[120] | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> |
---|
| 2 | <html> |
---|
| 3 | <head> |
---|
| 4 | <META http-equiv="Content-Type" content="text/html; charset=UTF-8"> |
---|
| 5 | <meta content="Apache Forrest" name="Generator"> |
---|
| 6 | <meta name="Forrest-version" content="0.8"> |
---|
| 7 | <meta name="Forrest-skin-name" content="pelt"> |
---|
| 8 | <title>Quick Start</title> |
---|
| 9 | <link type="text/css" href="skin/basic.css" rel="stylesheet"> |
---|
| 10 | <link media="screen" type="text/css" href="skin/screen.css" rel="stylesheet"> |
---|
| 11 | <link media="print" type="text/css" href="skin/print.css" rel="stylesheet"> |
---|
| 12 | <link type="text/css" href="skin/profile.css" rel="stylesheet"> |
---|
| 13 | <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> |
---|
| 14 | <link rel="shortcut icon" href="images/favicon.ico"> |
---|
| 15 | </head> |
---|
| 16 | <body onload="init()"> |
---|
| 17 | <script type="text/javascript">ndeSetTextSize();</script> |
---|
| 18 | <div id="top"> |
---|
| 19 | <!--+ |
---|
| 20 | |breadtrail |
---|
| 21 | +--> |
---|
| 22 | <div class="breadtrail"> |
---|
| 23 | <a href="http://www.apache.org/">Apache</a> > <a href="http://hadoop.apache.org/">Hadoop</a> > <a href="http://hadoop.apache.org/core/">Core</a><script src="skin/breadcrumbs.js" language="JavaScript" type="text/javascript"></script> |
---|
| 24 | </div> |
---|
| 25 | <!--+ |
---|
| 26 | |header |
---|
| 27 | +--> |
---|
| 28 | <div class="header"> |
---|
| 29 | <!--+ |
---|
| 30 | |start group logo |
---|
| 31 | +--> |
---|
| 32 | <div class="grouplogo"> |
---|
| 33 | <a href="http://hadoop.apache.org/"><img class="logoImage" alt="Hadoop" src="images/hadoop-logo.jpg" title="Apache Hadoop"></a> |
---|
| 34 | </div> |
---|
| 35 | <!--+ |
---|
| 36 | |end group logo |
---|
| 37 | +--> |
---|
| 38 | <!--+ |
---|
| 39 | |start Project Logo |
---|
| 40 | +--> |
---|
| 41 | <div class="projectlogo"> |
---|
| 42 | <a href="http://hadoop.apache.org/core/"><img class="logoImage" alt="Hadoop" src="images/core-logo.gif" title="Scalable Computing Platform"></a> |
---|
| 43 | </div> |
---|
| 44 | <!--+ |
---|
| 45 | |end Project Logo |
---|
| 46 | +--> |
---|
| 47 | <!--+ |
---|
| 48 | |start Search |
---|
| 49 | +--> |
---|
| 50 | <div class="searchbox"> |
---|
| 51 | <form action="http://www.google.com/search" method="get" class="roundtopsmall"> |
---|
| 52 | <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"> |
---|
| 53 | <input name="Search" value="Search" type="submit"> |
---|
| 54 | </form> |
---|
| 55 | </div> |
---|
| 56 | <!--+ |
---|
| 57 | |end search |
---|
| 58 | +--> |
---|
| 59 | <!--+ |
---|
| 60 | |start Tabs |
---|
| 61 | +--> |
---|
| 62 | <ul id="tabs"> |
---|
| 63 | <li> |
---|
| 64 | <a class="unselected" href="http://hadoop.apache.org/core/">Project</a> |
---|
| 65 | </li> |
---|
| 66 | <li> |
---|
| 67 | <a class="unselected" href="http://wiki.apache.org/hadoop">Wiki</a> |
---|
| 68 | </li> |
---|
| 69 | <li class="current"> |
---|
| 70 | <a class="selected" href="index.html">Hadoop 0.20 Documentation</a> |
---|
| 71 | </li> |
---|
| 72 | </ul> |
---|
| 73 | <!--+ |
---|
| 74 | |end Tabs |
---|
| 75 | +--> |
---|
