1. 在Linux集群下已经搭建了Zookeeper+Hadoop+HBase
| hostname | ip | 组件 |
|---|---|---|
| node0 | 192.168.1.160 | zookeeper,namenode,NodeManager,HMaster,HRegionServer |
| node1 | 192.168.1.161 | zookeeper,datanode,NodeManager,HRegionServer |
| node2 | 192.168.1.162 | zookeeper,datanode,ResourceManager,HMaster,HRegionServer |
2. 在Windows下搭建HBase应用程序开发环境
2.1 安装配置JDK
下载JDK1.8，配置环境变量
2.2 安装配置Maven
下载apache-maven-3.3.9，解压缩，配置环境变量
打开CMD，输入mvn -v
可以看到maven版本信息
2.3 配置Eclipse
目前的eclipse-javee版本已经自带maven插件了
winows-preferences-左边maven可以看到安装好的maven
2.4 创建Maven项目
在Wizards中输入maven
http://mvnrepository.com/
比如我们需要引入spring核心jar包spring-core，打开Maven Repository，搜索spring-core
选择最新版本3.2.0.RELEASE，可以看到其dependency写法如下红框所示：
将其复制到pom.xml中的中 。这样，Maven就会开始自动下载jar包到本地仓库，然后关联到你的项目中，下载完成后，我们展开工程目录中External Libraries。
<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>hbaseDemo</groupId>
<artifactId>hbaseDemo</artifactId>
<version>0.0.1-SNAPSHOT</version>
<packaging>jar</packaging>
<name>hbaseDemo</name>
<url>http://maven.apache.org</url>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
</properties>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>3.8.1</version>
<scope>test</scope>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-hdfs -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>2.7.3</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.hbase/hbase-client -->
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>1.2.4</version>
</dependency>
<dependency>
<groupId>jdk.tools</groupId>
<artifactId>jdk.tools</artifactId>
<version>1.8</version>
<scope>system</scope>
<systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
</dependency>
</dependencies>
</project>题外话，如果是WEB项目，还需要在pom.xml中导入 javaee-api.jar
<dependency>
<groupId>javax</groupId>
<artifactId>javaee-api</artifactId>
<version>7.0</version>
</dependency>2.5 编写应用程序
package hbaseDemo.dao;
import java.io.IOException;
import java.util.*;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Admin;
import org.apache.hadoop.hbase.client.Connection;
public class HbaseDao {
private static Configuration conf = HBaseConfiguration.create();
static {
conf.set("hbase.rootdir", "hdfs://cc/hbase");
// 设置Zookeeper,直接设置IP地址
conf.set("hbase.zookeeper.quorum", "192.168.1.160,192.168.1.162,192.168.1.163");
}
// 创建表
public static void createTable(String tablename, String columnFamily) throws Exception {
Connection connection = ConnectionFactory.createConnection(conf);
Admin admin = connection.getAdmin();
TableName tableNameObj = TableName.valueOf(tablename);
if (admin.tableExists(tableNameObj)) {
System.out.println("Table exists!");
System.exit(0);
} else {
HTableDescriptor tableDesc = new HTableDescriptor(TableName.valueOf(tablename));
tableDesc.addFamily(new HColumnDescriptor(columnFamily));
admin.createTable(tableDesc);
System.out.println("create table success!");
}
admin.close();
connection.close();
}
// 删除表
public static void deleteTable(String tableName) {
try {
Connection connection = ConnectionFactory.createConnection(conf);
Admin admin = connection.getAdmin();
TableName table = TableName.valueOf(tableName);
admin.disableTable(table);
admin.deleteTable(table);
System.out.println("delete table " + tableName + " ok.");
} catch (IOException e) {
e.printStackTrace();
}
}
// 插入一行记录
public static void addRecord(String tableName, String rowKey, String family, String qualifier, String value){
try {
Connection connection = ConnectionFactory.createConnection(conf);
Table table = connection.getTable(TableName.valueOf(tableName));
Put put = new Put(Bytes.toBytes(rowKey));
put.addColumn(Bytes.toBytes(family), Bytes.toBytes(qualifier), Bytes.toBytes(value));
put.addColumn(Bytes.toBytes(family), Bytes.toBytes(qualifier), Bytes.toBytes(value));
table.put(put);
table.close();
connection.close();
System.out.println("insert recored " + rowKey + " to table " + tableName + " ok.");
} catch (IOException e) {
e.printStackTrace();
}
}
public static void main(String[] args) throws Exception {
HbaseDao.createTable("testTb", "info");
HbaseDao.addRecord("testTb", "001", "info", "name", "zhangsan");
HbaseDao.addRecord("testTb", "001", "info", "age", "20");
//HbaseDao.deleteTable("testTb");
}
}
运行结果
[root@node0 ~]# hbase shell
2017-04-07 01:51:31,268 WARN [main] util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
SLF4J: Class path contains multiple SLF4J bindings.
