<!DOCTYPE html> <!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--> <!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]--> <head> <meta charset="utf-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>Cluster Training Using Fabric — PaddlePaddle documentation</title> <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> <link rel="index" title="Index" href="../../../genindex.html"/> <link rel="search" title="Search" href="../../../search.html"/> <link rel="top" title="PaddlePaddle documentation" href="../../../index.html"/> <link rel="up" title="Distributed Training" href="cluster_train_en.html"/> <link rel="next" title="Cluster Training Using OpenMPI" href="openmpi_en.html"/> <link rel="prev" title="Distributed Training" href="cluster_train_en.html"/> <link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" /> <link rel="stylesheet" href="../../../_static/css/override.css" type="text/css" /> <script> var _hmt = _hmt || []; (function() { var hm = document.createElement("script"); hm.src = "//hm.baidu.com/hm.js?b9a314ab40d04d805655aab1deee08ba"; var s = document.getElementsByTagName("script")[0]; s.parentNode.insertBefore(hm, s); })(); </script> <script src="../../../_static/js/modernizr.min.js"></script> </head> <body class="wy-body-for-nav" role="document"> <header class="site-header"> <div class="site-logo"> <a href="/"><img src="../../../_static/images/PP_w.png"></a> </div> <div class="site-nav-links"> <div class="site-menu"> <a class="fork-on-github" href="https://github.com/PaddlePaddle/Paddle" target="_blank"><i class="fa fa-github"></i>Fork me on Github</a> <div class="language-switcher dropdown"> <a type="button" data-toggle="dropdown"> <span>English</span> <i class="fa fa-angle-up"></i> <i class="fa fa-angle-down"></i> </a> <ul class="dropdown-menu"> <li><a href="/doc_cn">中文</a></li> <li><a href="/doc">English</a></li> </ul> </div> <ul class="site-page-links"> <li><a href="/">Home</a></li> </ul> </div> <div class="doc-module"> <ul class="current"> <li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a></li> <li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">HOW TO</a></li> <li class="toctree-l1"><a class="reference internal" href="../../../api/index_en.html">API</a></li> <li class="toctree-l1"><a class="reference internal" href="../../../mobile/index_en.html">MOBILE</a></li> </ul> <div role="search"> <form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get"> <input type="text" name="q" placeholder="Search docs" /> <input type="hidden" name="check_keywords" value="yes" /> <input type="hidden" name="area" value="default" /> </form> </div> </div> </div> </header> <div class="main-content-wrap"> <nav class="doc-menu-vertical" role="navigation"> <ul class="current"> <li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a><ul> <li class="toctree-l2"><a class="reference internal" href="../../../getstarted/build_and_install/index_en.html">Install and Build</a><ul> <li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/pip_install_en.html">Install Using pip</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/docker_install_en.html">Run in Docker Containers</a></li> <li class="toctree-l3"><a class="reference internal" href="../../dev/build_en.html">Build using Docker</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/build_from_source_en.html">Build from Sources</a></li> </ul> </li> </ul> </li> <li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">HOW TO</a><ul class="current"> <li class="toctree-l2"><a class="reference internal" href="../cmd_parameter/index_en.html">Set Command-line Parameters</a><ul> <li class="toctree-l3"><a class="reference internal" href="../cmd_parameter/use_case_en.html">Use Case</a></li> <li class="toctree-l3"><a class="reference internal" href="../cmd_parameter/arguments_en.html">Argument Outline</a></li> <li class="toctree-l3"><a class="reference internal" href="../cmd_parameter/detail_introduction_en.html">Detail Description</a></li> </ul> </li> <li class="toctree-l2 current"><a class="reference internal" href="cluster_train_en.html">Distributed Training</a><ul class="current"> <li class="toctree-l3 current"><a class="current reference internal" href="#">fabric</a></li> <li class="toctree-l3"><a class="reference internal" href="openmpi_en.html">openmpi</a></li> <li class="toctree-l3"><a class="reference internal" href="k8s_en.html">kubernetes</a></li> <li class="toctree-l3"><a class="reference internal" href="k8s_aws_en.html">kubernetes on AWS</a></li> </ul> </li> <li class="toctree-l2"><a class="reference internal" href="../../dev/new_layer_en.html">Write New Layers</a></li> <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_en.html">Contribute Code</a></li> <li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_en.html">Contribute Documentation</a></li> <li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a><ul> <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li> </ul> </li> <li class="toctree-l2"><a class="reference internal" href="../../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li> </ul> </li> <li class="toctree-l1"><a class="reference internal" href="../../../api/index_en.html">API</a><ul> <li