问题导读
1.hadoop mapreduce的通过哪两个类可以读取数据源?
2.如果没有mysql驱动包,一般会是什么问题?
3.如何添加包?
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:
1. CREATE TABLE `t` (
2. `id` int DEFAULT NULL,
3. `name` varchar(10) DEFAULT NULL
4. ) ENGINE=InnoDB DEFAULT CHARSET=utf8;
5.
6. CREATE TABLE `t2` (
7. `id` int DEFAULT NULL,
8. `name` varchar(10) DEFAULT NULL
9. ) ENGINE=InnoDB DEFAULT CHARSET=utf8;
10.
11. insert into t values (1,"june"),(2,"decli"),(3,"hello"),
12. (4,"june"),(5,"decli"),(6,"hello"),(7,"june"),
13. (8,"decli"),(9,"hello"),(10,"june"),
14. (11,"june"),(12,"decli"),(13,"hello");
复制代码
5、代码:
1. import java.io.DataInput;
2. import java.io.DataOutput;
3. import java.io.IOException;
4. import java.sql.PreparedStatement;
5. import java.sql.ResultSet;
6. import java.sql.SQLException;
7. import java.util.Iterator;
8.
9. import org.apache.hadoop.filecache.DistributedCache;
10. import org.apache.hadoop.fs.Path;
11. import org.apache.hadoop.io.LongWritable;
12. import org.apache.hadoop.io.Text;
13. import org.apache.hadoop.io.Writable;
14. import org.apache.hadoop.mapred.JobClient;
15. import org.apache.hadoop.mapred.JobConf;
16. import org.apache.hadoop.mapred.MapReduceBase;
17. import org.apache.hadoop.mapred.Mapper;
18. import org.apache.hadoop.mapred.OutputCollector;
19. import org.apache.hadoop.mapred.Reducer;
20. import org.apache.hadoop.mapred.Reporter;
21. import org.apache.hadoop.mapred.lib.IdentityReducer;
22. import org.apache.hadoop.mapred.lib.db.DBConfiguration;
23. import org.apache.hadoop.mapred.lib.db.DBInputFormat;
24. import org.apache.hadoop.mapred.lib.db.DBOutputFormat;
25. import org.apache.hadoop.mapred.lib.db.DBWritable;
26.
27. /**
28. * 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
29. * 实际当中,可能只需要从 mysql 读,或者写到 mysql 中。
30. * date: 2013-7-29 上午2:34:04 <br/>
31. * @author june
32. */
33. public class Mysql2Mr {
34. // DROP TABLE IF EXISTS `hadoop`.`studentinfo`;
35. // CREATE TABLE studentinfo (
36. // id INTEGER NOT NULL PRIMARY KEY,
37. // name VARCHAR(32) NOT NULL);
38.
39. public static class StudentinfoRecord implements Writable, DBWritable {
40. int id;
41. String name;
42.
43. public StudentinfoRecord() {
44.
45. }
46.
47. public void readFields(DataInput in) throws IOException {
48. this.id = in.readInt();
49. this.name = Text.readString(in);
50. }
51.
52. public String toString() {
53. return new String(this.id + " " + this.name);
54. }
55.
56. @Override
57. public void write(PreparedStatement stmt) throws SQLException {
58. stmt.setInt(1, this.id);
59. stmt.setString(2, this.name);
60. }
61.
62. @Override
63. public void readFields(ResultSet result) throws SQLException {
64. this.id = result.getInt(1);
65. this.name = result.getString(2);
66. }
67.
68. @Override
69. public void write(DataOutput out) throws IOException {
70. out.writeInt(this.id);
71. Text.writeString(out, this.name);
72. }
73. }
74.
75. // 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:
76. // Caused by: java.lang.NoSuchMethodException: DBInputMapper.<init>()
77. // http://stackoverflow.com/questions/7154125/custom-mapreduce-input-format-cant-find-constructor
78. // 网上脑残式的转帖,没见到一个写对的。。。
79. public static class DBInputMapper extends MapReduceBase implements
80. Mapper<LongWritable, StudentinfoRecord, LongWritable, Text> {
81. public void map(LongWritable key, StudentinfoRecord value,
82. OutputCollector<LongWritable, Text> collector, Reporter reporter) throws IOException {
83. collector.collect(new LongWritable(value.id), new Text(value.toString()));
84. }
85. }
86.
87. public static class MyReducer extends MapReduceBase implements
88. Reducer<LongWritable, Text, StudentinfoRecord, Text> {
89. @Override
90. public void reduce(LongWritable key, Iterator<Text> values,
91. OutputCollector<StudentinfoRecord, Text> output, Reporter reporter) throws IOException {
92. String[] splits = values.next().toString().split(" ");
93. StudentinfoRecord r = new StudentinfoRecord();
94. r.id = Integer.parseInt(splits[0]);
95. r.name = splits[1];
96. output.collect(r, new Text(r.name));
97. }
98. }
99.
