014_Flume

1Flume定义

什么是Flume。

流式架构

Flume的主要作用

​ 实时读取服务器本地硬盘的数据，将数据写入到HDFS中。

Flume的优点

​ 灵活

​ 缓冲区的作用，减轻hdfs的压力。

重平衡

Flume组成架构

2安装Flume

1：拷贝

使用版本apache-flume-1.7.0-bin.tar.gz

2：改名

将apache-flume-1.7.0-bin.tar.gz改为flume

3：设置JAVA_HOME

cp flume-env.sh.template flume-env.sh

3第一个案例

1： 安装nc，yum install -y nc

2：判断本机的4444端口是否被占用，netstat -tunlp | grep 44444

3：在flume文件夹先创建job，mkdir job

4：在job中创建文件touch flume-netcat-logger.conf，并向文件中写入配置信息

# 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 = 44444

# 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

5：启动flume，bin/flume-ng agent --conf conf/ --name a1 --conf-file job/flume-netcat-logger.conf -Dflume.root.logger=INFO,console

6: 重新打开一个窗口，用nc连接4444 端口， nc localhost 44444。

7：发送数据。

8：查看数据。

3第二个案例

1：拷贝jar包

2：touch flume-file-hdfs.conf

# Name the components on this agent
a2.sources = r2
a2.sinks = k2
a2.channels = c2

# Describe/configure the source
a2.sources.r2.type = exec
a2.sources.r2.command = tail -F /home/soft/hive/logs/hive.log
a2.sources.r2.shell = /bin/bash -c

# Describe the sink
a2.sinks.k2.type = hdfs
a2.sinks.k2.hdfs.path = hdfs://192.168.10.102:9000/flume/%Y%m%d/%H
#上传文件的前缀
a2.sinks.k2.hdfs.filePrefix = logs-
#是否按照时间滚动文件夹
a2.sinks.k2.hdfs.round = true
#多少时间单位创建一个新的文件夹
a2.sinks.k2.hdfs.roundValue = 1
#重新定义时间单位
a2.sinks.k2.hdfs.roundUnit = hour
#是否使用本地时间戳
a2.sinks.k2.hdfs.useLocalTimeStamp = true
#积攒多少个Event才flush到HDFS一次
a2.sinks.k2.hdfs.batchSize = 1000
#设置文件类型，可支持压缩
a2.sinks.k2.hdfs.fileType = DataStream
#多久生成一个新的文件
a2.sinks.k2.hdfs.rollInterval = 60
#设置每个文件的滚动大小
a2.sinks.k2.hdfs.rollSize = 134217700
#文件的滚动与Event数量无关
a2.sinks.k2.hdfs.rollCount = 0

# Use a channel which buffers events in memory
a2.channels.c2.type = memory
a2.channels.c2.capacity = 1000
a2.channels.c2.transactionCapacity = 100

# Bind the source and sink to the channel
a2.sources.r2.channels = c2
a2.sinks.k2.channel = c2

3：编辑文件写入数据

4：启动hdfs

5：启动flume，bin/flume-ng agent --conf conf/ --name a2 --conf-file job/flume-file-hdfs.conf

6：启动hive，bin/hive

7：登录网址验证

3第三个案例

1：touch flume-dir-hdfs.conf

2：vim flume-dir-hdfs.conf

a3.sources = r3
a3.sinks = k3
a3.channels = c3

# Describe/configure the source
a3.sources.r3.type = spooldir
a3.sources.r3.spoolDir = /home/soft/flume/upload
a3.sources.r3.fileSuffix = .COMPLETED
a3.sources.r3.fileHeader = true
#忽略所有以.tmp结尾的文件，不上传
a3.sources.r3.ignorePattern = ([^ ]*\.tmp)

# Describe the sink
a3.sinks.k3.type = hdfs
a3.sinks.k3.hdfs.path = hdfs://192.168.10.120:9000/flume/upload/%Y%m%d/%H
#上传文件的前缀
a3.sinks.k3.hdfs.filePrefix = upload-
#是否按照时间滚动文件夹
a3.sinks.k3.hdfs.round = true
#多少时间单位创建一个新的文件夹
a3.sinks.k3.hdfs.roundValue = 1
#重新定义时间单位
a3.sinks.k3.hdfs.roundUnit = hour
#是否使用本地时间戳
a3.sinks.k3.hdfs.useLocalTimeStamp = true
#积攒多少个Event才flush到HDFS一次
a3.sinks.k3.hdfs.batchSize = 100
#设置文件类型，可支持压缩
a3.sinks.k3.hdfs.fileType = DataStream
#多久生成一个新的文件
a3.sinks.k3.hdfs.rollInterval = 60
#设置每个文件的滚动大小大概是128M
a3.sinks.k3.hdfs.rollSize = 134217700
#文件的滚动与Event数量无关
a3.sinks.k3.hdfs.rollCount = 0

# Use a channel which buffers events in memory
a3.channels.c3.type = memory
a3.channels.c3.capacity = 1000
a3.channels.c3.transactionCapacity = 100

# Bind the source and sink to the channel
a3.sources.r3.channels = c3
a3.sinks.k3.channel = c3

3：bin/flume-ng agent --conf conf/ --name a3 --conf-file job/flume-dir-hdfs.conf

4：bin/flume-ng agent --conf conf/ --name a3 --conf-file job/flume-dir-hdfs.conf

5：登录网页查看。

a1.sources=r1
a1.channels=c1 c2

# configure source
a1.sources.r1.type = TAILDIR
a1.sources.r1.positionFile = /home/soft/flume/test/log_position.json
a1.sources.r1.filegroups = f1
a1.sources.r1.filegroups.f1 = /tmp/logs/app.+
a1.sources.r1.fileHeader = true
a1.sources.r1.channels = c1 c2

#interceptor
a1.sources.r1.interceptors =  i1 i2
a1.sources.r1.interceptors.i1.type = com.atguigu.flume.interceptor.LogETLInterceptor$Builder
a1.sources.r1.interceptors.i2.type = com.atguigu.flume.interceptor.LogTypeInterceptor$Builder

a1.sources.r1.selector.type = multiplexing
a1.sources.r1.selector.header = topic
a1.sources.r1.selector.mapping.topic_start = c1
a1.sources.r1.selector.mapping.topic_event = c2

# configure channel
a1.channels.c1.type = org.apache.flume.channel.kafka.KafkaChannel
a1.channels.c1.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
a1.channels.c1.kafka.topic = topic_start
a1.channels.c1.parseAsFlumeEvent = false
a1.channels.c1.kafka.consumer.group.id = flume-consumer

a1.channels.c2.type = org.apache.flume.channel.kafka.KafkaChannel
a1.channels.c2.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
a1.channels.c2.kafka.topic = topic_event
a1.channels.c2.parseAsFlumeEvent = false
a1.channels.c2.kafka.consumer.group.id = flume-consumer

#! /bin/bash

case $1 in
"start"){
        for i in hadoop102 hadoop103
        do
                echo " --------启动 $i 采集flume-------"
                ssh $i "nohup /opt/module/flume/bin/flume-ng agent --conf-file /opt/module/flume/conf/file-flume-kafka.conf --name a1 -Dflume.root.logger=INFO,LOGFILE >/dev/null 2>&1 &"
        done
};;	
"stop"){
        for i in hadoop102 hadoop103
        do
                echo " --------停止 $i 采集flume-------"
                ssh $i "ps -ef | grep file-flume-kafka | grep -v grep |awk '{print \$2}' | xargs kill"
        done

};;
esac