2、hbase 基本操作及性能优化

Hbase的API介绍

• 准备操作
  
• Hbase的DDL操作
  
• Hbase的DML操作：
  
• hbase的查询操作：查询hbase数据库中某一列族下的某一列的值，查询是要指定具体的rowKey
  
• HBase之六：HBase的RowKey设计
  https://www.cnblogs.com/duanxz/p/4660784.html
  

hbaseprotobuf讲解

• 安装 Google Protocol Buffer
  展示安装的组信息：
  查看软件需要依赖的组信息
  安装依赖的工具：
  
  
  
• 编辑phone.proto
  
• 利用protobuf工具生成对应的java文件
  
• 将多个列封装为对象，将整个对象插入到hbase数据表中
  

Hbase的优化

查看hbase的优化文档

Hbase与map/reducer的整合

package com.bjsxt.wc;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;


public class WCRunner {

	public static void main(String[] args) throws Exception {
		
		Configuration conf = new Configuration();
		conf.set("fs.defaultFS", "hdfs://node02:8020");
		conf.set("hbase.zookeeper.quorum", "node02,node03,node04");
		Job job = Job.getInstance(conf);
		job.setJarByClass(WCRunner.class);
		
		//指定mapper和reducer
		job.setMapperClass(WCMapper.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		//最后一个参数设置为false
		TableMapReduceUtil.initTableReducerJob("wc", WCReducer.class, job, null, null, null, null, false);
		
		FileInputFormat.addInputPath(job, new Path("/user/hive/warehouse/wc/"));
		job.waitForCompletion(true);
		
		
	}

}


package com.bjsxt.wc;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WCMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
	
	@Override
	protected void map(LongWritable key, Text value, Context context)
			throws IOException, InterruptedException {
		String[] strs = value.toString().split(" ");
		for (String string : strs) {
			context.write(new Text(string), new IntWritable(1));
		}
	}
}


package com.bjsxt.wc;

import java.io.IOException;

import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;

public class WCReducer extends TableReducer<Text, IntWritable, ImmutableBytesWritable>{
	
	@Override
	protected void reduce(Text text, Iterable<IntWritable> iterable,Context context)
			throws IOException, InterruptedException {
		
		int sum = 0;
		
		for (IntWritable it : iterable) {
			sum+=it.get();
		}
		
		Put put = new Put(text.toString().getBytes());
		
		put.add("cf".getBytes(), "ct".getBytes(), (""+sum).getBytes());
		
		context.write(null, put);
	}
}