100. public static void main(String[] args) throws IOException {
101. JobConf conf = new JobConf(Mysql2Mr.class);
102. DistributedCache.addFileToClassPath(new Path("/tmp/mysql-connector-java-5.0.8-bin.jar"), conf);
103.
104. conf.setMapOutputKeyClass(LongWritable.class);
105. conf.setMapOutputValueClass(Text.class);
106. conf.setOutputKeyClass(LongWritable.class);
107. conf.setOutputValueClass(Text.class);
108.
109. conf.setOutputFormat(DBOutputFormat.class);
110. conf.setInputFormat(DBInputFormat.class);
111. // // mysql to hdfs
112. // conf.setReducerClass(IdentityReducer.class);
113. // Path outPath = new Path("/tmp/1");
114. // FileSystem.get(conf).delete(outPath, true);
115. // FileOutputFormat.setOutputPath(conf, outPath);
116.
117. DBConfiguration.configureDB(conf, "com.mysql.jdbc.Driver", "jdbc:mysql://192.168.1.101:3306/test",
118. "root", "root");
119. String[] fields = { "id", "name" };
120. // 从 t 表读数据
121. DBInputFormat.setInput(conf, StudentinfoRecord.class, "t", null, "id", fields);
122. // mapreduce 将数据输出到 t2 表
123. DBOutputFormat.setOutput(conf, "t2", "id", "name");
124. // conf.setMapperClass(org.apache.hadoop.mapred.lib.IdentityMapper.class);
125. conf.setMapperClass(DBInputMapper.class);
126. conf.setReducerClass(MyReducer.class);
127.
128. JobClient.runJob(conf);
129. }
130. }
复制代码
6、结果:
执行两次后,你可以看到mysql结果:
1. mysql> select * from t2;
2. +------+-------+
3. | id | name |
4. +------+-------+
5. | 1 | june |
6. | 2 | decli |
7. | 3 | hello |
8. | 4 | june |
9. | 5 | decli |
10. | 6 | hello |
11. | 7 | june |
12. | 8 | decli |
13. | 9 | hello |
14. | 10 | june |
15. | 11 | june |
16. | 12 | decli |
17. | 13 | hello |
18. | 1 | june |
19. | 2 | decli |
20. | 3 | hello |
21. | 4 | june |
22. | 5 | decli |
23. | 6 | hello |
24. | 7 | june |
25. | 8 | decli |
26. | 9 | hello |
27. | 10 | june |
28. | 11 | june |
29. | 12 | decli |
30. | 13 | hello |
31. +------+-------+
32. 26 rows in set (0.00 sec)
33.
34. mysql>
复制代码
7、日志:
1. 13/07/29 02:33:03 WARN mapred.JobClient: Use GenericOptionsParser for parsing the arguments. Applications should implement Tool for the same.
2. 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
3. 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
4. 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
5. 13/07/29 02:33:03 INFO mapred.JobClient: Running job: job_local_0001
6. 13/07/29 02:33:03 INFO mapred.MapTask: numReduceTasks: 1
7. 13/07/29 02:33:03 INFO mapred.MapTask: io.sort.mb = 100
8. 13/07/29 02:33:03 INFO mapred.MapTask: data buffer = 79691776/99614720
9. 13/07/29 02:33:03 INFO mapred.MapTask: record buffer = 262144/327680
10. 13/07/29 02:33:03 INFO mapred.MapTask: Starting flush of map output
11. 13/07/29 02:33:03 INFO mapred.MapTask: Finished spill 0
12. 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. 13/07/29 02:33:04 INFO mapred.JobClient: map 0% reduce 0%
14. 13/07/29 02:33:06 INFO mapred.LocalJobRunner:
15. 13/07/29 02:33:06 INFO mapred.Task: Task 'attempt_local_0001_m_000000_0' done.
16. 13/07/29 02:33:06 INFO mapred.LocalJobRunner:
17. 13/07/29 02:33:06 INFO mapred.Merger: Merging 1 sorted segments
18. 13/07/29 02:33:06 INFO mapred.Merger: Down to the last merge-pass, with 1 segments left of total size: 235 bytes
19. 13/07/29 02:33:06 INFO mapred.LocalJobRunner:
20. 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
21. 13/07/29 02:33:07 INFO mapred.JobClient: map 100% reduce 0%
22. 13/07/29 02:33:09 INFO mapred.LocalJobRunner: reduce > reduce
23. 13/07/29 02:33:09 INFO mapred.Task: Task 'attempt_local_0001_r_000000_0' done.
