(4) Flume1.5.0的安装、部署、简单应用(含伪分布式、与hadoop2.2.0、hbase0.96的案例) (1-8)

　四、如何安装？
　　　　1)将下载的flume包，解压到/home/hadoop目录中，你就已经完成了50%：）简单吧

　　　　2)修改 flume-env.sh 配置文件,主要是JAVA_HOME变量设置

root@m1:/home/hadoop/flume-1.5.0-bin# cp conf/flume-env.sh.template conf/flume-env.sh
root@m1:/home/hadoop/flume-1.5.0-bin# vi conf/flume-env.sh
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
 
# If this file is placed at FLUME_CONF_DIR/flume-env.sh, it will be sourced
# during Flume startup.
 
# Enviroment variables can be set here.
 
JAVA_HOME=/usr/lib/jvm/java-7-oracle
 
# Give Flume more memory and pre-allocate, enable remote monitoring via JMX
#JAVA_OPTS="-Xms100m -Xmx200m -Dcom.sun.management.jmxremote"
 
# Note that the Flume conf directory is always included in the classpath.
#FLUME_CLASSPATH=""

3)验证是否安装成功

root@m1:/home/hadoop# /home/hadoop/flume-1.5.0-bin/bin/flume-ng version
Flume 1.5.0
Source code repository: https://git-wip-us.apache.org/repos/asf/flume.git
Revision: 8633220df808c4cd0c13d1cf0320454a94f1ea97
Compiled by hshreedharan on Wed May  7 14:49:18 PDT 2014
From source with checksum a01fe726e4380ba0c9f7a7d222db961f
root@m1:/home/hadoop#

　出现上面的信息，表示安装成功了

　五、flume的案例

#1)案例1：Avro   
#Avro可以发送一个给定的文件给Flume，Avro 源使用AVRO RPC机制。

#a)创建agent配置文件arvo.conf
a1.sources = r1
a1.sinks = k1
a1.channels = c1
  
# Describe/configure the source
a1.sources.r1.type = avro
a1.sources.r1.channels = c1
a1.sources.r1.bind = 0.0.0.0
a1.sources.r1.port = 4141
  
# 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

# b)启动flume agent a1
[pjm@localhost flume]$ ./bin/flume-ng agent --conf conf --conf-file ./conf/arvo.conf --name a1 -Dflume.root.logger=DEBUG,console

# c)创建指定文件
[pjm@localhost logs]$ echo "hello world pjm" > /usr/local/flume/log.00

# d)使用avro-client发送文件
[pjm@localhost flume]$ ./bin/flume-ng avro-client -c . -H 0.0.0.0 -p 4141 -F ./log.00 

#　f)在控制台，可以看到以下信息，注意最后一行
2015-01-07 15:14:10,585 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.LoggerSink.process(LoggerSink.java:70)]
Event: { headers:{} body: 68 65 6C 6C 6F 20 77 6F 72 6C 64 20 70 6A 6D    hello world pjm }

2)案例2：Spool

　　　　 Spool监测配置的目录下新增的文件，并将文件中的数据读取出来。需要注意两点：

　　　　1) 拷贝到spool目录下的文件不可以再打开编辑。

　　　　2) spool目录下不可包含相应的子目录

#a)创建agent配置文件

a1.sources = r1
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
a1.sources.r1.type = spooldir
a1.sources.r1.channels = c1
a1.sources.r1.spoolDir = /usr/local/flume/logs
a1.sources.r1.fileHeader = true

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

# Describe the sink
a1.sinks.k1.type = logger
a1.sinks.k1.channel = c1

# b)启动flume agent a1
[pjm@localhost flume]$ ./bin/flume-ng agent --conf conf --conf-file ./conf/spool.conf --name a1 -Dflume.root.logger=DEBUG,console

# c)追加文件到/home/hadoop/flume-1.5.0-bin/logs目录
root@m1:/home/hadoop# echo "spool test1" > /home/hadoop/flume-1.5.0-bin/logs/spool_text.log