SLF4J: Found binding in [jar:file:/usr/lib/hbase/lib/slf4j-log4j12-1.7.5.jar!/org/slf4j/impl/StaticLoggerBinder.class]
SLF4J: Found binding in [jar:file:/usr/lib/hadoop/lib/slf4j-log4j12-1.7.5.jar!/org/slf4j/impl/StaticLoggerBinder.class]
SLF4J: See http://www.slf4j.org/codes.html#multiple_bindings for an explanation.
SLF4J: Actual binding is of type [org.slf4j.impl.Log4jLoggerFactory]
HBase Shell; enter 'help<RETURN>' for list of supported commands.
Type "exit<RETURN>" to leave the HBase Shell
Version 1.2.4, r67592f3d062743907f8c5ae00dbbe1ae4f69e5af, Tue Oct 25 18:10:20 CDT 2016
hbase(main):001:0> list
TABLE
googlebook
testTb
2 row(s) in 0.2760 seconds
=> ["googlebook", "testTb"]
hbase(main):002:0> scan 'testTb'
ROW COLUMN+CELL
001 column=info:age, timestamp=1491544218337, value=20
001 column=info:name, timestamp=1491544218154, value=zhangsan
1 row(s) in 0.1980 seconds
2.6 批量导入数据
生成批量数据
[root@node0 data]# vi gen.sh
[root@node data]# cat gen.sh
#!/bin/sh
for i in {1..100000};do
echo -e $i'\t'$RANDOM'\t'$RANDOM'\t'$RANDOM
done;
[root@node0 data]# sh gen.sh > mydata.txt
[root@node0 data]# tail -10 mydata.txt
99991 5421 23010 14796
99992 8131 27221 11846
99993 20723 8007 14215
99994 20876 29543 5465
99995 14753 19926 20000
99996 26226 7228 25424
99997 18393 15515 13721
99998 1855 23042 27666
99999 16761 16120 24486
100000 14619 17100 556上传到HDFS
[root@node0 data]# hdfs dfs -put mydata.txt input
[root@node0 data]# hdfs dfs -ls input
Found 1 items
-rw-r--r-- 3 root hbase 1698432 2017-07-19 20:38 input/mydata.txt
You have mail in /var/spool/mail/root
[root@node0 data]#创建HBase表
hbase(main):021:0> create 'mydata','info'pom.xml
<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>hbaseDemo</groupId>
<artifactId>hbaseDemo</artifactId>
<version>0.0.1-SNAPSHOT</version>
<packaging>jar</packaging>
<name>hbaseDemo</name>
<url>http://maven.apache.org</url>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<hadoop.version>2.7.1</hadoop.version>
</properties>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>3.8.1</version>
<scope>test</scope>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>${hadoop.version}</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-hdfs -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.hbase/hbase-client -->
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>1.1.2</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-common</artifactId>
<version>1.1.2</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-server</artifactId>
<version>1.1.2</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.hbase/hbase-protocol -->
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-protocol</artifactId>
<version>1.1.2</version>
</dependency>
<dependency>
<groupId>jdk.tools</groupId>
<artifactId>jdk.tools</artifactId>
<version>1.8</version>
<scope>system</scope>
<systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
</dependency>
</dependencies>
</project>
编写MapReduce程序
package hbaseDemo.dao;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.mapreduce.TableOutputFormat;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
public class BatchImport {
public static class BatchImportMapper extends Mapper<LongWritable, Text, LongWritable, Text> {
protected void map(LongWritable key, Text value, Context context)
throws java.io.IOException, InterruptedException {
// super.setup( context );
//System.out.println(key + ":" + value);
context.write(key, value);
};
}
static class BatchImportReducer extends TableReducer<LongWritable, Text, NullWritable> {
protected void reduce(LongWritable key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
for (Text text : values) {
final String[] splited = text.toString().split("\t");
final Put put = new Put(Bytes.toBytes(splited[0]));// 第一列行键
put.addColumn(Bytes.toBytes("info"), Bytes.toBytes("data1"), Bytes.toBytes(splited[1]));
put.addColumn(Bytes.toBytes("info"), Bytes.toBytes("data2"), Bytes.toBytes(splited[2]));
put.addColumn(Bytes.toBytes("info"), Bytes.toBytes("data3"), Bytes.toBytes(splited[3]));
context.write(NullWritable.get(), put);
}
};
}
/**
* 之前一直报错，failed on connection exception 拒绝连接:nb0:8020
* 因为namenode节点不在192.168.1.160上，而在192.168.1.161和192.168.1.162
* @param args
* @throws Exception
*/
public static void main(String[] args) throws Exception {
final Configuration conf = new Configuration();
conf.set("hbase.rootdir", "hdfs://cetc32/hbase");
// 设置Zookeeper,直接设置IP地址
conf.set("hbase.zookeeper.quorum", "192.168.1.160,192.168.1.161,192.168.1.162");
// 设置hbase表名称(先在shell下创建一个表：create 'mydata','info')
conf.set(TableOutputFormat.OUTPUT_TABLE, "mydata");
// 将该值改大，防止hbase超时退出
conf.set("dfs.socket.timeout", "180000");
//System.setProperty("HADOOP_USER_NAME", "root");
// 设置fs.defaultFS
conf.set("fs.defaultFS", "hdfs://192.168.1.161:8020");
// 设置yarn.resourcemanager节点
conf.set("yarn.resourcemanager.hostname", "nb1");
Job job = Job.getInstance(conf);
job.setJobName("HBaseBatchImport");
job.setMapperClass(BatchImportMapper.class);
job.setReducerClass(BatchImportReducer.class);
// 设置map的输出，不设置reduce的输出类型
job.setMapOutputKeyClass(LongWritable.class);
job.setMapOutputValueClass(Text.class);
job.setInputFormatClass(TextInputFormat.class);
// 不再设置输出路径，而是设置输出格式类型
job.setOutputFormatClass(TableOutputFormat.class);
FileInputFormat.setInputPaths(job, "hdfs://192.168.1.161:8020/user/root/input/mydata.txt");
boolean flag=job.waitForCompletion(true);
System.out.println(flag);
}
}
Eclipse运行
log4j:WARN No appenders could be found for logger (org.apache.hadoop.metrics2.lib.MutableMetricsFactory).
