Hadoop 中利用 mapreduce 读写 mysql 数据

cocoIT

浏览: 50988 次
性别:
来自: 福建

最近访客更多访客>>

HincZhang

jack1007

画个逗号给明天qu

xiaoyulong1988

博主相关

博客

微博

相册

留言

关于我

文章分类

全部博客 (101)

社区版块

存档分类

有时候我们在项目中会遇到输入结果集很大，但是输出结果很小，比如一些 pv、uv 数据，然后为了实时查询的需求，或者一些 OLAP 的需求，我们需要 mapreduce 与 mysql 进行数据的交互，而这些特性正是 hbase 或者 hive 目前亟待改进的地方。

好了言归正传，简单的说说背景、原理以及需要注意的地方：

1、为了方便 MapReduce 直接访问关系型数据库（Mysql,Oracle），Hadoop提供了DBInputFormat和DBOutputFormat两个类。通过DBInputFormat类把数据库表数据读入到HDFS，根据DBOutputFormat类把MapReduce产生的结果集导入到数据库表中。

2、由于0.20版本对DBInputFormat和DBOutputFormat支持不是很好，该例用了0.19版本来说明这两个类的用法。

至少在我的 0.20.203 中的org.apache.hadoop.mapreduce.lib 下是没见到 db 包，所以本文也是以老版的 API 来为例说明的。

3、运行MapReduce时候报错：java.io.IOException: com.mysql.jdbc.Driver，一般是由于程序找不到mysql驱动包。解决方法是让每个tasktracker运行MapReduce程序时都可以找到该驱动包。

添加包有两种方式：

（1）在每个节点下的${HADOOP_HOME}/lib下添加该包。重启集群，一般是比较原始的方法。

（2）a)把包传到集群上： hadoop fs -put mysql-connector-java-5.1.0- bin.jar /hdfsPath/

b)在mr程序提交job前，添加语句：DistributedCache.addFileToClassPath(new Path(“/hdfsPath/mysql- connector-java- 5.1.0-bin.jar”), conf);

（3）虽然API用的是0.19的，但是使用0.20的API一样可用，只是会提示方法已过时而已。

4、测试数据：

CREATE TABLE `t` (
`id` int DEFAULT NULL,
`name` varchar(10) DEFAULT NULL
) ENGINE=InnoDB DEFAULT CHARSET=utf8;

CREATE TABLE `t2` (
`id` int DEFAULT NULL,
`name` varchar(10) DEFAULT NULL
) ENGINE=InnoDB DEFAULT CHARSET=utf8;

insert into t values (1,"june"),(2,"decli"),(3,"hello"),
	(4,"june"),(5,"decli"),(6,"hello"),(7,"june"),
	(8,"decli"),(9,"hello"),(10,"june"),
	(11,"june"),(12,"decli"),(13,"hello");

5、代码：

package mysql2mr;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.File;
import java.io.IOException;
import java.sql.PreparedStatement;
import java.sql.ResultSet;
import java.sql.SQLException;

import mapr.EJob;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.filecache.DistributedCache;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.db.DBConfiguration;
import org.apache.hadoop.mapreduce.lib.db.DBInputFormat;
import org.apache.hadoop.mapreduce.lib.db.DBOutputFormat;
import org.apache.hadoop.mapreduce.lib.db.DBWritable;

/**
 * Function: 测试 mr 与 mysql 的数据交互，此测试用例将一个表中的数据复制到另一张表中 实际当中，可能只需要从 mysql 读，或者写到
 * mysql 中。
 * 
 * @author administrator
 * 
 */
public class Mysql2Mr {
	public static class StudentinfoRecord implements Writable, DBWritable {
		int id;
		String name;

		public StudentinfoRecord() {

		}

		public String toString() {
			return new String(this.id + " " + this.name);
		}

		@Override
		public void readFields(ResultSet result) throws SQLException {
			this.id = result.getInt(1);
			this.name = result.getString(2);
		}

		@Override
		public void write(PreparedStatement stmt) throws SQLException {
			stmt.setInt(1, this.id);
			stmt.setString(2, this.name);
		}