| 76 | </div> |
---|
| 77 | </div> |
---|
| 78 | <div id="main"> |
---|
| 79 | <div id="publishedStrip"> |
---|
| 80 | <!--+ |
---|
| 81 | |start Subtabs |
---|
| 82 | +--> |
---|
| 83 | <div id="level2tabs"></div> |
---|
| 84 | <!--+ |
---|
| 85 | |end Endtabs |
---|
| 86 | +--> |
---|
| 87 | <script type="text/javascript"><!-- |
---|
| 88 | document.write("Last Published: " + document.lastModified); |
---|
| 89 | // --></script> |
---|
| 90 | </div> |
---|
| 91 | <!--+ |
---|
| 92 | |breadtrail |
---|
| 93 | +--> |
---|
| 94 | <div class="breadtrail"> |
---|
| 95 | |
---|
| 96 | |
---|
| 97 | </div> |
---|
| 98 | <!--+ |
---|
| 99 | |start Menu, mainarea |
---|
| 100 | +--> |
---|
| 101 | <!--+ |
---|
| 102 | |start Menu |
---|
| 103 | +--> |
---|
| 104 | <div id="menu"> |
---|
| 105 | <div onclick="SwitchMenu('menu_selected_1.1', 'skin/')" id="menu_selected_1.1Title" class="menutitle" style="background-image: url('skin/images/chapter_open.gif');">Getting Started</div> |
---|
| 106 | <div id="menu_selected_1.1" class="selectedmenuitemgroup" style="display: block;"> |
---|
| 107 | <div class="menuitem"> |
---|
| 108 | <a href="index.html">Overview</a> |
---|
| 109 | </div> |
---|
| 110 | <div class="menupage"> |
---|
| 111 | <div class="menupagetitle">Quick Start</div> |
---|
| 112 | </div> |
---|
| 113 | <div class="menuitem"> |
---|
| 114 | <a href="cluster_setup.html">Cluster Setup</a> |
---|
| 115 | </div> |
---|
| 116 | <div class="menuitem"> |
---|
| 117 | <a href="mapred_tutorial.html">Map/Reduce Tutorial</a> |
---|
| 118 | </div> |
---|
| 119 | </div> |
---|
| 120 | <div onclick="SwitchMenu('menu_1.2', 'skin/')" id="menu_1.2Title" class="menutitle">Programming Guides</div> |
---|
| 121 | <div id="menu_1.2" class="menuitemgroup"> |
---|
| 122 | <div class="menuitem"> |
---|
| 123 | <a href="commands_manual.html">Commands</a> |
---|
| 124 | </div> |
---|
| 125 | <div class="menuitem"> |
---|
| 126 | <a href="distcp.html">DistCp</a> |
---|
| 127 | </div> |
---|
| 128 | <div class="menuitem"> |
---|
| 129 | <a href="native_libraries.html">Native Libraries</a> |
---|
| 130 | </div> |
---|
| 131 | <div class="menuitem"> |
---|
| 132 | <a href="streaming.html">Streaming</a> |
---|
| 133 | </div> |
---|
| 134 | <div class="menuitem"> |
---|
| 135 | <a href="fair_scheduler.html">Fair Scheduler</a> |
---|
| 136 | </div> |
---|
| 137 | <div class="menuitem"> |
---|
| 138 | <a href="capacity_scheduler.html">Capacity Scheduler</a> |
---|
| 139 | </div> |
---|
| 140 | <div class="menuitem"> |
---|
| 141 | <a href="service_level_auth.html">Service Level Authorization</a> |
---|
| 142 | </div> |
---|
| 143 | <div class="menuitem"> |
---|
| 144 | <a href="vaidya.html">Vaidya</a> |
---|
| 145 | </div> |
---|
| 146 | <div class="menuitem"> |
---|
| 147 | <a href="hadoop_archives.html">Archives</a> |
---|
| 148 | </div> |
---|
| 149 | </div> |
---|
| 150 | <div onclick="SwitchMenu('menu_1.3', 'skin/')" id="menu_1.3Title" class="menutitle">HDFS</div> |
---|
| 151 | <div id="menu_1.3" class="menuitemgroup"> |
---|
| 152 | <div class="menuitem"> |
---|
| 153 | <a href="hdfs_user_guide.html">User Guide</a> |
---|
| 154 | </div> |
---|
| 155 | <div class="menuitem"> |
---|
