Hadoop自带Sort例子分析
/**
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/ package org.apache.hadoop.examples; import java.io.IOException;
import java.net.URI;
import java.util.*; import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.mapreduce.filecache.DistributedCache;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.mapred.ClusterStatus;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.hadoop.mapreduce.lib.partition.InputSampler;
import org.apache.hadoop.mapreduce.lib.partition.TotalOrderPartitioner;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner; /**
* This is the trivial map/reduce program that does absolutely nothing
* other than use the framework to fragment and sort the input values.
*
* To run: bin/hadoop jar build/hadoop-examples.jar sort
* [-r <i>reduces</i>]
* [-inFormat <i>input format class</i>]
* [-outFormat <i>output format class</i>]
* [-outKey <i>output key class</i>]
* [-outValue <i>output value class</i>]
* [-totalOrder <i>pcnt</i> <i>num samples</i> <i>max splits</i>]
* <i>in-dir</i> <i>out-dir</i>
*/
public class Sort<K,V> extends Configured implements Tool {
public static final String REDUCES_PER_HOST =
"mapreduce.sort.reducesperhost";
private Job job = null; static int printUsage() {
System.out.println("sort [-r <reduces>] " +
"[-inFormat <input format class>] " +
"[-outFormat <output format class>] " +
"[-outKey <output key class>] " +
"[-outValue <output value class>] " +
"[-totalOrder <pcnt> <num samples> <max splits>] " +
"<input> <output>");
ToolRunner.printGenericCommandUsage(System.out);
return 2;
} /**
* The main driver for sort program.
* Invoke this method to submit the map/reduce job.
* @throws IOException When there is communication problems with the
* job tracker.
*/
public int run(String[] args) throws Exception { Configuration conf = getConf();
JobClient client = new JobClient(conf);
ClusterStatus cluster = client.getClusterStatus();
int num_reduces = (int) (cluster.getMaxReduceTasks() * 0.9);
String sort_reduces = conf.get(REDUCES_PER_HOST);
if (sort_reduces != null) {
num_reduces = cluster.getTaskTrackers() *
Integer.parseInt(sort_reduces);
}
Class<? extends InputFormat> inputFormatClass =
SequenceFileInputFormat.class;
Class<? extends OutputFormat> outputFormatClass =
SequenceFileOutputFormat.class;
Class<? extends WritableComparable> outputKeyClass = BytesWritable.class;
Class<? extends Writable> outputValueClass = BytesWritable.class;
List<String> otherArgs = new ArrayList<String>();
InputSampler.Sampler<K,V> sampler = null;
for(int i=0; i < args.length; ++i) {
try {
if ("-r".equals(args[i])) {
num_reduces = Integer.parseInt(args[++i]);
} else if ("-inFormat".equals(args[i])) {
inputFormatClass =
Class.forName(args[++i]).asSubclass(InputFormat.class);
} else if ("-outFormat".equals(args[i])) {
outputFormatClass =
Class.forName(args[++i]).asSubclass(OutputFormat.class);
} else if ("-outKey".equals(args[i])) {
outputKeyClass =
Class.forName(args[++i]).asSubclass(WritableComparable.class);
} else if ("-outValue".equals(args[i])) {
outputValueClass =
Class.forName(args[++i]).asSubclass(Writable.class);
} else if ("-totalOrder".equals(args[i])) {
double pcnt = Double.parseDouble(args[++i]);
int numSamples = Integer.parseInt(args[++i]);
int maxSplits = Integer.parseInt(args[++i]);
if (0 >= maxSplits) maxSplits = Integer.MAX_VALUE;
sampler =
new InputSampler.RandomSampler<K,V>(pcnt, numSamples, maxSplits);
} else {
otherArgs.add(args[i]);
}
} catch (NumberFormatException except) {
System.out.println("ERROR: Integer expected instead of " + args[i]);
return printUsage();
} catch (ArrayIndexOutOfBoundsException except) {
System.out.println("ERROR: Required parameter missing from " +
args[i-1]);
return printUsage(); // exits
}
}
// Set user-supplied (possibly default) job configs
job = Job.getInstance(conf);
job.setJobName("sorter");
job.setJarByClass(Sort.class); job.setMapperClass(Mapper.class);
job.setReducerClass(Reducer.class); job.setNumReduceTasks(num_reduces); job.setInputFormatClass(inputFormatClass);
job.setOutputFormatClass(outputFormatClass); job.setOutputKeyClass(outputKeyClass);
job.setOutputValueClass(outputValueClass); // Make sure there are exactly 2 parameters left.
if (otherArgs.size() != 2) {
System.out.println("ERROR: Wrong number of parameters: " +
otherArgs.size() + " instead of 2.");
return printUsage();
}
FileInputFormat.setInputPaths(job, otherArgs.get(0));
FileOutputFormat.setOutputPath(job, new Path(otherArgs.get(1))); if (sampler != null) {
System.out.println("Sampling input to effect total-order sort...");
job.setPartitionerClass(TotalOrderPartitioner.class);
Path inputDir = FileInputFormat.getInputPaths(job)[0];
inputDir = inputDir.makeQualified(inputDir.getFileSystem(conf));
Path partitionFile = new Path(inputDir, "_sortPartitioning");
TotalOrderPartitioner.setPartitionFile(conf, partitionFile);
InputSampler.<K,V>writePartitionFile(job, sampler);
URI partitionUri = new URI(partitionFile.toString() +
"#" + "_sortPartitioning");
DistributedCache.addCacheFile(partitionUri, conf);
} System.out.println("Running on " +
cluster.getTaskTrackers() +
" nodes to sort from " +
FileInputFormat.getInputPaths(job)[0] + " into " +
FileOutputFormat.getOutputPath(job) +
" with " + num_reduces + " reduces.");
Date startTime = new Date();
System.out.println("Job started: " + startTime);
int ret = job.waitForCompletion(true) ? 0 : 1;
Date end_time = new Date();
System.out.println("Job ended: " + end_time);
System.out.println("The job took " +
(end_time.getTime() - startTime.getTime()) /1000 + " seconds.");
return ret;
} public static void main(String[] args) throws Exception {
int res = ToolRunner.run(new Configuration(), new Sort(), args);
System.exit(res);
} /**
* Get the last job that was run using this instance.
