目录

  • 读取本地目录至HDFS
  • 创建flume-dir-hdfs.conf文件
  • 执行监控
  • !!!要将flume/lib中的guava-11.0.2.jar包删除
  • 先开启Hadoop集群
  • 再执行监控命令
  • 测试
  • 读取本地文件至HDFS
  • 创建flume-file-hdfs.conf文件
  • 执行监控
  • 先开启Hadoop集群
  • 再执行监控命令
  • 测试



读取本地目录至HDFS

创建flume-dir-hdfs.conf文件

/flume/job文件夹下创建flume-dir-hdfs.conf并配置文件

vi flume-dir-hdfs.conf
a3.sources = r3
a3.sinks = k3
a3.channels = c3
      
# Describe/configure the source
a3.sources.r3.type = spooldir
a3.sources.r3.spoolDir = /usr/hadoop/flume/upload
a3.sources.r3.fileSuffix = .COMPLETED
a3.sources.r3.fileHeader = true
#忽略所有以.tmp结尾的文件,不上传
a3.sources.r3.ignorePattern = ([^ ]*\.tmp)

# Describe the sink
a3.sinks.k3.type = hdfs
a3.sinks.k3.hdfs.path = hdfs://master:9000/flume/upload/%Y%m%d/%H
#上传文件的前缀
a3.sinks.k3.hdfs.filePrefix = upload-
#是否按照时间滚动文件夹
a3.sinks.k3.hdfs.round = true
#多少时间单位创建一个新的文件夹
a3.sinks.k3.hdfs.roundValue = 1
#重新定义时间单位
a3.sinks.k3.hdfs.roundUnit = hour
#是否使用本地时间戳
a3.sinks.k3.hdfs.useLocalTimeStamp = true
#积攒多少个Event才flush到HDFS一次
a3.sinks.k3.hdfs.batchSize = 100
#设置文件类型,可支持压缩
a3.sinks.k3.hdfs.fileType = DataStream
#多久生成一个新的文件
a3.sinks.k3.hdfs.rollInterval = 60
#设置每个文件的滚动大小大概是128M
a3.sinks.k3.hdfs.rollSize = 134217700
#文件的滚动与Event数量无关
a3.sinks.k3.hdfs.rollCount = 0

# Use a channel which buffers events in memory
a3.channels.c3.type = memory
a3.channels.c3.capacity = 1000
a3.channels.c3.transactionCapacity = 100

# Bind the source and sink to the channel
a3.sources.r3.channels = c3
a3.sinks.k3.channel = c3

执行监控

!!!要将flume/lib中的guava-11.0.2.jar包删除

先开启Hadoop集群

start-all.sh

再执行监控命令

bin/flume-ng agent --conf conf/ --name a3 --conf-file job/flume-dir-hdfs.conf

flume 读取mysql json flume实时读取本地文件到hdfs_flume 读取mysql json

测试

将文件复制到监听的目录下

[root@master flume]# cp README.md /usr/hadoop/flume/upload/

完成后去浏览器查看是否生成监听文件

flume 读取mysql json flume实时读取本地文件到hdfs_flume_02


flume 读取mysql json flume实时读取本地文件到hdfs_linux_03

读取本地文件至HDFS

创建flume-file-hdfs.conf文件

/flume/job文件夹下创建flume-file-hdfs.conf并配置文件

[root@master job]# vi flume-file-hdfs.conf
# Name the components on this agent
#定义source
a2.sources = r2
#定义sink
a2.sinks = k2 
#定义channel             
a2.channels = c2                

# Describe/configure the source
#定义source类型为exec可执行命令的
a2.sources.r2.type = exec       
a2.sources.r2.command = tail -F /usr/hadoop/flume/datas/flume_tmp.log
#执行shell脚本的绝对路径
a2.sources.r2.shell = /bin/bash -c      

# Describe the sink
#定义sink类型为hdfs
a2.sinks.k2.type = hdfs                     
a2.sinks.k2.hdfs.path = hdfs://master:9000/flume/file/%Y%m%d/%H
#上传文件的前缀
a2.sinks.k2.hdfs.filePrefix = logs-         
#是否按照时间滚动文件夹
a2.sinks.k2.hdfs.round = true
#多少时间单位创建一个新的文件夹
a2.sinks.k2.hdfs.roundValue = 1
#重新定义时间单位
a2.sinks.k2.hdfs.roundUnit = hour
#是否使用本地时间戳
a2.sinks.k2.hdfs.useLocalTimeStamp = true
#积攒多少个Event才flush到HDFS一次
a2.sinks.k2.hdfs.batchSize = 200
#设置文件类型,可支持压缩
a2.sinks.k2.hdfs.fileType = DataStream
#多久生成一个新的文件
a2.sinks.k2.hdfs.rollInterval = 600
#设置每个文件的滚动大小
a2.sinks.k2.hdfs.rollSize = 134217700
#文件的滚动与Event数量无关
a2.sinks.k2.hdfs.rollCount = 0
#最小冗余数
a2.sinks.k2.hdfs.minBlockReplicas = 1

# Use a channel which buffers events in memory
a2.channels.c2.type = memory
a2.channels.c2.capacity = 1000
a2.channels.c2.transactionCapacity = 300

# Bind the source and sink to the channel
a2.sources.r2.channels = c2
a2.sinks.k2.channel = c2

执行监控

先开启Hadoop集群

start-all.sh

再执行监控命令

bin/flume-ng agent --conf conf/ --name a2 --conf-file job/flume-file-hdfs.conf

flume 读取mysql json flume实时读取本地文件到hdfs_flume 读取mysql json

测试

在创建的文件下写入东西

flume 读取mysql json flume实时读取本地文件到hdfs_flume_05


完成后去浏览器查看是否生成监听文件

flume 读取mysql json flume实时读取本地文件到hdfs_hadoop_06