我正在尝试使用测试 CombineFileInputFormat 来处理每个 8 MB 的几个小文件(20 个文件)。我按照此博客中给出的示例进行操作。我能够实现和测试它。最终结果是正确的。但令我惊讶的是,它总是以只有一张地图结束。我尝试设置属性“mapred.max.split.size”各种值,如 16MB、32MB 等(当然以字节为单位)但没有任何成功。还有什么我需要做的还是正确的行为?
我正在运行一个默认复制为 2 的两节点集群。下面给出的是开发的代码。非常感谢任何帮助。
package inverika.test.retail;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
import org.apache.hadoop.mapreduce.Reducer;
public class CategoryCount {
public static class CategoryMapper
extends Mapper<LongWritable, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private String[] columns = new String[8];
@Override
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
columns = value.toString().split(",");
context.write(new Text(columns[4]), one);
}
}
public static class CategoryReducer
extends Reducer< Text, IntWritable, Text, IntWritable> {
@Override
public void reduce(Text key, Iterable<IntWritable> values, Context context)
throws IOException, InterruptedException {
int sum = 0;
for (IntWritable value : values) {
sum += value.get();
}
context.write(key, new IntWritable(sum));
}
}
public static void main(String args[]) throws Exception {
if (args.length != 2) {
System.err.println("Usage: CategoryCount <input Path> <output Path>");
System.exit(-1);
}
Configuration conf = new Configuration();
conf.set("mapred.textoutputformat.separator", ",");
conf.set("mapred.max.split.size", "16777216"); // 16 MB
Job job = new Job(conf, "Retail Category Count");
job.setJarByClass(CategoryCount.class);
job.setMapperClass(CategoryMapper.class);
job.setReducerClass(CategoryReducer.class);
job.setInputFormatClass(CombinedInputFormat.class);
//CombineFileInputFormat.setMaxInputSplitSize(job, 16777216);
CombinedInputFormat.setMaxInputSplitSize(job, 16777216);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]) );
FileOutputFormat.setOutputPath(job, new Path(args[1]) );
//job.submit();
//System.exit(job.waitForCompletion(false) ? 0 : 1);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
这是实现的 CombinedFileInputFormat
package inverika.test.retail;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.CombineFileRecordReader;
import org.apache.hadoop.mapreduce.lib.input.CombineFileSplit;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.input.LineRecordReader;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.CombineFileInputFormat;
public class CombinedInputFormat extends CombineFileInputFormat<LongWritable, Text> {
@Override
public RecordReader<LongWritable, Text>
createRecordReader(InputSplit split, TaskAttemptContext context)
throws IOException {
CombineFileRecordReader<LongWritable, Text> reader =
new CombineFileRecordReader<LongWritable, Text>(
(CombineFileSplit) split, context, myCombineFileRecordReader.class);
return reader;
}
public static class myCombineFileRecordReader extends RecordReader<LongWritable, Text> {
private LineRecordReader lineRecordReader = new LineRecordReader();
public myCombineFileRecordReader(CombineFileSplit split,
TaskAttemptContext context, Integer index) throws IOException {
FileSplit fileSplit = new FileSplit(split.getPath(index),
split.getOffset(index),
split.getLength(index),
split.getLocations());
lineRecordReader.initialize(fileSplit, context);
}
@Override
public void initialize(InputSplit inputSplit, TaskAttemptContext context)
throws IOException, InterruptedException {
//linerecordReader.initialize(inputSplit, context);
}
@Override
public void close() throws IOException {
lineRecordReader.close();
}
@Override
public float getProgress() throws IOException {
return lineRecordReader.getProgress();
}
@Override
public LongWritable getCurrentKey() throws IOException,
InterruptedException {
return lineRecordReader.getCurrentKey();
}
@Override
public Text getCurrentValue() throws IOException, InterruptedException {
return lineRecordReader.getCurrentValue();
}
@Override
public boolean nextKeyValue() throws IOException, InterruptedException {
return lineRecordReader.nextKeyValue();
}
}
}