apache
/
hadoop
mirror of https://github.com/apache/hadoop.git


			
				
					
						
						
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348334933503351335233533354335533563357335833593360336133623363336433653366336733683369337033713372337333743375337633773378337933803381338233833384338533863387338833893390339133923393339433953396339733983399340034013402340334043405340634073408340934103411341234133414341534163417341834193420342134223423342434253426342734283429343034313432343334343435343634373438343934403441344234433444344534463447344834493450345134523453345434553456345734583459346034613462346334643465346634673468346934703471347234733474347534763477347834793480348134823483348434853486348734883489349034913492349334943495349634973498349935003501350235033504350535063507350835093510351135123513351435153516351735183519352035213522352335243525352635273528352935303531353235333534353535363537353835393540354135423543354435453546354735483549355035513552355335543555355635573558355935603561356235633564356535663567356835693570357135723573357435753576357735783579358035813582358335843585358635873588358935903591359235933594359535963597359835993600360136023603360436053606360736083609361036113612361336143615361636173618361936203621362236233624362536263627362836293630363136323633363436353636363736383639364036413642364336443645364636473648364936503651365236533654365536563657365836593660366136623663366436653666366736683669367036713672367336743675367636773678367936803681368236833684368536863687368836893690369136923693369436953696369736983699370037013702370337043705370637073708370937103711371237133714371537163717371837193720372137223723372437253726372737283729373037313732373337343735373637373738373937403741374237433744374537463747374837493750375137523753375437553756375737583759376037613762376337643765376637673768376937703771377237733774377537763777377837793780378137823783378437853786378737883789379037913792379337943795379637973798379938003801380238033804380538063807380838093810381138123813381438153816381738183819382038213822382338243825382638273828382938303831383238333834383538363837383838393840384138423843384438453846384738483849385038513852385338543855385638573858385938603861386238633864386538663867386838693870387138723873387438753876387738783879388038813882388338843885388638873888388938903891389238933894389538963897389838993900390139023903390439053906390739083909391039113912391339143915391639173918391939203921392239233924392539263927392839293930393139323933393439353936393739383939394039413942394339443945394639473948394939503951395239533954395539563957395839593960396139623963396439653966396739683969397039713972397339743975397639773978397939803981398239833984398539863987398839893990399139923993399439953996399739983999400040014002400340044005400640074008400940104011401240134014401540164017401840194020402140224023402440254026402740284029403040314032403340344035403640374038403940404041404240434044404540464047404840494050405140524053405440554056405740584059406040614062406340644065406640674068406940704071407240734074407540764077407840794080408140824083408440854086408740884089409040914092409340944095409640974098409941004101410241034104410541064107410841094110411141124113411441154116411741184119412041214122
							<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<META http-equiv="Content-Type" content="text/html; charset=UTF-8">
<meta content="Apache Forrest" name="Generator">
<meta name="Forrest-version" content="0.8">
<meta name="Forrest-skin-name" content="pelt">
<title>Hadoop Map/Reduce Tutorial</title>
<link type="text/css" href="skin/basic.css" rel="stylesheet">
<link media="screen" type="text/css" href="skin/screen.css" rel="stylesheet">
<link media="print" type="text/css" href="skin/print.css" rel="stylesheet">
<link type="text/css" href="skin/profile.css" rel="stylesheet">
<script src="skin/getBlank.js" language="javascript" type="text/javascript"></script><script src="skin/getMenu.js" language="javascript" type="text/javascript"></script><script src="skin/fontsize.js" language="javascript" type="text/javascript"></script>
<link rel="shortcut icon" href="images/favicon.ico">
</head>
<body onload="init()">
<script type="text/javascript">ndeSetTextSize();</script>
<div id="top">
<!--+
    |breadtrail
    +-->
<div class="breadtrail">
<a href="http://www.apache.org/">Apache</a> &gt; <a href="http://hadoop.apache.org/">Hadoop</a> &gt; <a href="http://hadoop.apache.org/core/">Core</a><script src="skin/breadcrumbs.js" language="JavaScript" type="text/javascript"></script>
</div>
<!--+
    |header
    +-->
<div class="header">
<!--+
    |start group logo
    +-->
<div class="grouplogo">
<a href="http://hadoop.apache.org/"><img class="logoImage" alt="Hadoop" src="images/hadoop-logo.jpg" title="Apache Hadoop"></a>
</div>
<!--+
    |end group logo
    +-->
<!--+
    |start Project Logo
    +-->
<div class="projectlogo">
<a href="http://hadoop.apache.org/core/"><img class="logoImage" alt="Hadoop" src="images/core-logo.gif" title="Scalable Computing Platform"></a>
</div>
<!--+
    |end Project Logo
    +-->
<!--+
    |start Search
    +-->
<div class="searchbox">
<form action="http://www.google.com/search" method="get" class="roundtopsmall">
<input value="hadoop.apache.org" name="sitesearch" type="hidden"><input onFocus="getBlank (this, 'Search the site with google');" size="25" name="q" id="query" type="text" value="Search the site with google">&nbsp; 
                    <input name="Search" value="Search" type="submit">
</form>
</div>
<!--+
    |end search
    +-->
<!--+
    |start Tabs
    +-->
<ul id="tabs">
<li>
<a class="unselected" href="http://hadoop.apache.org/core/">Project</a>
</li>
<li>
<a class="unselected" href="http://wiki.apache.org/hadoop">Wiki</a>
</li>
<li class="current">
<a class="selected" href="index.html">Hadoop 0.19 Documentation</a>
</li>
</ul>
<!--+
    |end Tabs
    +-->
</div>
</div>
<div id="main">
<div id="publishedStrip">
<!--+
    |start Subtabs
    +-->
<div id="level2tabs"></div>
<!--+
    |end Endtabs
    +-->
<script type="text/javascript"><!--
document.write("Last Published: " + document.lastModified);
//  --></script>
</div>
<!--+
    |breadtrail
    +-->
<div class="breadtrail">

             &nbsp;
           </div>
<!--+
    |start Menu, mainarea
    +-->
<!--+
    |start Menu
    +-->
<div id="menu">
<div onclick="SwitchMenu('menu_selected_1.1', 'skin/')" id="menu_selected_1.1Title" class="menutitle" style="background-image: url('skin/images/chapter_open.gif');">Documentation</div>
<div id="menu_selected_1.1" class="selectedmenuitemgroup" style="display: block;">
<div class="menuitem">
<a href="index.html">Overview</a>
</div>
<div class="menuitem">
<a href="quickstart.html">Hadoop Quick Start</a>
</div>
<div class="menuitem">
<a href="cluster_setup.html">Hadoop Cluster Setup</a>
</div>
<div class="menupage">
<div class="menupagetitle">Hadoop Map/Reduce Tutorial</div>
</div>
<div class="menuitem">
<a href="commands_manual.html">Hadoop Command Guide</a>
</div>
<div class="menuitem">
<a href="hdfs_shell.html">Hadoop FS Shell Guide</a>
</div>
<div class="menuitem">
<a href="distcp.html">Hadoop DistCp Guide</a>
</div>
<div class="menuitem">
<a href="native_libraries.html">Hadoop Native Libraries</a>
</div>
<div class="menuitem">
<a href="streaming.html">Hadoop Streaming</a>
</div>
<div class="menuitem">
<a href="hadoop_archives.html">Hadoop Archives</a>
</div>
<div class="menuitem">
<a href="hdfs_user_guide.html">HDFS User Guide</a>
</div>
<div class="menuitem">
<a href="hdfs_design.html">HDFS Architecture</a>
</div>
<div class="menuitem">
<a href="hdfs_permissions_guide.html">HDFS Admin Guide: Permissions</a>
</div>
<div class="menuitem">
<a href="hdfs_quota_admin_guide.html">HDFS Admin Guide: Quotas</a>
</div>
<div class="menuitem">
<a href="SLG_user_guide.html">HDFS Utilities</a>
</div>
<div class="menuitem">
<a href="libhdfs.html">HDFS C API</a>
</div>
<div class="menuitem">
<a href="hod_user_guide.html">HOD User Guide</a>
</div>
<div class="menuitem">
<a href="hod_admin_guide.html">HOD Admin Guide</a>
</div>
<div class="menuitem">
<a href="hod_config_guide.html">HOD Config Guide</a>
</div>
<div class="menuitem">
<a href="capacity_scheduler.html">Capacity Scheduler</a>
</div>
<div class="menuitem">
<a href="api/index.html">API Docs</a>
</div>
<div class="menuitem">
<a href="jdiff/changes.html">API Changes</a>
</div>
<div class="menuitem">
<a href="http://wiki.apache.org/hadoop/">Wiki</a>
</div>
<div class="menuitem">
<a href="http://wiki.apache.org/hadoop/FAQ">FAQ</a>
</div>
<div class="menuitem">
<a href="releasenotes.html">Release Notes</a>
</div>
<div class="menuitem">
<a href="changes.html">Change Log</a>
</div>
</div>
<div id="credit"></div>
<div id="roundbottom">
<img style="display: none" class="corner" height="15" width="15" alt="" src="skin/images/rc-b-l-15-1body-2menu-3menu.png"></div>
<!--+
  |alternative credits
  +-->
<div id="credit2"></div>
</div>
<!--+
    |end Menu
    +-->
<!--+
    |start content
    +-->
<div id="content">
<div title="Portable Document Format" class="pdflink">
<a class="dida" href="mapred_tutorial.pdf"><img alt="PDF -icon" src="skin/images/pdfdoc.gif" class="skin"><br>
        PDF</a>
</div>
<h1>Hadoop Map/Reduce Tutorial</h1>
<div id="minitoc-area">
<ul class="minitoc">
<li>
<a href="#Purpose">Purpose</a>
</li>
<li>
<a href="#Pre-requisites">Pre-requisites</a>
</li>
<li>
<a href="#Overview">Overview</a>
</li>
<li>
<a href="#Inputs+and+Outputs">Inputs and Outputs</a>
</li>
<li>
<a href="#Example%3A+WordCount+v1.0">Example: WordCount v1.0</a>
<ul class="minitoc">
<li>
<a href="#Source+Code">Source Code</a>
</li>
<li>
<a href="#Usage">Usage</a>
</li>
<li>
<a href="#Walk-through">Walk-through</a>
</li>
</ul>
</li>
<li>
<a href="#Map%2FReduce+-+User+Interfaces">Map/Reduce - User Interfaces</a>
<ul class="minitoc">
<li>
<a href="#Payload">Payload</a>
<ul class="minitoc">
<li>
<a href="#Mapper">Mapper</a>
</li>
<li>
<a href="#Reducer">Reducer</a>
</li>
<li>
<a href="#Partitioner">Partitioner</a>
</li>
<li>
<a href="#Reporter">Reporter</a>
</li>
<li>
<a href="#OutputCollector">OutputCollector</a>
</li>
</ul>
</li>
<li>
<a href="#Job+Configuration">Job Configuration</a>
</li>
<li>
<a href="#Task+Execution+%26+Environment">Task Execution &amp; Environment</a>
<ul class="minitoc">
<li>
<a href="#Memory+management"> Memory management</a>
</li>
<li>
<a href="#Map+Parameters">Map Parameters</a>
</li>
<li>
<a href="#Shuffle%2FReduce+Parameters">Shuffle/Reduce Parameters</a>
</li>
<li>
<a href="#Directory+Structure"> Directory Structure </a>
</li>
<li>
<a href="#Task+JVM+Reuse">Task JVM Reuse</a>
</li>
</ul>
</li>
<li>
<a href="#Job+Submission+and+Monitoring">Job Submission and Monitoring</a>
<ul class="minitoc">
<li>
<a href="#Job+Control">Job Control</a>
</li>
</ul>
</li>
<li>
<a href="#Job+Input">Job Input</a>
<ul class="minitoc">
<li>
<a href="#InputSplit">InputSplit</a>
</li>
<li>
<a href="#RecordReader">RecordReader</a>
</li>
</ul>
</li>
<li>
<a href="#Job+Output">Job Output</a>
<ul class="minitoc">
<li>
<a href="#OutputCommitter">OutputCommitter</a>
</li>
<li>
<a href="#Task+Side-Effect+Files">Task Side-Effect Files</a>
</li>
<li>
<a href="#RecordWriter">RecordWriter</a>
</li>
</ul>
</li>
<li>
<a href="#Other+Useful+Features">Other Useful Features</a>
<ul class="minitoc">
<li>
<a href="#Submitting+Jobs+to+Queues">Submitting Jobs to Queues</a>
</li>
<li>
<a href="#Counters">Counters</a>
</li>
<li>
<a href="#DistributedCache">DistributedCache</a>
</li>
<li>
<a href="#Tool">Tool</a>
</li>
<li>
<a href="#IsolationRunner">IsolationRunner</a>
</li>
<li>
<a href="#Profiling">Profiling</a>
</li>
<li>
<a href="#Debugging">Debugging</a>
</li>
<li>
<a href="#JobControl">JobControl</a>
</li>
<li>
<a href="#Data+Compression">Data Compression</a>
</li>
<li>
<a href="#Skipping+Bad+Records">Skipping Bad Records</a>
</li>
</ul>
</li>
</ul>
</li>
<li>
<a href="#Example%3A+WordCount+v2.0">Example: WordCount v2.0</a>
<ul class="minitoc">
<li>
<a href="#Source+Code-N10FA4">Source Code</a>
</li>
<li>
<a href="#Sample+Runs">Sample Runs</a>
</li>
<li>
<a href="#Highlights">Highlights</a>
</li>
</ul>
</li>
</ul>
</div>
  
    
<a name="N1000D"></a><a name="Purpose"></a>
<h2 class="h3">Purpose</h2>
<div class="section">
<p>This document comprehensively describes all user-facing facets of the 
      Hadoop Map/Reduce framework and serves as a tutorial.
      </p>
</div>
    
    
<a name="N10017"></a><a name="Pre-requisites"></a>
<h2 class="h3">Pre-requisites</h2>
<div class="section">
<p>Ensure that Hadoop is installed, configured and is running. More
      details:</p>
<ul>
        
<li>
          
<a href="quickstart.html">Hadoop Quick Start</a> for first-time users.
        </li>
        
<li>
          
<a href="cluster_setup.html">Hadoop Cluster Setup</a> for large, 
          distributed clusters.
        </li>
      
