转载自:http://zengzhaozheng.blog.51cto.com/8219051/1392961java
package com.mr.reduceSizeJoin; import java.io.DataInput; import java.io.DataOutput; import java.io.IOException; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.WritableComparable; public class CombineValues implements WritableComparable{ //private static final Logger logger = LoggerFactory.getLogger(CombineValues.class); private Text joinKey;//连接关键字 private Text flag;//文件来源标志 private Text secondPart;//除了连接键外的其余部分 public void setJoinKey(Text joinKey) { this.joinKey = joinKey; } public void setFlag(Text flag) { this.flag = flag; } public void setSecondPart(Text secondPart) { this.secondPart = secondPart; } public Text getFlag() { return flag; } public Text getSecondPart() { return secondPart; } public Text getJoinKey() { return joinKey; } public CombineValues() { this.joinKey = new Text(); this.flag = new Text(); this.secondPart = new Text(); } @Override public void write(DataOutput out) throws IOException { this.joinKey.write(out); this.flag.write(out); this.secondPart.write(out); } @Override public void readFields(DataInput in) throws IOException { this.joinKey.readFields(in); this.flag.readFields(in); this.secondPart.readFields(in); } @Override public int compareTo(CombineValues o) { return this.joinKey.compareTo(o.getJoinKey()); } @Override public String toString() { // TODO Auto-generated method stub return "[flag="+this.flag.toString()+",joinKey="+this.joinKey.toString()+",secondPart="+this.secondPart.toString()+"]"; } }
(2)map、reduce主体代码apache
package com.mr.reduceSizeJoin; import java.io.IOException; import java.util.ArrayList; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.conf.Configured; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.input.FileSplit; import org.apache.hadoop.mapreduce.lib.input.TextInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; import org.apache.hadoop.util.Tool; import org.apache.hadoop.util.ToolRunner; import org.slf4j.Logger; import org.slf4j.LoggerFactory; /** * @author zengzhaozheng * 用途说明: * reudce side join中的left outer join * 左链接,两个文件分别表明2个表,链接字段table1的id字段和table2的cityID字段 * table1(左表):tb_dim_city(id int,name string,orderid int,city_code,is_show) * tb_dim_city.dat文件内容,分隔符为"|": * id name orderid city_code is_show * 0 其余 9999 9999 0 * 1 长春 1 901 1 * 2 吉林 2 902 1 * 3 四平 3 903 1 * 4 松原 4 904 1 * 5 通化 5 905 1 * 6 辽源 6 906 1 * 7 白城 7 907 1 * 8 白山 8 908 1 * 9 延吉 9 909 1 * -------------------------风骚的分割线------------------------------- * table2(右表):tb_user_profiles(userID int,userName string,network string,double flow,cityID int) * tb_user_profiles.dat文件内容,分隔符为"|": * userID network flow cityID * 1 2G 123 1 * 2 3G 333 2 * 3 3G 555 1 * 4 2G 777 3 * 5 3G 666 4 * * -------------------------风骚的分割线------------------------------- * 结果: * 1 长春 1 901 1 1 2G 123 * 1 长春 1 901 1 3 3G 555 * 2 吉林 2 902 1 2 3G 333 * 3 四平 3 903 1 4 2G 777 * 4 松原 4 904 1 5 3G 666 */ public class ReduceSideJoin_LeftOuterJoin extends Configured implements Tool{ private static final Logger logger = LoggerFactory.getLogger(ReduceSideJoin_LeftOuterJoin.class); public static class LeftOutJoinMapper extends Mapper { private CombineValues combineValues = new CombineValues(); private Text flag = new Text(); private Text joinKey = new Text(); private Text secondPart = new Text(); @Override protected void map(Object key, Text value, Context context) throws IOException, InterruptedException { //得到文件输入路径 String pathName = ((FileSplit) context.getInputSplit()).getPath().toString(); //数据来自tb_dim_city.dat文件,标志即为"0" if(pathName.endsWith("tb_dim_city.dat")){ String[] valueItems = value.toString().split("\\|"); //过滤格式错误的记录 if(valueItems.length != 5){ return; } flag.set("0"); joinKey.set(valueItems[0]); secondPart.set(valueItems[1]+"\t"+valueItems[2]+"\t"+valueItems[3]+"\t"+valueItems[4]); combineValues.setFlag(flag); combineValues.setJoinKey(joinKey); combineValues.setSecondPart(secondPart); context.write(combineValues.getJoinKey(), combineValues); }//数据来自于tb_user_profiles.dat,标志即为"1" else if(pathName.endsWith("tb_user_profiles.dat")){ String[] valueItems = value.toString().split("\\|"); //过滤格式错误的记录 if(valueItems.length != 4){ return; } flag.set("1"); joinKey.set(valueItems[3]); secondPart.set(valueItems[0]+"\t"+valueItems[1]+"\t"+valueItems[2]); combineValues.setFlag(flag); combineValues.setJoinKey(joinKey); combineValues.setSecondPart(secondPart); context.write(combineValues.getJoinKey(), combineValues); } } } public static class LeftOutJoinReducer extends Reducer { //存储一个分组中的左表信息 private ArrayList leftTable = new ArrayList(); //存储一个分组中的右表信息 private ArrayList rightTable = new ArrayList(); private Text secondPar = null; private Text output = new Text(); /** * 一个分组调用一次reduce函数 */ @Override protected void reduce(Text key, Iterable value, Context context) throws IOException, InterruptedException { leftTable.clear(); rightTable.clear(); /** * 将分组中的元素按照文件分别进行存放 * 这种方法要注意的问题: * 若是一个分组内的元素太多的话,可能会致使在reduce阶段出现OOM, * 在处理分布式问题以前最好先了解数据的分布状况,根据不一样的分布采起最 * 适当的处理方法,这样能够有效的防止致使OOM和数据过分倾斜问题。 */ for(CombineValues cv : value){ secondPar = new Text(cv.getSecondPart().toString()); //左表tb_dim_city if("0".equals(cv.getFlag().toString().trim())){ leftTable.add(secondPar); } //右表tb_user_profiles else if("1".equals(cv.getFlag().toString().trim())){ rightTable.add(secondPar); } } logger.info("tb_dim_city:"+leftTable.toString()); logger.info("tb_user_profiles:"+rightTable.toString()); for(Text leftPart : leftTable){ for(Text rightPart : rightTable){ output.set(leftPart+ "\t" + rightPart); context.write(key, output); } } } } @Override public int run(String[] args) throws Exception { Configuration conf=getConf(); //得到配置文件对象 Job job=new Job(conf,"LeftOutJoinMR"); job.setJarByClass(ReduceSideJoin_LeftOuterJoin.class); FileInputFormat.addInputPath(job, new Path(args[0])); //设置map输入文件路径 FileOutputFormat.setOutputPath(job, new Path(args[1])); //设置reduce输出文件路径 job.setMapperClass(LeftOutJoinMapper.class); job.setReducerClass(LeftOutJoinReducer.class); job.setInputFormatClass(TextInputFormat.class); //设置文件输入格式 job.setOutputFormatClass(TextOutputFormat.class);//使用默认的output格格式 //设置map的输出key和value类型 job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(CombineValues.class); //设置reduce的输出key和value类型 job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.waitForCompletion(true); return job.isSuccessful()?0:1; } public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException { try { int returnCode = ToolRunner.run(new ReduceSideJoin_LeftOuterJoin(),args); System.exit(returnCode); } catch (Exception e) { // TODO Auto-generated catch block logger.error(e.getMessage()); } } }
其中具体的分析以及数据的输出输入请看代码中的注释已经写得比较清楚了,这里主要分析一下reduce join的一些不足。之因此会存在reduce join这种方式,咱们能够很明显的看出原:由于总体数据被分割了,每一个map task只处理一部分数据而不可以获取到全部须要的join字段,所以咱们须要在讲join key做为reduce端的分组将全部join key相同的记录集中起来进行处理,因此reduce join这种方式就出现了。这种方式的缺点很明显就是会形成map和reduce端也就是shuffle阶段出现大量的数据传输,效率很低.缓存
