案例一: MR实战之小文件合并(自定义inputFormat)
项目准备
- 需求
无论hdfs还是MapReduce，对于小文件都有损效率，实践中，又难免面临处理大量小文件的场景，此时，就需要有相应解决方案
-
测试数据
-
分析
小文件的优化无非以下几种方式：
- a) 在数据采集的时候，就将小文件或小批数据合成大文件再上传HDFS
- b) 在业务处理之前，在HDFS上使用MapReduce程序对小文件进行合并
- c) 在MapReduce处理时，可采用combineInputFormat提高效率
项目实现
注意:本节实现的是上述第二种方式
- 程序的核心机制：
自定义一个InputFormat
改写RecordReader，实现一次读取一个完整文件封装为KV
在输出时使用SequenceFileOutPutFormat输出合并文件
- 代码如下
a) 自定义InputFromat
/*** @Author 千锋大数据教学团队* @Company 千锋好程序员大数据* @Description */
public class WholeFileInputFormat extendsFileInputFormat<NullWritable, BytesWritable> {//设置每个小文件不可分片,保证一个小文件生成一个key-value键值对@Overrideprotected boolean isSplitable(JobContext context, Path file) {return false;}@Overridepublic RecordReader<NullWritable, BytesWritable> createRecordReader(InputSplit split, TaskAttemptContext context) throws IOException,InterruptedException {WholeFileRecordReader reader = new WholeFileRecordReader();reader.initialize(split, context);return reader;}
}
复制代码b) 自定义RecordReader
/*** @Author 千锋大数据教学团队* @Company 千锋好程序员大数据* @Description 自定义RecordReader*/
public class WholeFileRecordReader extends RecordReader<NullWritable, BytesWritable> {private FileSplit fileSplit;private Configuration conf;private BytesWritable value = new BytesWritable();private boolean processed = false;@Overridepublic void initialize(InputSplit split, TaskAttemptContext context)throws IOException, InterruptedException {this.fileSplit = (FileSplit) split;this.conf = context.getConfiguration();}@Overridepublic boolean nextKeyValue() throws IOException, InterruptedException {if (!processed) {byte[] contents = new byte[(int) fileSplit.getLength()];Path file = fileSplit.getPath();FileSystem fs = file.getFileSystem(conf);FSDataInputStream in = null;try {in = fs.open(file);IOUtils.readFully(in, contents, 0, contents.length);value.set(contents, 0, contents.length);} finally {IOUtils.closeStream(in);}processed = true;return true;}return false;}@Overridepublic NullWritable getCurrentKey() throws IOException,InterruptedException {return NullWritable.get();}@Overridepublic BytesWritable getCurrentValue() throws IOException,InterruptedException {return value;}@Overridepublic float getProgress() throws IOException {return processed ? 1.0f : 0.0f;}@Overridepublic void close() throws IOException {// do nothing}
}
复制代码c) 定义MapReduce处理流程
/*** @Author 千锋大数据教学团队* @Company 千锋好程序员大数据* @Description 定义MapReduce处理流程*/
public class SmallFilesToSequenceFileConverter extends Configured implementsTool {static class SequenceFileMapper extendsMapper<NullWritable, BytesWritable, Text, BytesWritable> {private Text filenameKey;@Overrideprotected void setup(Context context) throws IOException,InterruptedException {InputSplit split = context.getInputSplit();Path path = ((FileSplit) split).getPath();filenameKey = new Text(path.toString());}@Overrideprotected void map(NullWritable key, BytesWritable value,Context context) throws IOException, InterruptedException {context.write(filenameKey, value);}}@Overridepublic int run(String[] args) throws Exception {Configuration conf = new Configuration();System.setProperty("HADOOP_USER_NAME", "root");String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();if (otherArgs.length != 2) {System.err.println("Usage: combinefiles <in> <out>");System.exit(2);}Job job = Job.getInstance(conf,"combine small files to sequencefile");// job.setInputFormatClass(WholeFileInputFormat.class);job.setOutputFormatClass(SequenceFileOutputFormat.class);job.setOutputKeyClass(Text.class);job.setOutputValueClass(BytesWritable.class);job.setMapperClass(SequenceFileMapper.class);return job.waitForCompletion(true) ? 0 : 1;}public static void main(String[] args) throws Exception {int exitCode = ToolRunner.run(new SmallFilesToSequenceFileConverter(),args);System.exit(exitCode);}
}