</ul>
</div>
    
    
<a name="N10032"></a><a name="Overview"></a>
<h2 class="h3">Overview</h2>
<div class="section">
<p>Hadoop Map/Reduce is a software framework for easily writing 
      applications which process vast amounts of data (multi-terabyte data-sets) 
      in-parallel on large clusters (thousands of nodes) of commodity 
      hardware in a reliable, fault-tolerant manner.</p>
<p>A Map/Reduce <em>job</em> usually splits the input data-set into 
      independent chunks which are processed by the <em>map tasks</em> in a
      completely parallel manner. The framework sorts the outputs of the maps, 
      which are then input to the <em>reduce tasks</em>. Typically both the 
      input and the output of the job are stored in a file-system. The framework 
      takes care of scheduling tasks, monitoring them and re-executes the failed
      tasks.</p>
<p>Typically the compute nodes and the storage nodes are the same, that is, 
      the Map/Reduce framework and the Hadoop Distributed File System (see <a href="hdfs_design.html">HDFS Architecture </a>) 
      are running on the same set of nodes. This configuration
      allows the framework to effectively schedule tasks on the nodes where data 
      is already present, resulting in very high aggregate bandwidth across the 
      cluster.</p>
<p>The Map/Reduce framework consists of a single master 
      <span class="codefrag">JobTracker</span> and one slave <span class="codefrag">TaskTracker</span> per 
      cluster-node. The master is responsible for scheduling the jobs' component 
      tasks on the slaves, monitoring them and re-executing the failed tasks. The 
      slaves execute the tasks as directed by the master.</p>
<p>Minimally, applications specify the input/output locations and supply
      <em>map</em> and <em>reduce</em> functions via implementations of
      appropriate interfaces and/or abstract-classes. These, and other job 
      parameters, comprise the <em>job configuration</em>. The Hadoop 
      <em>job client</em> then submits the job (jar/executable etc.) and 
      configuration to the <span class="codefrag">JobTracker</span> which then assumes the 
      responsibility of distributing the software/configuration to the slaves, 
      scheduling tasks and monitoring them, providing status and diagnostic 
      information to the job-client.</p>
<p>Although the Hadoop framework is implemented in Java<sup>TM</sup>, 
      Map/Reduce applications need not be written in Java.</p>
<ul>
        
<li>
          
<a href="api/org/apache/hadoop/streaming/package-summary.html">
          Hadoop Streaming</a> is a utility which allows users to create and run 
          jobs with any executables (e.g. shell utilities) as the mapper and/or 
          the reducer.
        </li>
        
<li>
          
<a href="api/org/apache/hadoop/mapred/pipes/package-summary.html">
          Hadoop Pipes</a> is a <a href="http://www.swig.org/">SWIG</a>-
          compatible <em>C++ API</em> to implement Map/Reduce applications (non 
          JNI<sup>TM</sup> based).
        </li>
      
</ul>
</div>
    
    
<a name="N1008B"></a><a name="Inputs+and+Outputs"></a>
<h2 class="h3">Inputs and Outputs</h2>
<div class="section">
<p>The Map/Reduce framework operates exclusively on 
      <span class="codefrag">&lt;key, value&gt;</span> pairs, that is, the framework views the 
      input to the job as a set of <span class="codefrag">&lt;key, value&gt;</span> pairs and 
      produces a set of <span class="codefrag">&lt;key, value&gt;</span> pairs as the output of 
      the job, conceivably of different types.</p>
<p>The <span class="codefrag">key</span> and <span class="codefrag">value</span> classes have to be 
      serializable by the framework and hence need to implement the 
      <a href="api/org/apache/hadoop/io/Writable.html">Writable</a> 
      interface. Additionally, the <span class="codefrag">key</span> classes have to implement the
      <a href="api/org/apache/hadoop/io/WritableComparable.html">
      WritableComparable</a> interface to facilitate sorting by the framework.
      </p>
<p>Input and Output types of a Map/Reduce job:</p>
<p>
        (input) <span class="codefrag">&lt;k1, v1&gt;</span> 
        -&gt; 
        <strong>map</strong> 
        -&gt; 
        <span class="codefrag">&lt;k2, v2&gt;</span> 
        -&gt; 
        <strong>combine</strong> 
        -&gt; 
        <span class="codefrag">&lt;k2, v2&gt;</span> 
        -&gt; 
        <strong>reduce</strong> 
        -&gt; 
        <span class="codefrag">&lt;k3, v3&gt;</span> (output)
      </p>
</div>

    
<a name="N100CD"></a><a name="Example%3A+WordCount+v1.0"></a>
<h2 class="h3">Example: WordCount v1.0</h2>
<div class="section">
<p>Before we jump into the details, lets walk through an example Map/Reduce 
      application to get a flavour for how they work.</p>
<p>
<span class="codefrag">WordCount</span> is a simple application that counts the number of
      occurences of each word in a given input set.</p>
<p>This works with a local-standalone, pseudo-distributed or fully-distributed 
      Hadoop installation(see <a href="quickstart.html"> Hadoop Quick Start</a>).</p>
<a name="N100E2"></a><a name="Source+Code"></a>
<h3 class="h4">Source Code</h3>
<table class="ForrestTable" cellspacing="1" cellpadding="4">
          
<tr>
            
<th colspan="1" rowspan="1"></th>
            <th colspan="1" rowspan="1">WordCount.java</th>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">1.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">package org.myorg;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">2.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">3.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import java.io.IOException;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">4.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import java.util.*;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">5.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">6.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import org.apache.hadoop.fs.Path;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">7.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import org.apache.hadoop.conf.*;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">8.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import org.apache.hadoop.io.*;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">9.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import org.apache.hadoop.mapred.*;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">10.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import org.apache.hadoop.util.*;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">11.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">12.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">public class WordCount {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">13.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">14.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;
              <span class="codefrag">
                public static class Map extends MapReduceBase 
                implements Mapper&lt;LongWritable, Text, Text, IntWritable&gt; {
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">15.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                private final static IntWritable one = new IntWritable(1);
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">16.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">private Text word = new Text();</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">17.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">18.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                public void map(LongWritable key, Text value, 
                OutputCollector&lt;Text, IntWritable&gt; output, 
                Reporter reporter) throws IOException {
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">19.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">String line = value.toString();</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">20.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">StringTokenizer tokenizer = new StringTokenizer(line);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">21.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">while (tokenizer.hasMoreTokens()) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">22.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">word.set(tokenizer.nextToken());</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">23.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">output.collect(word, one);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">24.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">25.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">26.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">27.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">28.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;
              <span class="codefrag">
                public static class Reduce extends MapReduceBase implements 
                Reducer&lt;Text, IntWritable, Text, IntWritable&gt; {
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">29.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                public void reduce(Text key, Iterator&lt;IntWritable&gt; values,
                OutputCollector&lt;Text, IntWritable&gt; output, 
                Reporter reporter) throws IOException {
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">30.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">int sum = 0;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">31.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">while (values.hasNext()) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">32.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">sum += values.next().get();</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">33.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">34.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">output.collect(key, new IntWritable(sum));</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">35.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">36.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">37.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">38.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;
              <span class="codefrag">
                public static void main(String[] args) throws Exception {
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">39.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                JobConf conf = new JobConf(WordCount.class);
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">40.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setJobName("wordcount");</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">41.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">42.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setOutputKeyClass(Text.class);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">43.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setOutputValueClass(IntWritable.class);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">44.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">45.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setMapperClass(Map.class);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">46.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setCombinerClass(Reduce.class);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">47.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setReducerClass(Reduce.class);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">48.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">49.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setInputFormat(TextInputFormat.class);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">50.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setOutputFormat(TextOutputFormat.class);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">51.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">52.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">FileInputFormat.setInputPaths(conf, new Path(args[0]));</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">53.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">FileOutputFormat.setOutputPath(conf, new Path(args[1]));</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">54.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">55.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">JobClient.runJob(conf);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">57.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">58.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">59.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
        
</table>
<a name="N10464"></a><a name="Usage"></a>
<h3 class="h4">Usage</h3>
<p>Assuming <span class="codefrag">HADOOP_HOME</span> is the root of the installation and 
        <span class="codefrag">HADOOP_VERSION</span> is the Hadoop version installed, compile 
        <span class="codefrag">WordCount.java</span> and create a jar:</p>
<p>
          
<span class="codefrag">$ mkdir wordcount_classes</span>
<br>
          
<span class="codefrag">
            $ javac -classpath ${HADOOP_HOME}/hadoop-${HADOOP_VERSION}-core.jar 
              -d wordcount_classes WordCount.java
          </span>
<br>
          
<span class="codefrag">$ jar -cvf /usr/joe/wordcount.jar -C wordcount_classes/ .</span> 
        
</p>
<p>Assuming that:</p>
<ul>
          
<li>
            
<span class="codefrag">/usr/joe/wordcount/input</span>  - input directory in HDFS
          </li>
          
<li>
            
<span class="codefrag">/usr/joe/wordcount/output</span> - output directory in HDFS
          </li>
        
</ul>
<p>Sample text-files as input:</p>
<p>
          
<span class="codefrag">$ bin/hadoop dfs -ls /usr/joe/wordcount/input/</span>
<br>
          
<span class="codefrag">/usr/joe/wordcount/input/file01</span>
<br>
          
<span class="codefrag">/usr/joe/wordcount/input/file02</span>
<br>
          
<br>
          
<span class="codefrag">$ bin/hadoop dfs -cat /usr/joe/wordcount/input/file01</span>
<br>
          
<span class="codefrag">Hello World Bye World</span>
<br>
          
<br>
          
<span class="codefrag">$ bin/hadoop dfs -cat /usr/joe/wordcount/input/file02</span>
<br>
          
<span class="codefrag">Hello Hadoop Goodbye Hadoop</span>
        
</p>
<p>Run the application:</p>
<p>
          
<span class="codefrag">
            $ bin/hadoop jar /usr/joe/wordcount.jar org.myorg.WordCount 
              /usr/joe/wordcount/input /usr/joe/wordcount/output 
          </span>
        
</p>
<p>Output:</p>
<p>
          
<span class="codefrag">
            $ bin/hadoop dfs -cat /usr/joe/wordcount/output/part-00000
          </span>
          
<br>
          
<span class="codefrag">Bye    1</span>
<br>
          
<span class="codefrag">Goodbye    1</span>
<br>
          
<span class="codefrag">Hadoop    2</span>
<br>
          
<span class="codefrag">Hello    2</span>
<br>
          
<span class="codefrag">World    2</span>
<br>
        
</p>
<p> Applications can specify a comma separated list of paths which
        would be present in the current working directory of the task 
        using the option <span class="codefrag">-files</span>. The <span class="codefrag">-libjars</span>
        option allows applications to add jars to the classpaths of the maps
        and reduces. The <span class="codefrag">-archives</span> allows them to pass archives
        as arguments that are unzipped/unjarred and a link with name of the
        jar/zip are created in the current working directory of tasks. More
        details about the command line options are available at 
        <a href="commands_manual.html"> Hadoop Command Guide.</a>
</p>
<p>Running <span class="codefrag">wordcount</span> example with 
        <span class="codefrag">-libjars</span> and <span class="codefrag">-files</span>:<br>
        
<span class="codefrag"> hadoop jar hadoop-examples.jar wordcount -files cachefile.txt 
        -libjars mylib.jar input output </span> 
        
</p>
<a name="N10504"></a><a name="Walk-through"></a>
<h3 class="h4">Walk-through</h3>
<p>The <span class="codefrag">WordCount</span> application is quite straight-forward.</p>
<p>The <span class="codefrag">Mapper</span> implementation (lines 14-26), via the 
        <span class="codefrag">map</span> method (lines 18-25), processes one line at a time,
        as provided by the specified <span class="codefrag">TextInputFormat</span> (line 49). 
        It then splits the line into tokens separated by whitespaces, via the 
        <span class="codefrag">StringTokenizer</span>, and emits a key-value pair of 
        <span class="codefrag">&lt; &lt;word&gt;, 1&gt;</span>.</p>
<p>
          For the given sample input the first map emits:<br>
          
<span class="codefrag">&lt; Hello, 1&gt;</span>
<br>
          
<span class="codefrag">&lt; World, 1&gt;</span>
<br>
          
<span class="codefrag">&lt; Bye, 1&gt;</span>
<br>
          
<span class="codefrag">&lt; World, 1&gt;</span>
<br>
        
</p>
<p>
          The second map emits:<br>
          
<span class="codefrag">&lt; Hello, 1&gt;</span>
<br>
          
<span class="codefrag">&lt; Hadoop, 1&gt;</span>
<br>
          
<span class="codefrag">&lt; Goodbye, 1&gt;</span>
<br>
          
<span class="codefrag">&lt; Hadoop, 1&gt;</span>
<br>
        
</p>
<p>We'll learn more about the number of maps spawned for a given job, and
        how to control them in a fine-grained manner, a bit later in the 
        tutorial.</p>
<p>
<span class="codefrag">WordCount</span> also specifies a <span class="codefrag">combiner</span> (line 
        46). Hence, the output of each map is passed through the local combiner 
        (which is same as the <span class="codefrag">Reducer</span> as per the job 
        configuration) for local aggregation, after being sorted on the 
        <em>key</em>s.</p>
<p>
          The output of the first map:<br>
          
<span class="codefrag">&lt; Bye, 1&gt;</span>
<br>
          
<span class="codefrag">&lt; Hello, 1&gt;</span>
<br>
          
<span class="codefrag">&lt; World, 2&gt;</span>
<br>
        
</p>
<p>
          The output of the second map:<br>
          
<span class="codefrag">&lt; Goodbye, 1&gt;</span>
<br>
          
<span class="codefrag">&lt; Hadoop, 2&gt;</span>
<br>
          
<span class="codefrag">&lt; Hello, 1&gt;</span>
<br>
        
</p>
<p>The <span class="codefrag">Reducer</span> implementation (lines 28-36), via the
        <span class="codefrag">reduce</span> method (lines 29-35) just sums up the values,
        which are the occurence counts for each key (i.e. words in this example).
        </p>
<p>
          Thus the output of the job is:<br>
          
<span class="codefrag">&lt; Bye, 1&gt;</span>
<br>
          
<span class="codefrag">&lt; Goodbye, 1&gt;</span>
<br>
          
<span class="codefrag">&lt; Hadoop, 2&gt;</span>
<br>
          
<span class="codefrag">&lt; Hello, 2&gt;</span>
<br>
          
<span class="codefrag">&lt; World, 2&gt;</span>
<br>
        
</p>
<p>The <span class="codefrag">run</span> method specifies various facets of the job, such 
        as the input/output paths (passed via the command line), key/value 
        types, input/output formats etc., in the <span class="codefrag">JobConf</span>.
        It then calls the <span class="codefrag">JobClient.runJob</span> (line  55) to submit the
        and monitor its progress.</p>
<p>We'll learn more about <span class="codefrag">JobConf</span>, <span class="codefrag">JobClient</span>,
        <span class="codefrag">Tool</span> and other interfaces and classes a bit later in the 
        tutorial.</p>
</div>
    