class="toctree-l2"><a class="reference internal" href="../../../api/v2/model_configs.html">Model Configuration</a><ul> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/config/activation.html">Activation</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/config/layer.html">Layers</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/config/evaluators.html">Evaluators</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/config/optimizer.html">Optimizer</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/config/pooling.html">Pooling</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/config/networks.html">Networks</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/config/attr.html">Parameter Attribute</a></li> </ul> </li> <li class="toctree-l2"><a class="reference internal" href="../../../api/v2/data.html">Data Reader Interface and DataSets</a><ul> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/data/data_reader.html">Data Reader Interface</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/data/image.html">Image Interface</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/data/dataset.html">Dataset</a></li> </ul> </li> <li class="toctree-l2"><a class="reference internal" href="../../../api/v2/run_logic.html">Training and Inference</a></li> <li class="toctree-l2"><a class="reference internal" href="../../../api/v2/fluid.html">Fluid</a><ul> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/fluid/layers.html">Layers</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/fluid/data_feeder.html">DataFeeder</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/fluid/executor.html">Executor</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/fluid/initializer.html">Initializer</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/fluid/evaluator.html">Evaluator</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/fluid/nets.html">Nets</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/fluid/optimizer.html">Optimizer</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/fluid/param_attr.html">ParamAttr</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/fluid/profiler.html">Profiler</a></li> <li class="toctree-l3"><a class="reference internal" href="../../../api/v2/fluid/regularizer.html">Regularizer</a></li> </ul> </li> </ul> </li> <li class="toctree-l1"><a class="reference internal" href="../../../mobile/index_en.html">MOBILE</a><ul> <li class="toctree-l2"><a class="reference internal" href="../../../mobile/cross_compiling_for_android_en.html">Build PaddlePaddle for Android</a></li> <li class="toctree-l2"><a class="reference internal" href="../../../mobile/cross_compiling_for_ios_en.html">PaddlePaddle Compiling Guide for iOS</a></li> <li class="toctree-l2"><a class="reference internal" href="../../../mobile/cross_compiling_for_raspberry_en.html">Build PaddlePaddle for Raspberry Pi</a></li> </ul> </li> </ul> </nav> <section class="doc-content-wrap"> <div role="navigation" aria-label="breadcrumbs navigation"> <ul class="wy-breadcrumbs"> <li><a href="../../index_en.html">HOW TO</a> > </li> <li><a href="cluster_train_en.html">Distributed Training</a> > </li> <li>Cluster Training Using Fabric</li> </ul> </div> <div class="wy-nav-content" id="doc-content"> <div class="rst-content"> <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> <div itemprop="articleBody"> <div class="section" id="cluster-training-using-fabric"> <span id="cluster-training-using-fabric"></span><h1>Cluster Training Using Fabric<a class="headerlink" href="#cluster-training-using-fabric" title="Permalink to this headline">¶</a></h1> <div class="section" id="prepare-a-linux-cluster"> <span id="prepare-a-linux-cluster"></span><h2>Prepare a Linux cluster<a class="headerlink" href="#prepare-a-linux-cluster" title="Permalink to this headline">¶</a></h2> <p>Run <code class="docutils literal"><span class="pre">kubectl</span> <span class="pre">-f</span> <span class="pre">ssh_servers.yaml</span></code> under the directory: <code class="docutils literal"><span class="pre">paddle/scripts/cluster_train_v2/fabric/docker_cluster</span></code> will launch a demo cluster. Run <code class="docutils literal"><span class="pre">kubectl</span> <span class="pre">get</span> <span class="pre">po</span> <span class="pre">-o</span> <span class="pre">wide</span></code> to get IP addresses of these nodes.</p> </div> <div class="section" id="launching-cluster-job"> <span id="launching-cluster-job"></span><h2>Launching Cluster Job<a class="headerlink" href="#launching-cluster-job" title="Permalink to this headline">¶</a></h2> <p><code class="docutils literal"><span class="pre">paddle.py</span></code> provides automatical scripts to start all PaddlePaddle cluster processes in different nodes. By default, all command line options can be set as <code class="docutils literal"><span class="pre">paddle.py</span></code> command options and <code class="docutils literal"><span class="pre">paddle.py</span></code> will transparently and automatically set these options to PaddlePaddle lower level processes.</p> <p><code class="docutils literal"><span class="pre">paddle.py</span></code>provides two distinguished command option for easy job launching.