Hadoop - Mappers not emitting anything - hadoop

Question

I'm running the code below and no output is generated (well, the output folder and the reducer output file are created, but there is nothing wihtin the part-r-00000 file). From the logs, I suspect the mappers are not emitting anything.
The code:
package com.telefonica.iot.tidoop.mrlib;
import com.telefonica.iot.tidoop.mrlib.utils.Constants;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.log4j.Logger;
public class Count extends Configured implements Tool {
private static final Logger LOGGER = Logger.getLogger(Count.class);
public static class UnitEmitter extends Mapper<Object, Text, Text, LongWritable> {
private final Text commonKey = new Text("common-key");
#Override
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
context.write(commonKey, new LongWritable(1));
} // map
} // UnitEmitter
public static class Adder extends Reducer<Text, LongWritable, Text, LongWritable> {
#Override
public void reduce(Text key, Iterable<LongWritable> values, Context context)
throws IOException, InterruptedException {
long sum = 0;
for (LongWritable value : values) {
sum += value.get();
} // for
context.write(key, new LongWritable(sum));
} // reduce
} // Adder
public static class AdderWithTag extends Reducer<Text, LongWritable, Text, LongWritable> {
private String tag;
#Override
public void setup(Context context) throws IOException, InterruptedException {
tag = context.getConfiguration().get(Constants.PARAM_TAG, "");
} // setup
#Override
public void reduce(Text key, Iterable<LongWritable> values, Context context)
throws IOException, InterruptedException {
long sum = 0;
for (LongWritable value : values) {
sum += value.get();
} // for
context.write(new Text(tag), new LongWritable(sum));
} // reduce
} // AdderWithTag
public static void main(String[] args) throws Exception {
int res = ToolRunner.run(new Configuration(), new Filter(), args);
System.exit(res);
} // main
#Override
public int run(String[] args) throws Exception {
// check the number of arguments, show the usage if it is wrong
if (args.length != 3) {
showUsage();
return -1;
} // if
// get the arguments
String input = args[0];
String output = args[1];
String tag = args[2];
// create and configure a MapReduce job
Configuration conf = this.getConf();
conf.set(Constants.PARAM_TAG, tag);
Job job = Job.getInstance(conf, "tidoop-mr-lib-count");
job.setNumReduceTasks(1);
job.setJarByClass(Count.class);
job.setMapperClass(UnitEmitter.class);
job.setCombinerClass(Adder.class);
job.setReducerClass(AdderWithTag.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
FileInputFormat.addInputPath(job, new Path(input));
FileOutputFormat.setOutputPath(job, new Path(output));
// run the MapReduce job
return job.waitForCompletion(true) ? 0 : 1;
} // main
private void showUsage() {
System.out.println("...");
} // showUsage
} // Count
The command executed, and the output logs:
$ hadoop jar target/tidoop-mr-lib-0.0.0-SNAPSHOT-jar-with-dependencies.jar com.telefonica.iot.tidoop.mrlib.Count -libjars target/tidoop-mr-lib-0.0.0-SNAPSHOT-jar-with-dependencies.jar tidoop/numbers tidoop/numbers_count onetag
15/11/05 17:24:52 INFO input.FileInputFormat: Total input paths to process : 1
15/11/05 17:24:52 WARN snappy.LoadSnappy: Snappy native library is available
15/11/05 17:24:53 INFO util.NativeCodeLoader: Loaded the native-hadoop library
15/11/05 17:24:53 INFO snappy.LoadSnappy: Snappy native library loaded
15/11/05 17:24:53 INFO mapred.JobClient: Running job: job_201507101501_23002
15/11/05 17:24:54 INFO mapred.JobClient: map 0% reduce 0%
15/11/05 17:25:00 INFO mapred.JobClient: map 100% reduce 0%
15/11/05 17:25:07 INFO mapred.JobClient: map 100% reduce 33%
15/11/05 17:25:08 INFO mapred.JobClient: map 100% reduce 100%
15/11/05 17:25:09 INFO mapred.JobClient: Job complete: job_201507101501_23002
15/11/05 17:25:09 INFO mapred.JobClient: Counters: 25
15/11/05 17:25:09 INFO mapred.JobClient: Job Counters
15/11/05 17:25:09 INFO mapred.JobClient: Launched reduce tasks=1
15/11/05 17:25:09 INFO mapred.JobClient: SLOTS_MILLIS_MAPS=5350
15/11/05 17:25:09 INFO mapred.JobClient: Total time spent by all reduces waiting after reserving slots (ms)=0
15/11/05 17:25:09 INFO mapred.JobClient: Total time spent by all maps waiting after reserving slots (ms)=0
15/11/05 17:25:09 INFO mapred.JobClient: Rack-local map tasks=1
15/11/05 17:25:09 INFO mapred.JobClient: Launched map tasks=1
15/11/05 17:25:09 INFO mapred.JobClient: SLOTS_MILLIS_REDUCES=8702
15/11/05 17:25:09 INFO mapred.JobClient: FileSystemCounters
15/11/05 17:25:09 INFO mapred.JobClient: FILE_BYTES_READ=6
15/11/05 17:25:09 INFO mapred.JobClient: HDFS_BYTES_READ=1968928
15/11/05 17:25:09 INFO mapred.JobClient: FILE_BYTES_WRITTEN=108226
15/11/05 17:25:09 INFO mapred.JobClient: Map-Reduce Framework
15/11/05 17:25:09 INFO mapred.JobClient: Map input records=598001
15/11/05 17:25:09 INFO mapred.JobClient: Reduce shuffle bytes=6
15/11/05 17:25:09 INFO mapred.JobClient: Spilled Records=0
15/11/05 17:25:09 INFO mapred.JobClient: Map output bytes=0
15/11/05 17:25:09 INFO mapred.JobClient: CPU time spent (ms)=2920
15/11/05 17:25:09 INFO mapred.JobClient: Total committed heap usage (bytes)=355663872
15/11/05 17:25:09 INFO mapred.JobClient: Combine input records=0
15/11/05 17:25:09 INFO mapred.JobClient: SPLIT_RAW_BYTES=124
15/11/05 17:25:09 INFO mapred.JobClient: Reduce input records=0
15/11/05 17:25:09 INFO mapred.JobClient: Reduce input groups=0
15/11/05 17:25:09 INFO mapred.JobClient: Combine output records=0
15/11/05 17:25:09 INFO mapred.JobClient: Physical memory (bytes) snapshot=328683520
15/11/05 17:25:09 INFO mapred.JobClient: Reduce output records=0
15/11/05 17:25:09 INFO mapred.JobClient: Virtual memory (bytes) snapshot=1466642432
15/11/05 17:25:09 INFO mapred.JobClient: Map output records=0
The content of the output file:
$ hadoop fs -cat /user/frb/tidoop/numbers_count/part-r-00000
[frb#cosmosmaster-gi tidoop-mr-lib]$ hadoop fs -ls /user/frb/tidoop/numbers_count/
Found 3 items
-rw-r--r-- 3 frb frb 0 2015-11-05 17:25 /user/frb/tidoop/numbers_count/_SUCCESS
drwxr----- - frb frb 0 2015-11-05 17:24 /user/frb/tidoop/numbers_count/_logs
-rw-r--r-- 3 frb frb 0 2015-11-05 17:25 /user/frb/tidoop/numbers_count/part-r-00000
Any hints about what is happening?

Answer 1

Weird. I'd try using Mapper (identity mapper) with your job.
If the Mapper does not output anything there must be something weird with your hadoop installation, or job configuration.