    
<a name="N105BB"></a><a name="Map%2FReduce+-+User+Interfaces"></a>
<h2 class="h3">Map/Reduce - User Interfaces</h2>
<div class="section">
<p>This section provides a reasonable amount of detail on every user-facing 
      aspect of the Map/Reduce framwork. This should help users implement, 
      configure and tune their jobs in a fine-grained manner. However, please 
      note that the javadoc for each class/interface remains the most 
      comprehensive documentation available; this is only meant to be a tutorial.
      </p>
<p>Let us first take the <span class="codefrag">Mapper</span> and <span class="codefrag">Reducer</span> 
      interfaces. Applications typically implement them to provide the 
      <span class="codefrag">map</span> and <span class="codefrag">reduce</span> methods.</p>
<p>We will then discuss other core interfaces including 
      <span class="codefrag">JobConf</span>, <span class="codefrag">JobClient</span>, <span class="codefrag">Partitioner</span>, 
      <span class="codefrag">OutputCollector</span>, <span class="codefrag">Reporter</span>, 
      <span class="codefrag">InputFormat</span>, <span class="codefrag">OutputFormat</span>,
      <span class="codefrag">OutputCommitter</span> and others.</p>
<p>Finally, we will wrap up by discussing some useful features of the
      framework such as the <span class="codefrag">DistributedCache</span>, 
      <span class="codefrag">IsolationRunner</span> etc.</p>
<a name="N105F7"></a><a name="Payload"></a>
<h3 class="h4">Payload</h3>
<p>Applications typically implement the <span class="codefrag">Mapper</span> and 
        <span class="codefrag">Reducer</span> interfaces to provide the <span class="codefrag">map</span> and 
        <span class="codefrag">reduce</span> methods. These form the core of the job.</p>
<a name="N1060C"></a><a name="Mapper"></a>
<h4>Mapper</h4>
<p>
<a href="api/org/apache/hadoop/mapred/Mapper.html">
          Mapper</a> maps input key/value pairs to a set of intermediate 
          key/value pairs.</p>
<p>Maps are the individual tasks that transform input records into 
          intermediate records. The transformed intermediate records do not need
          to be of the same type as the input records. A given input pair may 
          map to zero or many output pairs.</p>
<p>The Hadoop Map/Reduce framework spawns one map task for each 
          <span class="codefrag">InputSplit</span> generated by the <span class="codefrag">InputFormat</span> for 
          the job.</p>
<p>Overall, <span class="codefrag">Mapper</span> implementations are passed the 
          <span class="codefrag">JobConf</span> for the job via the 
          <a href="api/org/apache/hadoop/mapred/JobConfigurable.html#configure(org.apache.hadoop.mapred.JobConf)">
          JobConfigurable.configure(JobConf)</a> method and override it to 
          initialize themselves. The framework then calls 
          <a href="api/org/apache/hadoop/mapred/Mapper.html#map(K1, V1, org.apache.hadoop.mapred.OutputCollector, org.apache.hadoop.mapred.Reporter)">
          map(WritableComparable, Writable, OutputCollector, Reporter)</a> for 
          each key/value pair in the <span class="codefrag">InputSplit</span> for that task.        
          Applications can then override the
          <a href="api/org/apache/hadoop/io/Closeable.html#close()">
          Closeable.close()</a> method to perform any required cleanup.</p>
<p>Output pairs do not need to be of the same types as input pairs. A 
          given input pair may map to zero or many output pairs.  Output pairs 
          are collected with calls to 
          <a href="api/org/apache/hadoop/mapred/OutputCollector.html#collect(K, V)">
          OutputCollector.collect(WritableComparable,Writable)</a>.</p>
<p>Applications can use the <span class="codefrag">Reporter</span> to report 
          progress, set application-level status messages and update 
          <span class="codefrag">Counters</span>, or just indicate that they are alive.</p>
<p>All intermediate values associated with a given output key are 
          subsequently grouped by the framework, and passed to the
          <span class="codefrag">Reducer</span>(s) to  determine the final output. Users can 
          control the grouping by specifying a <span class="codefrag">Comparator</span> via 
          <a href="api/org/apache/hadoop/mapred/JobConf.html#setOutputKeyComparatorClass(java.lang.Class)">
          JobConf.setOutputKeyComparatorClass(Class)</a>.</p>
<p>The <span class="codefrag">Mapper</span> outputs are sorted and then 
          partitioned per <span class="codefrag">Reducer</span>. The total number of partitions is 
          the same as the number of reduce tasks for the job. Users can control 
          which keys (and hence records) go to which <span class="codefrag">Reducer</span> by 
          implementing a custom <span class="codefrag">Partitioner</span>.</p>
<p>Users can optionally specify a <span class="codefrag">combiner</span>, via 
          <a href="api/org/apache/hadoop/mapred/JobConf.html#setCombinerClass(java.lang.Class)">
          JobConf.setCombinerClass(Class)</a>, to perform local aggregation of 
          the intermediate outputs, which helps to cut down the amount of data 
          transferred from the <span class="codefrag">Mapper</span> to the <span class="codefrag">Reducer</span>.
          </p>
<p>The intermediate, sorted outputs are always stored in a simple 
          (key-len, key, value-len, value) format. 
          Applications can control if, and how, the 
          intermediate outputs are to be compressed and the 
          <a href="api/org/apache/hadoop/io/compress/CompressionCodec.html">
          CompressionCodec</a> to be used via the <span class="codefrag">JobConf</span>.
          </p>
<a name="N10682"></a><a name="How+Many+Maps%3F"></a>
<h5>How Many Maps?</h5>
<p>The number of maps is usually driven by the total size of the 
            inputs, that is, the total number of blocks of the input files.</p>
<p>The right level of parallelism for maps seems to be around 10-100 
            maps per-node, although it has been set up to 300 maps for very 
            cpu-light map tasks. Task setup takes awhile, so it is best if the 
            maps take at least a minute to execute.</p>
<p>Thus, if you expect 10TB of input data and have a blocksize of 
            <span class="codefrag">128MB</span>, you'll end up with 82,000 maps, unless 
            <a href="api/org/apache/hadoop/mapred/JobConf.html#setNumMapTasks(int)">
            setNumMapTasks(int)</a> (which only provides a hint to the framework) 
            is used to set it even higher.</p>
<a name="N1069A"></a><a name="Reducer"></a>
<h4>Reducer</h4>
<p>
<a href="api/org/apache/hadoop/mapred/Reducer.html">
          Reducer</a> reduces a set of intermediate values which share a key to
          a smaller set of values.</p>
<p>The number of reduces for the job is set by the user 
          via <a href="api/org/apache/hadoop/mapred/JobConf.html#setNumReduceTasks(int)">
          JobConf.setNumReduceTasks(int)</a>.</p>
<p>Overall, <span class="codefrag">Reducer</span> implementations are passed the 
          <span class="codefrag">JobConf</span> for the job via the 
          <a href="api/org/apache/hadoop/mapred/JobConfigurable.html#configure(org.apache.hadoop.mapred.JobConf)">
          JobConfigurable.configure(JobConf)</a> method and can override it to 
          initialize themselves. The framework then calls   
          <a href="api/org/apache/hadoop/mapred/Reducer.html#reduce(K2, java.util.Iterator, org.apache.hadoop.mapred.OutputCollector, org.apache.hadoop.mapred.Reporter)">
          reduce(WritableComparable, Iterator, OutputCollector, Reporter)</a>
          method for each <span class="codefrag">&lt;key, (list of values)&gt;</span> 
          pair in the grouped inputs. Applications can then override the           
          <a href="api/org/apache/hadoop/io/Closeable.html#close()">
          Closeable.close()</a> method to perform any required cleanup.</p>
<p>
<span class="codefrag">Reducer</span> has 3 primary phases: shuffle, sort and reduce.
          </p>
<a name="N106CA"></a><a name="Shuffle"></a>
<h5>Shuffle</h5>
<p>Input to the <span class="codefrag">Reducer</span> is the sorted output of the
            mappers. In this phase the framework fetches the relevant partition 
            of the output of all the mappers, via HTTP.</p>
<a name="N106D7"></a><a name="Sort"></a>
<h5>Sort</h5>
<p>The framework groups <span class="codefrag">Reducer</span> inputs by keys (since 
            different mappers may have output the same key) in this stage.</p>
<p>The shuffle and sort phases occur simultaneously; while 
            map-outputs are being fetched they are merged.</p>
<a name="N106E6"></a><a name="Secondary+Sort"></a>
<h5>Secondary Sort</h5>
<p>If equivalence rules for grouping the intermediate keys are 
              required to be different from those for grouping keys before 
              reduction, then one may specify a <span class="codefrag">Comparator</span> via 
              <a href="api/org/apache/hadoop/mapred/JobConf.html#setOutputValueGroupingComparator(java.lang.Class)">
              JobConf.setOutputValueGroupingComparator(Class)</a>. Since 
              <a href="api/org/apache/hadoop/mapred/JobConf.html#setOutputKeyComparatorClass(java.lang.Class)">
              JobConf.setOutputKeyComparatorClass(Class)</a> can be used to 
              control how intermediate keys are grouped, these can be used in 
              conjunction to simulate <em>secondary sort on values</em>.</p>
<a name="N106FF"></a><a name="Reduce"></a>
<h5>Reduce</h5>
<p>In this phase the 
            <a href="api/org/apache/hadoop/mapred/Reducer.html#reduce(K2, java.util.Iterator, org.apache.hadoop.mapred.OutputCollector, org.apache.hadoop.mapred.Reporter)">
            reduce(WritableComparable, Iterator, OutputCollector, Reporter)</a>
            method is called for each <span class="codefrag">&lt;key, (list of values)&gt;</span> 
            pair in the grouped inputs.</p>
<p>The output of the reduce task is typically written to the 
            <a href="api/org/apache/hadoop/fs/FileSystem.html">
            FileSystem</a> via 
            <a href="api/org/apache/hadoop/mapred/OutputCollector.html#collect(K, V)">
            OutputCollector.collect(WritableComparable, Writable)</a>.</p>
<p>Applications can use the <span class="codefrag">Reporter</span> to report 
            progress, set application-level status messages and update 
            <span class="codefrag">Counters</span>, or just indicate that they are alive.</p>
<p>The output of the <span class="codefrag">Reducer</span> is <em>not sorted</em>.</p>
<a name="N1072D"></a><a name="How+Many+Reduces%3F"></a>
<h5>How Many Reduces?</h5>
<p>The right number of reduces seems to be <span class="codefrag">0.95</span> or 
            <span class="codefrag">1.75</span> multiplied by (&lt;<em>no. of nodes</em>&gt; * 
            <span class="codefrag">mapred.tasktracker.reduce.tasks.maximum</span>).</p>
<p>With <span class="codefrag">0.95</span> all of the reduces can launch immediately 
            and start transfering map outputs as the maps finish. With 
            <span class="codefrag">1.75</span> the faster nodes will finish their first round of 
            reduces and launch a second wave of reduces doing a much better job 
            of load balancing.</p>
<p>Increasing the number of reduces increases the framework overhead, 
            but increases load balancing and lowers the cost of failures.</p>
<p>The scaling factors above are slightly less than whole numbers to 
            reserve a few reduce slots in the framework for speculative-tasks and
            failed tasks.</p>
<a name="N10752"></a><a name="Reducer+NONE"></a>
<h5>Reducer NONE</h5>
<p>It is legal to set the number of reduce-tasks to <em>zero</em> if 
            no reduction is desired.</p>
<p>In this case the outputs of the map-tasks go directly to the
            <span class="codefrag">FileSystem</span>, into the output path set by 
            <a href="api/org/apache/hadoop/mapred/FileOutputFormat.html#setOutputPath(org.apache.hadoop.mapred.JobConf,%20org.apache.hadoop.fs.Path)">
            setOutputPath(Path)</a>. The framework does not sort the 
            map-outputs before writing them out to the <span class="codefrag">FileSystem</span>.
            </p>
<a name="N1076D"></a><a name="Partitioner"></a>
<h4>Partitioner</h4>
<p>
<a href="api/org/apache/hadoop/mapred/Partitioner.html">
          Partitioner</a> partitions the key space.</p>
<p>Partitioner controls the partitioning of the keys of the 
          intermediate map-outputs. The key (or a subset of the key) is used to 
          derive the partition, typically by a <em>hash function</em>. The total 
          number of partitions is the same as the number of reduce tasks for the 
          job. Hence this controls which of the <span class="codefrag">m</span> reduce tasks the 
          intermediate key (and hence the record) is sent to for reduction.</p>
<p>
<a href="api/org/apache/hadoop/mapred/lib/HashPartitioner.html">
          HashPartitioner</a> is the default <span class="codefrag">Partitioner</span>.</p>
<a name="N1078C"></a><a name="Reporter"></a>
<h4>Reporter</h4>
<p>
<a href="api/org/apache/hadoop/mapred/Reporter.html">
          Reporter</a> is a facility for Map/Reduce applications to report 
          progress, set application-level status messages and update 
          <span class="codefrag">Counters</span>.</p>
<p>
<span class="codefrag">Mapper</span> and <span class="codefrag">Reducer</span> implementations can use 
          the <span class="codefrag">Reporter</span> to report progress or just indicate 
          that they are alive. In scenarios where the application takes a
          significant amount of time to process individual key/value pairs, 
          this is crucial since the framework might assume that the task has 
          timed-out and kill that task. Another way to avoid this is to 
          set the configuration parameter <span class="codefrag">mapred.task.timeout</span> to a
          high-enough value (or even set it to <em>zero</em> for no time-outs).
          </p>
<p>Applications can also update <span class="codefrag">Counters</span> using the 
          <span class="codefrag">Reporter</span>.</p>
<a name="N107B6"></a><a name="OutputCollector"></a>
<h4>OutputCollector</h4>
<p>
<a href="api/org/apache/hadoop/mapred/OutputCollector.html">
          OutputCollector</a> is a generalization of the facility provided by
          the Map/Reduce framework to collect data output by the 
          <span class="codefrag">Mapper</span> or the <span class="codefrag">Reducer</span> (either the 
          intermediate outputs or the output of the job).</p>
<p>Hadoop Map/Reduce comes bundled with a 
        <a href="api/org/apache/hadoop/mapred/lib/package-summary.html">
        library</a> of generally useful mappers, reducers, and partitioners.</p>
<a name="N107D1"></a><a name="Job+Configuration"></a>
<h3 class="h4">Job Configuration</h3>
<p>
<a href="api/org/apache/hadoop/mapred/JobConf.html">
        JobConf</a> represents a Map/Reduce job configuration.</p>
<p>
<span class="codefrag">JobConf</span> is the primary interface for a user to describe
        a Map/Reduce job to the Hadoop framework for execution. The framework 
        tries to faithfully execute the job as described by <span class="codefrag">JobConf</span>, 
        however:</p>
<ul>
          
