flume实战记录

使用Flume关键就是写配置文件

需求一：

从指定网络端口采集数据输出到控制台

conf的书写

# 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 = hadoop01
a1.sources.r1.port = 44444


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


# Use a channel which buffers events in memory
a1.channels.c1.type = memory




# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

命令的编写：

flume-ng agent \
--name a1 \
--conf $FLUME_HOME/conf \
--conf-file $FLUME_HOME/conf/example.conf

-Dflume.root.logger=INFO,console

需求二：

监控一个文件实时采集新增的数据输出到控制台

conf的配置

# 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/data/data.log
a1.sources.r1.shell = /bin/sh -c


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


# Use a channel which buffers events in memory
a1.channels.c1.type = memory




# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1



命令的编写
flume-ng agent \
--name a1 \
--conf $FLUME_HOME/conf \
--conf-file $FLUME_HOME/conf/exec-memory-logger.conf \

-Dflume.root.logger=INFO,console

需求三：

将A服务器上的日志实时采集到B服务器

跨节点一般都会采用avro的sink

配置exec-memory-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/data/data.log
a1.sources.r1.shell = /bin/sh -c


# Describe the sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = hadoop02//！！！！！！！注意这里的保存的位置和后面的avro-memory-logger.conf要保持一致
a1.sinks.k1.port = 44444

# Use a channel which buffers events in memory
a1.channels.c1.type = memory

# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

命令的编写
flume-ng agent \
--name a1 \
--conf $FLUME_HOME/conf \
--conf-file $FLUME_HOME/conf/exec-memory-avro.conf \
-Dflume.root.logger=INFO,console


配置avro-memory-logger.conf:


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


# Describe/configure the source
a1.sources.r1.type = avro
a1.sources.r1.bind = hadoop02 //！！！！！！！注意这里的保存的位置和前面exec-memory-avro.conf要保持一致
a1.sources.r1.port = 44444


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


# Use a channel which buffers events in memory
a1.channels.c1.type = memory




# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1



命令的编写
flume-ng agent \
--name a1 \
--conf $FLUME_HOME/conf \
--conf-file $FLUME_HOME/conf/avro-memory-logger.conf \
-Dflume.root.logger=INFO,console