* @return the results of the last job that was run
*/
public Job getResult() {
return job;
}
}
看了源码的第一印象就是,我啥时候写MapReduce也这么规范,这么屌......
Hadoop自带Sort例子分析的更多相关文章
- 如何运行Hadoop自带的例子
bin/hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-2.6.4.jar wordcount /WordCount/WordC ...
- 三.hadoop mapreduce之WordCount例子
目录: 目录见文章1 这个案列完成对单词的计数,重写map,与reduce方法,完成对mapreduce的理解. Mapreduce初析 Mapreduce是一个计算框架,既然是做计算的框架,那么表现 ...
- hadoop自带例子wordcount的具体运行步骤
1.在hadoop所在目录“usr/local”下创建一个文件夹input root@ubuntu:/usr/local# mkdir input 2.在文件夹input中创建两个文本文件file1. ...
- 几个有关Hadoop自带的性能测试工具的应用
http://www.talkwithtrend.com/Question/177983-1247453 一些测试的描述如下内容最为详细,供你参考: 测试对于验证系统的正确性.分析系统的性能来说非常重 ...
- VS2010自带的性能分析工具分析.NET程序的性能
这篇博文给大家分享的是,如何使用VS自带的性能分析工具来分析我们编写的.NET程序,一边找出程序性能的瓶颈,改善代码的质量.在实际开发中,性能真的很重要,往往决定一个产品的生死~良好的用户体验的基础之 ...
- ZT 复杂的函数指针例子分析 2008
复杂的函数指针例子分析 2008-01-26 11:38:22 分类: 一个最简单的函数指针定义如下: Void (*funcPtr) (); //funcptr是一个函数指针,它指向的函数没有参数 ...
- 使用VS自带的工具分析.NET程序的性能
(转自:http://www.cnblogs.com/DebugLZQ/archive/2012/07/10/2585245.html) 这篇博文给大家分享的是,如何使用VS自带的性能分析工具来分析我 ...
- hadoop自带的writable类型
Hadoop 中,并没有使用Java自带的基本类型类(Integer.Float等),而是使用自己开发的类.Hadoop 自带有很多序列化类型,大致分为以下两种: 实现了WritableCompara ...
- spark JavaDirectKafkaWordCount 例子分析
spark JavaDirectKafkaWordCount 例子分析: 1. KafkaUtils.createDirectStream( jssc, String.class, String.c ...
随机推荐
- [BZOJ3920]Yuuna的礼物
题目大意: 给你一个长度为$n(n\le40000)$的数列$\{a_i\}(1\le a_i\le n)$,给出$m(m\le40000)$次询问,每次给出$l,r,k_1,k_2$询问区间$[l, ...
- js日常笔记
写在前面: 在工作中,有时候会遇到一些零零碎碎的小知识点,虽然这些网上都可以查询到,但还是想把一些自己不是很熟悉的当做笔记记录下来,方便以后查询. 1.按钮隐藏/显示/可用/不可用 $("# ...
- hdu 1015 Safecracker 水题一枚
题目链接:HDU - 1015 === Op tech briefing, 2002/11/02 06:42 CST === "The item is locked in a Klein s ...
- Microsoft SQL Server Version List [sqlserver 7.0-------sql server 2016]
http://sqlserverbuilds.blogspot.jp/ What version of SQL Server do I have? This unofficial build ch ...
- 全面理解java自动装箱和拆箱(转)
自动装箱和拆箱从Java 1.5开始引入,目的是将原始类型值转自动地转换成对应的对象.自动装箱与拆箱的机制可以让我们在Java的变量赋值或者是方法调用等情况下使用原始类型或者对象类型更加简单直接. 如 ...
- ubuntu常用 命令
卸载软件 ,比如chrome sudo apt-get remove google-chrome-stable
- hmac的python实现
Hash-based message authentication code,利用哈希算法,以一个密钥和一个消息为输入,生成一个消息摘要作为输出 可以查看python的内置模块hmac.py的源码来学 ...
- DotnetBrowser高级教程-(4)使用MVC框架4-过滤器
dotnetbrowser内置了过滤器,所谓过滤器,就是实现了Action前后拦截,请看下例: 1.增加目录Filters,在该目录下增加新的过滤器PerformanceFilter,代码如下: pu ...
- SQL JOB 调用 SSIS package 权限问题
来自: http://www.cnblogs.com/sodacc/archive/2012/11/26/2789135.html 第一次用SQL给SSIS包排JOB的时候,都会遇到这样一个问题:单独 ...
- OkHttpClient简单封装
一.接口 public interface HttpListener { void onFinish(String reponse); void onError(Exception e); } 二.O ...