<li>f
            Some configuration parameters may have been marked as 
            <a href="api/org/apache/hadoop/conf/Configuration.html#FinalParams">
            final</a> by administrators and hence cannot be altered.
          </li>
          
<li>
            While some job parameters are straight-forward to set (e.g. 
            <a href="api/org/apache/hadoop/mapred/JobConf.html#setNumReduceTasks(int)">
            setNumReduceTasks(int)</a>), other parameters interact subtly with 
            the rest of the framework and/or job configuration and are 
            more complex to set (e.g. 
            <a href="api/org/apache/hadoop/mapred/JobConf.html#setNumMapTasks(int)">
            setNumMapTasks(int)</a>).
          </li>
        
</ul>
<p>
<span class="codefrag">JobConf</span> is typically used to specify the 
        <span class="codefrag">Mapper</span>, combiner (if any), <span class="codefrag">Partitioner</span>, 
        <span class="codefrag">Reducer</span>, <span class="codefrag">InputFormat</span>, 
        <span class="codefrag">OutputFormat</span> and <span class="codefrag">OutputCommitter</span> 
        implementations. <span class="codefrag">JobConf</span> also 
        indicates the set of input files 
        (<a href="api/org/apache/hadoop/mapred/FileInputFormat.html#setInputPaths(org.apache.hadoop.mapred.JobConf,%20org.apache.hadoop.fs.Path[])">setInputPaths(JobConf, Path...)</a>
        /<a href="api/org/apache/hadoop/mapred/FileInputFormat.html#addInputPath(org.apache.hadoop.mapred.JobConf,%20org.apache.hadoop.fs.Path)">addInputPath(JobConf, Path)</a>)
        and (<a href="api/org/apache/hadoop/mapred/FileInputFormat.html#setInputPaths(org.apache.hadoop.mapred.JobConf,%20java.lang.String)">setInputPaths(JobConf, String)</a>
        /<a href="api/org/apache/hadoop/mapred/FileInputFormat.html#addInputPath(org.apache.hadoop.mapred.JobConf,%20java.lang.String)">addInputPaths(JobConf, String)</a>)
        and where the output files should be written
        (<a href="api/org/apache/hadoop/mapred/FileOutputFormat.html#setOutputPath(org.apache.hadoop.mapred.JobConf,%20org.apache.hadoop.fs.Path)">setOutputPath(Path)</a>).</p>
<p>Optionally, <span class="codefrag">JobConf</span> is used to specify other advanced 
        facets of the job such as the <span class="codefrag">Comparator</span> to be used, files 
        to be put in the <span class="codefrag">DistributedCache</span>, whether intermediate 
        and/or job outputs are to be compressed (and how), debugging via 
        user-provided scripts
        (<a href="api/org/apache/hadoop/mapred/JobConf.html#setMapDebugScript(java.lang.String)">setMapDebugScript(String)</a>/<a href="api/org/apache/hadoop/mapred/JobConf.html#setReduceDebugScript(java.lang.String)">setReduceDebugScript(String)</a>) 
        , whether job tasks can be executed in a <em>speculative</em> manner 
        (<a href="api/org/apache/hadoop/mapred/JobConf.html#setMapSpeculativeExecution(boolean)">setMapSpeculativeExecution(boolean)</a>)/(<a href="api/org/apache/hadoop/mapred/JobConf.html#setReduceSpeculativeExecution(boolean)">setReduceSpeculativeExecution(boolean)</a>)
        , maximum number of attempts per task
        (<a href="api/org/apache/hadoop/mapred/JobConf.html#setMaxMapAttempts(int)">setMaxMapAttempts(int)</a>/<a href="api/org/apache/hadoop/mapred/JobConf.html#setMaxReduceAttempts(int)">setMaxReduceAttempts(int)</a>) 
        , percentage of tasks failure which can be tolerated by the job
        (<a href="api/org/apache/hadoop/mapred/JobConf.html#setMaxMapTaskFailuresPercent(int)">setMaxMapTaskFailuresPercent(int)</a>/<a href="api/org/apache/hadoop/mapred/JobConf.html#setMaxReduceTaskFailuresPercent(int)">setMaxReduceTaskFailuresPercent(int)</a>) 
        etc.</p>
<p>Of course, users can use 
        <a href="api/org/apache/hadoop/conf/Configuration.html#set(java.lang.String, java.lang.String)">set(String, String)</a>/<a href="api/org/apache/hadoop/conf/Configuration.html#get(java.lang.String, java.lang.String)">get(String, String)</a>
        to set/get arbitrary parameters needed by applications. However, use the 
        <span class="codefrag">DistributedCache</span> for large amounts of (read-only) data.</p>
<a name="N10866"></a><a name="Task+Execution+%26+Environment"></a>
<h3 class="h4">Task Execution &amp; Environment</h3>
<p>The <span class="codefrag">TaskTracker</span> executes the <span class="codefrag">Mapper</span>/ 
        <span class="codefrag">Reducer</span>  <em>task</em> as a child process in a separate jvm.
        </p>
<p>The child-task inherits the environment of the parent 
        <span class="codefrag">TaskTracker</span>. The user can specify additional options to the
        child-jvm via the <span class="codefrag">mapred.child.java.opts</span> configuration
        parameter in the <span class="codefrag">JobConf</span> such as non-standard paths for the 
        run-time linker to search shared libraries via 
        <span class="codefrag">-Djava.library.path=&lt;&gt;</span> etc. If the 
        <span class="codefrag">mapred.child.java.opts</span> contains the symbol <em>@taskid@</em> 
        it is interpolated with value of <span class="codefrag">taskid</span> of the map/reduce
        task.</p>
<p>Here is an example with multiple arguments and substitutions, 
        showing jvm GC logging, and start of a passwordless JVM JMX agent so that
        it can connect with jconsole and the likes to watch child memory, 
        threads and get thread dumps. It also sets the maximum heap-size of the 
        child jvm to 512MB and adds an additional path to the 
        <span class="codefrag">java.library.path</span> of the child-jvm.</p>
<p>
          
<span class="codefrag">&lt;property&gt;</span>
<br>
          &nbsp;&nbsp;<span class="codefrag">&lt;name&gt;mapred.child.java.opts&lt;/name&gt;</span>
<br>
          &nbsp;&nbsp;<span class="codefrag">&lt;value&gt;</span>
<br>
          &nbsp;&nbsp;&nbsp;&nbsp;<span class="codefrag">
                    -Xmx512M -Djava.library.path=/home/mycompany/lib
                    -verbose:gc -Xloggc:/tmp/@taskid@.gc</span>
<br>
          &nbsp;&nbsp;&nbsp;&nbsp;<span class="codefrag">
                    -Dcom.sun.management.jmxremote.authenticate=false 
                    -Dcom.sun.management.jmxremote.ssl=false</span>
<br>
          &nbsp;&nbsp;<span class="codefrag">&lt;/value&gt;</span>
<br>
          
<span class="codefrag">&lt;/property&gt;</span>
        
</p>
<a name="N108B7"></a><a name="Memory+management"></a>
<h4> Memory management</h4>
<p>Users/admins can also specify the maximum virtual memory 
        of the launched child-task, and any sub-process it launches 
        recursively, using <span class="codefrag">mapred.child.ulimit</span>. Note that
        the value set here is a per process limit.
        The value for <span class="codefrag">mapred.child.ulimit</span> should be specified 
        in kilo bytes (KB). And also the value must be greater than
        or equal to the -Xmx passed to JavaVM, else the VM might not start. 
        </p>
<p>Note: <span class="codefrag">mapred.child.java.opts</span> are used only for 
        configuring the launched child tasks from task tracker. Configuring 
        the memory options for daemons is documented in 
        <a href="cluster_setup.html#Configuring+the+Environment+of+the+Hadoop+Daemons">
        cluster_setup.html </a>
</p>
<p>The memory available to some parts of the framework is also
        configurable. In map and reduce tasks, performance may be influenced
        by adjusting parameters influencing the concurrency of operations and
        the frequency with which data will hit disk. Monitoring the filesystem
        counters for a job- particularly relative to byte counts from the map
        and into the reduce- is invaluable to the tuning of these
        parameters.</p>
<a name="N108D3"></a><a name="Map+Parameters"></a>
<h4>Map Parameters</h4>
<p>A record emitted from a map will be serialized into a buffer and
          metadata will be stored into accounting buffers. As described in the
          following options, when either the serialization buffer or the
          metadata exceed a threshold, the contents of the buffers will be
          sorted and written to disk in the background while the map continues
          to output records. If either buffer fills completely while the spill
          is in progress, the map thread will block. When the map is finished,
          any remaining records are written to disk and all on-disk segments
          are merged into a single file. Minimizing the number of spills to
          disk can decrease map time, but a larger buffer also decreases the
          memory available to the mapper.</p>
<table class="ForrestTable" cellspacing="1" cellpadding="4">
            
<tr>
<th colspan="1" rowspan="1">Name</th><th colspan="1" rowspan="1">Type</th><th colspan="1" rowspan="1">Description</th>
</tr>
            
<tr>
<td colspan="1" rowspan="1">io.sort.mb</td><td colspan="1" rowspan="1">int</td>
                <td colspan="1" rowspan="1">The cumulative size of the serialization and accounting
                buffers storing records emitted from the map, in megabytes.
                </td>
</tr>
            
<tr>
<td colspan="1" rowspan="1">io.sort.record.percent</td><td colspan="1" rowspan="1">float</td>
                <td colspan="1" rowspan="1">The ratio of serialization to accounting space can be
                adjusted. Each serialized record requires 16 bytes of
                accounting information in addition to its serialized size to
                effect the sort. This percentage of space allocated from
                <span class="codefrag">io.sort.mb</span> affects the probability of a spill to
                disk being caused by either exhaustion of the serialization
                buffer or the accounting space. Clearly, for a map outputting
                small records, a higher value than the default will likely
                decrease the number of spills to disk.</td>
</tr>
            
<tr>
<td colspan="1" rowspan="1">io.sort.spill.percent</td><td colspan="1" rowspan="1">float</td>
                <td colspan="1" rowspan="1">This is the threshold for the accounting and serialization
                buffers. When this percentage of either buffer has filled,
                their contents will be spilled to disk in the background. Let
                <span class="codefrag">io.sort.record.percent</span> be <em>r</em>,
                <span class="codefrag">io.sort.mb</span> be <em>x</em>, and this value be
                <em>q</em>. The maximum number of records collected before the
                collection thread will spill is <span class="codefrag">r * x * q * 2^16</span>.
                Note that a higher value may decrease the number of- or even
                eliminate- merges, but will also increase the probability of
                the map task getting blocked. The lowest average map times are
                usually obtained by accurately estimating the size of the map
                output and preventing multiple spills.</td>
</tr>
          
</table>
<p>Other notes</p>
<ul>
            
<li>If either spill threshold is exceeded while a spill is in
            progress, collection will continue until the spill is finished.
            For example, if <span class="codefrag">io.sort.buffer.spill.percent</span> is set
            to 0.33, and the remainder of the buffer is filled while the spill
            runs, the next spill will include all the collected records, or
            0.66 of the buffer, and will not generate additional spills. In
            other words, the thresholds are defining triggers, not
            blocking.</li>
            
<li>A record larger than the serialization buffer will first
            trigger a spill, then be spilled to a separate file. It is
            undefined whether or not this record will first pass through the
            combiner.</li>
          
</ul>
<a name="N1093F"></a><a name="Shuffle%2FReduce+Parameters"></a>
<h4>Shuffle/Reduce Parameters</h4>
<p>As described previously, each reduce fetches the output assigned
          to it by the Partitioner via HTTP into memory and periodically
          merges these outputs to disk. If intermediate compression of map
          outputs is turned on, each output is decompressed into memory. The
          following options affect the frequency of these merges to disk prior
          to the reduce and the memory allocated to map output during the
          reduce.</p>
<table class="ForrestTable" cellspacing="1" cellpadding="4">
            
<tr>
<th colspan="1" rowspan="1">Name</th><th colspan="1" rowspan="1">Type</th><th colspan="1" rowspan="1">Description</th>
</tr>
            
<tr>
<td colspan="1" rowspan="1">io.sort.factor</td><td colspan="1" rowspan="1">int</td>
                <td colspan="1" rowspan="1">Specifies the number of segments on disk to be merged at
                the same time. It limits the number of open files and
                compression codecs during the merge. If the number of files
                exceeds this limit, the merge will proceed in several passes.
                Though this limit also applies to the map, most jobs should be
                configured so that hitting this limit is unlikely
                there.</td>
</tr>
            
<tr>
<td colspan="1" rowspan="1">mapred.inmem.merge.threshold</td><td colspan="1" rowspan="1">int</td>
                <td colspan="1" rowspan="1">The number of sorted map outputs fetched into memory
                before being merged to disk. Like the spill thresholds in the
                preceding note, this is not defining a unit of partition, but
                a trigger. In practice, this is usually set very high (1000)
                or disabled (0), since merging in-memory segments is often
                less expensive than merging from disk (see notes following
                this table). This threshold influences only the frequency of
                in-memory merges during the shuffle.</td>
</tr>
            
<tr>
<td colspan="1" rowspan="1">mapred.job.shuffle.merge.percent</td><td colspan="1" rowspan="1">float</td>
                <td colspan="1" rowspan="1">The memory threshold for fetched map outputs before an
                in-memory merge is started, expressed as a percentage of
                memory allocated to storing map outputs in memory. Since map
                outputs that can't fit in memory can be stalled, setting this
                high may decrease parallelism between the fetch and merge.
                Conversely, values as high as 1.0 have been effective for
                reduces whose input can fit entirely in memory. This parameter
                influences only the frequency of in-memory merges during the
                shuffle.</td>
</tr>
            
<tr>
<td colspan="1" rowspan="1">mapred.job.shuffle.input.buffer.percent</td><td colspan="1" rowspan="1">float</td>
                <td colspan="1" rowspan="1">The percentage of memory- relative to the maximum heapsize
                as typically specified in <span class="codefrag">mapred.child.java.opts</span>-
                that can be allocated to storing map outputs during the
                shuffle. Though some memory should be set aside for the
                framework, in general it is advantageous to set this high
                enough to store large and numerous map outputs.</td>
</tr>
            
