1、flume日志收集架构如下

 

 

 2、解压安装包，修改文件夹名称，配置环境变量

tar -zxvf apache-flume-1.6.0-bin.tar.gz

 export FLUME_HOME=/soft/flume

 export PATH=$PATH:$FLUME_HOME/bin

修改conf下的flume-env.sh，在里面配置JAVA_HOME

3、从netcat收集日志

1、先在flume的conf目录下新建一个文件
vi   netcat-logger.conf
# 定义这个agent中各组件的名字
a1.sources = r1
a1.sinks = k1
a1.channels = c1

# 描述和配置source组件：r1
a1.sources.r1.type = netcat
a1.sources.r1.bind = localhost
a1.sources.r1.port = 44444

# 描述和配置sink组件：k1
a1.sinks.k1.type = logger

# 描述和配置channel组件，此处使用是内存缓存的方式
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000 内存里面存放1000个事件
a1.channels.c1.transactionCapacity = 100

# 描述和配置source  channel   sink之间的连接关系
a1.sources.r1.channels = c1

a1.sinks.k1.channel = c1

启动命令如下，请注意路径是否正确，a1是配置文件里面的

bin/flume-ng agent -c conf -f conf/netcat-logger.conf -n a1an  -Dflume.root.logger=INFO,console

测试效果，安装

sudo yum install nmap-ncat.x86_64
nc localhost 44444
hello word

4、从文件夹收集日志到hdfs

建立配置文件如下

agent1.sources = source1
agent1.sinks = sink1
agent1.channels = channel1

# 配置source组件
agent1.sources.source1.type = spooldir
agent1.sources.source1.spoolDir = /home/hadoop/logs/
agent1.sources.source1.fileHeader = false

#配置拦截器
agent1.sources.source1.interceptors = i1
agent1.sources.source1.interceptors.i1.type = host
agent1.sources.source1.interceptors.i1.hostHeader = hostname

# 配置sink组件
agent1.sinks.sink1.type = hdfs
agent1.sinks.sink1.hdfs.path =hdfs://hadoop1/weblog/flume-collection/%y-%m-%d/
agent1.sinks.sink1.hdfs.filePrefix = access_log
agent1.sinks.sink1.hdfs.maxOpenFiles = 5000
agent1.sinks.sink1.hdfs.batchSize= 100
agent1.sinks.sink1.hdfs.fileType = DataStream
agent1.sinks.sink1.hdfs.writeFormat =Text
agent1.sinks.sink1.hdfs.rollSize = 102400
agent1.sinks.sink1.hdfs.rollCount = 1000000
agent1.sinks.sink1.hdfs.rollInterval = 60
#agent1.sinks.sink1.hdfs.round = true
#agent1.sinks.sink1.hdfs.roundValue = 10
#agent1.sinks.sink1.hdfs.roundUnit = minute
agent1.sinks.sink1.hdfs.useLocalTimeStamp = true
# Use a channel which buffers events in memory
agent1.channels.channel1.type = memory
agent1.channels.channel1.keep-alive = 120
agent1.channels.channel1.capacity = 500000
agent1.channels.channel1.transactionCapacity = 600

# Bind the source and sink to the channel
agent1.sources.source1.channels = channel1
agent1.sinks.sink1.channel = channel1

启动脚本如下

../bin/flume-ng agent -c conf -f spooldir.conf -n agent1  -Dflume.root.logger=INFO,console

测试自己建立文件夹自己测试

5、从文件收集日志到hdfs，自己测试

agent1.sources = source1
agent1.sinks = sink1
agent1.channels = channel1

# Describe/configure tail -F source1
agent1.sources.source1.type = exec
agent1.sources.source1.command = tail -F /home/hadoop/logs/access_log
agent1.sources.source1.channels = channel1

#configure host for source
agent1.sources.source1.interceptors = i1
agent1.sources.source1.interceptors.i1.type = host
agent1.sources.source1.interceptors.i1.hostHeader = hostname

# Describe sink1
agent1.sinks.sink1.type = hdfs
#a1.sinks.k1.channel = c1
agent1.sinks.sink1.hdfs.path =hdfs://hadoop1/weblog22/flume/%y-%m-%d/
agent1.sinks.sink1.hdfs.filePrefix = access_log
agent1.sinks.sink1.hdfs.maxOpenFiles = 5000
agent1.sinks.sink1.hdfs.batchSize= 100
agent1.sinks.sink1.hdfs.fileType = DataStream
agent1.sinks.sink1.hdfs.writeFormat =Text
agent1.sinks.sink1.hdfs.rollSize = 102400
agent1.sinks.sink1.hdfs.rollCount = 1000000
agent1.sinks.sink1.hdfs.rollInterval = 60
#agent1.sinks.sink1.hdfs.round = true
#agent1.sinks.sink1.hdfs.roundValue = 10
#agent1.sinks.sink1.hdfs.roundUnit = minute
agent1.sinks.sink1.hdfs.useLocalTimeStamp = true

# Use a channel which buffers events in memory
agent1.channels.channel1.type = memory
agent1.channels.channel1.keep-alive = 120
agent1.channels.channel1.capacity = 500000
agent1.channels.channel1.transactionCapacity = 600

# Bind the source and sink to the channel
agent1.sources.source1.channels = channel1
agent1.sinks.sink1.channel = channel1

 

sudo yum install nmap-ncat.x86_64