| 156 | <a href="hdfs_design.html">Architecture</a> |
---|
| 157 | </div> |
---|
| 158 | <div class="menuitem"> |
---|
| 159 | <a href="hdfs_shell.html">File System Shell Guide</a> |
---|
| 160 | </div> |
---|
| 161 | <div class="menuitem"> |
---|
| 162 | <a href="hdfs_permissions_guide.html">Permissions Guide</a> |
---|
| 163 | </div> |
---|
| 164 | <div class="menuitem"> |
---|
| 165 | <a href="hdfs_quota_admin_guide.html">Quotas Guide</a> |
---|
| 166 | </div> |
---|
| 167 | <div class="menuitem"> |
---|
| 168 | <a href="SLG_user_guide.html">Synthetic Load Generator Guide</a> |
---|
| 169 | </div> |
---|
| 170 | <div class="menuitem"> |
---|
| 171 | <a href="libhdfs.html">C API libhdfs</a> |
---|
| 172 | </div> |
---|
| 173 | </div> |
---|
| 174 | <div onclick="SwitchMenu('menu_1.4', 'skin/')" id="menu_1.4Title" class="menutitle">HOD</div> |
---|
| 175 | <div id="menu_1.4" class="menuitemgroup"> |
---|
| 176 | <div class="menuitem"> |
---|
| 177 | <a href="hod_user_guide.html">User Guide</a> |
---|
| 178 | </div> |
---|
| 179 | <div class="menuitem"> |
---|
| 180 | <a href="hod_admin_guide.html">Admin Guide</a> |
---|
| 181 | </div> |
---|
| 182 | <div class="menuitem"> |
---|
| 183 | <a href="hod_config_guide.html">Config Guide</a> |
---|
| 184 | </div> |
---|
| 185 | </div> |
---|
| 186 | <div onclick="SwitchMenu('menu_1.5', 'skin/')" id="menu_1.5Title" class="menutitle">Miscellaneous</div> |
---|
| 187 | <div id="menu_1.5" class="menuitemgroup"> |
---|
| 188 | <div class="menuitem"> |
---|
| 189 | <a href="api/index.html">API Docs</a> |
---|
| 190 | </div> |
---|
| 191 | <div class="menuitem"> |
---|
| 192 | <a href="jdiff/changes.html">API Changes</a> |
---|
| 193 | </div> |
---|
| 194 | <div class="menuitem"> |
---|
| 195 | <a href="http://wiki.apache.org/hadoop/">Wiki</a> |
---|
| 196 | </div> |
---|
| 197 | <div class="menuitem"> |
---|
| 198 | <a href="http://wiki.apache.org/hadoop/FAQ">FAQ</a> |
---|
| 199 | </div> |
---|
| 200 | <div class="menuitem"> |
---|
| 201 | <a href="releasenotes.html">Release Notes</a> |
---|
| 202 | </div> |
---|
| 203 | <div class="menuitem"> |
---|
| 204 | <a href="changes.html">Change Log</a> |
---|
| 205 | </div> |
---|
| 206 | </div> |
---|
| 207 | <div id="credit"></div> |
---|
| 208 | <div id="roundbottom"> |
---|
| 209 | <img style="display: none" class="corner" height="15" width="15" alt="" src="skin/images/rc-b-l-15-1body-2menu-3menu.png"></div> |
---|
| 210 | <!--+ |
---|
| 211 | |alternative credits |
---|
| 212 | +--> |
---|
| 213 | <div id="credit2"></div> |
---|
| 214 | </div> |
---|
| 215 | <!--+ |
---|
| 216 | |end Menu |
---|
| 217 | +--> |
---|
| 218 | <!--+ |
---|
| 219 | |start content |
---|
| 220 | +--> |
---|
| 221 | <div id="content"> |
---|
| 222 | <div title="Portable Document Format" class="pdflink"> |
---|
| 223 | <a class="dida" href="quickstart.pdf"><img alt="PDF -icon" src="skin/images/pdfdoc.gif" class="skin"><br> |
---|
| 224 | PDF</a> |
---|
| 225 | </div> |
---|
| 226 | <h1>Quick Start</h1> |
---|
| 227 | <div id="minitoc-area"> |
---|
| 228 | <ul class="minitoc"> |
---|
| 229 | <li> |
---|
| 230 | <a href="#Purpose">Purpose</a> |
---|
| 231 | </li> |
---|
| 232 | <li> |
---|