package com.mr.mapSideJoin; import java.io.BufferedReader; import java.io.FileReader; import java.io.IOException; import java.util.HashMap; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.conf.Configured; import org.apache.hadoop.filecache.DistributedCache; import org.apache.hadoop.fs.Path; 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; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; import org.apache.hadoop.util.Tool; import org.apache.hadoop.util.ToolRunner; import org.slf4j.Logger; import org.slf4j.LoggerFactory; /** * @author zengzhaozheng * * 用途说明: * Map side join中的left outer join * 左链接,两个文件分别表明2个表,链接字段table1的id字段和table2的cityID字段 * table1(左表):tb_dim_city(id int,name string,orderid int,city_code,is_show), * 假设tb_dim_city文件记录数不多,tb_dim_city.dat文件内容,分隔符为"|": * id name orderid city_code is_show * 0 其余 9999 9999 0 * 1 长春 1 901 1 * 2 吉林 2 902 1 * 3 四平 3 903 1 * 4 松原 4 904 1 * 5 通化 5 905 1 * 6 辽源 6 906 1 * 7 白城 7 907 1 * 8 白山 8 908 1 * 9 延吉 9 909 1 * -------------------------风骚的分割线------------------------------- * table2(右表):tb_user_profiles(userID int,userName string,network string,double flow,cityID int) * tb_user_profiles.dat文件内容,分隔符为"|": * userID network flow cityID * 1 2G 123 1 * 2 3G 333 2 * 3 3G 555 1 * 4 2G 777 3 * 5 3G 666 4 * -------------------------风骚的分割线------------------------------- * 结果: * 1 长春 1 901 1 1 2G 123 * 1 长春 1 901 1 3 3G 555 * 2 吉林 2 902 1 2 3G 333 * 3 四平 3 903 1 4 2G 777 * 4 松原 4 904 1 5 3G 666 */ public class MapSideJoinMain extends Configured implements Tool{ private static final Logger logger = LoggerFactory.getLogger(MapSideJoinMain.class); public static class LeftOutJoinMapper extends Mapper { private HashMap city_info = new HashMap(); private Text outPutKey = new Text(); private Text outPutValue = new Text(); private String mapInputStr = null; private String mapInputSpit[] = null; private String city_secondPart = null; /** * 此方法在每一个task开始以前执行,这里主要用做从DistributedCache * 中取到tb_dim_city文件,并将里边记录取出放到内存中。 */ @Override protected void setup(Context context) throws IOException, InterruptedException { BufferedReader br = null; //得到当前做业的DistributedCache相关文件 Path[] distributePaths = DistributedCache.getLocalCacheFiles(context.getConfiguration()); String cityInfo = null; for(Path p : distributePaths){ if(p.toString().endsWith("tb_dim_city.dat")){ //读缓存文件,并放到mem中 br = new BufferedReader(new FileReader(p.toString())); while(null!=(cityInfo=br.readLine())){ String[] cityPart = cityInfo.split("\\|",5); if(cityPart.length ==5){ city_info.put(cityPart[0], cityPart[1]+"\t"+cityPart[2]+"\t"+cityPart[3]+"\t"+cityPart[4]); } } } } } /** * Map端的实现至关简单,直接判断tb_user_profiles.dat中的 * cityID是否存在个人map中就ok了,这样就能够实现Map Join了 */ @Override protected void map(Object key, Text value, Context context) throws IOException, InterruptedException { //排掉空行 if(value == null || value.toString().equals("")){ return; } mapInputStr = value.toString(); mapInputSpit = mapInputStr.split("\\|",4); //过滤非法记录 if(mapInputSpit.length != 4){ return; } //判断连接字段是否在map中存在 city_secondPart = city_info.get(mapInputSpit[3]); if(city_secondPart != null){ this.outPutKey.set(mapInputSpit[3]); this.outPutValue.set(city_secondPart+"\t"+mapInputSpit[0]+"\t"+mapInputSpit[1]+"\t"+mapInputSpit[2]); context.write(outPutKey, outPutValue); } } } @Override public int run(String[] args) throws Exception { Configuration conf=getConf(); //得到配置文件对象 DistributedCache.addCacheFile(new Path(args[1]).toUri(), conf);//为该job添加缓存文件 