<tr>
<td colspan="1" rowspan="1">mapred.job.reduce.input.buffer.percent</td><td colspan="1" rowspan="1">float</td>
                <td colspan="1" rowspan="1">The percentage of memory relative to the maximum heapsize
                in which map outputs may be retained during the reduce. When
                the reduce begins, map outputs will be merged to disk until
                those that remain are under the resource limit this defines.
                By default, all map outputs are merged to disk before the
                reduce begins to maximize the memory available to the reduce.
                For less memory-intensive reduces, this should be increased to
                avoid trips to disk.</td>
</tr>
          
</table>
<p>Other notes</p>
<ul>
            
<li>If a map output is larger than 25 percent of the memory
            allocated to copying map outputs, it will be written directly to
            disk without first staging through memory.</li>
            
<li>When running with a combiner, the reasoning about high merge
            thresholds and large buffers may not hold. For merges started
            before all map outputs have been fetched, the combiner is run
            while spilling to disk. In some cases, one can obtain better
            reduce times by spending resources combining map outputs- making
            disk spills small and parallelizing spilling and fetching- rather
            than aggressively increasing buffer sizes.</li>
            
<li>When merging in-memory map outputs to disk to begin the
            reduce, if an intermediate merge is necessary because there are
            segments to spill and at least <span class="codefrag">io.sort.factor</span>
            segments already on disk, the in-memory map outputs will be part
            of the intermediate merge.</li>
          
</ul>
<a name="N109BA"></a><a name="Directory+Structure"></a>
<h4> Directory Structure </h4>
<p>The task tracker has local directory,
        <span class="codefrag"> ${mapred.local.dir}/taskTracker/</span> to create localized
        cache and localized job. It can define multiple local directories 
        (spanning multiple disks) and then each filename is assigned to a
        semi-random local directory. When the job starts, task tracker 
        creates a localized job directory relative to the local directory
        specified in the configuration. Thus the task tracker directory 
        structure looks the following: </p>
<ul>
        
<li>
<span class="codefrag">${mapred.local.dir}/taskTracker/archive/</span> :
        The distributed cache. This directory holds the localized distributed
        cache. Thus localized distributed cache is shared among all
        the tasks and jobs </li>
        
<li>
<span class="codefrag">${mapred.local.dir}/taskTracker/jobcache/$jobid/</span> :
        The localized job directory 
        <ul>
        
<li>
<span class="codefrag">${mapred.local.dir}/taskTracker/jobcache/$jobid/work/</span> 
        : The job-specific shared directory. The tasks can use this space as 
        scratch space and share files among them. This directory is exposed
        to the users through the configuration property  
        <span class="codefrag">job.local.dir</span>. The directory can accessed through 
        api <a href="api/org/apache/hadoop/mapred/JobConf.html#getJobLocalDir()">
        JobConf.getJobLocalDir()</a>. It is available as System property also.
        So, users (streaming etc.) can call 
        <span class="codefrag">System.getProperty("job.local.dir")</span> to access the 
        directory.</li>
        
<li>
<span class="codefrag">${mapred.local.dir}/taskTracker/jobcache/$jobid/jars/</span>
        : The jars directory, which has the job jar file and expanded jar.
        The <span class="codefrag">job.jar</span> is the application's jar file that is
        automatically distributed to each machine. It is expanded in jars
        directory before the tasks for the job start. The job.jar location
        is accessible to the application through the api
        <a href="api/org/apache/hadoop/mapred/JobConf.html#getJar()"> 
        JobConf.getJar() </a>. To access the unjarred directory,
        JobConf.getJar().getParent() can be called.</li>
        
<li>
<span class="codefrag">${mapred.local.dir}/taskTracker/jobcache/$jobid/job.xml</span>
        : The job.xml file, the generic job configuration, localized for 
        the job. </li>
        
<li>
<span class="codefrag">${mapred.local.dir}/taskTracker/jobcache/$jobid/$taskid</span>
        : The task directory for each task attempt. Each task directory
        again has the following structure :
        <ul>
        
<li>
<span class="codefrag">${mapred.local.dir}/taskTracker/jobcache/$jobid/$taskid/job.xml</span>
        : A job.xml file, task localized job configuration, Task localization
        means that properties have been set that are specific to
        this particular task within the job. The properties localized for 
        each task are described below.</li>
        
<li>
<span class="codefrag">${mapred.local.dir}/taskTracker/jobcache/$jobid/$taskid/output</span>
        : A directory for intermediate output files. This contains the
        temporary map reduce data generated by the framework
        such as map output files etc. </li>
        
<li>
<span class="codefrag">${mapred.local.dir}/taskTracker/jobcache/$jobid/$taskid/work</span>
        : The curernt working directory of the task. 
        With <a href="#Task+JVM+Reuse">jvm reuse</a> enabled for tasks, this 
        directory will be the directory on which the jvm has started</li>
        
<li>
<span class="codefrag">${mapred.local.dir}/taskTracker/jobcache/$jobid/$taskid/work/tmp</span>
        : The temporary directory for the task. 
        (User can specify the property <span class="codefrag">mapred.child.tmp</span> to set
        the value of temporary directory for map and reduce tasks. This 
        defaults to <span class="codefrag">./tmp</span>. If the value is not an absolute path,
        it is prepended with task's working directory. Otherwise, it is
        directly assigned. The directory will be created if it doesn't exist.
        Then, the child java tasks are executed with option
        <span class="codefrag">-Djava.io.tmpdir='the absolute path of the tmp dir'</span>.
        Anp pipes and streaming are set with environment variable,
        <span class="codefrag">TMPDIR='the absolute path of the tmp dir'</span>). This 
        directory is created, if <span class="codefrag">mapred.child.tmp</span> has the value
        <span class="codefrag">./tmp</span> 
</li>
        
</ul>
        
</li>
        
</ul>
        
</li>
        
</ul>
<a name="N10A29"></a><a name="Task+JVM+Reuse"></a>
<h4>Task JVM Reuse</h4>
<p>Jobs can enable task JVMs to be reused by specifying the job 
        configuration <span class="codefrag">mapred.job.reuse.jvm.num.tasks</span>. If the
        value is 1 (the default), then JVMs are not reused 
        (i.e. 1 task per JVM). If it is -1, there is no limit to the number
        of tasks a JVM can run (of the same job). One can also specify some
        value greater than 1 using the api 
        <a href="api/org/apache/hadoop/mapred/JobConf.html#setNumTasksToExecutePerJvm(int)">
        JobConf.setNumTasksToExecutePerJvm(int)</a>
</p>
<p>The following properties are localized in the job configuration 
         for each task's execution: </p>
<table class="ForrestTable" cellspacing="1" cellpadding="4">
          
<tr>
<th colspan="1" rowspan="1">Name</th><th colspan="1" rowspan="1">Type</th><th colspan="1" rowspan="1">Description</th>
</tr>
          
<tr>
<td colspan="1" rowspan="1">mapred.job.id</td><td colspan="1" rowspan="1">String</td><td colspan="1" rowspan="1">The job id</td>
</tr>
          
<tr>
<td colspan="1" rowspan="1">mapred.jar</td><td colspan="1" rowspan="1">String</td>
              <td colspan="1" rowspan="1">job.jar location in job directory</td>
</tr>
          
<tr>
<td colspan="1" rowspan="1">job.local.dir</td><td colspan="1" rowspan="1"> String</td>
              <td colspan="1" rowspan="1"> The job specific shared scratch space</td>
</tr>
          
<tr>
<td colspan="1" rowspan="1">mapred.tip.id</td><td colspan="1" rowspan="1"> String</td>
              <td colspan="1" rowspan="1"> The task id</td>
</tr>
          
<tr>
<td colspan="1" rowspan="1">mapred.task.id</td><td colspan="1" rowspan="1"> String</td>
              <td colspan="1" rowspan="1"> The task attempt id</td>
</tr>
          
<tr>
<td colspan="1" rowspan="1">mapred.task.is.map</td><td colspan="1" rowspan="1"> boolean </td>
              <td colspan="1" rowspan="1">Is this a map task</td>
</tr>
          
<tr>
<td colspan="1" rowspan="1">mapred.task.partition</td><td colspan="1" rowspan="1"> int </td>
              <td colspan="1" rowspan="1">The id of the task within the job</td>
</tr>
          
<tr>
<td colspan="1" rowspan="1">map.input.file</td><td colspan="1" rowspan="1"> String</td>
              <td colspan="1" rowspan="1"> The filename that the map is reading from</td>
</tr>
          
<tr>
<td colspan="1" rowspan="1">map.input.start</td><td colspan="1" rowspan="1"> long</td>
              <td colspan="1" rowspan="1"> The offset of the start of the map input split</td>
</tr>
          
<tr>
<td colspan="1" rowspan="1">map.input.length </td><td colspan="1" rowspan="1">long </td>
              <td colspan="1" rowspan="1">The number of bytes in the map input split</td>
</tr>
          
<tr>
<td colspan="1" rowspan="1">mapred.work.output.dir</td><td colspan="1" rowspan="1"> String </td>
              <td colspan="1" rowspan="1">The task's temporary output directory</td>
</tr>
        
</table>
<p>The standard output (stdout) and error (stderr) streams of the task 
        are read by the TaskTracker and logged to 
        <span class="codefrag">${HADOOP_LOG_DIR}/userlogs</span>
</p>
<p>The <a href="#DistributedCache">DistributedCache</a> can also be used
        to distribute both jars and native libraries for use in the map 
        and/or reduce tasks. The child-jvm always has its 
        <em>current working directory</em> added to the
        <span class="codefrag">java.library.path</span> and <span class="codefrag">LD_LIBRARY_PATH</span>. 
        And hence the cached libraries can be loaded via 
        <a href="http://java.sun.com/javase/6/docs/api/java/lang/System.html#loadLibrary(java.lang.String)">
        System.loadLibrary</a> or 
        <a href="http://java.sun.com/javase/6/docs/api/java/lang/System.html#load(java.lang.String)">
        System.load</a>. More details on how to load shared libraries through 
        distributed cache are documented at 
        <a href="native_libraries.html#Loading+native+libraries+through+DistributedCache">
        native_libraries.html</a>
</p>
<a name="N10B12"></a><a name="Job+Submission+and+Monitoring"></a>
<h3 class="h4">Job Submission and Monitoring</h3>
<p>
<a href="api/org/apache/hadoop/mapred/JobClient.html">
        JobClient</a> is the primary interface by which user-job interacts
        with the <span class="codefrag">JobTracker</span>.</p>
<p>
<span class="codefrag">JobClient</span> provides facilities to submit jobs, track their 
        progress, access component-tasks' reports and logs, get the Map/Reduce 
        cluster's status information and so on.</p>
<p>The job submission process involves:</p>
<ol>
          
<li>Checking the input and output specifications of the job.</li>
          
<li>Computing the <span class="codefrag">InputSplit</span> values for the job.</li>
          
<li>
            Setting up the requisite accounting information for the 
            <span class="codefrag">DistributedCache</span> of the job, if necessary.
          </li>
          
<li>
            Copying the job's jar and configuration to the Map/Reduce system 
            directory on the <span class="codefrag">FileSystem</span>.
          </li>
          
<li>
            Submitting the job to the <span class="codefrag">JobTracker</span> and optionally 
            monitoring it's status.
          </li>
        
</ol>
<p> Job history files are also logged to user specified directory
        <span class="codefrag">hadoop.job.history.user.location</span> 
        which defaults to job output directory. The files are stored in
        "_logs/history/" in the specified directory. Hence, by default they
        will be in mapred.output.dir/_logs/history. User can stop
        logging by giving the value <span class="codefrag">none</span> for 
        <span class="codefrag">hadoop.job.history.user.location</span>
</p>
<p> User can view the history logs summary in specified directory 
        using the following command <br>
        
<span class="codefrag">$ bin/hadoop job -history output-dir</span>
<br> 
        This command will print job details, failed and killed tip
        details. <br>
        More details about the job such as successful tasks and 
        task attempts made for each task can be viewed using the  
        following command <br>
       
<span class="codefrag">$ bin/hadoop job -history all output-dir</span>
<br>
</p>
<p> User can use 
        <a href="api/org/apache/hadoop/mapred/OutputLogFilter.html">OutputLogFilter</a>
        to filter log files from the output directory listing. </p>
<p>Normally the user creates the application, describes various facets 
        of the job via <span class="codefrag">JobConf</span>, and then uses the 
        <span class="codefrag">JobClient</span> to submit the job and monitor its progress.</p>
<a name="N10B72"></a><a name="Job+Control"></a>
<h4>Job Control</h4>
<p>Users may need to chain Map/Reduce jobs to accomplish complex
          tasks which cannot be done via a single Map/Reduce job. This is fairly
          easy since the output of the job typically goes to distributed 
          file-system, and the output, in turn, can be used as the input for the 
          next job.</p>
<p>However, this also means that the onus on ensuring jobs are 
          complete (success/failure) lies squarely on the clients. In such 
          cases, the various job-control options are:</p>
<ul>
            
<li>
              
<a href="api/org/apache/hadoop/mapred/JobClient.html#runJob(org.apache.hadoop.mapred.JobConf)">
              runJob(JobConf)</a> : Submits the job and returns only after the 
              job has completed.
            </li>
            
<li>
              
<a href="api/org/apache/hadoop/mapred/JobClient.html#submitJob(org.apache.hadoop.mapred.JobConf)">
              submitJob(JobConf)</a> : Only submits the job, then poll the 
              returned handle to the 
              <a href="api/org/apache/hadoop/mapred/RunningJob.html">
              RunningJob</a> to query status and make scheduling decisions.
            </li>
            
<li>
              
<a href="api/org/apache/hadoop/mapred/JobConf.html#setJobEndNotificationURI(java.lang.String)">
              JobConf.setJobEndNotificationURI(String)</a> : Sets up a 
              notification upon job-completion, thus avoiding polling.
            </li>
          
</ul>
<a name="N10B9C"></a><a name="Job+Input"></a>
<h3 class="h4">Job Input</h3>
<p>
<a href="api/org/apache/hadoop/mapred/InputFormat.html">
        InputFormat</a> describes the input-specification for a Map/Reduce job.
        </p>
<p>The Map/Reduce framework relies on the <span class="codefrag">InputFormat</span> of 
        the job to:</p>
<ol>
          
<li>Validate the input-specification of the job.</li>
          
<li>
            Split-up the input file(s) into logical <span class="codefrag">InputSplit</span> 
            instances, each of which is then assigned to an individual 
            <span class="codefrag">Mapper</span>.
          </li>
          