log4j:WARN Please initialize the log4j system properly.
log4j:WARN See http://logging.apache.org/log4j/1.2/faq.html#noconfig for more info.
true查看Hbase
hbase(main):021:0> count 'mydata'
Current count: 1000, row: 10897
Current count: 2000, row: 11797
Current count: 3000, row: 12697
Current count: 4000, row: 13597
Current count: 5000, row: 14497
Current count: 6000, row: 15397
Current count: 7000, row: 16297
Current count: 8000, row: 17197
Current count: 9000, row: 18097
Current count: 10000, row: 18998
Current count: 11000, row: 19898
Current count: 12000, row: 20797
Current count: 13000, row: 21697
Current count: 14000, row: 22597
Current count: 15000, row: 23497
Current count: 16000, row: 24397
Current count: 17000, row: 25297
Current count: 18000, row: 26197
Current count: 19000, row: 27097
Current count: 20000, row: 27998
Current count: 21000, row: 28898
Current count: 22000, row: 29798
Current count: 23000, row: 30697
Current count: 24000, row: 31597
Current count: 25000, row: 32497
Current count: 26000, row: 33397
Current count: 27000, row: 34297
Current count: 28000, row: 35197
Current count: 29000, row: 36097
Current count: 30000, row: 36998
Current count: 31000, row: 37898
Current count: 32000, row: 38798
Current count: 33000, row: 39698
Current count: 34000, row: 40597
Current count: 35000, row: 41497
Current count: 36000, row: 42397
Current count: 37000, row: 43297
Current count: 38000, row: 44197
Current count: 39000, row: 45097
Current count: 40000, row: 45998
Current count: 41000, row: 46898
Current count: 42000, row: 47798
Current count: 43000, row: 48698
Current count: 44000, row: 49598
Current count: 45000, row: 50497
Current count: 46000, row: 51397
Current count: 47000, row: 52297
Current count: 48000, row: 53197
Current count: 49000, row: 54097
Current count: 50000, row: 54998
Current count: 51000, row: 55898
Current count: 52000, row: 56798
Current count: 53000, row: 57698
Current count: 54000, row: 58598
Current count: 55000, row: 59498
Current count: 56000, row: 60397
Current count: 57000, row: 61297
Current count: 58000, row: 62197
Current count: 59000, row: 63097
Current count: 60000, row: 63998
Current count: 61000, row: 64898
Current count: 62000, row: 65798
Current count: 63000, row: 66698
Current count: 64000, row: 67598
Current count: 65000, row: 68498
Current count: 66000, row: 69398
Current count: 67000, row: 70297
Current count: 68000, row: 71197
Current count: 69000, row: 72097
Current count: 70000, row: 72998
Current count: 71000, row: 73898
Current count: 72000, row: 74798
Current count: 73000, row: 75698
Current count: 74000, row: 76598
Current count: 75000, row: 77498
Current count: 76000, row: 78398
Current count: 77000, row: 79298
Current count: 78000, row: 80197
Current count: 79000, row: 81097
Current count: 80000, row: 81998
Current count: 81000, row: 82898
Current count: 82000, row: 83798
Current count: 83000, row: 84698
Current count: 84000, row: 85598
Current count: 85000, row: 86498
Current count: 86000, row: 87398
Current count: 87000, row: 88298
Current count: 88000, row: 89198
Current count: 89000, row: 90097
Current count: 90000, row: 90998
Current count: 91000, row: 91898
Current count: 92000, row: 92798
Current count: 93000, row: 93698
Current count: 94000, row: 94598
Current count: 95000, row: 95498
Current count: 96000, row: 96398
Current count: 97000, row: 97298
Current count: 98000, row: 98198
Current count: 99000, row: 99098
Current count: 100000, row: 99999
100000 row(s) in 7.0460 seconds
=> 100000
hbase(main):022:0>
扫一扫
170
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
