Hadoop 中利用 mapreduce 讀寫 mysql 數據

時間 2019-11-06

標籤 hadoop 利用 mapreduce 讀寫 mysql 數據欄目 Hadoop 简体版

原文原文鏈接

有時候咱們在項目中會遇到輸入結果集很大，可是輸出結果很小，好比一些 pv、uv 數據，而後爲了實時查詢的需求，或者一些 OLAP 的需求，咱們須要 mapreduce 與 mysql 進行數據的交互，而這些特性正是 hbase 或者 hive 目前亟待改進的地方。 java

好了言歸正傳，簡單的說說背景、原理以及須要注意的地方： mysql

一、爲了方便 MapReduce 直接訪問關係型數據庫（Mysql,Oracle），Hadoop提供了DBInputFormat和DBOutputFormat兩個類。經過DBInputFormat類把數據庫表數據讀入到HDFS，根據DBOutputFormat類把MapReduce產生的結果集導入到數據庫表中。 sql

二、因爲0.20版本對DBInputFormat和DBOutputFormat支持不是很好，該例用了0.19版原本說明這兩個類的用法。 shell

至少在個人 0.20.203 中的 org.apache.hadoop.mapreduce.lib 下是沒見到 db 包，因此本文也是以老版的 API 來爲例說明的。數據庫

三、運行MapReduce時候報錯：java.io.IOException: com.mysql.jdbc.Driver，通常是因爲程序找不到mysql驅動包。解決方法是讓每一個tasktracker運行MapReduce程序時均可以找到該驅動包。 apache

添加包有兩種方式： app

（1）在每一個節點下的${HADOOP_HOME}/lib下添加該包。重啓集羣，通常是比較原始的方法。 ide

（2）a)把包傳到集羣上： hadoop fs -put mysql-connector-java-5.1.0- bin.jar /hdfsPath/ oop

b)在mr程序提交job前，添加語句：DistributedCache.addFileToClassPath(new Path(「/hdfsPath/mysql- connector-java- 5.1.0-bin.jar」), conf); 測試

（3）雖然API用的是0.19的，可是使用0.20的API同樣可用，只是會提示方法已過期而已。

四、測試數據：

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");

五、代碼：

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

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.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.lib.IdentityReducer;
import org.apache.hadoop.mapred.lib.db.DBConfiguration;
import org.apache.hadoop.mapred.lib.db.DBInputFormat;
import org.apache.hadoop.mapred.lib.db.DBOutputFormat;
import org.apache.hadoop.mapred.lib.db.DBWritable;

/**
 * Function: 測試 mr 與 mysql 的數據交互，此測試用例將一個表中的數據複製到另外一張表中
 * 			 實際當中，可能只須要從 mysql 讀，或者寫到 mysql 中。
 * date: 2013-7-29 上午2:34:04 <br/>
 * @author june
 */
public class Mysql2Mr {
	// DROP TABLE IF EXISTS `hadoop`.`studentinfo`;
	// CREATE TABLE studentinfo (
	// id INTEGER NOT NULL PRIMARY KEY,
	// name VARCHAR(32) NOT NULL);

	public static class StudentinfoRecord implements Writable, DBWritable {
		int id;
		String name;

		public StudentinfoRecord() {

		}

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

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

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

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

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

	// 記住此處是靜態內部類，要否則你本身實現無參構造器，或者等着拋異常：
	// Caused by: java.lang.NoSuchMethodException: DBInputMapper.<init>()
	// http://stackoverflow.com/questions/7154125/custom-mapreduce-input-format-cant-find-constructor
	// 網上腦殘式的轉帖，沒見到一個寫對的。。。
	public static class DBInputMapper extends MapReduceBase implements
			Mapper<LongWritable, StudentinfoRecord, LongWritable, Text> {
		public void map(LongWritable key, StudentinfoRecord value,
				OutputCollector<LongWritable, Text> collector, Reporter reporter) throws IOException {
			collector.collect(new LongWritable(value.id), new Text(value.toString()));
		}
	}

