hbase hdfs sink

bin/flume-ng agent --conf conf --conf-file conf/hbase.conf --name a1 -Dflume.root.logger=INFO,console

 

 

# example.conf: A single-node Flume configuration

 

# Name the components on this agent

a1.sources = r1

a1.sinks = k1

a1.channels = c1

 

# Describe/configure the source

a1.sources.r1.type = netcat

a1.sources.r1.bind = localhost

a1.sources.r1.port = 12345

 

# Describe the sink

a1.sinks.k1.type = logger

 

# 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

 

#HDFS sink

a1.channels = c1

a1.sinks = k1

a1.sinks.k1.type = hdfs

a1.sinks.k1.channel = c1

a1.sinks.k1.hdfs.path = /flume/%y-%m-%d/%H

a1.sinks.k1.hdfs.filePrefix = events-

a1.sinks.k1.hdfs.round = true

a1.sinks.k1.hdfs.roundValue = 10

a1.sinks.k1.hdfs.roundUnit = minute

a1.sinks.k1.hdfs.useLocalTimeStamp = true                        #sink是hdfs，然后使用目录自动生成功能。出现如题的错误，看官网文档说的是需要在每个文件记录行的开头需要有时间戳，但是时间戳的格式可能比较难调节，所以亦可设置   hdfs.useLocalTimeStamp这个参数，比如以每个小时作为一个文件夹，那么配置应该是这样

##解决错误：

java.lang.NullPointerException: Expected timestamp in the Flume event headers, but it was null

#HBASE

a1.channels = c1

a1.sinks = k1

a1.sinks.k1.type = hbase

a1.sinks.k1.table = flume

a1.sinks.k1.columnFamily = f1

a1.sinks.k1.serializer = org.apache.flume.sink.hbase.RegexHbaseEventSerializer

a1.sinks.k1.channel = c1

 

 

 

读取数据通道的方式：

netcat

a1.sources.r1.type = netcat

a1.sources.r1.bind = localhost

a1.sources.r1.port = 12345

根据端口连接传数据

telnet localhost 233333

 

avro

agent1.sources.source1.type = avro

agent1.sources.source1.bind = localhost

agent1.sources.source1.port = 44444

处理序列化数据

 

e xec

a1.sources = r1

a1.channels = c1

a1.sources.r1.type = exec

a1.sources.r1.command = tail -F /var/log/secure

a1.sources.r1.channels = c1

处理命令行

 

测试端口

netstat -tnl | grep 23

tcp        0      0 0.0.0.0:36232               0.0.0.0:*                   LISTEN     
tcp        0      0 :::23                       :::*                        LISTEN     

 

访问端口

telnet localhost 23

 

查看端口任务

ps -ef|grep 23

 

 

查看端口占用状态

lsof -i：23

 

 

 

# example.conf: A single-node Flume configuration

 

# Name the components on this agent

a1.sources = r1

a1.sinks = k1

a1.channels = c1

 

# Describe/configure the source

a1.sources.r1.type = netcat

a1.sources.r1.bind = localhost

a1.sources.r1.port = 12345

 

# Describe the sink

a1.sinks.k1.type = logger

 

# 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

 

#HDFS sink

a1.channels = c1

a1.sinks = k1

a1.sinks.k1.type = hdfs

a1.sinks.k1.channel = c1

a1.sinks.k1.hdfs.path = /flume/%y-%m-%d/%H

a1.sinks.k1.hdfs.filePrefix = events-

a1.sinks.k1.hdfs.round = true

a1.sinks.k1.hdfs.roundValue = 10

a1.sinks.k1.hdfs.roundUnit = minute

a1.sinks.k1.hdfs.useLocalTimeStamp = true

 

#HBASE

a1.channels = c1

a1.sinks = k1

a1.sinks.k1.type = hbase

a1.sinks.k1.table = flume

a1.sinks.k1.columnFamily = f1

a1.sinks.k1.serializer = org.apache.flume.sink.hbase.RegexHbaseEventSerializer

a1.sinks.k1.channel = c1