MapReduce中的partitioner
1.日志源文件:
1363157985066 13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 24 27 2481 24681 200 1363157995052 13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0 264 0 200 1363157991076 13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 2 4 132 1512 200 1363154400022 13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 4 0 240 0 200 1363157993044 18211575961 94-71-AC-CD-E6-18:CMCC-EASY 120.196.100.99 iface.qiyi.com 视频网站 15 12 1527 2106 200 1363157995074 84138413 5C-0E-8B-8C-E8-20:7DaysInn 120.197.40.4 122.72.52.12 20 16 4116 1432 200 1363157993055 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 18 15 1116 954 200 1363157995033 15920133257 5C-0E-8B-C7-BA-20:CMCC 120.197.40.4 sug.so.360.cn 信息安全 20 20 3156 2936 200 1363157983019 13719199419 68-A1-B7-03-07-B1:CMCC-EASY 120.196.100.82 4 0 240 0 200 1363157984041 13660577991 5C-0E-8B-92-5C-20:CMCC-EASY 120.197.40.4 s19.cnzz.com 站点统计 24 9 6960 690 200 1363157973098 15013685858 5C-0E-8B-C7-F7-90:CMCC 120.197.40.4 rank.ie.sogou.com 搜索引擎 28 27 3659 3538 200 1363157986029 15989002119 E8-99-C4-4E-93-E0:CMCC-EASY 120.196.100.99 www.umeng.com 站点统计 3 3 1938 180 200 1363157992093 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 15 9 918 4938 200 1363157986041 13480253104 5C-0E-8B-C7-FC-80:CMCC-EASY 120.197.40.4 3 3 180 180 200 1363157984040 13602846565 5C-0E-8B-8B-B6-00:CMCC 120.197.40.4 2052.flash2-http.qq.com 综合门户 15 12 1938 2910 200 1363157995093 13922314466 00-FD-07-A2-EC-BA:CMCC 120.196.100.82 img.qfc.cn 12 12 3008 3720 200 1363157982040 13502468823 5C-0A-5B-6A-0B-D4:CMCC-EASY 120.196.100.99 y0.ifengimg.com 综合门户 57 102 7335 110349 200 1363157986072 18320173382 84-25-DB-4F-10-1A:CMCC-EASY 120.196.100.99 input.shouji.sogou.com 搜索引擎 21 18 9531 2412 200 1363157990043 13925057413 00-1F-64-E1-E6-9A:CMCC 120.196.100.55 t3.baidu.com 搜索引擎 69 63 11058 48243 200 1363157988072 13760778710 00-FD-07-A4-7B-08:CMCC 120.196.100.82 2 2 120 120 200 1363157985079 13823070001 20-7C-8F-70-68-1F:CMCC 120.196.100.99 6 3 360 180 200 1363157985069 13600217502 00-1F-64-E2-E8-B1:CMCC 120.196.100.55 18 138 1080 186852 200
2.写含有partitioner的MR代码:
1 import java.io.DataInput; 2 import java.io.DataOutput; 3 import java.io.IOException; 4 import java.util.HashMap; 5 import java.util.Map; 6 7 import org.apache.hadoop.conf.Configuration; 8 import org.apache.hadoop.fs.Path; 9 import org.apache.hadoop.io.LongWritable; 10 import org.apache.hadoop.io.Text; 11 import org.apache.hadoop.io.Writable; 12 import org.apache.hadoop.mapreduce.Job; 13 import org.apache.hadoop.mapreduce.Mapper; 14 import org.apache.hadoop.mapreduce.Partitioner; 15 import org.apache.hadoop.mapreduce.Reducer; 16 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; 17 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; 18 19 public class TrafficApp { 20 public static void main(String[] args) throws Exception { 21 Job job = Job.getInstance(new Configuration(), TrafficApp.class.getSimpleName()); 22 job.setJarByClass(TrafficApp.class); 23 24 FileInputFormat.setInputPaths(job, args[0]); 25 26 job.setMapperClass(TrafficMapper.class); 27 job.setMapOutputKeyClass(Text.class); 28 job.setMapOutputValueClass(TrafficWritable.class); 29 30 //job.setNumReduceTasks(2);//设定Reduce的数量为2 这个针对TrafficPartitioner.class 31 //job.setPartitionerClass(TrafficPartitioner.class);//设定一个Partitioner的类. 