24. 13/07/29 02:33:09 WARN mapred.FileOutputCommitter: Output path is null in cleanup
25. 13/07/29 02:33:10 INFO mapred.JobClient: map 100% reduce 100%
26. 13/07/29 02:33:10 INFO mapred.JobClient: Job complete: job_local_0001
27. 13/07/29 02:33:10 INFO mapred.JobClient: Counters: 18
28. 13/07/29 02:33:10 INFO mapred.JobClient: File Input Format Counters
29. 13/07/29 02:33:10 INFO mapred.JobClient: Bytes Read=0
30. 13/07/29 02:33:10 INFO mapred.JobClient: File Output Format Counters
31. 13/07/29 02:33:10 INFO mapred.JobClient: Bytes Written=0
32. 13/07/29 02:33:10 INFO mapred.JobClient: FileSystemCounters
33. 13/07/29 02:33:10 INFO mapred.JobClient: FILE_BYTES_READ=1211691
34. 13/07/29 02:33:10 INFO mapred.JobClient: HDFS_BYTES_READ=1081704
35. 13/07/29 02:33:10 INFO mapred.JobClient: FILE_BYTES_WRITTEN=2392844
36. 13/07/29 02:33:10 INFO mapred.JobClient: Map-Reduce Framework
37. 13/07/29 02:33:10 INFO mapred.JobClient: Map output materialized bytes=239
38. 13/07/29 02:33:10 INFO mapred.JobClient: Map input records=13
39. 13/07/29 02:33:10 INFO mapred.JobClient: Reduce shuffle bytes=0
40. 13/07/29 02:33:10 INFO mapred.JobClient: Spilled Records=26
41. 13/07/29 02:33:10 INFO mapred.JobClient: Map output bytes=207
42. 13/07/29 02:33:10 INFO mapred.JobClient: Map input bytes=13
43. 13/07/29 02:33:10 INFO mapred.JobClient: SPLIT_RAW_BYTES=75
44. 13/07/29 02:33:10 INFO mapred.JobClient: Combine input records=0
45. 13/07/29 02:33:10 INFO mapred.JobClient: Reduce input records=13
46. 13/07/29 02:33:10 INFO mapred.JobClient: Reduce input groups=13
47. 13/07/29 02:33:10 INFO mapred.JobClient: Combine output records=0
48. 13/07/29 02:33:10 INFO mapred.JobClient: Reduce output records=13
49. 13/07/29 02:33:10 INFO mapred.JobClient: Map output records=13
复制代码
MapReduce直接连接Mysql获取数据
Mysql中数据:
1. mysql> select * from lxw_tbls;
2. +---------------------+----------------+
3. | TBL_NAME | TBL_TYPE |
4. +---------------------+----------------+
5. | lxw_test_table | EXTERNAL_TABLE |
6. | lxw_t | MANAGED_TABLE |
7. | lxw_t1 | MANAGED_TABLE |
8. | tt | MANAGED_TABLE |
9. | tab_partition | MANAGED_TABLE |
10. | lxw_hbase_table_1 | MANAGED_TABLE |
11. | lxw_hbase_user_info | MANAGED_TABLE |
12. | t | EXTERNAL_TABLE |
13. | lxw_jobid | MANAGED_TABLE |
14. +---------------------+----------------+
15. 9 rows in set (0.01 sec)
16.
17. mysql> select * from lxw_tbls where TBL_NAME like 'lxw%' order by TBL_NAME;
18. +---------------------+----------------+
19. | TBL_NAME | TBL_TYPE |
20. +---------------------+----------------+
21. | lxw_hbase_table_1 | MANAGED_TABLE |
22. | lxw_hbase_user_info | MANAGED_TABLE |
23. | lxw_jobid | MANAGED_TABLE |
24. | lxw_t | MANAGED_TABLE |
25. | lxw_t1 | MANAGED_TABLE |
26. | lxw_test_table | EXTERNAL_TABLE |
27. +---------------------+----------------+
28. 6 rows in set (0.00 sec)
复制代码
MapReduce程序代码,ConnMysql.java:
1. package com.lxw.study;
2.
3. import java.io.DataInput;
4. import java.io.DataOutput;
5. import java.io.IOException;
6. import java.net.URI;
7. import java.sql.PreparedStatement;
8. import java.sql.ResultSet;
9. import java.sql.SQLException;
10. import java.util.Iterator;
11.
12. import org.apache.hadoop.conf.Configuration;
13. import org.apache.hadoop.filecache.DistributedCache;
14. import org.apache.hadoop.fs.FileSystem;
15. import org.apache.hadoop.fs.Path;
16. import org.apache.hadoop.io.LongWritable;
17. import org.apache.hadoop.io.Text;
18. import org.apache.hadoop.io.Writable;
19. import org.apache.hadoop.mapreduce.Job;
20. import org.apache.hadoop.mapreduce.Mapper;
21. import org.apache.hadoop.mapreduce.Reducer;
22. import org.apache.hadoop.mapreduce.lib.db.DBConfiguration;
23. import org.apache.hadoop.mapreduce.lib.db.DBInputFormat;
24. import org.apache.hadoop.mapreduce.lib.db.DBWritable;
25. import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
26.
