1
0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 19:20:19 +01:00

Add documentation on distributed Coach. (#158)

* Added documentation on distributed Coach.
This commit is contained in:
Balaji Subramaniam
2018-11-27 02:26:15 -08:00
committed by Gal Novik
parent e3ecf445e2
commit d06197f663
151 changed files with 5302 additions and 643 deletions

View File

@@ -0,0 +1,627 @@
<!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>rl_coach.orchestrators.kubernetes_orchestrator &mdash; Reinforcement Learning Coach 0.11.0 documentation</title>
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/css/custom.css" type="text/css" />
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
<script src="../../../_static/js/modernizr.min.js"></script>
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search">
<a href="../../../index.html" class="icon icon-home"> Reinforcement Learning Coach
<img src="../../../_static/dark_logo.png" class="logo" alt="Logo"/>
</a>
<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 class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<p class="caption"><span class="caption-text">Intro</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../usage.html">Usage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../dist_usage.html">Usage - Distributed Coach</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../features/index.html">Features</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../selecting_an_algorithm.html">Selecting an Algorithm</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../dashboard.html">Coach Dashboard</a></li>
</ul>
<p class="caption"><span class="caption-text">Design</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../design/control_flow.html">Control Flow</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../design/network.html">Network Design</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../design/horizontal_scaling.html">Distributed Coach - Horizontal Scale-Out</a></li>
</ul>
<p class="caption"><span class="caption-text">Contributing</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_agent.html">Adding a New Agent</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_env.html">Adding a New Environment</a></li>
</ul>
<p class="caption"><span class="caption-text">Components</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../components/agents/index.html">Agents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/architectures/index.html">Architectures</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/data_stores/index.html">Data Stores</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/environments/index.html">Environments</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/exploration_policies/index.html">Exploration Policies</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/filters/index.html">Filters</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/memories/index.html">Memories</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/memory_backends/index.html">Memory Backends</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/orchestrators/index.html">Orchestrators</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/core_types.html">Core Types</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/spaces.html">Spaces</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../components/additional_parameters.html">Additional Parameters</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../index.html">Reinforcement Learning Coach</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../index.html">Module code</a> &raquo;</li>
<li>rl_coach.orchestrators.kubernetes_orchestrator</li>
<li class="wy-breadcrumbs-aside">
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<h1>Source code for rl_coach.orchestrators.kubernetes_orchestrator</h1><div class="highlight"><pre>
<span></span><span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">uuid</span>
<span class="kn">import</span> <span class="nn">json</span>
<span class="kn">import</span> <span class="nn">time</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">from</span> <span class="nn">enum</span> <span class="k">import</span> <span class="n">Enum</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="k">import</span> <span class="n">List</span>
<span class="kn">from</span> <span class="nn">configparser</span> <span class="k">import</span> <span class="n">ConfigParser</span><span class="p">,</span> <span class="n">Error</span>
<span class="kn">from</span> <span class="nn">multiprocessing</span> <span class="k">import</span> <span class="n">Process</span>
<span class="kn">from</span> <span class="nn">rl_coach.base_parameters</span> <span class="k">import</span> <span class="n">RunType</span>
<span class="kn">from</span> <span class="nn">rl_coach.orchestrators.deploy</span> <span class="k">import</span> <span class="n">Deploy</span><span class="p">,</span> <span class="n">DeployParameters</span>
<span class="kn">from</span> <span class="nn">kubernetes</span> <span class="k">import</span> <span class="n">client</span> <span class="k">as</span> <span class="n">k8sclient</span><span class="p">,</span> <span class="n">config</span> <span class="k">as</span> <span class="n">k8sconfig</span>
<span class="kn">from</span> <span class="nn">rl_coach.memories.backend.memory</span> <span class="k">import</span> <span class="n">MemoryBackendParameters</span>
<span class="kn">from</span> <span class="nn">rl_coach.memories.backend.memory_impl</span> <span class="k">import</span> <span class="n">get_memory_backend</span>
<span class="kn">from</span> <span class="nn">rl_coach.data_stores.data_store</span> <span class="k">import</span> <span class="n">DataStoreParameters</span>
<span class="kn">from</span> <span class="nn">rl_coach.data_stores.data_store_impl</span> <span class="k">import</span> <span class="n">get_data_store</span>
<span class="k">class</span> <span class="nc">RunTypeParameters</span><span class="p">():</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">image</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">command</span><span class="p">:</span> <span class="nb">list</span><span class="p">(),</span> <span class="n">arguments</span><span class="p">:</span> <span class="nb">list</span><span class="p">()</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">run_type</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">RunType</span><span class="o">.</span><span class="n">TRAINER</span><span class="p">),</span> <span class="n">checkpoint_dir</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;/checkpoint&quot;</span><span class="p">,</span>
<span class="n">num_replicas</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span> <span class="n">orchestration_params</span><span class="p">:</span> <span class="nb">dict</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">image</span> <span class="o">=</span> <span class="n">image</span>