32 33 //job.setNumReduceTasks(3);//设定Reduce的数量为3 这个针对ProviderPartitioner 34 //也可以通过参数指定 35 job.setNumReduceTasks(Integer.parseInt(args[2])); 36 job.setPartitionerClass(ProviderPartitioner.class); 37 38 /* 39 *Partitioner是如何实现不同的Map输出分配到不同的Reduce中? 40 *在不适用指定的Partitioner时,有 一个默认的Partitioner. 41 *就是HashPartitioner. 42 *其只有一行代码,其意思就是过来的key,不管是什么,模numberReduceTasks之后 返回值就是reduce任务的编号. 43 *numberReduceTasks的默认值是1. 任何一个数模1(取余数)都是0. 44 *这个地方0就是取编号为0的Reduce.(Reduce从0开始编号.) 45 */ 46 47 job.setReducerClass(TrafficReducer.class); 48 job.setOutputKeyClass(Text.class); 49 job.setOutputValueClass(TrafficWritable.class); 50 51 FileOutputFormat.setOutputPath(job, new Path(args[1])); 52 job.waitForCompletion(true); 53 } 54 55 public static class TrafficPartitioner extends Partitioner<Text,TrafficWritable>{//k2,v2 56 57 @Override 58 public int getPartition(Text key, TrafficWritable value,int numPartitions) { 59 long phoneNumber = Long.parseLong(key.toString()); 60 return (int)(phoneNumber%numPartitions); 61 } 62 63 } 64 65 //根据号码所属的运营商进行分区,号码的前三位(也可以根据号码所在的行政区域进行分区,号码的前七位) 66 public static class ProviderPartitioner extends Partitioner<Text,TrafficWritable>{//k2,v2 67 //初始化映射关系 68 /* 69 * 这两个静态的static的执行的先后顺序是 从上往下,先执行providerMap 再 执行static静态块. 70 */ 71 private static Map<String,Integer> providerMap = new HashMap<String,Integer>(); 72 static{ 73 providerMap.put("135", 1);//1是移动,2是联通,3是电信 74 providerMap.put("136", 1); 75 providerMap.put("137", 1); 76 providerMap.put("138", 1); 77 providerMap.put("139", 1); 78 providerMap.put("134", 2); 79 providerMap.put("150", 2); 80 providerMap.put("159", 2); 81 providerMap.put("183", 3); 82 providerMap.put("182", 3); 83 } 84 @Override 85 public int getPartition(Text key, TrafficWritable value,int numPartitions) { 86 //15013685858 87 String account = key.toString(); 88 //150 89 String sub_account = account.substring(0,3);//从第0位开始取,取三位...这个东西不需要记,忘了就自己写个代码试一下. 90 //2 91 Integer code = providerMap.get(sub_account); 92 if(code == null){ 93 code = 0;//代表是其他的运行商. 94 } 95 return code; 96 } 97 } 98 99 /** 100 * 第一个参数是LongWritable类型是文本一行数据开头的字节数 101 * 第二个参数是文本中的一行数据 Text类型 102 * 第三个参数是要输出的手机号 Text类型 103 * 第四个参数是需要我们自定义的流量类型TrafficWritable 104 * @author ABC 105 * 106 */ 107 public static class TrafficMapper extends Mapper<LongWritable, Text, Text, TrafficWritable>{ 108 Text k2 = new Text(); 109 TrafficWritable v2 = null; 110 @Override 111 protected void map(LongWritable key,Text value, Mapper<LongWritable, Text, Text, TrafficWritable>.Context context) 112 throws IOException, InterruptedException { 113 String line = value.toString(); 114 String[] splited = line.split("\t"); 115 116 