目录
准备工作
分配flume文件夹
将flume文件夹分别传输给slave1和slave2
[root@master hadoop]# scp -r flume/ root@slave1:/usr/hadoop/
[root@master hadoop]# scp -r flume/ root@slave2:/usr/hadoop/
分配环境变量并刷新配置
配置环境变量,将之前已经配置好的环境变量分发过去
[root@master hadoop]# scp -r /etc/profile root@slave1:/etc/profile
[root@master hadoop]# scp -r /etc/profile root@slave2:/etc/profile
刷新一下配置信息
[root@slave1 ~]# source /etc/profile
[root@slave2 ~]# source /etc/profile
实现步骤
创建group文件夹
在/usr/hadoop/flume/job目录下创建group文件夹
[root@master job]# mkdir group
在master1创建flume-netcat-flume.conf
[root@master group]# vi flume-netcat-flume.conf
# Name the components on this agent
a1.sources = r1
a1.channels = c1
a1.sinkgroups = g1
a1.sinks = k1 k2
a1.sinkgroups.g1.processor.type = load_balance
a1.sinkgroups.g1.processor.backoff = true
a1.sinkgroups.g1.processor.selector = round_robin
a1.sinkgroups.g1.processor.selector.maxTimeOut=10000
# Describe the sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = slave1
a1.sinks.k1.port = 4141
a1.sinks.k2.type = avro
a1.sinks.k2.hostname = slave2
a1.sinks.k2.port = 4142
# Describe the channel
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100
a1.sources.r1.channels = c1
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /usr/hadoop/flume/datas/test.log
# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinkgroups.g1.sinks = k1 k2
a1.sinks.k1.channel = c1
a1.sinks.k2.channel = c1
在slave1创建flume-flume-console1.conf
[root@master group]# vi flume-flume-console1.conf
# Name the components on this agent
a2.sources = r1
a2.sinks = k1
a2.channels = c1
# Describe/configure the source
a2.sources.r1.type = avro
a2.sources.r1.bind = slave1
a2.sources.r1.port = 4141
# Describe the sink
a2.sinks.k1.type = logger
# Describe the channel
a2.channels.c1.type = memory
a2.channels.c1.capacity = 1000
a2.channels.c1.transactionCapacity = 100
# Bind the source and sink to the channel
a2.sources.r1.channels = c1
a2.sinks.k1.channel = c1
在slave2创建flume-flume-console2.conf
[root@master group]# vi flume-flume-console2.conf
# Name the components on this agent
a3.sources = r1
a3.sinks = k1
a3.channels = c2
# Describe/configure the source
a3.sources.r1.type = avro
a3.sources.r1.bind = slave2
a3.sources.r1.port = 4142
# Describe the sink
a3.sinks.k1.type = logger
# Describe the channel
a3.channels.c2.type = memory
a3.channels.c2.capacity = 1000
a3.channels.c2.transactionCapacity = 100
# Bind the source and sink to the channel
a3.sources.r1.channels = c2
a3.sinks.k1.channel = c2
启动测试
启动得从最后一级到第一级如a3–>a1,如同接水管得从远离水源的那头接起
[root@slave1 flume]$ bin/flume-ng agent --conf conf/ --name a3 --conf-file job/group/flume-flume-console2.conf -Dflume.root.logger=INFO,console
[root@slave2 flume]$ bin/flume-ng agent --conf conf/ --name a2 --conf-file job/group/flume-flume-console1.conf -Dflume.root.logger=INFO,console
[root@master flume]$ bin/flume-ng agent --conf conf/ --name a1 --conf-file job/group/flume-netcat-flume.conf
a3启动结果
a2启动结果
a1启动结果
当a1启动成功时,slave1,slave2会处于运行状态
均衡测试
故障转移
在创建的conf文件下加入以下代码就能够实现故障转移功能
#故障转移
a1.sinks = k1 k2
a1.sinkgroups.g1.processor.type = failover
a1.sinkgroups.g1.processor.priority.k1 = 5
a1.sinkgroups.g1.processor.priority.k2 = 10
a1.sinkgroups.g1.processor.maxpenalty = 10000