部署分布式数据库——HBase
学习背景: 以下采用伪分布式方式搭建HBase 故而采用内置的Zookeeper协调处理，不再搭建外置ZooKeeper，因此会存在单点故障问题，若需要解决这个情况，可采用Zookeeper部署一个HA(高可用)的Habse集群解决。
(1) 安装JDK、Hadoop，这里采用的JDK1.8，Hadoop2.7.4，CentOS7.6
本次部署测试的ip地址设为： 192.168.6.166 运行Hadoop环境，测试是否正常通过，启动命令: start-dfs.sh
(2）下载HBase安装包。官网地址:https://archive.apache.org/dist/hbase 相关大数据框架下载整理
(3) 安装
- 3.1 上传并完成解压HBase安装包
[root@hadoop1 ~]# tar -zxvf hbase-1.2.1-bin.tar.gz(4) 准备配置文件
- 4.1 拷贝配置文件
[root@hadoop1 ~]# cp /usr/local/hadoop/hadoop-2.7.4/etc//hadoop/{hdfs-site.xml,core-site.xml} /usr/local/hbase/hbase-1.2.1/conf/- 4.2 修改配置文件hbase-env.sh
# 加入jdk的安装路径到JAVA_HOME
[root@hadoop1 ~]# vim hbase-env.sh - 4.3 设置
HBase的环境变量
[root@hadoop1 ~]# vim /etc/profile
#HBase environment variable
export HBASE_HOME=/usr/local/hbase/hbase-1.2.1
export PATH=$PATH:$HBASE_HOME/bin:
#更新配置文件profile生效
[root@hadoop1 ~]# source /etc/profile# 查看hbase的版本
[root@hadoop1 ~]# hbase version运行HBase数据库
代码语言：javascript复制[root@hadoop1 conf]# start-hbase.sh运行成功后，已通过浏览器访问:http://hadoop1:16010/master-status
注意： 可以通过修改hosts来实现访问主机名进入web界面 具体路径： C:WindowsSystem32driversetchosts 在hosts文件内的最后一行加入: 192.168.6.166 hadoop1
HBase的基本操作
方式一：HBase的Shell操作
代码语言：javascript复制#启动交互界面
[root@hadoop1 ~]# hbase shell# 创建表
hbase(main):001:0> create 'student','info'
0 row(s) in 3.1630 seconds
=> Hbase::Table - student
# 查询表
hbase(main):002:0> list
TABLE
student
1 row(s) in 0.5240 seconds
=> ["student"]- 插入数据
# 插入数据
hbase(main):003:0> put 'student','1001','info:name','zhangsan'
0 row(s) in 3.0910 seconds
hbase(main):004:0> put 'student','1001','info:age','19'
0 row(s) in 0.1290 seconds
hbase(main):005:0> put 'student','1001','info:gender','male'
0 row(s) in 0.2760 seconds
hbase(main):006:0> put 'student','1002','info:name','lisi'
0 row(s) in 0.0090 seconds
hbase(main):007:0> put 'student','1002','info:age','21'
0 row(s) in 0.0800 seconds
hbase(main):008:0> put 'student','1002','info:gender','female'
0 row(s) in 0.0150 seconds- 扫描数据
hbase(main):009:0> scan 'student'
ROW COLUMN CELL
1001 column=info:age, timestamp=1650086163620, value=19
1001 column=info:gender, timestamp=1650086205652, value=male
1001 column=info:name, timestamp=1650085979553, value=zhangsan
1002 column=info:age, timestamp=1650086249277, value=21
1002 column=info:gender, timestamp=1650086265874, value=female
1002 column=info:name, timestamp=1650086227559, value=lisi
2 row(s) in 0.1450 seconds- 查看表结构
hbase(main):010:0> describe 'student'
Table student is ENABLED
student
COLUMN FAMILIES DESCRIPTION
{NAME => 'info', BLOOMFILTER => 'ROW', VERSIONS => '1', IN_MEMORY => 'false', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER',
COMPRESSION => 'NONE', MIN_VERSIONS => '0', BLOCKCACHE => 'true', BLOCKSIZE => '65536', REPLICATION_SCOPE => '0'}
1 row(s) in 0.2190 seconds- 更新语句
hbase(main):011:0> put 'student','1002','info:age','22'
0 row(s) in 0.1000 seconds
# 修改后查询验证是否修改成功
hbase(main):016:0> scan 'student'
ROW COLUMN CELL
1001 column=info:age, timestamp=1650086163620, value=19
1001 column=info:gender, timestamp=1650086205652, value=male
1001 column=info:name, timestamp=1650085979553, value=zhangsan
1002 column=info:age, timestamp=1650086635741, value=22
