flume入门

# example.conf: A single-node Flume configuration

# Name the components on this agent
#给那三个组件取个名字
a1.sources = r1
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
#类型, 从网络端口接收数据,在本机启动, 所以localhost, type=spoolDir采集目录源,目录里有就采
a1.sources.r1.type = netcat
a1.sources.r1.bind = localhost
a1.sources.r1.port = 44444

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

# Use a channel which buffers events in memory
#下沉的时候是一批一批的, 下沉的时候是一个个eventChannel参数解释：
#capacity：默认该通道中最大的可以存储的event数量
#trasactionCapacity：每次最大可以从source中拿到或者送到sink中的event数量
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

启动命令：
#告诉flum启动一个agent,指定配置参数, --name:agent的名字,
$ bin/flume-ng agent --conf conf --conf-file conf/netcat-logger.conf --name a1 -Dflume.root.logger=INFO,console

首先要启动hdfs，

使用telnet通信就可以做测试，如果是其他机器访问的那么netcat要配置成ip而不是localhost，netcat默认读取字符长度是16个数字，可以设置更大

 启动flume 之后 telnet mini2 44444 

文件系统 到hdfs

agent1.sources=source1
agent1.sinks=sink1
agent1.channels=channel1
#source1
agent1.sources.source1.type=spooldir
agent1.sources.source1.spoolDir=/home/hadoop/flume/test/logs
agent1.sources.source1.channels=channel1
agent1.sources.source1.fileHeader=false
agent1.sources.source1.interceptors = i1
agent1.sources.source1.interceptors.i1.type = timestamp
#sink1
agent1.sinks.sink1.type=hdfs
agent1.sinks.sink1.hdfs.path=hdfs://mini1:9000/flume/data
agent1.sinks.sink1.hdfs.fileType=DataStream
agent1.sinks.sink1.hdfs.writeFormat=TEXT
agent1.sinks.sink1.hdfs.rollInterval=1
agent1.sinks.sink1.hdfs.useLocalTimeStamp = true
agent1.sinks.sink1.channel=channel1
agent1.sinks.sink1.hdfs.filePrefix=%Y-%m-%d
#配置channel1
agent1.channels.channel1.type=file
agent1.channels.channel1.checkpointDir=/home/hadoop/flume/channel_data.backup
agent1.channels.channel1.dataDirs=/home/hadoop/flume/channel_data