Flume采集配置

Flume采集配置，打印日志

bin/flume-ng agent -c conf/ -f dir-hdfs.conf -n ag1 -Dflume.root.logger=INFO,console

#bin/flume-ng agent:运行flume agent
#-c conf :运行flume自己的配置文件
#-f dir-hdfs.conf:运行自己写的source,sinks,channels配置文件
#-n ag1：自己配置文件里定义的agent的name
#-Dflume.root.logger=INFO,concole:向jvm里传参数，把日志信息打印在控制台

Flume配置文件

指定source,channels,sinks

#定义三大组件的名称
ag1.sources = source1
ag1.sinks = sink1
ag1.channels = channel1

# 配置source组件
ag1.sources.source1.type = spooldir
ag1.sources.source1.spoolDir = /root/log/
ag1.sources.source1.fileSuffix=.FINISHED
ag1.sources.source1.deserializer.maxLineLength=5120

# 配置sink组件
ag1.sinks.sink1.type = hdfs
ag1.sinks.sink1.hdfs.path =hdfs://master:9000/access_log/%y-%m-%d/%H-%M
ag1.sinks.sink1.hdfs.filePrefix = app_log
ag1.sinks.sink1.hdfs.fileSuffix = .log
ag1.sinks.sink1.hdfs.batchSize= 100
ag1.sinks.sink1.hdfs.fileType = DataStream
ag1.sinks.sink1.hdfs.writeFormat =Text

## roll：滚动切换：控制写文件的切换规则
ag1.sinks.sink1.hdfs.rollSize = 512000    ## 按文件体积（字节）来切   
ag1.sinks.sink1.hdfs.rollCount = 1000000  ## 按event条数切
ag1.sinks.sink1.hdfs.rollInterval = 60    ## 按时间间隔切换文件

## 控制生成目录的规则
ag1.sinks.sink1.hdfs.round = true
ag1.sinks.sink1.hdfs.roundValue = 10
ag1.sinks.sink1.hdfs.roundUnit = minute

ag1.sinks.sink1.hdfs.useLocalTimeStamp = true

# channel组件配置
ag1.channels.channel1.type = memory
ag1.channels.channel1.capacity = 500000   ## event条数
ag1.channels.channel1.transactionCapacity = 600  ##flume事务控制所需要的缓存容量600条event

# 绑定source、channel和sink之间的连接
ag1.sources.source1.channels = channel1
ag1.sinks.sink1.channel = channel1

flume官方文档
加粗是必备配置属性

Flume采集配置–多级agent串联

avro source:avro是一种通用的序列化协议，它是跨平台，跨语言的序列化协议。
其他类似的序列化方式有：jdk的serializable，hadoop的Writable。谷歌的protobuf通用序列化协议。
tail-avro.conf文件负责从tail命令获取数据发送到avro端口
另一个节点可以配置一个avro源来中继数据，发送到外部存储中
tail-avro.conf

# 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 /root/log/access.log


# Describe the sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = slave1
a1.sinks.k1.port = 4141
a1.sinks.k1.batch-size = 2



# 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

avro-hdfs.conf采集配置文件负责从avro端口接收数据，下沉到hdfs

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

# Describe/configure the source
##source中的avro组件是一个接收者服务
a1.sources.r1.type = avro
a1.sources.r1.bind = slave1
a1.sources.r1.port = 4141


# Describe the sink
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path = /flume/taildata/%y-%m-%d/
a1.sinks.k1.hdfs.filePrefix = tail-
a1.sinks.k1.hdfs.round = true
a1.sinks.k1.hdfs.roundValue = 24
#hdfs中的目录按照日期分割
a1.sinks.k1.hdfs.roundUnit = hour
a1.sinks.k1.hdfs.rollInterval = 0
a1.sinks.k1.hdfs.rollSize = 0
a1.sinks.k1.hdfs.rollCount = 50
a1.sinks.k1.hdfs.batchSize = 10
a1.sinks.k1.hdfs.useLocalTimeStamp = true
#生成的文件类型，默认是Sequencefile，可用DataStream，则为普通文本
a1.sinks.k1.hdfs.fileType = DataStream

# 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