</p> <ul class="simple"> <li><code class="docutils literal"><span class="pre">job_dispatch_package</span></code> set it with local <code class="docutils literal"><span class="pre">workspace</span></code> directory, it will be dispatched to all nodes which is set in <code class="docutils literal"><span class="pre">conf.py</span></code>. It could be helpful for frequently manipulating workspace files. otherwise, frequent multi-nodes workspace deployment is very annoying.</li> <li><code class="docutils literal"><span class="pre">job_workspace</span></code> set it with already deployed workspace directory, <code class="docutils literal"><span class="pre">paddle.py</span></code> will skip dispatch stage to directly launch cluster job with all nodes. It could help to reduce heavy dispatch latency.</li> </ul> <p><code class="docutils literal"><span class="pre">cluster_train/run.sh</span></code> provides command line sample to run <code class="docutils literal"><span class="pre">demo/recommendation</span></code> cluster job, just modify <code class="docutils literal"><span class="pre">job_dispatch_package</span></code> and <code class="docutils literal"><span class="pre">job_workspace</span></code> with your defined directory, then:</p> <div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">sh</span> <span class="n">run</span><span class="o">.</span><span class="n">sh</span> </pre></div> </div> <p>The cluster Job will start in several seconds.</p> </div> <div class="section" id="kill-cluster-job"> <span id="kill-cluster-job"></span><h2>Kill Cluster Job<a class="headerlink" href="#kill-cluster-job" title="Permalink to this headline">¶</a></h2> <p><code class="docutils literal"><span class="pre">paddle.py</span></code> can capture <code class="docutils literal"><span class="pre">Ctrl</span> <span class="pre">+</span> <span class="pre">C</span></code> SIGINT signal to automatically kill all processes launched by it. So just stop <code class="docutils literal"><span class="pre">paddle.py</span></code> to kill cluster job. You should manually kill the job if the program crashed.</p> </div> <div class="section" id="check-cluster-training-result"> <span id="check-cluster-training-result"></span><h2>Check Cluster Training Result<a class="headerlink" href="#check-cluster-training-result" title="Permalink to this headline">¶</a></h2> <p>Check log in $workspace/log for details, each node owns same log structure.</p> <p><code class="docutils literal"><span class="pre">paddle_trainer.INFO</span></code> It provides almost all internal output log for training, same as local training. Check runtime model convergence here.</p> <p><code class="docutils literal"><span class="pre">paddle_pserver2.INFO</span></code> It provides parameter server running log, which could help to diagnose distributed error.</p> <p><code class="docutils literal"><span class="pre">server.log</span></code> It provides stderr and stdout of parameter server process. Check error log if training crashes.</p> <p><code class="docutils literal"><span class="pre">train.log</span></code> It provides stderr and stdout of trainer process. Check error log if training crashes.</p> </div> <div class="section" id="check-model-output"> <span id="check-model-output"></span><h2>Check Model Output<a class="headerlink" href="#check-model-output" title="Permalink to this headline">¶</a></h2> <p>After one pass finished, model files will be written in <code class="docutils literal"><span class="pre">output</span></code> directory in node 0. <code class="docutils literal"><span class="pre">nodefile</span></code> in workspace indicates the node id of current cluster job.</p> </div> </div> </div> </div> <footer> <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> <a href="openmpi_en.html" class="btn btn-neutral float-right" title="Cluster Training Using OpenMPI" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a> <a href="cluster_train_en.html" class="btn btn-neutral" title="Distributed Training" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a> </div> <hr/> <div role="contentinfo"> <p> © Copyright 2016, PaddlePaddle developers. </p> </div> Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. </footer> </div> </div> </section> </div> <script type="text/javascript"> var DOCUMENTATION_OPTIONS = { URL_ROOT:'../../../', VERSION:'', COLLAPSE_INDEX:false, FILE_SUFFIX:'.html', HAS_SOURCE: true, SOURCELINK_SUFFIX: ".txt", }; </script> <script type="text/javascript" src="../../../_static/jquery.js"></script> <script type="text/javascript" src="../../../_static/underscore.js"></script> <script type="text/javascript" src="../../../_static/doctools.js"></script> <script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script> <script type="text/javascript" src="../../../_static/js/theme.js"></script> <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js" integrity="sha384-Tc5IQib027qvyjSMfHjOMaLkfuWVxZxUPnCJA7l2mCWNIpG9mGCD8wGNIcPD7Txa" crossorigin="anonymous"></script> <script src="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/js/perfect-scrollbar.jquery.min.js"></script> <script src="../../../_static/js/paddle_doc_init.js"></script> </body> </html>