<span class="bp">self</span><span class="o">.</span><span class="n">command</span> <span class="o">=</span> <span class="n">command</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">arguments</span><span class="p">:</span>
<span class="n">arguments</span> <span class="o">=</span> <span class="nb">list</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">arguments</span> <span class="o">=</span> <span class="n">arguments</span>
<span class="bp">self</span><span class="o">.</span><span class="n">run_type</span> <span class="o">=</span> <span class="n">run_type</span>
<span class="bp">self</span><span class="o">.</span><span class="n">checkpoint_dir</span> <span class="o">=</span> <span class="n">checkpoint_dir</span>
<span class="bp">self</span><span class="o">.</span><span class="n">num_replicas</span> <span class="o">=</span> <span class="n">num_replicas</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">orchestration_params</span><span class="p">:</span>
<span class="n">orchestration_params</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">orchestration_params</span> <span class="o">=</span> <span class="n">orchestration_params</span>
<span class="k">class</span> <span class="nc">KubernetesParameters</span><span class="p">(</span><span class="n">DeployParameters</span><span class="p">):</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">run_type_params</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">RunTypeParameters</span><span class="p">],</span> <span class="n">kubeconfig</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">namespace</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">nfs_server</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">nfs_path</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">checkpoint_dir</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s1">&#39;/checkpoint&#39;</span><span class="p">,</span>
<span class="n">memory_backend_parameters</span><span class="p">:</span> <span class="n">MemoryBackendParameters</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">data_store_params</span><span class="p">:</span> <span class="n">DataStoreParameters</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">run_type_params</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">for</span> <span class="n">run_type_param</span> <span class="ow">in</span> <span class="n">run_type_params</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">run_type_params</span><span class="p">[</span><span class="n">run_type_param</span><span class="o">.</span><span class="n">run_type</span><span class="p">]</span> <span class="o">=</span> <span class="n">run_type_param</span>
<span class="bp">self</span><span class="o">.</span><span class="n">kubeconfig</span> <span class="o">=</span> <span class="n">kubeconfig</span>
<span class="bp">self</span><span class="o">.</span><span class="n">namespace</span> <span class="o">=</span> <span class="n">namespace</span>
<span class="bp">self</span><span class="o">.</span><span class="n">nfs_server</span> <span class="o">=</span> <span class="n">nfs_server</span>
<span class="bp">self</span><span class="o">.</span><span class="n">nfs_path</span> <span class="o">=</span> <span class="n">nfs_path</span>
<span class="bp">self</span><span class="o">.</span><span class="n">checkpoint_dir</span> <span class="o">=</span> <span class="n">checkpoint_dir</span>
<span class="bp">self</span><span class="o">.</span><span class="n">memory_backend_parameters</span> <span class="o">=</span> <span class="n">memory_backend_parameters</span>
<span class="bp">self</span><span class="o">.</span><span class="n">data_store_params</span> <span class="o">=</span> <span class="n">data_store_params</span>
<div class="viewcode-block" id="Kubernetes"><a class="viewcode-back" href="../../../components/orchestrators/index.html#rl_coach.orchestrators.kubernetes_orchestrator.Kubernetes">[docs]</a><span class="k">class</span> <span class="nc">Kubernetes</span><span class="p">(</span><span class="n">Deploy</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> An orchestrator implmentation which uses Kubernetes to deploy the components such as training and rollout workers</span>
<span class="sd"> and Redis Pub/Sub in Coach when used in the distributed mode.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">params</span><span class="p">:</span> <span class="n">KubernetesParameters</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> :param params: The Kubernetes parameters which are used for deploying the components in Coach. These parameters</span>
<span class="sd"> include namespace and kubeconfig.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">params</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">params</span> <span class="o">=</span> <span class="n">params</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">kubeconfig</span><span class="p">:</span>
<span class="n">k8sconfig</span><span class="o">.</span><span class="n">load_kube_config</span><span class="p">()</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">k8sconfig</span><span class="o">.</span><span class="n">load_incluster_config</span><span class="p">()</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">namespace</span><span class="p">:</span>
<span class="n">_</span><span class="p">,</span> <span class="n">current_context</span> <span class="o">=</span> <span class="n">k8sconfig</span><span class="o">.</span><span class="n">list_kube_config_contexts</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">namespace</span> <span class="o">=</span> <span class="n">current_context</span><span class="p">[</span><span class="s1">&#39;context&#39;</span><span class="p">][</span><span class="s1">&#39;namespace&#39;</span><span class="p">]</span>
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;http_proxy&#39;</span><span class="p">):</span>
<span class="n">k8sclient</span><span class="o">.</span><span class="n">Configuration</span><span class="o">.</span><span class="n">_default</span><span class="o">.</span><span class="n">proxy</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;http_proxy&#39;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">memory_backend_parameters</span><span class="o">.</span><span class="n">orchestrator_params</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;namespace&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">namespace</span><span class="p">}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">memory_backend</span> <span class="o">=</span> <span class="n">get_memory_backend</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">memory_backend_parameters</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">data_store_params</span><span class="o">.</span><span class="n">orchestrator_params</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;namespace&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">namespace</span><span class="p">}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">data_store_params</span><span class="o">.</span><span class="n">namespace</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">namespace</span>