<li>
            Provide the <span class="codefrag">RecordReader</span> implementation used to
            glean input records from the logical <span class="codefrag">InputSplit</span> for 
            processing by the <span class="codefrag">Mapper</span>.
          </li>
        
</ol>
<p>The default behavior of file-based <span class="codefrag">InputFormat</span>
        implementations, typically sub-classes of 
        <a href="api/org/apache/hadoop/mapred/FileInputFormat.html">
        FileInputFormat</a>, is to split the input into <em>logical</em> 
        <span class="codefrag">InputSplit</span> instances based on the total size, in bytes, of 
        the input files. However, the <span class="codefrag">FileSystem</span> blocksize of the 
        input files is treated as an upper bound for input splits. A lower bound
        on the split size can be set via <span class="codefrag">mapred.min.split.size</span>.</p>
<p>Clearly, logical splits based on input-size is insufficient for many
        applications since record boundaries must be respected. In such cases, 
        the application should implement a <span class="codefrag">RecordReader</span>, who is 
        responsible for respecting record-boundaries and presents a 
        record-oriented view of the logical <span class="codefrag">InputSplit</span> to the 
        individual task.</p>
<p>
<a href="api/org/apache/hadoop/mapred/TextInputFormat.html">
        TextInputFormat</a> is the default <span class="codefrag">InputFormat</span>.</p>
<p>If <span class="codefrag">TextInputFormat</span> is the <span class="codefrag">InputFormat</span> for a 
        given job, the framework detects input-files with the <em>.gz</em> and 
        <em>.lzo</em> extensions and automatically decompresses them using the 
        appropriate <span class="codefrag">CompressionCodec</span>. However, it must be noted that
        compressed files with the above extensions cannot be <em>split</em> and 
        each compressed file is processed in its entirety by a single mapper.</p>
<a name="N10C06"></a><a name="InputSplit"></a>
<h4>InputSplit</h4>
<p>
<a href="api/org/apache/hadoop/mapred/InputSplit.html">
          InputSplit</a> represents the data to be processed by an individual 
          <span class="codefrag">Mapper</span>.</p>
<p>Typically <span class="codefrag">InputSplit</span> presents a byte-oriented view of
          the input, and it is the responsibility of <span class="codefrag">RecordReader</span>
          to process and present a record-oriented view.</p>
<p>
<a href="api/org/apache/hadoop/mapred/FileSplit.html">
          FileSplit</a> is the default <span class="codefrag">InputSplit</span>. It sets 
          <span class="codefrag">map.input.file</span> to the path of the input file for the
          logical split.</p>
<a name="N10C2B"></a><a name="RecordReader"></a>
<h4>RecordReader</h4>
<p>
<a href="api/org/apache/hadoop/mapred/RecordReader.html">
          RecordReader</a> reads <span class="codefrag">&lt;key, value&gt;</span> pairs from an 
          <span class="codefrag">InputSplit</span>.</p>
<p>Typically the <span class="codefrag">RecordReader</span> converts the byte-oriented 
          view of the input, provided by the <span class="codefrag">InputSplit</span>, and 
          presents a record-oriented to the <span class="codefrag">Mapper</span> implementations 
          for processing. <span class="codefrag">RecordReader</span> thus assumes the 
          responsibility of processing record boundaries and presents the tasks 
          with keys and values.</p>
<a name="N10C4E"></a><a name="Job+Output"></a>
<h3 class="h4">Job Output</h3>
<p>
<a href="api/org/apache/hadoop/mapred/OutputFormat.html">
        OutputFormat</a> describes the output-specification for a Map/Reduce 
        job.</p>
<p>The Map/Reduce framework relies on the <span class="codefrag">OutputFormat</span> of 
        the job to:</p>
<ol>
          
<li>
            Validate the output-specification of the job; for example, check that 
            the output directory doesn't already exist.
          </li>
          
<li>
            Provide the <span class="codefrag">RecordWriter</span> implementation used to 
            write the output files of the job. Output files are stored in a 
            <span class="codefrag">FileSystem</span>.
          </li>
        
</ol>
<p>
<span class="codefrag">TextOutputFormat</span> is the default 
        <span class="codefrag">OutputFormat</span>.</p>
<a name="N10C77"></a><a name="OutputCommitter"></a>
<h4>OutputCommitter</h4>
<p>
<a href="api/org/apache/hadoop/mapred/OutputCommitter.html">
        OutputCommitter</a> describes the commit of task output for a 
        Map/Reduce job.</p>
<p>The Map/Reduce framework relies on the <span class="codefrag">OutputCommitter</span>
        of the job to:</p>
<ol>
          
<li>
            Setup the job during initialization. For example, create
            the temporary output directory for the job during the
            initialization of the job. 
            Job setup is done by a separate task when the job is
            in PREP state and after initializing tasks. Once the setup task
            completes, the job will be moved to RUNNING state.
          </li>
          
<li>
            Cleanup the job after the job completion. For example, remove the
            temporary output directory after the job completion.
            Job cleanup is done by a separate task at the end of the job.
            Job is declared SUCCEDED/FAILED/KILLED after the cleanup
            task completes.
          </li>
          
<li>
            Setup the task temporary output.
            Task setup is done as part of the same task, during task initialization.
          </li> 
          
<li>
            Check whether a task needs a commit. This is to avoid the commit
            procedure if a task does not need commit.
          </li>
          
<li>
            Commit of the task output. 
            Once task is done, the task will commit it's output if required.  
          </li> 
          
<li>
            Discard the task commit.
            If the task has been failed/killed, the output will be cleaned-up. 
            If task could not cleanup (in exception block), a separate task 
            will be launched with same attempt-id to do the cleanup.
          </li>
        
</ol>
<p>
<span class="codefrag">FileOutputCommitter</span> is the default 
        <span class="codefrag">OutputCommitter</span>. Job setup/cleanup tasks occupy 
        map or reduce slots, whichever is free on the TaskTracker. And
        JobCleanup task, TaskCleanup tasks and JobSetup task have the highest
        priority, and in that order.</p>
<a name="N10CA7"></a><a name="Task+Side-Effect+Files"></a>
<h4>Task Side-Effect Files</h4>
<p>In some applications, component tasks need to create and/or write to
          side-files, which differ from the actual job-output files.</p>
<p>In such cases there could be issues with two instances of the same 
          <span class="codefrag">Mapper</span> or <span class="codefrag">Reducer</span> running simultaneously (for
          example, speculative tasks) trying to open and/or write to the same 
          file (path) on the <span class="codefrag">FileSystem</span>. Hence the 
          application-writer will have to pick unique names per task-attempt 
          (using the attemptid, say <span class="codefrag">attempt_200709221812_0001_m_000000_0</span>), 
          not just per task.</p>
<p>To avoid these issues the Map/Reduce framework, when the 
          <span class="codefrag">OutputCommitter</span> is <span class="codefrag">FileOutputCommitter</span>, 
          maintains a special 
          <span class="codefrag">${mapred.output.dir}/_temporary/_${taskid}</span> sub-directory
          accessible via <span class="codefrag">${mapred.work.output.dir}</span>
          for each task-attempt on the <span class="codefrag">FileSystem</span> where the output
          of the task-attempt is stored. On successful completion of the 
          task-attempt, the files in the 
          <span class="codefrag">${mapred.output.dir}/_temporary/_${taskid}</span> (only) 
          are <em>promoted</em> to <span class="codefrag">${mapred.output.dir}</span>. Of course, 
          the framework discards the sub-directory of unsuccessful task-attempts. 
          This process is completely transparent to the application.</p>
<p>The application-writer can take advantage of this feature by 
          creating any side-files required in <span class="codefrag">${mapred.work.output.dir}</span>
          during execution of a task via 
          <a href="api/org/apache/hadoop/mapred/FileOutputFormat.html#getWorkOutputPath(org.apache.hadoop.mapred.JobConf)">
          FileOutputFormat.getWorkOutputPath()</a>, and the framework will promote them 
          similarly for succesful task-attempts, thus eliminating the need to 
          pick unique paths per task-attempt.</p>
<p>Note: The value of <span class="codefrag">${mapred.work.output.dir}</span> during 
          execution of a particular task-attempt is actually 
          <span class="codefrag">${mapred.output.dir}/_temporary/_{$taskid}</span>, and this value is 
          set by the Map/Reduce framework. So, just create any side-files in the 
          path  returned by
          <a href="api/org/apache/hadoop/mapred/FileOutputFormat.html#getWorkOutputPath(org.apache.hadoop.mapred.JobConf)">
          FileOutputFormat.getWorkOutputPath() </a>from map/reduce 
          task to take advantage of this feature.</p>
<p>The entire discussion holds true for maps of jobs with 
           reducer=NONE (i.e. 0 reduces) since output of the map, in that case, 
           goes directly to HDFS.</p>
<a name="N10CF5"></a><a name="RecordWriter"></a>
<h4>RecordWriter</h4>
<p>
<a href="api/org/apache/hadoop/mapred/RecordWriter.html">
          RecordWriter</a> writes the output <span class="codefrag">&lt;key, value&gt;</span> 
          pairs to an output file.</p>
<p>RecordWriter implementations write the job outputs to the 
          <span class="codefrag">FileSystem</span>.</p>
<a name="N10D0C"></a><a name="Other+Useful+Features"></a>
<h3 class="h4">Other Useful Features</h3>
<a name="N10D12"></a><a name="Submitting+Jobs+to+Queues"></a>
<h4>Submitting Jobs to Queues</h4>
<p>Users submit jobs to Queues. Queues, as collection of jobs, 
          allow the system to provide specific functionality. For example, 
          queues use ACLs to control which users 
          who can submit jobs to them. Queues are expected to be primarily 
          used by Hadoop Schedulers. </p>
<p>Hadoop comes configured with a single mandatory queue, called 
          'default'. Queue names are defined in the 
          <span class="codefrag">mapred.queue.names</span> property of the Hadoop site
          configuration. Some job schedulers, such as the 
          <a href="capacity_scheduler.html">Capacity Scheduler</a>, 
          support multiple queues.</p>
<p>A job defines the queue it needs to be submitted to through the
          <span class="codefrag">mapred.job.queue.name</span> property, or through the
          <a href="api/org/apache/hadoop/mapred/JobConf.html#setQueueName(java.lang.String)">setQueueName(String)</a>
          API. Setting the queue name is optional. If a job is submitted 
          without an associated queue name, it is submitted to the 'default' 
          queue.</p>
<a name="N10D30"></a><a name="Counters"></a>
<h4>Counters</h4>
<p>
<span class="codefrag">Counters</span> represent global counters, defined either by 
          the Map/Reduce framework or applications. Each <span class="codefrag">Counter</span> can 
          be of any <span class="codefrag">Enum</span> type. Counters of a particular 
          <span class="codefrag">Enum</span> are bunched into groups of type 
          <span class="codefrag">Counters.Group</span>.</p>
<p>Applications can define arbitrary <span class="codefrag">Counters</span> (of type 
          <span class="codefrag">Enum</span>) and update them via 
          <a href="api/org/apache/hadoop/mapred/Reporter.html#incrCounter(java.lang.Enum, long)">
          Reporter.incrCounter(Enum, long)</a> or 
          <a href="api/org/apache/hadoop/mapred/Reporter.html#incrCounter(java.lang.String, java.lang.String, long amount)">
          Reporter.incrCounter(String, String, long)</a>
          in the <span class="codefrag">map</span> and/or 
          <span class="codefrag">reduce</span> methods. These counters are then globally 
          aggregated by the framework.</p>
<a name="N10D5F"></a><a name="DistributedCache"></a>
<h4>DistributedCache</h4>
<p>
<a href="api/org/apache/hadoop/filecache/DistributedCache.html">
          DistributedCache</a> distributes application-specific, large, read-only 
          files efficiently.</p>
<p>
<span class="codefrag">DistributedCache</span> is a facility provided by the 
          Map/Reduce framework to cache files (text, archives, jars and so on) 
          needed by applications.</p>
<p>Applications specify the files to be cached via urls (hdfs://)
          in the <span class="codefrag">JobConf</span>. The <span class="codefrag">DistributedCache</span> 
          assumes that the files specified via hdfs:// urls are already present 
          on the <span class="codefrag">FileSystem</span>.</p>
<p>The framework will copy the necessary files to the slave node 
          before any tasks for the job are executed on that node. Its 
          efficiency stems from the fact that the files are only copied once 
          per job and the ability to cache archives which are un-archived on 
          the slaves.</p>
<p>
<span class="codefrag">DistributedCache</span> tracks the modification timestamps of 
          the cached files. Clearly the cache files should not be modified by 
          the application or externally while the job is executing.</p>
<p>
<span class="codefrag">DistributedCache</span> can be used to distribute simple, 
          read-only data/text files and more complex types such as archives and
          jars. Archives (zip, tar, tgz and tar.gz files) are 
          <em>un-archived</em> at the slave nodes. Files 
          have <em>execution permissions</em> set. </p>
<p>The files/archives can be distributed by setting the property
          <span class="codefrag">mapred.cache.{files|archives}</span>. If more than one 
          file/archive has to be distributed, they can be added as comma
          separated paths. The properties can also be set by APIs 
          <a href="api/org/apache/hadoop/filecache/DistributedCache.html#addCacheFile(java.net.URI,%20org.apache.hadoop.conf.Configuration)">
          DistributedCache.addCacheFile(URI,conf)</a>/ 
          <a href="api/org/apache/hadoop/filecache/DistributedCache.html#addCacheArchive(java.net.URI,%20org.apache.hadoop.conf.Configuration)">
          DistributedCache.addCacheArchive(URI,conf)</a> and
          <a href="api/org/apache/hadoop/filecache/DistributedCache.html#setCacheFiles(java.net.URI[],%20org.apache.hadoop.conf.Configuration)">
          DistributedCache.setCacheFiles(URIs,conf)</a>/
          <a href="api/org/apache/hadoop/filecache/DistributedCache.html#setCacheArchives(java.net.URI[],%20org.apache.hadoop.conf.Configuration)">
          DistributedCache.setCacheArchives(URIs,conf)</a> 
          where URI is of the form
          <span class="codefrag">hdfs://host:port/absolute-path#link-name</span>.
          In Streaming, the files can be distributed through command line
          option <span class="codefrag">-cacheFile/-cacheArchive</span>.</p>
<p>Optionally users can also direct the <span class="codefrag">DistributedCache</span>
          to <em>symlink</em> the cached file(s) into the <span class="codefrag">current working 
          directory</span> of the task via the 
          <a href="api/org/apache/hadoop/filecache/DistributedCache.html#createSymlink(org.apache.hadoop.conf.Configuration)">
          DistributedCache.createSymlink(Configuration)</a> api. Or by setting
          the configuration property <span class="codefrag">mapred.create.symlink</span>
          as <span class="codefrag">yes</span>. The DistributedCache will use the 
          <span class="codefrag">fragment</span> of the URI as the name of the symlink. 
          For example, the URI 
          <span class="codefrag">hdfs://namenode:port/lib.so.1#lib.so</span>
          will have the symlink name as <span class="codefrag">lib.so</span> in task's cwd
          for the file <span class="codefrag">lib.so.1</span> in distributed cache.</p>
<p>The <span class="codefrag">DistributedCache</span> can also be used as a 
          rudimentary software distribution mechanism for use in the
          map and/or reduce tasks. It can be used to distribute both
          jars and native libraries. The 
          <a href="api/org/apache/hadoop/filecache/DistributedCache.html#addArchiveToClassPath(org.apache.hadoop.fs.Path,%20org.apache.hadoop.conf.Configuration)">
          DistributedCache.addArchiveToClassPath(Path, Configuration)</a> or 
          <a href="api/org/apache/hadoop/filecache/DistributedCache.html#addFileToClassPath(org.apache.hadoop.fs.Path,%20org.apache.hadoop.conf.Configuration)">
          DistributedCache.addFileToClassPath(Path, Configuration)</a> api 
          can be used to cache files/jars and also add them to the 
          <em>classpath</em> of child-jvm. The same can be done by setting
          the configuration properties 
          <span class="codefrag">mapred.job.classpath.{files|archives}</span>. Similarly the
          cached files that are symlinked into the working directory of the
          task can be used to distribute native libraries and load them.</p>
<a name="N10DE2"></a><a name="Tool"></a>
<h4>Tool</h4>
<p>The <a href="api/org/apache/hadoop/util/Tool.html">Tool</a> 
          interface supports the handling of generic Hadoop command-line options.
          </p>
<p>
<span class="codefrag">Tool</span> is the standard for any Map/Reduce tool or 
          application. The application should delegate the handling of 
          standard command-line options to 
          <a href="api/org/apache/hadoop/util/GenericOptionsParser.html">
          GenericOptionsParser</a> via          
          <a href="api/org/apache/hadoop/util/ToolRunner.html#run(org.apache.hadoop.util.Tool, java.lang.String[])">
          ToolRunner.run(Tool, String[])</a> and only handle its custom 
          arguments.</p>
<p>
            The generic Hadoop command-line options are:<br>
            