Job job=new Job(conf,"MapJoinMR"); job.setNumReduceTasks(0); FileInputFormat.addInputPath(job, new Path(args[0])); //设置map输入文件路径 FileOutputFormat.setOutputPath(job, new Path(args[2])); //设置reduce输出文件路径 job.setJarByClass(MapSideJoinMain.class); job.setMapperClass(LeftOutJoinMapper.class); job.setInputFormatClass(TextInputFormat.class); //设置文件输入格式 job.setOutputFormatClass(TextOutputFormat.class);//使用默认的output格式 //设置map的输出key和value类型 job.setMapOutputKeyClass(Text.class); //设置reduce的输出key和value类型 job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.waitForCompletion(true); return job.isSuccessful()?0:1; } public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException { try { int returnCode = ToolRunner.run(new MapSideJoinMain(),args); System.exit(returnCode); } catch (Exception e) { // TODO Auto-generated catch block logger.error(e.getMessage()); } } }
package com.mr.SemiJoin; import java.io.BufferedReader; import java.io.FileReader; import java.io.IOException; import java.util.ArrayList; import java.util.HashSet; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.conf.Configured; import org.apache.hadoop.filecache.DistributedCache; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.input.FileSplit; import org.apache.hadoop.mapreduce.lib.input.TextInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; import org.apache.hadoop.util.Tool; import org.apache.hadoop.util.ToolRunner; import org.slf4j.Logger; import org.slf4j.LoggerFactory; /** * @author zengzhaozheng * * 用途说明: * reudce side join中的left outer join * 左链接,两个文件分别表明2个表,链接字段table1的id字段和table2的cityID字段 * table1(左表):tb_dim_city(id int,name string,orderid int,city_code,is_show) * tb_dim_city.dat文件内容,分隔符为"|": * id name orderid city_code is_show * 0 其余 9999 9999 0 * 1 长春 1 901 1 * 2 吉林 2 902 1 * 3 四平 3 903 1 * 4 松原 4 904 1 * 5 通化 5 905 1 * 6 辽源 6 906 1 * 7 白城 7 907 1 * 8 白山 8 908 1 * 9 延吉 9 909 1 * -------------------------风骚的分割线------------------------------- * table2(右表):tb_user_profiles(userID int,userName string,network string,double flow,cityID int) * tb_user_profiles.dat文件内容,分隔符为"|": * userID network flow cityID * 1 2G 123 1 * 2 3G 333 2 * 3 3G 555 1 * 4 2G 777 3 * 5 3G 666 4 * -------------------------风骚的分割线------------------------------- * joinKey.dat内容: * city_code * 1 * 2 * 3 * 4 * -------------------------风骚的分割线------------------------------- * 结果: * 1 长春 1 901 1 1 2G 123 * 1 长春 1 901 1 3 3G 555 * 2 吉林 2 902 1 2 3G 333 * 3 四平 3 903 1 4 2G 777 * 4 松原 4 904 1 5 3G 666 */ public class SemiJoin extends Configured implements Tool{ private static final Logger logger = LoggerFactory.getLogger(SemiJoin.class); public static class SemiJoinMapper extends Mapper { private CombineValues combineValues = new CombineValues(); private HashSet joinKeySet = new HashSet(); private Text flag = new Text(); private Text joinKey = new Text(); private Text secondPart = new Text(); /** * 将参加join的key从DistributedCache取出放到内存中,以便在map端将要参加join的key过滤出来。b */ @Override protected void setup(Context context) throws IOException, InterruptedException { BufferedReader br = null; //得到当前做业的DistributedCache相关文件 Path[] distributePaths = DistributedCache.getLocalCacheFiles(context.getConfiguration()); String joinKeyStr = null; for(Path p : distributePaths){ if(p.toString().endsWith("joinKey.dat")){ //读缓存文件,并放到mem中 br = new BufferedReader(new FileReader(p.toString())); while(null!