| 233 | <a href="#PreReqs">Pre-requisites</a> |
---|
| 234 | <ul class="minitoc"> |
---|
| 235 | <li> |
---|
| 236 | <a href="#Supported+Platforms">Supported Platforms</a> |
---|
| 237 | </li> |
---|
| 238 | <li> |
---|
| 239 | <a href="#Required+Software">Required Software</a> |
---|
| 240 | </li> |
---|
| 241 | <li> |
---|
| 242 | <a href="#Installing+Software">Installing Software</a> |
---|
| 243 | </li> |
---|
| 244 | </ul> |
---|
| 245 | </li> |
---|
| 246 | <li> |
---|
| 247 | <a href="#Download">Download</a> |
---|
| 248 | </li> |
---|
| 249 | <li> |
---|
| 250 | <a href="#Prepare+to+Start+the+Hadoop+Cluster">Prepare to Start the Hadoop Cluster</a> |
---|
| 251 | </li> |
---|
| 252 | <li> |
---|
| 253 | <a href="#Local">Standalone Operation</a> |
---|
| 254 | </li> |
---|
| 255 | <li> |
---|
| 256 | <a href="#PseudoDistributed">Pseudo-Distributed Operation</a> |
---|
| 257 | <ul class="minitoc"> |
---|
| 258 | <li> |
---|
| 259 | <a href="#Configuration">Configuration</a> |
---|
| 260 | </li> |
---|
| 261 | <li> |
---|
| 262 | <a href="#Setup+passphraseless">Setup passphraseless ssh</a> |
---|
| 263 | </li> |
---|
| 264 | <li> |
---|
| 265 | <a href="#Execution">Execution</a> |
---|
| 266 | </li> |
---|
| 267 | </ul> |
---|
| 268 | </li> |
---|
| 269 | <li> |
---|
| 270 | <a href="#FullyDistributed">Fully-Distributed Operation</a> |
---|
| 271 | </li> |
---|
| 272 | </ul> |
---|
| 273 | </div> |
---|
| 274 | |
---|
| 275 | |
---|
| 276 | <a name="N1000D"></a><a name="Purpose"></a> |
---|
| 277 | <h2 class="h3">Purpose</h2> |
---|
| 278 | <div class="section"> |
---|
| 279 | <p>The purpose of this document is to help you get a single-node Hadoop |
---|
| 280 | installation up and running very quickly so that you can get a flavour |
---|
| 281 | of the Hadoop Distributed File System |
---|
| 282 | (see <a href="hdfs_design.html"> <acronym title="Hadoop Distributed File System">HDFS</acronym> Architecture</a>) and |
---|
| 283 | the Map/Reduce framework; that is, perform simple operations on HDFS and |
---|
| 284 | run example jobs.</p> |
---|
| 285 | </div> |
---|
| 286 | |
---|
| 287 | |
---|
| 288 | <a name="N1001F"></a><a name="PreReqs"></a> |
---|
| 289 | <h2 class="h3">Pre-requisites</h2> |
---|
| 290 | <div class="section"> |
---|
| 291 | <a name="N10025"></a><a name="Supported+Platforms"></a> |
---|
| 292 | <h3 class="h4">Supported Platforms</h3> |
---|
| 293 | <ul> |
---|
| 294 | |
---|
| 295 | <li> |
---|
| 296 | GNU/Linux is supported as a development and production platform. |
---|
| 297 | Hadoop has been demonstrated on GNU/Linux clusters with 2000 nodes. |
---|
| 298 | </li> |
---|
| 299 | |
---|
| 300 | <li> |
---|
| 301 | Win32 is supported as a <em>development platform</em>. Distributed |
---|
| 302 | operation has not been well tested on Win32, so it is not |
---|
| 303 | supported as a <em>production platform</em>. |
---|
| 304 | </li> |
---|
| 305 | |
---|
| 306 | </ul> |
---|
| 307 | <a name="N1003B"></a><a name="Required+Software"></a> |
---|
| 308 | <h3 class="h4">Required Software</h3> |
---|
| 309 | <p>Required software for Linux and Windows include:</p> |
---|
| 310 | <ol> |
---|
| 311 | |
---|
| 312 | <li> |
---|