k2.set(splited[1]);//这个值对应的是手机号码 117 v2 = new TrafficWritable(splited[6], splited[7], splited[8], splited[9]); 118 context.write(k2, v2); 119 } 120 121 } 122 123 public static class TrafficReducer extends Reducer <Text, TrafficWritable, Text, TrafficWritable>{ 124 @Override 125 protected void reduce(Text k2,Iterable<TrafficWritable> v2s, 126 Reducer<Text, TrafficWritable, Text, TrafficWritable>.Context context) 127 throws IOException, InterruptedException { 128 //遍历v2s 流量都这个集合里面 129 long t1 = 0L; 130 long t2 = 0L; 131 long t3 = 0L; 132 long t4 = 0L; 133 134 for (TrafficWritable v2 : v2s) { 135 t1 += v2.getT1(); 136 t2 += v2.getT2(); 137 t3 += v2.getT3(); 138 t4 += v2.getT4(); 139 } 140 TrafficWritable v3 = new TrafficWritable(t1, t2, t3, t4); 141 context.write(k2, v3); 142 } 143 } 144 145 public static class TrafficWritable implements Writable{ 146 private long t1; 147 private long t2; 148 private long t3; 149 private long t4; 150 //写两个构造方法,一个是有参数的构造方法,一个是无参数的构造方法. 151 //必须要有 一个无参数的构造方法,否则程序运行会报错. 152 153 public TrafficWritable(){ 154 super(); 155 } 156 157 public TrafficWritable(long t1, long t2, long t3, long t4) { 158 super(); 159 this.t1 = t1; 160 this.t2 = t2; 161 this.t3 = t3; 162 this.t4 = t4; 163 } 164 //在程序中读取文本穿过来的都是字符串,所以再搞一个字符串类型的构造方法 165 public TrafficWritable(String t1, String t2, String t3, String t4) { 166 super(); 167 this.t1 = Long.parseLong(t1); 168 this.t2 = Long.parseLong(t2); 169 this.t3 = Long.parseLong(t3); 170 this.t4 = Long.parseLong(t4); 171 } 172 173 public void write(DataOutput out) throws IOException { 174 //对各个成员变量进行序列化 175 out.writeLong(t1); 176 out.writeLong(t2); 177 out.writeLong(t3); 178 out.writeLong(t4); 179 } 180 181 public void readFields(DataInput in) throws IOException { 182 //对成员变量进行反序列化 183 this.t1 = in.readLong(); 184 this.t2 = in.readLong(); 185 this.t3 = in.readLong(); 186 this.t4 = in.readLong(); 187 } 188 189 public long getT1() { 190 return t1; 191 } 192 193 public void setT1(long t1) { 194 this.t1 = t1; 195 } 196 197 public long getT2() { 198 return t2; 199 } 200 201 public void setT2(long t2) { 202 this.t2 = t2; 203 } 204 205 public long getT3() { 206 return t3; 207 } 208 209 public void setT3(long t3) { 210 this.t3 = t3; 211 } 212 213 public long getT4() { 214 return t4; 215 } 216 217 public void setT4(long t4) { 218 this.t4 = t4; 219 } 220 221 @Override 222 public String toString() { 223 return t1 + "\t" + t2 + "\t" + t3 + "\t" + t4 ; 224 } 225 226 } 227 }
3.命令执行:
hadoop jar /root/itcastmr.jar mapreduce.TrafficApp /files/traffic /traffic_provider3 4
产生的结果文件:
代码中的逻辑是对应4个分区,设置了4个分区,就产生了4个分区文件...
查看各个文件中的内容:
4.其他情况:
①
如果代码中不设置分区的数量: job.setNumReduceTasks(Integer.parseInt(args[2])); 运行命令执行会发现只产生了一个结果文件.
因为MR默认只启动一个reducer...一个reducer对应一个结果文件. 不是分区所要的效果.
②
如果代码中设置的分区数量大于实际的产生的分区数量. 比如以上代码根据数据情况只产生4个分区,但是设置6个分区.
同样会产生6个结果文件,但是后两个结果文件中是没有值的.
③
代码中的分区数量小于实际产生的分区数量. 比如以上代码根据数据情况会产生4个分区,但是只设置2个分区.
报错:(就是因为182对应应该在3号分区,但是实际是只设置了2个分区)
还有设置分区之后代码执行会变慢:因为之前只需要之前只需要把结果发给一个reducer,现在要根据某个属性把mapper的结果分发到不同的reducer中.