openmpi_cn.html



<!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>在OpenMPI集群中启动训练 &mdash; PaddlePaddle  文档</title>
  

    <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
  

        <link rel="index" title="索引"
              href="../../../genindex.html"/>
        <link rel="search" title="搜索" href="../../../search.html"/>
    <link rel="top" title="PaddlePaddle  文档" href="../../../index.html"/>
        <link rel="up" title="在不同集群中运行" href="index_cn.html"/>
        <link rel="next" title="使用fabric启动集群训练" href="fabric_cn.html"/>
        <link rel="prev" title="Kubernetes分布式训练" href="k8s_distributed_cn.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_cn.html">新手入门</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../build_and_install/index_cn.html">安装与编译</a></li>
<li class="toctree-l1 current"><a class="reference internal" href="../../index_cn.html">进阶使用</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../dev/index_cn.html">开发标准</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../faq/index_cn.html">FAQ</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_cn.html">新手入门</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../getstarted/quickstart_cn.html">快速开始</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../getstarted/concepts/use_concepts_cn.html">基本使用概念</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../build_and_install/index_cn.html">安装与编译</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../build_and_install/pip_install_cn.html">使用pip安装</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../build_and_install/docker_install_cn.html">使用Docker安装运行</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../build_and_install/build_from_source_cn.html">从源码编译</a></li>
</ul>
</li>
<li class="toctree-l1 current"><a class="reference internal" href="../../index_cn.html">进阶使用</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../../cmd_parameter/index_cn.html">命令行参数设置</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../cmd_parameter/use_case_cn.html">使用案例</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../cmd_parameter/arguments_cn.html">参数概述</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../cmd_parameter/detail_introduction_cn.html">细节描述</a></li>
</ul>
</li>
<li class="toctree-l2 current"><a class="reference internal" href="../index_cn.html">分布式训练</a><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="../preparations_cn.html">环境准备</a></li>
<li class="toctree-l3"><a class="reference internal" href="../cmd_argument_cn.html">启动参数说明</a></li>
<li class="toctree-l3 current"><a class="reference internal" href="index_cn.html">在不同集群中运行</a><ul class="current">
<li class="toctree-l4"><a class="reference internal" href="k8s_cn.html">Kubernetes单机训练</a></li>
<li class="toctree-l4"><a class="reference internal" href="k8s_distributed_cn.html">Kubernetes分布式训练</a></li>
<li class="toctree-l4 current"><a class="current reference internal" href="#">在OpenMPI集群中启动训练</a></li>
<li class="toctree-l4"><a class="reference internal" href="fabric_cn.html">使用fabric启动集群训练</a></li>
<li class="toctree-l4"><a class="reference internal" href="k8s_aws_cn.html">Kubernetes on AWS</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../capi/index_cn.html">C-API预测库</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../capi/compile_paddle_lib_cn.html">安装与编译C-API预测库</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../capi/organization_of_the_inputs_cn.html">输入/输出数据组织</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../capi/workflow_of_capi_cn.html">C-API使用流程</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../rnn/index_cn.html">RNN模型</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../rnn/rnn_config_cn.html">RNN配置</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../optimization/gpu_profiling_cn.html">GPU性能调优</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../dev/index_cn.html">开发标准</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../dev/write_docs_cn.html">如何贡献文档</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../faq/index_cn.html">FAQ</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../faq/build_and_install/index_cn.html">编译安装与单元测试</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../faq/model/index_cn.html">模型配置</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../faq/parameter/index_cn.html">参数设置</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../faq/local/index_cn.html">本地训练与预测</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../faq/cluster/index_cn.html">集群训练与预测</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_cn.html">进阶使用</a> > </li>
      
        <li><a href="../index_cn.html">分布式训练</a> > </li>
      
        <li><a href="index_cn.html">在不同集群中运行</a> > </li>
      
    <li>在OpenMPI集群中启动训练</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="openmpi">
<span id="openmpi"></span><h1>在OpenMPI集群中启动训练<a class="headerlink" href="#openmpi" title="永久链接至标题">¶</a></h1>
<div class="section" id="openmpi">
<span id="id1"></span><h2>准备OpenMPI集群<a class="headerlink" href="#openmpi" title="永久链接至标题">¶</a></h2>
<p>执行下面的命令以启动3个节点的OpenMPI集群和一个&#8221;head&#8221;节点：</p>
<div class="highlight-bash"><div class="highlight"><pre><span></span>paddle/scripts/cluster_train_v2/openmpi/docker_cluster
kubectl create -f head.yaml
kubectl create -f mpi-nodes.yaml
</pre></div>
</div>
<p>然后可以从head节点ssh无密码登录到OpenMPI的每个节点上。</p>
</div>
<div class="section" id="">
<span id="id2"></span><h2>启动集群作业<a class="headerlink" href="#" title="永久链接至标题">¶</a></h2>
<p>您可以按照下面的步骤在OpenMPI集群中提交paddle训练任务：</p>
<div class="highlight-bash"><div class="highlight"><pre><span></span><span class="c1"># 获得head和node节点的IP地址</span>
kubectl get po -o wide
<span class="c1"># 将node节点的IP地址保存到machines文件中</span>
kubectl get po -o wide <span class="p">|</span> grep nodes <span class="p">|</span> awk <span class="s1">&#39;{print $6}&#39;</span> &gt; machines
<span class="c1"># 拷贝必要的文件到head节点</span>
scp -i ssh/id_rsa.mpi.pub machines prepare.py train.py start_mpi_train.sh tutorial@<span class="o">[</span>headIP<span class="o">]</span>:~
<span class="c1"># ssh 登录到head节点</span>
ssh -i ssh/id_rsa.mpi.pub tutorial@<span class="o">[</span>headIP<span class="o">]</span>
<span class="c1"># --------------- 以下操作均在head节点中执行 ---------------</span>
<span class="c1"># 准备训练数据</span>
python prepare.py
<span class="c1"># 拷贝训练程序和字典文件到每台MPI节点</span>
cat machines <span class="p">|</span> xargs -i scp word_dict.pickle train.py start_mpi_train.sh machines <span class="o">{}</span>:/home/tutorial
<span class="c1"># 创建日志目录</span>
mpirun -hostfile machines -n <span class="m">3</span> mkdir /home/tutorial/logs
<span class="c1"># 拷贝训练数据到各自的节点</span>
scp train.txt-00000 test.txt-00000 <span class="o">[</span>node1IP<span class="o">]</span>:/home/tutorial
scp train.txt-00001 test.txt-00001 <span class="o">[</span>node2IP<span class="o">]</span>:/home/tutorial
scp train.txt-00002 test.txt-00002 <span class="o">[</span>node3IP<span class="o">]</span>:/home/tutorial
<span class="c1"># 启动训练任务</span>
mpirun -hostfile machines -n <span class="m">3</span>  /home/tutorial/start_mpi_train.sh
</pre></div>
</div>
</div>
</div>


           </div>
          </div>
          <footer>
  
    <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
      
        <a href="fabric_cn.html" class="btn btn-neutral float-right" title="使用fabric启动集群训练" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
      
      
        <a href="k8s_distributed_cn.html" class="btn btn-neutral" title="Kubernetes分布式训练" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
      
    </div>
  

  <hr/>

  <div role="contentinfo">
    <p>
        &copy; 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="../../../_static/translations.js"></script>
      <script type="text/javascript" src="https://cdn.bootcss.com/mathjax/2.7.0/MathJax.js"></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>