| 313 | Java<sup>TM</sup> 1.6.x, preferably from Sun, must be installed. |
---|
| 314 | </li> |
---|
| 315 | |
---|
| 316 | <li> |
---|
| 317 | |
---|
| 318 | <strong>ssh</strong> must be installed and <strong>sshd</strong> must |
---|
| 319 | be running to use the Hadoop scripts that manage remote Hadoop |
---|
| 320 | daemons. |
---|
| 321 | </li> |
---|
| 322 | |
---|
| 323 | </ol> |
---|
| 324 | <p>Additional requirements for Windows include:</p> |
---|
| 325 | <ol> |
---|
| 326 | |
---|
| 327 | <li> |
---|
| 328 | |
---|
| 329 | <a href="http://www.cygwin.com/">Cygwin</a> - Required for shell |
---|
| 330 | support in addition to the required software above. |
---|
| 331 | </li> |
---|
| 332 | |
---|
| 333 | </ol> |
---|
| 334 | <a name="N10064"></a><a name="Installing+Software"></a> |
---|
| 335 | <h3 class="h4">Installing Software</h3> |
---|
| 336 | <p>If your cluster doesn't have the requisite software you will need to |
---|
| 337 | install it.</p> |
---|
| 338 | <p>For example on Ubuntu Linux:</p> |
---|
| 339 | <p> |
---|
| 340 | |
---|
| 341 | <span class="codefrag">$ sudo apt-get install ssh</span> |
---|
| 342 | <br> |
---|
| 343 | |
---|
| 344 | <span class="codefrag">$ sudo apt-get install rsync</span> |
---|
| 345 | |
---|
| 346 | </p> |
---|
| 347 | <p>On Windows, if you did not install the required software when you |
---|
| 348 | installed cygwin, start the cygwin installer and select the packages:</p> |
---|
| 349 | <ul> |
---|
| 350 | |
---|
| 351 | <li>openssh - the <em>Net</em> category</li> |
---|
| 352 | |
---|
| 353 | </ul> |
---|
| 354 | </div> |
---|
| 355 | |
---|
| 356 | |
---|
| 357 | <a name="N10088"></a><a name="Download"></a> |
---|
| 358 | <h2 class="h3">Download</h2> |
---|
| 359 | <div class="section"> |
---|
| 360 | <p> |
---|
| 361 | To get a Hadoop distribution, download a recent |
---|
| 362 | <a href="http://hadoop.apache.org/core/releases.html">stable release</a> from one of the Apache Download |
---|
| 363 | Mirrors. |
---|
| 364 | </p> |
---|
| 365 | </div> |
---|
| 366 | |
---|
| 367 | |
---|
| 368 | <a name="N10096"></a><a name="Prepare+to+Start+the+Hadoop+Cluster"></a> |
---|
| 369 | <h2 class="h3">Prepare to Start the Hadoop Cluster</h2> |
---|
| 370 | <div class="section"> |
---|
| 371 | <p> |
---|
| 372 | Unpack the downloaded Hadoop distribution. In the distribution, edit the |
---|
| 373 | file <span class="codefrag">conf/hadoop-env.sh</span> to define at least |
---|
| 374 | <span class="codefrag">JAVA_HOME</span> to be the root of your Java installation. |
---|
| 375 | </p> |
---|
| 376 | <p> |
---|
| 377 | Try the following command:<br> |
---|
| 378 | |
---|
| 379 | <span class="codefrag">$ bin/hadoop</span> |
---|
| 380 | <br> |
---|
| 381 | This will display the usage documentation for the <strong>hadoop</strong> |
---|
| 382 | script. |
---|
| 383 | </p> |
---|
| 384 | <p>Now you are ready to start your Hadoop cluster in one of the three supported |
---|
| 385 | modes: |
---|
| 386 | </p> |
---|
| 387 | <ul> |
---|
| 388 | |
---|
| 389 | <li>Local (Standalone) Mode</li> |
---|
| 390 | |
---|
| 391 | <li>Pseudo-Distributed Mode</li> |
---|
| 392 | |
---|
| 393 | <li>Fully-Distributed Mode</li> |
---|
| 394 | |
---|
| 395 | </ul> |