　3)案例3：Exec

　　　　 EXEC 执行一个给定的命令获得输出的源,如果要使用tail命令，必选使得file足够大才能看到输出内容

  a)创建agent配置文件

root@m1:/home/hadoop# vi /home/hadoop/flume-1.5.0-bin/conf/exec_tail.conf
 
a1.sources = r1
a1.sinks = k1
a1.channels = c1
 
# Describe/configure the source
a1.sources.r1.type = exec
a1.sources.r1.channels = c1
a1.sources.r1.command = tail -F /home/hadoop/flume-1.5.0-bin/log_exec_tail
 
# 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

b) 启动flume agent a1

root@m1:/home/hadoop# /home/hadoop/flume-1.5.0-bin/bin/flume-ng agent -c . -f /home/hadoop/flume-1.5.0-bin/conf/exec_tail.conf -n a1 -Dflume.root.logger=INFO,console

c) 生成足够多的内容在文件里

root@m1:/home/hadoop# for i in {1..100};do echo "exec tail$i" >> /home/hadoop/flume-1.5.0-bin/log_exec_tail;echo $i;sleep 0.1;done

e) 在m1的控制台，可以看到以下信息：

2014-08-10 10:59:25,513 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.LoggerSink.process(LoggerSink.java:70)] Event: { headers:{} body: 65 78 65 63 20 74 61 69 6C 20 74 65 73 74       exec tail test }
2014-08-10 10:59:34,535 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.LoggerSink.process(LoggerSink.java:70)] Event: { headers:{} body: 65 78 65 63 20 74 61 69 6C 20 74 65 73 74       exec tail test }
2014-08-10 11:01:40,557 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.LoggerSink.process(LoggerSink.java:70)] Event: { headers:{} body: 65 78 65 63 20 74 61 69 6C 31                   exec tail1 }
2014-08-10 11:01:41,180 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.LoggerSink.process(LoggerSink.java:70)] Event: { headers:{} body: 65 78 65 63 20 74 61 69 6C 32                   exec tail2 }
2014-08-10 11:01:41,180 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.LoggerSink.process(LoggerSink.java:70)] Event: { headers:{} body: 65 78 65 63 20 74 61 69 6C 33                   exec tail3 }
2014-08-10 11:01:41,181 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.LoggerSink.process(LoggerSink.java:70)] Event: { headers:{} body: 65 78 65 63 20 74 61 69 6C 34                   exec tail4 }
2014-08-10 11:01:41,181 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.LoggerSink.process(LoggerSink.java:70)] Event: { headers:{} body: 65 78 65 63 20 74 61 69 6C 35                   exec tail5 }
2014-08-10 11:01:41,181 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.LoggerSink.process(LoggerSink.java:70)] Event: { headers:{} body: 65 78 65 63 20 74 61 69 6C 36                   exec tail6 }
....
....
....
2014-08-10 11:01:51,550 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.LoggerSink.process(LoggerSink.java:70)] Event: { headers:{} body: 65 78 65 63 20 74 61 69 6C 39 36                exec tail96 }
2014-08-10 11:01:51,550 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.LoggerSink.process(LoggerSink.java:70)] Event: { headers:{} body: 65 78 65 63 20 74 61 69 6C 39 37                exec tail97 }
2014-08-10 11:01:51,551 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.LoggerSink.process(LoggerSink.java:70)] Event: { headers:{} body: 65 78 65 63 20 74 61 69 6C 39 38                exec tail98 }
2014-08-10 11:01:51,551 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.LoggerSink.process(LoggerSink.java:70)] Event: { headers:{} body: 65 78 65 63 20 74 61 69 6C 39 39                exec tail99 }
2014-08-10 11:01:51,551 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.LoggerSink.process(LoggerSink.java:70)] Event: { headers:{} body: 65 78 65 63 20 74 61 69 6C 31 30 30             exec tail100 }

4)案例4：Syslogtcp

　　　　 Syslogtcp 监听TCP的端口做为数据源