文章目录
环境:CentOS6.7、Hadoop2.7.3、HBase1.2.5、Zookeeper3.4.6
安装Flume1.7
以root用户登录
su root
进入home目录
cd /home
下载flume1.7到本地
wget http://archive.apache.org/dist/flume/1.7.0/apache-flume-1.7.0-bin.tar.gz
解压
tar xvf apache-flume-1.7.0-bin.tar.gz
配置环境变量
vi /etc/profile
文件末尾添加
export FLUME_HOME=/home/apache-flume-1.7.0-bin
export FLUME_CONF_DIR=$FLUME_HOME/conf
export PATH=$PATH:$FLUME_HOME/bin
使环境变量生效
source /etc/profile
进入Flume的配置目录
cd /home/apache-flume-1.7.0-bin/conf/
拷贝flume-env.sh的模板文件
cp flume-env.sh.template flume-env.sh
配置flume-env.sh文件
vi flume-env.sh
末尾添加
#若是解压安装的jdk,需设置为解压的安装目录
export JAVA_HOME=/usr/java/default
使环境配置生效
source flume-env.sh
验证安装Flume成功
flume-ng version
Flume使用
使用Flume接收AvroSource信息
创建Agent配置文件
cd /home/apache-flume-1.7.0-bin/conf/
vi avro.conf
文件末尾添加
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
启动日志控制台
flume-ng agent -c . -f avro.conf -n a1 -Dflume.root.logger=INFO,console
按Ctrl+C可退出日志控制台,暂时先不退出
新建一个命令窗口,创建包含hello world的log文件并发送给Flume
cd /home/apache-flume-1.7.0-bin/
sh -c 'echo "hello world"> /home/log.00'
flume-ng avro-client -c . -H localhost -p 4141 -F /home/log.00
切回日志控制台的命令窗口接收到消息
使用Flume接收NetcatSource信息
创建agent配置文件
cd /home/apache-flume-1.7.0-bin/conf/
vi example.conf
在文件末尾添加
#example.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 = 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
启动日志控制台
flume-ng agent --conf-file example.conf --name a1 -Dflume.root.logger=INFO,console
安装telnet
yum -y install telnet
再创建一个命令窗口,测试本地44444端口是否连通
telnet localhost 44444
在该命令窗口下输入ok和hello world后,日志控制台窗口同步显示输入的消息
安装Kafka
进入home目录
cd /home
下载Kafka0.10.1
wget http://archive.apache.org/dist/kafka/0.10.1.0/kafka_2.10-0.10.1.0.tgz
解压
tar xvf kafka_2.10-0.10.1.0.tgz
进入Kafka的安装目录
cd /home/kafka_2.10-0.10.1.0/
启动zookeeper
./bin/zookeeper-server-start.sh config/zookeeper.properties
新建命令行窗口,进入Kafka的安装目录
cd /home/kafka_2.10-0.10.1.0/
启动Kafka
./bin/kafka-server-start.sh config/server.properties
新建命令行窗口,进入Kafka的安装目录
cd /home/kafka_2.10-0.10.1.0/
创建名为dblab的topic
./bin/kafka-topics.sh --create --zookeeper localhost:2181 --replication-factor 1 --partitions 1 --topic dblab
查看已创建的topic
./bin/kafka-topics.sh --list --zookeeper localhost:2181
启动producer
./bin/kafka-console-producer.sh --broker-list localhost:9092 --topic dblab
启动后(无提示),输入信息以生产数据
新建命令行窗口,进入Kafka的安装目录
cd /home/kafka_2.10-0.10.1.0/
启动consumer接受数据
./bin/kafka-console-consumer.sh --zookeeper localhost:2181 --topic dblab --from-beginning
安装Sqoop
进入home目录
cd /home
下载Sqoop1.4.6
wget http://archive.apache.org/dist/sqoop/1.4.6/sqoop-1.4.6.bin__hadoop-2.0.4-alpha.tar.gz
解压
tar xvf sqoop-1.4.6.bin__hadoop-2.0.4-alpha.tar.gz
进入Sqoop配置目录
cd /home/sqoop-1.4.6.bin__hadoop-2.0.4-alpha/conf/
拷贝Sqoop的环境配置的模板文件
cp sqoop-env-template.sh sqoop-env.sh
配置Sqoop环境文件
vi sqoop-env.sh
文件末尾添加
#HADOOP_COMMON_HOME和HADOOP_MAPRED_HOME也可和HADOOP_HOME设置为相同
#HADOOP_HOME即Hadoop的安装目录,可通过find / -name hadoop-daemon.sh,得到的查找结果的上一级目录即为Hadoop的安装目录
export HADOOP_COMMON_HOME=/home/hadoop-2.7.3/share/hadoop/common
export HADOOP_MAPRED_HOME=/home/hadoop-2.7.3/share/hadoop/mapreduce
export HBASE_HOME=/home/hbase-1.2.5
export HIVE_HOME=/home/apache-hive-2.1.1-bin
#此为Zookeeper的安装目录
export ZOOKEEPER_HOME=/home/zookeeper-3.4.6
使配置文件生效
source sqoop-env.sh
配置系统环境变量文件
vi /etc/profile
文件末尾添加
export SQOOP_HOME=/home/sqoop-1.4.6.bin__hadoop-2.0.4-alpha
export PATH=$PATH:$SBT_HOME/bin:$SQOOP_HOME/bin
export CLASSPATH=$CLASSPATH:$SQOOP_HOME/lib
使配置文件生效
source /etc/profile
在安装MySql环境的基础下,进入Sqoop的lib目录
cd /home/sqoop-1.4.6.bin__hadoop-2.0.4-alpha/lib
下载mysql驱动程序
weget https://repo1.maven.org/maven2/mysql/mysql-connector-java/5.1.27/mysql-connector-java-5.1.27.jar
(由于我有mysql驱动程序,就直接到相应目录拷贝到Sqoop的lib目录下)
启动Mysql
service mysqld start
测试Sqoop与Mysql是否连接
sqoop list - databases --connect jdbc:mysql://127.0.0.1:3306/ --username root -P
出现如下报错!
需在Sqoop_env.sh文件中配置ACCUMULO_HOME
进入Sqoop的配置目录
cd /home/sqoop-1.4.6.bin__hadoop-2.0.4-alpha/conf/
修改Sqoop_env.sh文件
vi sqoop_env.sh
文件末尾输入
export ACCUMULO_HOME=/var/lib/accumulo
使配置文件生效
source sqoop-env.sh
创建accumulo文件夹
mkdir /var/lib/accumulo
继续测试
又报错
配置HCAT_HOME,同上
进入Sqoop的配置目录
cd /home/sqoop-1.4.6.bin__hadoop-2.0.4-alpha/conf/
修改Sqoop_env.sh文件
vi sqoop_env.sh
文件末尾输入
export HCAT_HOME=/var/lib/hcat
使配置文件生效
source sqoop-env.sh
创建accumulo文件夹
mkdir /var/lib/hcat
继续测试,成功连上mysql
sqoop list-databases --connect jdbc:mysql://127.0.0.1:3306/ --username root -P