flume部署（集群日志上传至hdfs）

---

官方参考文档

---

下载安装包

官方链接
实验版本：1.6.0

解压至目标目录

tar -zxvf 文件名 -C 目标目录

配置环境变量及配置文件

vi /etc/profile
# 添加：
export FLUME_HOME=/root/software/flume-1.6.0
export PATH=$PATH:$FLUME_HOME/bin
export FLUME_CONF_DIR=/root/software/flume-1.6.0/conf

# 创建目录 logs
mkdir /root/software/flume-1.6.0/logs

#修改配置
cp flume-env.sh.template flume-env.sh
vi flume-env.sh

添加 java 的安装路径

添加配置文件

vi flume-conf.properties 
# 添加：
# a.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 = spooldir
a1.sources.r1.spoolDir = /root/software/flume-1.6.0/logs
a1.sources.r1.fileHeader = true
a1.sources.r1.deserializer.outputCharset=UTF-8
# Describe the sink
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path = hdfs://master:9000/log
a1.sinks.k1.hdfs.fileType = DataStream
a1.sinks.k1.hdfs.writeFormat=Text
a1.sinks.k1.hdfs.maxOpenFiles = 1
a1.sinks.k1.hdfs.rollCount = 0
a1.sinks.k1.hdfs.rollInterval = 0
a1.sinks.k1.hdfs.rollSize = 1000000
a1.sinks.k1.hdfs.batchSize = 100000
# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000000
a1.channels.c1.transactionCapacity = 100000
# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

此处根据情况修改

启动

flume-ng agent --conf conf --conf-file flume-conf.properties --name a1 -Dflume.root.logger=INFO,console

检测

新建一个终端
复制文件到 /root/software/flume-1.6.0/logs

**返回终端查看发现文件后缀发生改变

---

---

---

---

集群配置文件

---

Master

#对于source的配置描述 监听avro
a1.sources.r1.type = avro
# hostname是最终传给的主机名称或者ip地址
a1.sources.r1.bind = master
a1.sources.r1.port = 44444


#定义拦截器，为消息添加时间戳  
a1.sources.r1.interceptors = i1  
a1.sources.r1.interceptors.i1.type = org.apache.flume.interceptor.TimestampInterceptor$Builder

#对于sink的配置描述 传递到hdfs上面
a1.sinks.k1.type = hdfs  
#集群的nameservers名字
#单节点的直接写：hdfs://主机名(ip):9000/xxx
#ns是hadoop集群名称
a1.sinks.k1.hdfs.path = hdfs://master:9000/flume/%Y%m%d  
a1.sinks.k1.hdfs.filePrefix = events-  
a1.sinks.k1.hdfs.fileType = DataStream  
#不按照条数生成文件  
a1.sinks.k1.hdfs.rollCount = 0  
#HDFS上的文件达到128M时生成一个文件  
a1.sinks.k1.hdfs.rollSize = 134217728  
#HDFS上的文件达到60秒生成一个文件  
a1.sinks.k1.hdfs.rollInterval = 60  


#对于channel的配置描述 使用内存缓冲区域做数据的临时缓存
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

#通过channel c1将source r1和sink k1关联起来
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1  

---

Slave

# 主要作用是监听目录中的新增数据，采集到数据之后，输出到avro （输出到agent）
# 注意：Flume agent的运行，主要就是配置source channel sink
# 下面的a1就是agent的代号，source叫r1 channel叫c1 sink叫k1

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

#具体定义source  
a1.sources.r1.type = spooldir
#先创建此目录，保证里面空的  
a1.sources.r1.spoolDir = /root/flume-test-logs 

#对于sink的配置描述 使用avro日志做数据的消费
a1.sinks.k1.type = avro
# hostname是最终传给的主机名称或者ip地址
a1.sinks.k1.hostname = master
a1.sinks.k1.port = 44444

#对于channel的配置描述 使用文件做数据的临时缓存 这种的安全性要高
a1.channels.c1.type = file
a1.channels.c1.checkpointDir = /root/flume-channel/checkpoint
a1.channels.c1.dataDirs = /root/flume-channel/data

#通过channel c1将source r1和sink k1关联起来
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1