1002 column=info:gender, timestamp=1650086265874, value=female
1002 column=info:name, timestamp=1650086227559, value=lisi
2 row(s) in 0.0330 seconds- 获取指定字段的操作
hbase(main):002:0> get 'student','1001'
COLUMN CELL
info:age timestamp=1650086163620, value=19
info:gender timestamp=1650086205652, value=male
info:name timestamp=1650085979553, value=zhangsan
3 row(s) in 0.0420 seconds- 删除语句
hbase(main):008:0> delete 'student','1002','info:gender'
0 row(s) in 0.0900 seconds
# 删除后查询验证是否修改成功
hbase(main):009:0> scan 'student'
ROW COLUMN CELL
1001 column=info:age, timestamp=1650086163620, value=19
1001 column=info:gender, timestamp=1650086205652, value=male
1001 column=info:name, timestamp=1650085979553, value=zhangsan
1002 column=info:age, timestamp=1650086635741, value=22
1002 column=info:name, timestamp=1650086227559, value=lisi
2 row(s) in 0.0530 seconds- 1.创建Maven项目
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>cn.javabs</groupId>
<artifactId>JAVA_HBASE</artifactId>
<version>1.0-SNAPSHOT</version>
<dependencies>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-common</artifactId>
<version>1.2.6</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>1.2.6</version>
</dependency>
</dependencies>
</project>- 导入坐标，并完成类的创建
- 编写代码
package cn.javabs;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.Bytes;
import org.junit.Before;
import org.junit.Test;
import java.io.IOException;
import java.util.List;
public class HBaseTest {
Configuration conf = null;
Connection conn = null;
@Before
public void init() throws IOException {
// 1. 获取配置对象conf
conf = HBaseConfiguration.create();
// 2. 通过配置对象conf 设置hbase的入口
// conf.set("hbase.rootdir","hdfs://hadoop1:9000/hbase");
conf.set("hbase.zookeeper.quorum","hadoop1:2181");/*采用内置的zookeeper*/
// 3. 获取连接，利用连接工厂进行创建连接，借助配置对象conf
conn = ConnectionFactory.createConnection(conf);
}
/**
* 创建表
* @throws IOException
*/
@Test
public void createTable() throws IOException {
// 1. 通过conn获取表的管理对象
Admin admin = conn.getAdmin();
long beginTime = System.currentTimeMillis();
// 2. 创建表的描述符对象，并且完成指定的表名：t_user
HTableDescriptor tableDescriptor = new HTableDescriptor(TableName.valueOf("teacher".getBytes()));
// 3. 创建列族、并赋值为info
HColumnDescriptor hcd = new HColumnDescriptor("data");
// 将列族添加到 表描述符对象
tableDescriptor.addFamily(hcd);
// 利用表管理器对象 来创建表
admin.createTable(tableDescriptor);
long endime = System.currentTimeMillis();
System.out.println("创建完成，结束了！" ( endime - beginTime) "毫秒");
// 关闭资源
admin.close();
conn.close();
}
/**
* 指定查询
* @throws IOException
*/
@Test
public void getData() throws IOException{
Table table = conn.getTable(TableName.valueOf("student"));
// 1. 创建get对象是 查询参数的对象 用于指定要查询的哪一行
Get get = new Get("1002".getBytes());
// 2. 返回查询结果的数据
Result result = table.get(get);
// 3. 获取结果中所有的cell
List<Cell> cellList = result.listCells();
// 4. 循环遍历 所以的cell
for(Cell c : cellList){
// 5. 获取打印行健
System.out.println("行:" Bytes.toString(CellUtil.cloneRow(c)));
// 6. 获取打印列族
System.out.println("列族:" Bytes.toString(CellUtil.cloneFamily(c)));
// 7. 获取打印值
System.out.println("值:" Bytes.toString(CellUtil.cloneValue(c)));
}
// 8. 关闭资源
table.close();
conn.close();
}
}
