小文件处理案例(自定义InputFormat)
1)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。将多个小文件合并成一个文件SequenceFile,SequenceFile里面存储着多个文件,存储的形式为文件路径+名称为key,文件内容为value。
2)输入数据
1:
yongpeng weidong weinan
sanfeng luozong xiaoming
2:
longlong fanfan
mazong kailun yuhang yixin
longlong fanfan
mazong kailun yuhang yixin
3:
shuaige changmo zhenqiang
dongli lingu xuanxuan
最终预期文件格式:
SEQorg.apache.hadoop.io.Text"org.apache.hadoop.io.BytesWritable ã;ŠCW
uÊÚX@ù½ü˜í W "!file:/e:/inputinputformat/one.txt 1yongpeng weidong weinan
sanfeng luozong xiaoming Y $#file:/e:/inputinputformat/three.txt 1shuaige changmo zhenqiang
dongli lingu xuanxuan € "!file:/e:/inputinputformat/two.txt Zlonglong fanfan
mazong kailun yuhang yixin
longlong fanfan
mazong kailun yuhang yixin
3)分析
小文件的优化无非以下几种方式:
(1)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
(2)在业务处理之前,在HDFS上使用mapreduce程序对小文件进行合并
(3)在mapreduce处理时,可采用CombineTextInputFormat提高效率
4)具体实现
本节采用自定义InputFormat的方式,处理输入小文件的问题。
(1)自定义一个类继承FileInputFormat
(2)改写RecordReader,实现一次读取一个完整文件封装为KV
(3)在输出时使用SequenceFileOutPutFormat输出合并文件
5)程序实现:
(1)自定义InputFromat
package com.atguigu.mapreduce.inputformat; import java.io.IOException; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.BytesWritable; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.mapreduce.InputSplit; import org.apache.hadoop.mapreduce.JobContext; import org.apache.hadoop.mapreduce.RecordReader; import org.apache.hadoop.mapreduce.TaskAttemptContext; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
// 定义类继承FileInputFormat public class WholeFileInputformat extends FileInputFormat<NullWritable, BytesWritable>{
@Override protected boolean isSplitable(JobContext context, Path filename) { return false; }
@Override public RecordReader<NullWritable, BytesWritable> createRecordReader(InputSplit split, TaskAttemptContext context) throws IOException, InterruptedException {
WholeRecordReader recordReader = new WholeRecordReader(); recordReader.initialize(split, context);
return recordReader; } } |
(2)自定义RecordReader
package com.atguigu.mapreduce.inputformat; import java.io.IOException; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.FSDataInputStream; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.BytesWritable; import org.apache.hadoop.io.IOUtils; import org.apache.hadoop.io.NullWritable; 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.FileSplit;
public class WholeRecordReader extends RecordReader<NullWritable, BytesWritable>{
private Configuration configuration; private FileSplit split;
private boolean processed = false; private BytesWritable value = new BytesWritable();
@Override public void initialize(InputSplit split, TaskAttemptContext context) throws IOException, InterruptedException {
this.split = (FileSplit)split; configuration = context.getConfiguration(); }
@Override public boolean nextKeyValue() throws IOException, InterruptedException {
if (!processed) { // 1 定义缓存区 byte[] contents = new byte[(int)split.getLength()];
FileSystem fs = null; FSDataInputStream fis = null;
try { // 2 获取文件系统 Path path = split.getPath(); fs = path.getFileSystem(configuration);
// 3 读取数据 fis = fs.open(path);
// 4 读取文件内容 IOUtils.readFully(fis, contents, 0, contents.length);
// 5 输出文件内容 value.set(contents, 0, contents.length); } catch (Exception e) {
}finally { IOUtils.closeStream(fis); }
processed = true;
return true; }
return false; }
@Override public NullWritable getCurrentKey() throws IOException, InterruptedException { return NullWritable.get(); }
@Override public BytesWritable getCurrentValue() throws IOException, InterruptedException { return value; }
@Override public float getProgress() throws IOException, InterruptedException { return processed? 1:0; }
@Override public void close() throws IOException { } } |
(3)SequenceFileMapper处理流程
package com.atguigu.mapreduce.inputformat; import java.io.IOException; import org.apache.hadoop.io.BytesWritable; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.lib.input.FileSplit;
public class SequenceFileMapper extends Mapper<NullWritable, BytesWritable, Text, BytesWritable>{
Text k = new Text();
@Override protected void setup(Mapper<NullWritable, BytesWritable, Text, BytesWritable>.Context context) throws IOException, InterruptedException { // 1 获取文件切片信息 FileSplit inputSplit = (FileSplit) context.getInputSplit(); // 2 获取切片名称 String name = inputSplit.getPath().toString(); // 3 设置key的输出 k.set(name); }
@Override protected void map(NullWritable key, BytesWritable value, Context context) throws IOException, InterruptedException {
context.write(k, value); } } |
(4)SequenceFileReducer处理流程
package com.atguigu.mapreduce.inputformat; import java.io.IOException; import org.apache.hadoop.io.BytesWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Reducer;
public class SequenceFileReducer extends Reducer<Text, BytesWritable, Text, BytesWritable> {
@Override protected void reduce(Text key, Iterable<BytesWritable> values, Context context) throws IOException, InterruptedException {
context.write(key, values.iterator().next()); } } |
(5)SequenceFileDriver处理流程
package com.atguigu.mapreduce.inputformat; import java.io.IOException; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.BytesWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
public class SequenceFileDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
args = new String[] { "e:/input/inputinputformat", "e:/output1" }; Configuration conf = new Configuration();
Job job = Job.getInstance(conf); job.setJarByClass(SequenceFileDriver.class); job.setMapperClass(SequenceFileMapper.class); job.setReducerClass(SequenceFileReducer.class);
// 设置输入的inputFormat job.setInputFormatClass(WholeFileInputformat.class); // 设置输出的outputFormat job.setOutputFormatClass(SequenceFileOutputFormat.class);
job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(BytesWritable.class);
job.setOutputKeyClass(Text.class); job.setOutputValueClass(BytesWritable.class);
FileInputFormat.setInputPaths(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean result = job.waitForCompletion(true);
System.exit(result ? 0 : 1); } } |