	public static class MyReducer extends MapReduceBase implements
			Reducer<LongWritable, Text, StudentinfoRecord, Text> {
		@Override
		public void reduce(LongWritable key, Iterator<Text> values,
				OutputCollector<StudentinfoRecord, Text> output, Reporter reporter) throws IOException {
			String[] splits = values.next().toString().split(" ");
			StudentinfoRecord r = new StudentinfoRecord();
			r.id = Integer.parseInt(splits[0]);
			r.name = splits[1];
			output.collect(r, new Text(r.name));
		}
	}

	public static void main(String[] args) throws IOException {
		JobConf conf = new JobConf(Mysql2Mr.class);
		DistributedCache.addFileToClassPath(new Path("/tmp/mysql-connector-java-5.0.8-bin.jar"), conf);

		conf.setMapOutputKeyClass(LongWritable.class);
		conf.setMapOutputValueClass(Text.class);
		conf.setOutputKeyClass(LongWritable.class);
		conf.setOutputValueClass(Text.class);

		conf.setOutputFormat(DBOutputFormat.class);
		conf.setInputFormat(DBInputFormat.class);
		// // mysql to hdfs
		// conf.setReducerClass(IdentityReducer.class);
		// Path outPath = new Path("/tmp/1");
		// FileSystem.get(conf).delete(outPath, true);
		// FileOutputFormat.setOutputPath(conf, outPath);

		DBConfiguration.configureDB(conf, "com.mysql.jdbc.Driver", "jdbc:mysql://192.168.1.101:3306/test",
				"root", "root");
		String[] fields = { "id", "name" };
		// 從 t 表讀數據
		DBInputFormat.setInput(conf, StudentinfoRecord.class, "t", null, "id", fields);
		// mapreduce 將數據輸出到 t2 表
		DBOutputFormat.setOutput(conf, "t2", "id", "name");
		// conf.setMapperClass(org.apache.hadoop.mapred.lib.IdentityMapper.class);
		conf.setMapperClass(DBInputMapper.class);
		conf.setReducerClass(MyReducer.class);