<span class="codefrag">
              -conf &lt;configuration file&gt;
            </span>
            
<br>
            
<span class="codefrag">
              -D &lt;property=value&gt;
            </span>
            
<br>
            
<span class="codefrag">
              -fs &lt;local|namenode:port&gt;
            </span>
            
<br>
            
<span class="codefrag">
              -jt &lt;local|jobtracker:port&gt;
            </span>
          
</p>
<a name="N10E14"></a><a name="IsolationRunner"></a>
<h4>IsolationRunner</h4>
<p>
<a href="api/org/apache/hadoop/mapred/IsolationRunner.html">
          IsolationRunner</a> is a utility to help debug Map/Reduce programs.</p>
<p>To use the <span class="codefrag">IsolationRunner</span>, first set 
          <span class="codefrag">keep.failed.tasks.files</span> to <span class="codefrag">true</span> 
          (also see <span class="codefrag">keep.tasks.files.pattern</span>).</p>
<p>
            Next, go to the node on which the failed task ran and go to the 
            <span class="codefrag">TaskTracker</span>'s local directory and run the 
            <span class="codefrag">IsolationRunner</span>:<br>
            
<span class="codefrag">$ cd &lt;local path&gt;/taskTracker/${taskid}/work</span>
<br>
            
<span class="codefrag">
              $ bin/hadoop org.apache.hadoop.mapred.IsolationRunner ../job.xml
            </span>
          
</p>
<p>
<span class="codefrag">IsolationRunner</span> will run the failed task in a single 
          jvm, which can be in the debugger, over precisely the same input.</p>
<a name="N10E47"></a><a name="Profiling"></a>
<h4>Profiling</h4>
<p>Profiling is a utility to get a representative (2 or 3) sample
          of built-in java profiler for a sample of maps and reduces. </p>
<p>User can specify whether the system should collect profiler
          information for some of the tasks in the job by setting the
          configuration property <span class="codefrag">mapred.task.profile</span>. The
          value can be set using the api 
          <a href="api/org/apache/hadoop/mapred/JobConf.html#setProfileEnabled(boolean)">
          JobConf.setProfileEnabled(boolean)</a>. If the value is set 
          <span class="codefrag">true</span>, the task profiling is enabled. The profiler
          information is stored in the user log directory. By default, 
          profiling is not enabled for the job.  </p>
<p>Once user configures that profiling is needed, she/he can use
          the configuration property 
          <span class="codefrag">mapred.task.profile.{maps|reduces}</span> to set the ranges
          of map/reduce tasks to profile. The value can be set using the api 
          <a href="api/org/apache/hadoop/mapred/JobConf.html#setProfileTaskRange(boolean,%20java.lang.String)">
          JobConf.setProfileTaskRange(boolean,String)</a>.
          By default, the specified range is <span class="codefrag">0-2</span>.</p>
<p>User can also specify the profiler configuration arguments by 
          setting the configuration property 
          <span class="codefrag">mapred.task.profile.params</span>. The value can be specified 
          using the api
          <a href="api/org/apache/hadoop/mapred/JobConf.html#setProfileParams(java.lang.String)">
          JobConf.setProfileParams(String)</a>. If the string contains a 
          <span class="codefrag">%s</span>, it will be replaced with the name of the profiling
          output file when the task runs. These parameters are passed to the
          task child JVM on the command line. The default value for 
          the profiling parameters is 
          <span class="codefrag">-agentlib:hprof=cpu=samples,heap=sites,force=n,thread=y,verbose=n,file=%s</span>
          
</p>
<a name="N10E7B"></a><a name="Debugging"></a>
<h4>Debugging</h4>
<p>The Map/Reduce framework provides a facility to run user-provided 
          scripts for debugging. When a map/reduce task fails, a user can run 
          a debug script, to process task logs for example. The script is 
          given access to the task's stdout and stderr outputs, syslog and 
          jobconf. The output from the debug script's stdout and stderr is 
          displayed on the console diagnostics and also as part of the 
          job UI. </p>
<p> In the following sections we discuss how to submit a debug script
          with a job. The script file needs to be distributed and submitted to 
          the framework.</p>
<a name="N10E87"></a><a name="How+to+distribute+the+script+file%3A"></a>
<h5> How to distribute the script file: </h5>
<p>
          The user needs to use  
          <a href="mapred_tutorial.html#DistributedCache">DistributedCache</a>
          to <em>distribute</em> and <em>symlink</em> the script file.</p>
<a name="N10E9B"></a><a name="How+to+submit+the+script%3A"></a>
<h5> How to submit the script: </h5>
<p> A quick way to submit the debug script is to set values for the 
          properties <span class="codefrag">mapred.map.task.debug.script</span> and 
          <span class="codefrag">mapred.reduce.task.debug.script</span>, for debugging map and 
          reduce tasks respectively. These properties can also be set by using APIs 
          <a href="api/org/apache/hadoop/mapred/JobConf.html#setMapDebugScript(java.lang.String)">
          JobConf.setMapDebugScript(String) </a> and
          <a href="api/org/apache/hadoop/mapred/JobConf.html#setReduceDebugScript(java.lang.String)">
          JobConf.setReduceDebugScript(String) </a>. In streaming mode, a debug 
          script can be submitted with the command-line options 
          <span class="codefrag">-mapdebug</span> and <span class="codefrag">-reducedebug</span>, for debugging 
          map and reduce tasks respectively.</p>
<p>The arguments to the script are the task's stdout, stderr, 
          syslog and jobconf files. The debug command, run on the node where
          the map/reduce task failed, is: <br>
          
<span class="codefrag"> $script $stdout $stderr $syslog $jobconf </span> 
</p>
<p> Pipes programs have the c++ program name as a fifth argument
          for the command. Thus for the pipes programs the command is <br> 
          
<span class="codefrag">$script $stdout $stderr $syslog $jobconf $program </span>  
          
</p>
<a name="N10EC9"></a><a name="Default+Behavior%3A"></a>
<h5> Default Behavior: </h5>
<p> For pipes, a default script is run to process core dumps under
          gdb, prints stack trace and gives info about running threads. </p>
<a name="N10ED4"></a><a name="JobControl"></a>
<h4>JobControl</h4>
<p>
<a href="api/org/apache/hadoop/mapred/jobcontrol/package-summary.html">
          JobControl</a> is a utility which encapsulates a set of Map/Reduce jobs
          and their dependencies.</p>
<a name="N10EE1"></a><a name="Data+Compression"></a>
<h4>Data Compression</h4>
<p>Hadoop Map/Reduce provides facilities for the application-writer to
          specify compression for both intermediate map-outputs and the
          job-outputs i.e. output of the reduces. It also comes bundled with
          <a href="api/org/apache/hadoop/io/compress/CompressionCodec.html">
          CompressionCodec</a> implementations for the 
          <a href="http://www.zlib.net/">zlib</a> and <a href="http://www.oberhumer.com/opensource/lzo/">lzo</a> compression 
          algorithms. The <a href="http://www.gzip.org/">gzip</a> file format is also
          supported.</p>
<p>Hadoop also provides native implementations of the above compression
          codecs for reasons of both performance (zlib) and non-availability of
          Java libraries (lzo). More details on their usage and availability are
          available <a href="native_libraries.html">here</a>.</p>
<a name="N10F01"></a><a name="Intermediate+Outputs"></a>
<h5>Intermediate Outputs</h5>
<p>Applications can control compression of intermediate map-outputs
            via the 
            <a href="api/org/apache/hadoop/mapred/JobConf.html#setCompressMapOutput(boolean)">
            JobConf.setCompressMapOutput(boolean)</a> api and the 
            <span class="codefrag">CompressionCodec</span> to be used via the
            <a href="api/org/apache/hadoop/mapred/JobConf.html#setMapOutputCompressorClass(java.lang.Class)">
            JobConf.setMapOutputCompressorClass(Class)</a> api.</p>
<a name="N10F16"></a><a name="Job+Outputs"></a>
<h5>Job Outputs</h5>
<p>Applications can control compression of job-outputs via the
            <a href="api/org/apache/hadoop/mapred/FileOutputFormat.html#setCompressOutput(org.apache.hadoop.mapred.JobConf,%20boolean)">
            FileOutputFormat.setCompressOutput(JobConf, boolean)</a> api and the 
            <span class="codefrag">CompressionCodec</span> to be used can be specified via the
            <a href="api/org/apache/hadoop/mapred/FileOutputFormat.html#setOutputCompressorClass(org.apache.hadoop.mapred.JobConf,%20java.lang.Class)">
            FileOutputFormat.setOutputCompressorClass(JobConf, Class)</a> api.</p>
<p>If the job outputs are to be stored in the 
            <a href="api/org/apache/hadoop/mapred/SequenceFileOutputFormat.html">
            SequenceFileOutputFormat</a>, the required
            <span class="codefrag">SequenceFile.CompressionType</span> (i.e. <span class="codefrag">RECORD</span> / 
            <span class="codefrag">BLOCK</span> - defaults to <span class="codefrag">RECORD</span>) can be 
            specified via the 
            <a href="api/org/apache/hadoop/mapred/SequenceFileOutputFormat.html#setOutputCompressionType(org.apache.hadoop.mapred.JobConf,%20org.apache.hadoop.io.SequenceFile.CompressionType)">
            SequenceFileOutputFormat.setOutputCompressionType(JobConf, 
            SequenceFile.CompressionType)</a> api.</p>
<a name="N10F43"></a><a name="Skipping+Bad+Records"></a>
<h4>Skipping Bad Records</h4>
<p>Hadoop provides an option where a certain set of bad input 
          records can be skipped when processing map inputs. Applications 
          can control this feature through the  
          <a href="api/org/apache/hadoop/mapred/SkipBadRecords.html">
          SkipBadRecords</a> class.</p>
<p>This feature can be used when map tasks crash deterministically 
          on certain input. This usually happens due to bugs in the 
          map function. Usually, the user would have to fix these bugs. 
          This is, however, not possible sometimes. The bug may be in third 
          party libraries, for example, for which the source code is not 
          available. In such cases, the task never completes successfully even
          after multiple attempts, and the job fails. With this feature, only 
          a small portion of data surrounding the 
          bad records is lost, which may be acceptable for some applications 
          (those performing statistical analysis on very large data, for 
          example). </p>
<p>By default this feature is disabled. For enabling it, 
          refer to <a href="api/org/apache/hadoop/mapred/SkipBadRecords.html#setMapperMaxSkipRecords(org.apache.hadoop.conf.Configuration, long)">
          SkipBadRecords.setMapperMaxSkipRecords(Configuration, long)</a> and 
          <a href="api/org/apache/hadoop/mapred/SkipBadRecords.html#setReducerMaxSkipGroups(org.apache.hadoop.conf.Configuration, long)">
          SkipBadRecords.setReducerMaxSkipGroups(Configuration, long)</a>.
          </p>
<p>With this feature enabled, the framework gets into 'skipping 
          mode' after a certain number of map failures. For more details, 
          see <a href="api/org/apache/hadoop/mapred/SkipBadRecords.html#setAttemptsToStartSkipping(org.apache.hadoop.conf.Configuration, int)">
          SkipBadRecords.setAttemptsToStartSkipping(Configuration, int)</a>. 
          In 'skipping mode', map tasks maintain the range of records being 
          processed. To do this, the framework relies on the processed record 
          counter. See <a href="api/org/apache/hadoop/mapred/SkipBadRecords.html#COUNTER_MAP_PROCESSED_RECORDS">
          SkipBadRecords.COUNTER_MAP_PROCESSED_RECORDS</a> and 
          <a href="api/org/apache/hadoop/mapred/SkipBadRecords.html#COUNTER_REDUCE_PROCESSED_GROUPS">
          SkipBadRecords.COUNTER_REDUCE_PROCESSED_GROUPS</a>. 
          This counter enables the framework to know how many records have 
          been processed successfully, and hence, what record range caused 
          a task to crash. On further attempts, this range of records is 
          skipped.</p>
<p>The number of records skipped depends on how frequently the 
          processed record counter is incremented by the application. 
          It is recommended that this counter be incremented after every 
          record is processed. This may not be possible in some applications 
          that typically batch their processing. In such cases, the framework 
          may skip additional records surrounding the bad record. Users can 
          control the number of skipped records through 
          <a href="api/org/apache/hadoop/mapred/SkipBadRecords.html#setMapperMaxSkipRecords(org.apache.hadoop.conf.Configuration, long)">
          SkipBadRecords.setMapperMaxSkipRecords(Configuration, long)</a> and 
          <a href="api/org/apache/hadoop/mapred/SkipBadRecords.html#setReducerMaxSkipGroups(org.apache.hadoop.conf.Configuration, long)">
          SkipBadRecords.setReducerMaxSkipGroups(Configuration, long)</a>. 
          The framework tries to narrow the range of skipped records using a 
          binary search-like approach. The skipped range is divided into two 
          halves and only one half gets executed. On subsequent 
          failures, the framework figures out which half contains 
          bad records. A task will be re-executed till the
          acceptable skipped value is met or all task attempts are exhausted.
          To increase the number of task attempts, use
          <a href="api/org/apache/hadoop/mapred/JobConf.html#setMaxMapAttempts(int)">
          JobConf.setMaxMapAttempts(int)</a> and 
          <a href="api/org/apache/hadoop/mapred/JobConf.html#setMaxReduceAttempts(int)">
          JobConf.setMaxReduceAttempts(int)</a>.
          </p>
<p>Skipped records are written to HDFS in the sequence file 
          format, for later analysis. The location can be changed through 
          <a href="api/org/apache/hadoop/mapred/SkipBadRecords.html#setSkipOutputPath(org.apache.hadoop.mapred.JobConf, org.apache.hadoop.fs.Path)">
          SkipBadRecords.setSkipOutputPath(JobConf, Path)</a>.
          </p>
</div>