---|
| 396 | </div> |
---|
| 397 | |
---|
| 398 | |
---|
| 399 | <a name="N100C1"></a><a name="Local"></a> |
---|
| 400 | <h2 class="h3">Standalone Operation</h2> |
---|
| 401 | <div class="section"> |
---|
| 402 | <p>By default, Hadoop is configured to run in a non-distributed |
---|
| 403 | mode, as a single Java process. This is useful for debugging.</p> |
---|
| 404 | <p> |
---|
| 405 | The following example copies the unpacked <span class="codefrag">conf</span> directory to |
---|
| 406 | use as input and then finds and displays every match of the given regular |
---|
| 407 | expression. Output is written to the given <span class="codefrag">output</span> directory. |
---|
| 408 | <br> |
---|
| 409 | |
---|
| 410 | <span class="codefrag">$ mkdir input</span> |
---|
| 411 | <br> |
---|
| 412 | |
---|
| 413 | <span class="codefrag">$ cp conf/*.xml input</span> |
---|
| 414 | <br> |
---|
| 415 | |
---|
| 416 | <span class="codefrag"> |
---|
| 417 | $ bin/hadoop jar hadoop-*-examples.jar grep input output 'dfs[a-z.]+' |
---|
| 418 | </span> |
---|
| 419 | <br> |
---|
| 420 | |
---|
| 421 | <span class="codefrag">$ cat output/*</span> |
---|
| 422 | |
---|
| 423 | </p> |
---|
| 424 | </div> |
---|
| 425 | |
---|
| 426 | |
---|
| 427 | <a name="N100E5"></a><a name="PseudoDistributed"></a> |
---|
| 428 | <h2 class="h3">Pseudo-Distributed Operation</h2> |
---|
| 429 | <div class="section"> |
---|
| 430 | <p>Hadoop can also be run on a single-node in a pseudo-distributed mode |
---|
| 431 | where each Hadoop daemon runs in a separate Java process.</p> |
---|
| 432 | <a name="N100EE"></a><a name="Configuration"></a> |
---|
| 433 | <h3 class="h4">Configuration</h3> |
---|
| 434 | <p>Use the following: |
---|
| 435 | <br> |
---|
| 436 | |
---|
| 437 | <span class="codefrag">conf/core-site.xml</span>:</p> |
---|
| 438 | <table class="ForrestTable" cellspacing="1" cellpadding="4"> |
---|
| 439 | |
---|
| 440 | <tr> |
---|
| 441 | <td colspan="1" rowspan="1"><configuration></td> |
---|
| 442 | </tr> |
---|
| 443 | |
---|
| 444 | |
---|
| 445 | <tr> |
---|
| 446 | <td colspan="1" rowspan="1"> <property></td> |
---|
| 447 | </tr> |
---|
| 448 | |
---|
| 449 | <tr> |
---|
| 450 | <td colspan="1" rowspan="1"> <name>fs.default.name</name></td> |
---|
| 451 | </tr> |
---|
| 452 | |
---|
| 453 | <tr> |
---|
| 454 | <td colspan="1" rowspan="1"> <value>hdfs://localhost:9000</value></td> |
---|
| 455 | </tr> |
---|
| 456 | |
---|
| 457 | <tr> |
---|
| 458 | <td colspan="1" rowspan="1"> </property></td> |
---|
| 459 | </tr> |
---|
| 460 | |
---|
| 461 | |
---|
| 462 | <tr> |
---|
| 463 | <td colspan="1" rowspan="1"></configuration></td> |
---|
| 464 | </tr> |
---|
| 465 | |
---|
| 466 | </table> |
---|
| 467 | <p> |
---|
| 468 | <br> |
---|
| 469 | <span class="codefrag">conf/hdfs-site.xml</span>:</p> |
---|
| 470 | <table class="ForrestTable" cellspacing="1" cellpadding="4"> |
---|
| 471 | |
---|
| 472 | <tr> |
---|
| 473 | <td colspan="1" rowspan="1"><configuration></td> |
---|
| 474 | </tr> |
---|
| 475 | |
---|
| 476 | |
---|
| 477 | <tr> |
---|
| 478 | <td colspan="1" rowspan="1"> <property></td> |
---|
| 479 | </tr> |
---|
| 480 | |
---|
| 481 | <tr> |
---|
