node02
a1.sources.r1.port = 52021

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

# Describe the sink
a1.sinks.k1.type = logger

# Bind the source and sink to the channel 
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
  • node03:
  • 创建文件,添加数据
vim tmpconf/f3.conf

数据

# Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
a1.sources.r1.type = avro
a1.sources.r1.bind = node03
a1.sources.r1.port = 52021

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

# Describe the sink
a1.sinks.k1.type = logger

# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
  • 执行
bin/flume-ng agent -c conf -f tmpconf/f3.conf -n a1  -Dflume.root.logger=INFO,console
bin/flume-ng agent -c conf -f tmpconf/f2.conf -n a1  -Dflume.root.logger=INFO,console
bin/flume-ng agent -c conf -f tmpconf/f1.conf -n a1  -Dflume.root.logger=INFO,console

过滤器

  • node01
  • node02
  • 创建文件,添加数据
 vim tmpconf/g1.conf

数据

# Name the components on this agent
a1.sources = r1 r2 r3
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /export/taillogs/access.log
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = static
##  static拦截器的功能就是往采集到的数据的header中插入自己定## 义的key-value对
a1.sources.r1.interceptors.i1.key = type
a1.sources.r1.interceptors.i1.value = access

a1.sources.r2.type = exec
a1.sources.r2.command = tail -F /export/taillogs/nginx.log
a1.sources.r2.interceptors = i2
a1.sources.r2.interceptors.i2.type = static
a1.sources.r2.interceptors.i2.key = type
a1.sources.r2.interceptors.i2.value = nginx

a1.sources.r3.type = exec
a1.sources.r3.command = tail -F /export/taillogs/web.log
a1.sources.r3.interceptors = i3
a1.sources.r3.interceptors.i3.type = static
a1.sources.r3.interceptors.i3.key = type
a1.sources.r3.interceptors.i3.value = web

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 20000
a1.channels.c1.transactionCapacity = 10000

# Describe the sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = node03
a1.sinks.k1.port = 41414

# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sources.r2.channels = c1
a1.sources.r3.channels = c1
a1.sinks.k1.channel = c1
  • node03:
  • 创建问价,添加数据
 vim tmpconf/g1.conf

数据

a1.sources = r1
a1.sinks = k1
a1.channels = c1
#定义source
a1.sources.r1.type = avro
a1.sources.r1.bind = 192.168.52.120
a1.sources.r1.port =41414

#添加时间拦截器
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = org.apache.flume.interceptor.TimestampInterceptor$Builder

#定义channels
a1.channels.c1.type = memory
a1.channels.c1.capacity = 20000
a1.channels.c1.transactionCapacity = 10000

#定义sink
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path=hdfs://192.168.52.100:8020/source/logs/%{type}/%Y%m%d
 
#组装source、channel、sink
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

创建文件添加脚本

vim mkdata2.sh

脚本数据

#!/bin/bash
while true
do  
 date >> /export/taillogs/access.log; 
 date >> /export/taillogs/web.log;
 date >> /export/taillogs/nginx.log;
  sleep 0.5;
done

执行

bin/flume-ng agent -c conf -f tmpconf/g3.conf -n a1  -Dflume.root.logger=INFO,console 
bin/flume-ng agent -c conf -f tmpconf/g1.conf -n a1  -Dflume.root.logger=INFO,console
bin/flume-ng agent -c conf -f tmpconf/g2.conf -n a1  -Dflume.root.logger=INFO,console
  • 2
    点赞
  • 2
    评论
  • 0
    收藏
  • 一键三连
    一键三连
  • 扫一扫,分享海报

©️2021 CSDN 皮肤主题: 酷酷鲨 设计师:CSDN官方博客 返回首页
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、C币套餐、付费专栏及课程。

余额充值