    
<a name="N10F8A"></a><a name="Example%3A+WordCount+v2.0"></a>
<h2 class="h3">Example: WordCount v2.0</h2>
<div class="section">
<p>Here is a more complete <span class="codefrag">WordCount</span> which uses many of the
      features provided by the Map/Reduce framework we discussed so far.</p>
<p>This needs the HDFS to be up and running, especially for the 
      <span class="codefrag">DistributedCache</span>-related features. Hence it only works with a 
      <a href="quickstart.html#SingleNodeSetup">pseudo-distributed</a> or
      <a href="quickstart.html#Fully-Distributed+Operation">fully-distributed</a> 
      Hadoop installation.</p>
<a name="N10FA4"></a><a name="Source+Code-N10FA4"></a>
<h3 class="h4">Source Code</h3>
<table class="ForrestTable" cellspacing="1" cellpadding="4">
          
<tr>
            
<th colspan="1" rowspan="1"></th>
            <th colspan="1" rowspan="1">WordCount.java</th>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">1.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">package org.myorg;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">2.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">3.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import java.io.*;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">4.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import java.util.*;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">5.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">6.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import org.apache.hadoop.fs.Path;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">7.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import org.apache.hadoop.filecache.DistributedCache;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">8.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import org.apache.hadoop.conf.*;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">9.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import org.apache.hadoop.io.*;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">10.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import org.apache.hadoop.mapred.*;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">11.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">import org.apache.hadoop.util.*;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">12.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">13.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">public class WordCount extends Configured implements Tool {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">14.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">15.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;
              <span class="codefrag">
                public static class Map extends MapReduceBase 
                implements Mapper&lt;LongWritable, Text, Text, IntWritable&gt; {
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">16.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">17.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                static enum Counters { INPUT_WORDS }
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">18.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">19.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                private final static IntWritable one = new IntWritable(1);
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">20.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">private Text word = new Text();</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">21.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">22.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">private boolean caseSensitive = true;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">23.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">private Set&lt;String&gt; patternsToSkip = new HashSet&lt;String&gt;();</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">24.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">25.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">private long numRecords = 0;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">26.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">private String inputFile;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">27.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">28.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">public void configure(JobConf job) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">29.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                caseSensitive = job.getBoolean("wordcount.case.sensitive", true);
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">30.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">inputFile = job.get("map.input.file");</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">31.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">32.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">if (job.getBoolean("wordcount.skip.patterns", false)) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">33.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">Path[] patternsFiles = new Path[0];</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">34.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">try {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">35.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                patternsFiles = DistributedCache.getLocalCacheFiles(job);
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">36.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">} catch (IOException ioe) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">37.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                System.err.println("Caught exception while getting cached files: " 
                + StringUtils.stringifyException(ioe));
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">38.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">39.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">for (Path patternsFile : patternsFiles) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">40.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">parseSkipFile(patternsFile);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">41.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">42.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">43.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">44.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">45.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">private void parseSkipFile(Path patternsFile) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">46.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">try {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">47.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                BufferedReader fis = 
                  new BufferedReader(new FileReader(patternsFile.toString()));
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">48.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">String pattern = null;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">49.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">while ((pattern = fis.readLine()) != null) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">50.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">patternsToSkip.add(pattern);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">51.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">52.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">} catch (IOException ioe) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">53.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                System.err.println("Caught exception while parsing the cached file '" +
                                   patternsFile + "' : " + 
                                   StringUtils.stringifyException(ioe));
                
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">54.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">55.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">56.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">57.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                public void map(LongWritable key, Text value, 
                OutputCollector&lt;Text, IntWritable&gt; output, 
                Reporter reporter) throws IOException {
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">58.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                String line = 
                  (caseSensitive) ? value.toString() : 
                                    value.toString().toLowerCase();
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">59.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">60.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">for (String pattern : patternsToSkip) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">61.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">line = line.replaceAll(pattern, "");</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">62.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">63.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">64.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">StringTokenizer tokenizer = new StringTokenizer(line);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">65.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">while (tokenizer.hasMoreTokens()) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">66.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">word.set(tokenizer.nextToken());</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">67.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">output.collect(word, one);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">68.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">reporter.incrCounter(Counters.INPUT_WORDS, 1);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">69.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">70.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">71.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">if ((++numRecords % 100) == 0) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">72.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                reporter.setStatus("Finished processing " + numRecords + 
                                   " records " + "from the input file: " + 
                                   inputFile);
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">73.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">74.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">75.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">76.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">77.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;
              <span class="codefrag">
                public static class Reduce extends MapReduceBase implements 
                Reducer&lt;Text, IntWritable, Text, IntWritable&gt; {
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">78.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                public void reduce(Text key, Iterator&lt;IntWritable&gt; values,
                OutputCollector&lt;Text, IntWritable&gt; output, 
                Reporter reporter) throws IOException {
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">79.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">int sum = 0;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">80.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">while (values.hasNext()) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">81.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">sum += values.next().get();</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">82.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">83.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">output.collect(key, new IntWritable(sum));</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">84.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">85.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">86.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">87.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;
              <span class="codefrag">public int run(String[] args) throws Exception {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">88.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                JobConf conf = new JobConf(getConf(), WordCount.class);
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">89.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setJobName("wordcount");</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">90.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">91.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setOutputKeyClass(Text.class);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">92.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setOutputValueClass(IntWritable.class);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">93.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">94.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setMapperClass(Map.class);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">95.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setCombinerClass(Reduce.class);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">96.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setReducerClass(Reduce.class);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">97.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">98.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setInputFormat(TextInputFormat.class);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">99.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">conf.setOutputFormat(TextOutputFormat.class);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">100.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">101.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                List&lt;String&gt; other_args = new ArrayList&lt;String&gt;();
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">102.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">for (int i=0; i &lt; args.length; ++i) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">103.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">if ("-skip".equals(args[i])) {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">104.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                DistributedCache.addCacheFile(new Path(args[++i]).toUri(), conf);
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">105.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                conf.setBoolean("wordcount.skip.patterns", true);
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">106.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">} else {</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">107.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">other_args.add(args[i]);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">108.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">109.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">110.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">111.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">FileInputFormat.setInputPaths(conf, new Path(other_args.get(0)));</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">112.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">113.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">114.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">JobClient.runJob(conf);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">115.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">return 0;</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">116.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">117.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">118.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;
              <span class="codefrag">
                public static void main(String[] args) throws Exception {
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">119.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">
                int res = ToolRunner.run(new Configuration(), new WordCount(), 
                                         args);
              </span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">120.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;&nbsp;&nbsp;
              <span class="codefrag">System.exit(res);</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">121.</td>
            <td colspan="1" rowspan="1">
              &nbsp;&nbsp;
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">122.</td>
            <td colspan="1" rowspan="1">
              <span class="codefrag">}</span>
            </td>
          
</tr>
          
<tr>
            
<td colspan="1" rowspan="1">123.</td>
            <td colspan="1" rowspan="1"></td>
          
</tr>
        
</table>
<a name="N11706"></a><a name="Sample+Runs"></a>
<h3 class="h4">Sample Runs</h3>
<p>Sample text-files as input:</p>
<p>
          
<span class="codefrag">$ bin/hadoop dfs -ls /usr/joe/wordcount/input/</span>
<br>
          
<span class="codefrag">/usr/joe/wordcount/input/file01</span>
<br>
          
<span class="codefrag">/usr/joe/wordcount/input/file02</span>
<br>
          
<br>
          
<span class="codefrag">$ bin/hadoop dfs -cat /usr/joe/wordcount/input/file01</span>
<br>
          
<span class="codefrag">Hello World, Bye World!</span>
<br>
          
<br>
          
<span class="codefrag">$ bin/hadoop dfs -cat /usr/joe/wordcount/input/file02</span>
<br>
          
<span class="codefrag">Hello Hadoop, Goodbye to hadoop.</span>
        
</p>
<p>Run the application:</p>
<p>
          
<span class="codefrag">
            $ bin/hadoop jar /usr/joe/wordcount.jar org.myorg.WordCount 
              /usr/joe/wordcount/input /usr/joe/wordcount/output 
          </span>
        
</p>
<p>Output:</p>
<p>
          
<span class="codefrag">
            $ bin/hadoop dfs -cat /usr/joe/wordcount/output/part-00000
          </span>
          
<br>
          
<span class="codefrag">Bye    1</span>
<br>
          
<span class="codefrag">Goodbye    1</span>
<br>
          
<span class="codefrag">Hadoop,    1</span>
<br>
          
<span class="codefrag">Hello    2</span>
<br>
          
<span class="codefrag">World!    1</span>
<br>
          
<span class="codefrag">World,    1</span>
<br>
          
<span class="codefrag">hadoop.    1</span>
<br>
          
<span class="codefrag">to    1</span>
<br>
        
</p>
<p>Notice that the inputs differ from the first version we looked at, 
        and how they affect the outputs.</p>
<p>Now, lets plug-in a pattern-file which lists the word-patterns to be 
        ignored, via the <span class="codefrag">DistributedCache</span>.</p>
<p>
          
<span class="codefrag">$ hadoop dfs -cat /user/joe/wordcount/patterns.txt</span>
<br>
          
<span class="codefrag">\.</span>
<br>
          
<span class="codefrag">\,</span>
<br>
          
<span class="codefrag">\!</span>
<br>
          
<span class="codefrag">to</span>
<br>
        
</p>
<p>Run it again, this time with more options:</p>
<p>
          
<span class="codefrag">
            $ bin/hadoop jar /usr/joe/wordcount.jar org.myorg.WordCount 
              -Dwordcount.case.sensitive=true /usr/joe/wordcount/input 
              /usr/joe/wordcount/output -skip /user/joe/wordcount/patterns.txt
          </span>
        
</p>
<p>As expected, the output:</p>
<p>
          
<span class="codefrag">
            $ bin/hadoop dfs -cat /usr/joe/wordcount/output/part-00000
          </span>
          
<br>
          
<span class="codefrag">Bye    1</span>
<br>
          
<span class="codefrag">Goodbye    1</span>
<br>
          
<span class="codefrag">Hadoop    1</span>
<br>
          
<span class="codefrag">Hello    2</span>
<br>
          
<span class="codefrag">World    2</span>
<br>
          
<span class="codefrag">hadoop    1</span>
<br>
        
</p>
<p>Run it once more, this time switch-off case-sensitivity:</p>
<p>
          
<span class="codefrag">
            $ bin/hadoop jar /usr/joe/wordcount.jar org.myorg.WordCount 
              -Dwordcount.case.sensitive=false /usr/joe/wordcount/input 
              /usr/joe/wordcount/output -skip /user/joe/wordcount/patterns.txt
          </span>
        
</p>
<p>Sure enough, the output:</p>
<p>
          
<span class="codefrag">
            $ bin/hadoop dfs -cat /usr/joe/wordcount/output/part-00000
          </span>
          
<br>
          
<span class="codefrag">bye    1</span>
<br>
          
<span class="codefrag">goodbye    1</span>
<br>
          
<span class="codefrag">hadoop    2</span>
<br>
          
<span class="codefrag">hello    2</span>
<br>
          
<span class="codefrag">world    2</span>
<br>
        
</p>
<a name="N117DA"></a><a name="Highlights"></a>
<h3 class="h4">Highlights</h3>
<p>The second version of <span class="codefrag">WordCount</span> improves upon the 
        previous one by using some features offered by the Map/Reduce framework:
        </p>
<ul>
          
<li>
            Demonstrates how applications can access configuration parameters
            in the <span class="codefrag">configure</span> method of the <span class="codefrag">Mapper</span> (and
            <span class="codefrag">Reducer</span>) implementations (lines 28-43).
          </li>
          
<li>
            Demonstrates how the <span class="codefrag">DistributedCache</span> can be used to 
            distribute read-only data needed by the jobs. Here it allows the user 
            to specify word-patterns to skip while counting (line 104).
          </li>
          
<li>
            Demonstrates the utility of the <span class="codefrag">Tool</span> interface and the
            <span class="codefrag">GenericOptionsParser</span> to handle generic Hadoop 
            command-line options (lines 87-116, 119).
          </li>
          
<li>
            Demonstrates how applications can use <span class="codefrag">Counters</span> (line 68)
            and how they can set application-specific status information via 
            the <span class="codefrag">Reporter</span> instance passed to the <span class="codefrag">map</span> (and
            <span class="codefrag">reduce</span>) method (line 72).
          </li>
        
</ul>
</div>

    
<p>
      
<em>Java and JNI are trademarks or registered trademarks of 
      Sun Microsystems, Inc. in the United States and other countries.</em>
    
</p>
    
  
</div>
<!--+
    |end content
    +-->
<div class="clearboth">&nbsp;</div>
</div>
<div id="footer">
<!--+
    |start bottomstrip
    +-->
<div class="lastmodified">
<script type="text/javascript"><!--
document.write("Last Published: " + document.lastModified);
//  --></script>
</div>
<div class="copyright">
        Copyright &copy;
         2008 <a href="http://www.apache.org/licenses/">The Apache Software Foundation.</a>
</div>
<!--+
    |end bottomstrip
    +-->
</div>
</body>
</html>