| 482 | <td colspan="1" rowspan="1"> <name>dfs.replication</name></td> |
---|
| 483 | </tr> |
---|
| 484 | |
---|
| 485 | <tr> |
---|
| 486 | <td colspan="1" rowspan="1"> <value>1</value></td> |
---|
| 487 | </tr> |
---|
| 488 | |
---|
| 489 | <tr> |
---|
| 490 | <td colspan="1" rowspan="1"> </property></td> |
---|
| 491 | </tr> |
---|
| 492 | |
---|
| 493 | |
---|
| 494 | <tr> |
---|
| 495 | <td colspan="1" rowspan="1"></configuration></td> |
---|
| 496 | </tr> |
---|
| 497 | |
---|
| 498 | </table> |
---|
| 499 | <p> |
---|
| 500 | <br> |
---|
| 501 | <span class="codefrag">conf/mapred-site.xml</span>:</p> |
---|
| 502 | <table class="ForrestTable" cellspacing="1" cellpadding="4"> |
---|
| 503 | |
---|
| 504 | <tr> |
---|
| 505 | <td colspan="1" rowspan="1"><configuration></td> |
---|
| 506 | </tr> |
---|
| 507 | |
---|
| 508 | |
---|
| 509 | <tr> |
---|
| 510 | <td colspan="1" rowspan="1"> <property></td> |
---|
| 511 | </tr> |
---|
| 512 | |
---|
| 513 | <tr> |
---|
| 514 | <td colspan="1" rowspan="1"> <name>mapred.job.tracker</name></td> |
---|
| 515 | </tr> |
---|
| 516 | |
---|
| 517 | <tr> |
---|
| 518 | <td colspan="1" rowspan="1"> <value>localhost:9001</value></td> |
---|
| 519 | </tr> |
---|
| 520 | |
---|
| 521 | <tr> |
---|
| 522 | <td colspan="1" rowspan="1"> </property></td> |
---|
| 523 | </tr> |
---|
| 524 | |
---|
| 525 | |
---|
| 526 | <tr> |
---|
| 527 | <td colspan="1" rowspan="1"></configuration></td> |
---|
| 528 | </tr> |
---|
| 529 | |
---|
| 530 | </table> |
---|
| 531 | <a name="N1017E"></a><a name="Setup+passphraseless"></a> |
---|
| 532 | <h3 class="h4">Setup passphraseless ssh</h3> |
---|
| 533 | <p> |
---|
| 534 | Now check that you can ssh to the localhost without a passphrase:<br> |
---|
| 535 | |
---|
| 536 | <span class="codefrag">$ ssh localhost</span> |
---|
| 537 | |
---|
| 538 | </p> |
---|
| 539 | <p> |
---|
| 540 | If you cannot ssh to localhost without a passphrase, execute the |
---|
| 541 | following commands:<br> |
---|
| 542 | |
---|
| 543 | <span class="codefrag">$ ssh-keygen -t dsa -P '' -f ~/.ssh/id_dsa</span> |
---|
| 544 | <br> |
---|
| 545 | |
---|
| 546 | <span class="codefrag">$ cat ~/.ssh/id_dsa.pub >> ~/.ssh/authorized_keys</span> |
---|
| 547 | |
---|
| 548 | </p> |
---|
| 549 | <a name="N1019B"></a><a name="Execution"></a> |
---|
| 550 | <h3 class="h4">Execution</h3> |
---|
| 551 | <p> |
---|
| 552 | Format a new distributed-filesystem:<br> |
---|
| 553 | |
---|
| 554 | <span class="codefrag">$ bin/hadoop namenode -format</span> |
---|
| 555 | |
---|
| 556 | </p> |
---|
| 557 | <p> |
---|
| 558 | Start the hadoop daemons:<br> |
---|
| 559 | |
---|
| 560 | <span class="codefrag">$ bin/start-all.sh</span> |
---|
| 561 | |
---|
| 562 | </p> |
---|
| 563 | <p>The hadoop daemon log output is written to the |
---|
| 564 | <span class="codefrag">${HADOOP_LOG_DIR}</span> directory (defaults to |
---|
| 565 | <span class="codefrag">${HADOOP_HOME}/logs</span>).</p> |
---|
| 566 | <p>Browse the web interface for the NameNode and the JobTracker; by |
---|
| 567 | default they are available at:</p> |
---|
| 568 | <ul> |
---|
| 569 | |
---|
| 570 | <li> |
---|
| 571 | |
---|
| 572 | <span class="codefrag">NameNode</span> - |
---|
