This topic describes an example of running UserDefinedCounters in MapReduce.
Prerequisites
Complete the environment configuration for testing, see Getting started.
Preparations
Prepare the JAR package of the test program. In this topic, the JAR package is named mapreduce-examples.jar and stored in the bin\data\resources directory in the local installation path of MaxCompute.
Prepare test tables and resources for UserDefinedCounters.
Create test tables.
CREATE TABLE wc_in (key STRING, value STRING); CREATE TABLE wc_out(key STRING, cnt BIGINT);Add test resources.
-- When adding the JAR package for the first time, you can ignore the -f flag. add jar data\resources\mapreduce-examples.jar -f;
Use Tunnel to import the
data.txtfile from the bin directory of the MaxCompute client into thewc_intable.tunnel upload data.txt wc_in;The following data is imported to the wc_in table:
hello,odps
Procedure
Run UserDefinedCounters on the MaxCompute client.
jar -resources mapreduce-examples.jar -classpath data\resources\mapreduce-examples.jar
com.aliyun.odps.mapred.open.example.UserDefinedCounters wc_in wc_outExpected result
The job runs normally. The following user-defined counters are returned:
Counters: 3
com.aliyun.odps.mapred.open.example.UserDefinedCounters$MyCounter
MAP_TASKS=1
REDUCE_TASKS=1
TOTAL_TASKS=2The following data is returned in the wc_out table:
+------------+------------+
| key | cnt |
+------------+------------+
| hello | 1 |
| odps | 1 |
+------------+------------+Sample code
For information about Project Object Model (POM) dependencies, see Precautions.
package com.aliyun.odps.mapred.open.example;
import java.io.IOException;
import java.util.Iterator;
import com.aliyun.odps.counter.Counter;
import com.aliyun.odps.counter.Counters;
import com.aliyun.odps.data.Record;
import com.aliyun.odps.mapred.JobClient;
import com.aliyun.odps.mapred.MapperBase;
import com.aliyun.odps.mapred.ReducerBase;
import com.aliyun.odps.mapred.RunningJob;
import com.aliyun.odps.mapred.conf.JobConf;
import com.aliyun.odps.mapred.utils.SchemaUtils;
import com.aliyun.odps.mapred.utils.InputUtils;
import com.aliyun.odps.mapred.utils.OutputUtils;
import com.aliyun.odps.data.TableInfo;
/**
*
* User Defined Counters
*
**/
public class UserDefinedCounters {
enum MyCounter {
TOTAL_TASKS, MAP_TASKS, REDUCE_TASKS
}
public static class TokenizerMapper extends MapperBase {
private Record word;
private Record one;
@Override
public void setup(TaskContext context) throws IOException {
super.setup(context);
Counter map_tasks = context.getCounter(MyCounter.MAP_TASKS);
Counter total_tasks = context.getCounter(MyCounter.TOTAL_TASKS);
map_tasks.increment(1);
total_tasks.increment(1);
word = context.createMapOutputKeyRecord();
one = context.createMapOutputValueRecord();
one.set(new Object[] { 1L });
}
@Override
public void map(long recordNum, Record record, TaskContext context)
throws IOException {
for (int i = 0; i < record.getColumnCount(); i++) {
word.set(new Object[] { record.get(i).toString() });
context.write(word, one);
}
}
}
public static class SumReducer extends ReducerBase {
private Record result = null;
@Override
public void setup(TaskContext context) throws IOException {
result = context.createOutputRecord();
Counter reduce_tasks = context.getCounter(MyCounter.REDUCE_TASKS);
Counter total_tasks = context.getCounter(MyCounter.TOTAL_TASKS);
reduce_tasks.increment(1);
total_tasks.increment(1);
}
@Override
public void reduce(Record key, Iterator<Record> values, TaskContext context)
throws IOException {
long count = 0;
while (values.hasNext()) {
Record val = values.next();
count += (Long) val.get(0);
}
result.set(0, key.get(0));
result.set(1, count);
context.write(result);
}
}
public static void main(String[] args) throws Exception {
if (args.length != 2) {
System.err
.println("Usage: TestUserDefinedCounters <in_table> <out_table>");
System.exit(2);
}
JobConf job = new JobConf();
job.setMapperClass(TokenizerMapper.class);
job.setReducerClass(SumReducer.class);
job.setMapOutputKeySchema(SchemaUtils.fromString("word:string"));
job.setMapOutputValueSchema(SchemaUtils.fromString("count:bigint"));
InputUtils.addTable(TableInfo.builder().tableName(args[0]).build(), job);
OutputUtils.addTable(TableInfo.builder().tableName(args[1]).build(), job);
RunningJob rJob = JobClient.runJob(job);
/** The job runs normally. The values of the custom counters in the job are returned. */
Counters counters = rJob.getCounters();
long m = counters.findCounter(MyCounter.MAP_TASKS).getValue();
long r = counters.findCounter(MyCounter.REDUCE_TASKS).getValue();
long total = counters.findCounter(MyCounter.TOTAL_TASKS).getValue();
System.exit(0);
}
}