		@Override
		public void readFields(DataInput in) throws IOException {
			this.id = in.readInt();
			this.name = Text.readString(in);
		}

		@Override
		public void write(DataOutput out) throws IOException {
			out.writeInt(this.id);
			Text.writeString(out, this.name);
		}

	}

	// 记住此处是静态内部类，要不然你自己实现无参构造器，或者等着抛异常：
    // Caused by: java.lang.NoSuchMethodException: DBInputMapper.<init>()
    // http://stackoverflow.com/questions/7154125/custom-mapreduce-input-format-cant-find-constructor
    // 网上脑残式的转帖，没见到一个写对的。。。
	public static class DBInputMapper extends
			Mapper<LongWritable, StudentinfoRecord, LongWritable, Text> {
		@Override
		public void map(LongWritable key, StudentinfoRecord value,
				Context context) throws IOException, InterruptedException {
			context.write(new LongWritable(value.id), new Text(value.toString()));
		}
	}

	
	public static class MyReducer extends Reducer<LongWritable, Text, StudentinfoRecord, Text> {
		@Override
		public void reduce(LongWritable key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
			String[] splits = values.iterator().next().toString().split(" ");
			StudentinfoRecord r = new StudentinfoRecord();
			r.id = Integer.parseInt(splits[0]);
			r.name = splits[1];
			context.write(r, new Text(r.name));
			
		}
	}
	
	@SuppressWarnings("deprecation")
	public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
		File jarfile = EJob.createTempJar("bin");
		EJob.addClasspath("usr/hadoop/conf");

		ClassLoader classLoader = EJob.getClassLoader();
		Thread.currentThread().setContextClassLoader(classLoader);
		
		Configuration conf = new Configuration();
		// 这句话很关键
		conf.set("mapred.job.tracker", "172.30.1.245:9001");
		DistributedCache.addFileToClassPath(new Path(
				"hdfs://172.30.1.245:9000/user/hadoop/jar/mysql-connector-java-5.1.6-bin.jar"), conf);
		DBConfiguration.configureDB(conf, "com.mysql.jdbc.Driver", "jdbc:mysql://172.30.1.245:3306/sqooptest", "sqoop", "sqoop");
		
		Job job = new  Job(conf, "Mysql2Mr");
//		job.setJarByClass(Mysql2Mr.class);
		((JobConf)job.getConfiguration()).setJar(jarfile.toString());
		job.setMapOutputKeyClass(LongWritable.class);
		job.setMapOutputValueClass(Text.class);
		
		job.setMapperClass(DBInputMapper.class);
		job.setReducerClass(MyReducer.class);
		
		job.setOutputKeyClass(LongWritable.class);
		job.setOutputValueClass(Text.class);
		
		job.setOutputFormatClass(DBOutputFormat.class);
		job.setInputFormatClass(DBInputFormat.class);
		
		String[] fields = {"id","name"};
		 // 从 t 表读数据
		DBInputFormat.setInput(job, StudentinfoRecord.class, "t", null, "id", fields);
		// mapreduce 将数据输出到 t2 表
		DBOutputFormat.setOutput(job, "t2", "id", "name");
		
		System.exit(job.waitForCompletion(true)? 0:1);
	}
}

6、结果：

执行两次后，你可以看到mysql结果：

mysql> select * from t2;
+------+-------+
| id   | name  |
+------+-------+
|    1 | june  |
|    2 | decli |
|    3 | hello |
|    4 | june  |
|    5 | decli |
|    6 | hello |
|    7 | june  |
|    8 | decli |
|    9 | hello |
|   10 | june  |
|   11 | june  |
|   12 | decli |
|   13 | hello |
|    1 | june  |
|    2 | decli |
|    3 | hello |
|    4 | june  |
|    5 | decli |
|    6 | hello |
|    7 | june  |
|    8 | decli |
|    9 | hello |
|   10 | june  |
|   11 | june  |
|   12 | decli |
|   13 | hello |
+------+-------+
26 rows in set (0.00 sec)

mysql>

分享到：