27. public class ConnMysql {
28.
29. private static Configuration conf = new Configuration();
30.
31. static {
32. conf.addResource(new Path("F:/lxw-hadoop/hdfs-site.xml"));
33. conf.addResource(new Path("F:/lxw-hadoop/mapred-site.xml"));
34. conf.addResource(new Path("F:/lxw-hadoop/core-site.xml"));
35. conf.set("mapred.job.tracker", "10.133.103.21:50021");
36. }
37.
38. public static class TblsRecord implements Writable, DBWritable {
39. String tbl_name;
40. String tbl_type;
41.
42. public TblsRecord() {
43.
44. }
45.
46. @Override
47. public void write(PreparedStatement statement) throws SQLException {
48. // TODO Auto-generated method stub
49. statement.setString(1, this.tbl_name);
50. statement.setString(2, this.tbl_type);
51. }
52.
53. @Override
54. public void readFields(ResultSet resultSet) throws SQLException {
55. // TODO Auto-generated method stub
56. this.tbl_name = resultSet.getString(1);
57. this.tbl_type = resultSet.getString(2);
58. }
59.
60. @Override
61. public void write(DataOutput out) throws IOException {
62. // TODO Auto-generated method stub
63. Text.writeString(out, this.tbl_name);
64. Text.writeString(out, this.tbl_type);
65. }
66.
67. @Override
68. public void readFields(DataInput in) throws IOException {
69. // TODO Auto-generated method stub
70. this.tbl_name = Text.readString(in);
71. this.tbl_type = Text.readString(in);
72. }
73.
74. public String toString() {
75. return new String(this.tbl_name + " " + this.tbl_type);
76. }
77.
78. }
79.
80. public static class ConnMysqlMapper extends Mapper<LongWritable,TblsRecord,Text,Text> {
81. public void map(LongWritable key,TblsRecord values,Context context)
82. throws IOException,InterruptedException {
83. context.write(new Text(values.tbl_name), new Text(values.tbl_type));
84. }
85. }
86.
87. public static class ConnMysqlReducer extends Reducer<Text,Text,Text,Text> {
88. public void reduce(Text key,Iterable<Text> values,Context context)
89. throws IOException,InterruptedException {
90. for(Iterator<Text> itr = values.iterator();itr.hasNext();) {
91. context.write(key, itr.next());
92. }
93. }
94. }
95.
96. public static void main(String[] args) throws Exception {
97. Path output = new Path("/user/lxw/output/");
98.
99. FileSystem fs = FileSystem.get(URI.create(output.toString()), conf);
100. if (fs.exists(output)) {
101. fs.delete(output);
102. }
103.
104. //mysql的jdbc驱动
105. DistributedCache.addFileToClassPath(new Path(
106. "hdfs://hd022-test.nh.sdo.com/user/liuxiaowen/mysql-connector-java-5.1.13-bin.jar"), conf);
107.
108. DBConfiguration.configureDB(conf, "com.mysql.jdbc.Driver",
109. "jdbc:mysql://10.133.103.22:3306/hive", "hive", "hive");
110.
111. Job job = new Job(conf,"test mysql connection");
112. job.setJarByClass(ConnMysql.class);
113.
114. job.setMapperClass(ConnMysqlMapper.class);
115. job.setReducerClass(ConnMysqlReducer.class);
116.
117. job.setOutputKeyClass(Text.class);
118. job.setOutputValueClass(Text.class);
119.
120. job.setInputFormatClass(DBInputFormat.class);
121. FileOutputFormat.setOutputPath(job, output);
122.
123. //列名
124. String[] fields = { "TBL_NAME", "TBL_TYPE" };
125. //六个参数分别为:
126. //1.Job;2.Class<? extends DBWritable>
127. //3.表名;4.where条件
128. //5.order by语句;6.列名
129. DBInputFormat.setInput(job, TblsRecord.class,
130. "lxw_tbls", "TBL_NAME like 'lxw%'", "TBL_NAME", fields);
131.
132. System.exit(job.waitForCompletion(true) ? 0 : 1);
133. }
134.
135. }
复制代码
运行结果:
1. [lxw@hd025-test ~]$ hadoop fs -cat /user/lxw/output/part-r-00000
2. lxw_hbase_table_1 MANAGED_TABLE
3. lxw_hbase_user_info MANAGED_TABLE
4. lxw_jobid MANAGED_TABLE
5. lxw_t MANAGED_TABLE
6. lxw_t1 MANAGED_TABLE
7. lxw_test_table EXTERNAL_TABLE