| 573 | <a href="http://localhost:50070/">http://localhost:50070/</a> |
---|
| 574 | |
---|
| 575 | </li> |
---|
| 576 | |
---|
| 577 | <li> |
---|
| 578 | |
---|
| 579 | <span class="codefrag">JobTracker</span> - |
---|
| 580 | <a href="http://localhost:50030/">http://localhost:50030/</a> |
---|
| 581 | |
---|
| 582 | </li> |
---|
| 583 | |
---|
| 584 | </ul> |
---|
| 585 | <p> |
---|
| 586 | Copy the input files into the distributed filesystem:<br> |
---|
| 587 | |
---|
| 588 | <span class="codefrag">$ bin/hadoop fs -put conf input</span> |
---|
| 589 | |
---|
| 590 | </p> |
---|
| 591 | <p> |
---|
| 592 | Run some of the examples provided:<br> |
---|
| 593 | |
---|
| 594 | <span class="codefrag"> |
---|
| 595 | $ bin/hadoop jar hadoop-*-examples.jar grep input output 'dfs[a-z.]+' |
---|
| 596 | </span> |
---|
| 597 | |
---|
| 598 | </p> |
---|
| 599 | <p>Examine the output files:</p> |
---|
| 600 | <p> |
---|
| 601 | Copy the output files from the distributed filesystem to the local |
---|
| 602 | filesytem and examine them:<br> |
---|
| 603 | |
---|
| 604 | <span class="codefrag">$ bin/hadoop fs -get output output</span> |
---|
| 605 | <br> |
---|
| 606 | |
---|
| 607 | <span class="codefrag">$ cat output/*</span> |
---|
| 608 | |
---|
| 609 | </p> |
---|
| 610 | <p> or </p> |
---|
| 611 | <p> |
---|
| 612 | View the output files on the distributed filesystem:<br> |
---|
| 613 | |
---|
| 614 | <span class="codefrag">$ bin/hadoop fs -cat output/*</span> |
---|
| 615 | |
---|
| 616 | </p> |
---|
| 617 | <p> |
---|
| 618 | When you're done, stop the daemons with:<br> |
---|
| 619 | |
---|
| 620 | <span class="codefrag">$ bin/stop-all.sh</span> |
---|
| 621 | |
---|
| 622 | </p> |
---|
| 623 | </div> |
---|
| 624 | |
---|
| 625 | |
---|
| 626 | <a name="N10208"></a><a name="FullyDistributed"></a> |
---|
| 627 | <h2 class="h3">Fully-Distributed Operation</h2> |
---|
| 628 | <div class="section"> |
---|
| 629 | <p>For information on setting up fully-distributed, non-trivial clusters |
---|
| 630 | see <a href="cluster_setup.html">Hadoop Cluster Setup</a>.</p> |
---|
| 631 | </div> |
---|
| 632 | |
---|
| 633 | |
---|
| 634 | <p> |
---|
| 635 | |
---|
| 636 | <em>Java and JNI are trademarks or registered trademarks of |
---|
| 637 | Sun Microsystems, Inc. in the United States and other countries.</em> |
---|
| 638 | |
---|
| 639 | </p> |
---|
| 640 | |
---|
| 641 | |
---|
| 642 | </div> |
---|
| 643 | <!--+ |
---|
| 644 | |end content |
---|
| 645 | +--> |
---|
| 646 | <div class="clearboth"> </div> |
---|
| 647 | </div> |
---|
| 648 | <div id="footer"> |
---|
| 649 | <!--+ |
---|
| 650 | |start bottomstrip |
---|
| 651 | +--> |
---|
| 652 | <div class="lastmodified"> |
---|
| 653 | <script type="text/javascript"><!-- |
---|
| 654 | document.write("Last Published: " + document.lastModified); |
---|
| 655 | // --></script> |
---|
| 656 | </div> |
---|
| 657 | <div class="copyright"> |
---|
| 658 | Copyright © |
---|
| 659 | 2008 <a href="http://www.apache.org/licenses/">The Apache Software Foundation.</a> |
---|
| 660 | </div> |
---|
| 661 | <!--+ |
---|
| 662 | |end bottomstrip |
---|
| 663 | +--> |
---|
| 664 | </div> |
---|
| 665 | </body> |
---|
| 666 | </html> |
---|