=(joinKeyStr=br.readLine())){ joinKeySet.add(joinKeyStr); } } } } @Override protected void map(Object key, Text value, Context context) throws IOException, InterruptedException { //得到文件输入路径 String pathName = ((FileSplit) context.getInputSplit()).getPath().toString(); //数据来自tb_dim_city.dat文件,标志即为"0" if(pathName.endsWith("tb_dim_city.dat")){ String[] valueItems = value.toString().split("\\|"); //过滤格式错误的记录 if(valueItems.length != 5){ return; } //过滤掉不须要参加join的记录 if(joinKeySet.contains(valueItems[0])){ flag.set("0"); joinKey.set(valueItems[0]); secondPart.set(valueItems[1]+"\t"+valueItems[2]+"\t"+valueItems[3]+"\t"+valueItems[4]); combineValues.setFlag(flag); combineValues.setJoinKey(joinKey); combineValues.setSecondPart(secondPart); context.write(combineValues.getJoinKey(), combineValues); }else{ return ; } }//数据来自于tb_user_profiles.dat,标志即为"1" else if(pathName.endsWith("tb_user_profiles.dat")){ String[] valueItems = value.toString().split("\\|"); //过滤格式错误的记录 if(valueItems.length != 4){ return; } //过滤掉不须要参加join的记录 if(joinKeySet.contains(valueItems[3])){ flag.set("1"); joinKey.set(valueItems[3]); secondPart.set(valueItems[0]+"\t"+valueItems[1]+"\t"+valueItems[2]); combineValues.setFlag(flag); combineValues.setJoinKey(joinKey); combineValues.setSecondPart(secondPart); context.write(combineValues.getJoinKey(), combineValues); }else{ return ; } } } } public static class SemiJoinReducer extends Reducer { //存储一个分组中的左表信息 private ArrayList leftTable = new ArrayList(); //存储一个分组中的右表信息 private ArrayList rightTable = new ArrayList(); private Text secondPar = null; private Text output = new Text(); /** * 一个分组调用一次reduce函数 */ @Override protected void reduce(Text key, Iterable value, Context context) throws IOException, InterruptedException { leftTable.clear(); rightTable.clear(); /** * 将分组中的元素按照文件分别进行存放 * 这种方法要注意的问题: * 若是一个分组内的元素太多的话,可能会致使在reduce阶段出现OOM, * 在处理分布式问题以前最好先了解数据的分布状况,根据不一样的分布采起最 * 适当的处理方法,这样能够有效的防止致使OOM和数据过分倾斜问题。 */ for(CombineValues cv : value){ secondPar = new Text(cv.getSecondPart().toString()); //左表tb_dim_city if("0".equals(cv.getFlag().toString().trim())){ leftTable.add(secondPar); } //右表tb_user_profiles else if("1".equals(cv.getFlag().toString().trim())){ rightTable.add(secondPar); } } logger.info("tb_dim_city:"+leftTable.toString()); logger.info("tb_user_profiles:"+rightTable.toString()); for(Text leftPart : leftTable){ for(Text rightPart : rightTable){ output.set(leftPart+ "\t" + rightPart); context.write(key, output); } } } } @Override public int run(String[] args) throws Exception { Configuration conf=getConf(); //得到配置文件对象 DistributedCache.addCacheFile(new Path(args[2]).toUri(), conf); Job job=new Job(conf,"LeftOutJoinMR"); job.setJarByClass(SemiJoin.class); FileInputFormat.addInputPath(job, new Path(args[0])); //设置map输入文件路径 FileOutputFormat.setOutputPath(job, new Path(args[1])); //设置reduce输出文件路径 job.setMapperClass(SemiJoinMapper.class); job.setReducerClass(SemiJoinReducer.class); job.setInputFormatClass(TextInputFormat.class); //设置文件输入格式 job.setOutputFormatClass(TextOutputFormat.class);//使用默认的output格式 //设置map的输出key和value类型 job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(CombineValues.class); //设置reduce的输出key和value类型 job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.waitForCompletion(true); return job.isSuccessful()?0:1; } public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException { try { int returnCode = ToolRunner.run(new SemiJoin(),args); System.exit(returnCode); } catch (Exception e) { logger.error(e.getMessage()); } } }