flume负载均衡个故障转移
3）实现步骤
0.准备工作
在/opt/module/flume/job目录下创建group2文件夹
[root@hadoop102 job]$ cd group2/
1.创建flume-netcat-flume.conf
配置1个netcat source和1个channel、1个sink group（2个sink），分别输送给flume-flume-console1和flume-flume-console2。
编辑配置文件
[root@hadoop102 group2]$ vim flume-netcat-flume.conf
添加如下内容
模式一：——容灾模式
a1.sources = r1
a1.channels = c1
a1.sinkgroups = g1
a1.sinks = k1 k2
# Describe/configure the source
a1.sources.r1.type = netcat
a1.sources.r1.bind = localhost
a1.sources.r1.port = 44444
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
# Describe the sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = hadoop102
a1.sinks.k1.port = 4141
a1.sinks.k2.type = avro
a1.sinks.k2.hostname = hadoop102
a1.sinks.k2.port = 4142
# Describe the channel
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.sinkgroups.g1.sinks = k1 k2
a1.sinks.k1.channel = c1
a1.sinks.k2.channel = c1
模式二：——负载均衡模式
a1.sources = r1
a1.channels = c1
a1.sinkgroups = g1
a1.sinks = k1 k2
# Describe/configure the source
a1.sources.r1.type = netcat
a1.sources.r1.bind = localhost
a1.sources.r1.port = 44444
a1.sinkgroups = g1
a1.sinkgroups.g1.sinks = k1 k2
a1.sinkgroups.g1.processor.type = load_balance
a1.sinkgroups.g1.processor.backoff = true
a1.sinkgroups.g1.processor.selector = round_robin
# Describe the sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = hadoop102
a1.sinks.k1.port = 4141
a1.sinks.k2.type = avro
a1.sinks.k2.hostname = hadoop102
a1.sinks.k2.port = 4142
# Describe the channel
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.sinkgroups.g1.sinks = k1 k2
a1.sinks.k1.channel = c1
a1.sinks.k2.channel = c1
2.创建flume-flume-console1.conf
配置上级Flume输出的Source，输出是到本地控制台。
编辑配置文件
[root@hadoop102 group2]$ vim flume-flume-console1.conf
添加如下内容
a2.sources = r1
a2.sinks = k1
a2.channels = c1
# Describe/configure the source
a2.sources.r1.type = avro
a2.sources.r1.bind = hadoop102
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
3.创建flume-flume-console2.conf
配置上级Flume输出的Source，输出是到本地控制台。
编辑配置文件
[root@hadoop102 group2]$ vim flume-flume-console2.conf
添加如下内容
a3.sources = r1
a3.sinks = k1
a3.channels = c2
# Describe/configure the source
a3.sources.r1.type = avro
a3.sources.r1.bind = hadoop102
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
4.执行配置文件
分别开启对应配置文件：flume-flume-console2，flume-flume-console1，flume-netcat-flume。
[root@hadoop102 flume]$ bin/flume-ng agent --conf conf/ --name a3 --conf-file job/group2/flume-flume-console2.conf -Dflume.root.logger=INFO,console
[root@hadoop102 flume]$ bin/flume-ng agent --conf conf/ --name a2 --conf-file job/group2/flume-flume-console1.conf -Dflume.root.logger=INFO,console
[root@hadoop102 flume]$ bin/flume-ng agent --conf conf/ --name a1 --conf-file job/group2/flume-netcat-flume.conf
5.使用netcat工具向本机的44444端口发送内容
$ nc localhost 44444
6.查看Flume2及Flume3的控制台打印日志
7.将Flume2 kill，观察Flume3的控制台打印情况。
注：使用jps -ml查看Flume进程。
- 聚合
1）案例需求：
hadoop102上的Flume-1监控文件/opt/module/group.log，
hadoop103上的Flume-2监控某一个端口的数据流，
Flume-1与Flume-2将数据发送给hadoop104上的Flume-3，Flume-3将最终数据打印到控制台。
2）需求分析
多数据源汇总案例
3）实现步骤：
0.准备工作
分发Flume
[root@hadoop102 module]$ xsync flume
在hadoop102、hadoop103以及hadoop104的/opt/module/flume/job目录下创建一个group3文件夹。
[root@hadoop102 job]$ mkdir group3
[root@hadoop103 job]$ mkdir group3
[root@hadoop104 job]$ mkdir group3
1.创建flume1-logger-flume.conf
配置Source用于监控hive.log文件，配置Sink输出数据到下一级Flume。
在hadoop102上编辑配置文件
[root@hadoop102 group3]$ vim flume1-logger-flume.conf
添加如下内容
a1.sources = r1
a1.sinks = k1
a1.channels = c1
# Describe/configure the source
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /opt/module/group.log
a1.sources.r1.shell = /bin/bash -c
# Describe the sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = hadoop104
a1.sinks.k1.port = 4141
# Describe the channel
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
2.创建flume2-netcat-flume.conf
配置Source监控端口44444数据流，配置Sink数据到下一级Flume：
在hadoop103上编辑配置文件
[root@hadoop102 group3]$ vim flume2-netcat-flume.conf
添加如下内容
a2.sources = r1
a2.sinks = k1
a2.channels = c1
# Describe/configure the source
a2.sources.r1.type = netcat
a2.sources.r1.bind = hadoop103
a2.sources.r1.port = 44444
# Describe the sink
a2.sinks.k1.type = avro
a2.sinks.k1.hostname = hadoop104
a2.sinks.k1.port = 4141
# Use a channel which buffers events in memory
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
3.创建flume3-flume-logger.conf
配置source用于接收flume1与flume2发送过来的数据流，最终合并后sink到控制台。
在hadoop104上编辑配置文件
[root@hadoop104 group3]$ touch flume3-flume-logger.conf
[root@hadoop104 group3]$ vim flume3-flume-logger.conf
添加如下内容
a3.sources = r1
a3.sinks = k1
a3.channels = c1
# Describe/configure the source
a3.sources.r1.type = avro
a3.sources.r1.bind = hadoop104
a3.sources.r1.port = 4141
# Describe the sink
# Describe the sink
a3.sinks.k1.type = logger
# Describe the channel
a3.channels.c1.type = memory
a3.channels.c1.capacity = 1000
a3.channels.c1.transactionCapacity = 100
# Bind the source and sink to the channel
a3.sources.r1.channels = c1
a3.sinks.k1.channel = c1
4.执行配置文件
分别开启对应配置文件：flume3-flume-logger.conf，flume2-netcat-flume.conf，flume1-logger-flume.conf。
[root@hadoop104 flume]$ bin/flume-ng agent --conf conf/ --name a3 --conf-file job/group3/flume3-flume-logger.conf -Dflume.root.logger=INFO,console
[root@hadoop102 flume]$ bin/flume-ng agent --conf conf/ --name a2 --conf-file job/group3/flume1-logger-flume.conf
[root@hadoop103 flume]$ bin/flume-ng agent --conf conf/ --name a1 --conf-file job/group3/flume2-netcat-flume.conf
5．在hadoop103上向/opt/module目录下的group.log追加内容
[root@hadoop103 module]$ echo ‘hello’ > group.log
6．在hadoop102上向44444端口发送数据
[root@hadoop102 flume]$ telnet hadoop102 44444
7.检查hadoop104上数据