		JobClient.runJob(conf);
	}
}

六、結果：

執行兩次後，你能夠看到mysql結果：

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>

七、日誌：

13/07/29 02:33:03 WARN mapred.JobClient: Use GenericOptionsParser for parsing the arguments. Applications should implement Tool for the same.
13/07/29 02:33:03 INFO filecache.TrackerDistributedCacheManager: Creating mysql-connector-java-5.0.8-bin.jar in /tmp/hadoop-june/mapred/local/archive/-8943686319031389138_-1232673160_640840668/192.168.1.101/tmp-work--8372797484204470322 with rwxr-xr-x
13/07/29 02:33:03 INFO filecache.TrackerDistributedCacheManager: Cached hdfs://192.168.1.101:9000/tmp/mysql-connector-java-5.0.8-bin.jar as /tmp/hadoop-june/mapred/local/archive/-8943686319031389138_-1232673160_640840668/192.168.1.101/tmp/mysql-connector-java-5.0.8-bin.jar
13/07/29 02:33:03 INFO filecache.TrackerDistributedCacheManager: Cached hdfs://192.168.1.101:9000/tmp/mysql-connector-java-5.0.8-bin.jar as /tmp/hadoop-june/mapred/local/archive/-8943686319031389138_-1232673160_640840668/192.168.1.101/tmp/mysql-connector-java-5.0.8-bin.jar
13/07/29 02:33:03 INFO mapred.JobClient: Running job: job_local_0001
13/07/29 02:33:03 INFO mapred.MapTask: numReduceTasks: 1
13/07/29 02:33:03 INFO mapred.MapTask: io.sort.mb = 100
13/07/29 02:33:03 INFO mapred.MapTask: data buffer = 79691776/99614720
13/07/29 02:33:03 INFO mapred.MapTask: record buffer = 262144/327680
13/07/29 02:33:03 INFO mapred.MapTask: Starting flush of map output
13/07/29 02:33:03 INFO mapred.MapTask: Finished spill 0
13/07/29 02:33:03 INFO mapred.Task: Task:attempt_local_0001_m_000000_0 is done. And is in the process of commiting
13/07/29 02:33:04 INFO mapred.JobClient:  map 0% reduce 0%
13/07/29 02:33:06 INFO mapred.LocalJobRunner: 
13/07/29 02:33:06 INFO mapred.Task: Task 'attempt_local_0001_m_000000_0' done.
13/07/29 02:33:06 INFO mapred.LocalJobRunner: 
13/07/29 02:33:06 INFO mapred.Merger: Merging 1 sorted segments
13/07/29 02:33:06 INFO mapred.Merger: Down to the last merge-pass, with 1 segments left of total size: 235 bytes
13/07/29 02:33:06 INFO mapred.LocalJobRunner: 
13/07/29 02:33:06 INFO mapred.Task: Task:attempt_local_0001_r_000000_0 is done. And is in the process of commiting
13/07/29 02:33:07 INFO mapred.JobClient:  map 100% reduce 0%
13/07/29 02:33:09 INFO mapred.LocalJobRunner: reduce > reduce
13/07/29 02:33:09 INFO mapred.Task: Task 'attempt_local_0001_r_000000_0' done.
13/07/29 02:33:09 WARN mapred.FileOutputCommitter: Output path is null in cleanup
13/07/29 02:33:10 INFO mapred.JobClient:  map 100% reduce 100%
13/07/29 02:33:10 INFO mapred.JobClient: Job complete: job_local_0001
13/07/29 02:33:10 INFO mapred.JobClient: Counters: 18
13/07/29 02:33:10 INFO mapred.JobClient:   File Input Format Counters 
13/07/29 02:33:10 INFO mapred.JobClient:     Bytes Read=0
13/07/29 02:33:10 INFO mapred.JobClient:   File Output Format Counters 
13/07/29 02:33:10 INFO mapred.JobClient:     Bytes Written=0
13/07/29 02:33:10 INFO mapred.JobClient:   FileSystemCounters
13/07/29 02:33:10 INFO mapred.JobClient:     FILE_BYTES_READ=1211691
13/07/29 02:33:10 INFO mapred.JobClient:     HDFS_BYTES_READ=1081704
13/07/29 02:33:10 INFO mapred.JobClient:     FILE_BYTES_WRITTEN=2392844
13/07/29 02:33:10 INFO mapred.JobClient:   Map-Reduce Framework
13/07/29 02:33:10 INFO mapred.JobClient:     Map output materialized bytes=239
13/07/29 02:33:10 INFO mapred.JobClient:     Map input records=13
13/07/29 02:33:10 INFO mapred.JobClient:     Reduce shuffle bytes=0
13/07/29 02:33:10 INFO mapred.JobClient:     Spilled Records=26
13/07/29 02:33:10 INFO mapred.JobClient:     Map output bytes=207
13/07/29 02:33:10 INFO mapred.JobClient:     Map input bytes=13
13/07/29 02:33:10 INFO mapred.JobClient:     SPLIT_RAW_BYTES=75
13/07/29 02:33:10 INFO mapred.JobClient:     Combine input records=0
13/07/29 02:33:10 INFO mapred.JobClient:     Reduce input records=13
13/07/29 02:33:10 INFO mapred.JobClient:     Reduce input groups=13
13/07/29 02:33:10 INFO mapred.JobClient:     Combine output records=0
13/07/29 02:33:10 INFO mapred.JobClient:     Reduce output records=13
13/07/29 02:33:10 INFO mapred.JobClient:     Map output records=13

八、REF：

新版 API 寫法：

http://superlxw1234.iteye.com/blog/1880712

老版：

http://blog.csdn.net/dajuezhao/article/details/5799371

http://www.zhengmenbb.com/archives/583.htm