<span class="bp">self</span><span class="o">.</span><span class="n">data_store</span> <span class="o">=</span> <span class="n">get_data_store</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">data_store_params</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">data_store_params</span><span class="o">.</span><span class="n">store_type</span> <span class="o">==</span> <span class="s2">&quot;s3&quot;</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">s3_access_key</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">s3_secret_key</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">data_store_params</span><span class="o">.</span><span class="n">creds_file</span><span class="p">:</span>
<span class="n">s3config</span> <span class="o">=</span> <span class="n">ConfigParser</span><span class="p">()</span>
<span class="n">s3config</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">data_store_params</span><span class="o">.</span><span class="n">creds_file</span><span class="p">)</span>
<span class="k">try</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">s3_access_key</span> <span class="o">=</span> <span class="n">s3config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;default&#39;</span><span class="p">,</span> <span class="s1">&#39;aws_access_key_id&#39;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">s3_secret_key</span> <span class="o">=</span> <span class="n">s3config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;default&#39;</span><span class="p">,</span> <span class="s1">&#39;aws_secret_access_key&#39;</span><span class="p">)</span>
<span class="k">except</span> <span class="n">Error</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Error when reading S3 credentials file: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">s3_access_key</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;ACCESS_KEY_ID&#39;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">s3_secret_key</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;SECRET_ACCESS_KEY&#39;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">setup</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">bool</span><span class="p">:</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Deploys the memory backend and data stores if required.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">memory_backend</span><span class="o">.</span><span class="n">deploy</span><span class="p">()</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_store</span><span class="o">.</span><span class="n">deploy</span><span class="p">():</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">data_store_params</span><span class="o">.</span><span class="n">store_type</span> <span class="o">==</span> <span class="s2">&quot;nfs&quot;</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">nfs_pvc</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_store</span><span class="o">.</span><span class="n">get_info</span><span class="p">()</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="k">def</span> <span class="nf">deploy_trainer</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">bool</span><span class="p">:</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Deploys the training worker in Kubernetes.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">trainer_params</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">run_type_params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">RunType</span><span class="o">.</span><span class="n">TRAINER</span><span class="p">),</span> <span class="kc">None</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">trainer_params</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="n">trainer_params</span><span class="o">.</span><span class="n">command</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">&#39;--memory_backend_params&#39;</span><span class="p">,</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">memory_backend_parameters</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">)]</span>
<span class="n">trainer_params</span><span class="o">.</span><span class="n">command</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">&#39;--data_store_params&#39;</span><span class="p">,</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">data_store_params</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">)]</span>
<span class="n">name</span> <span class="o">=</span> <span class="s2">&quot;</span><span class="si">{}</span><span class="s2">-</span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">trainer_params</span><span class="o">.</span><span class="n">run_type</span><span class="p">,</span> <span class="n">uuid</span><span class="o">.</span><span class="n">uuid4</span><span class="p">())</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">data_store_params</span><span class="o">.</span><span class="n">store_type</span> <span class="o">==</span> <span class="s2">&quot;nfs&quot;</span><span class="p">:</span>
<span class="n">container</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">V1Container</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">,</span>
<span class="n">image</span><span class="o">=</span><span class="n">trainer_params</span><span class="o">.</span><span class="n">image</span><span class="p">,</span>
<span class="n">command</span><span class="o">=</span><span class="n">trainer_params</span><span class="o">.</span><span class="n">command</span><span class="p">,</span>
<span class="n">args</span><span class="o">=</span><span class="n">trainer_params</span><span class="o">.</span><span class="n">arguments</span><span class="p">,</span>
<span class="n">image_pull_policy</span><span class="o">=</span><span class="s1">&#39;Always&#39;</span><span class="p">,</span>
<span class="n">volume_mounts</span><span class="o">=</span><span class="p">[</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1VolumeMount</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="s1">&#39;nfs-pvc&#39;</span><span class="p">,</span>
<span class="n">mount_path</span><span class="o">=</span><span class="n">trainer_params</span><span class="o">.</span><span class="n">checkpoint_dir</span>
<span class="p">)],</span>
<span class="n">stdin</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">tty</span><span class="o">=</span><span class="kc">True</span>
<span class="p">)</span>
<span class="n">template</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">V1PodTemplateSpec</span><span class="p">(</span>
<span class="n">metadata</span><span class="o">=</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1ObjectMeta</span><span class="p">(</span><span class="n">labels</span><span class="o">=</span><span class="p">{</span><span class="s1">&#39;app&#39;</span><span class="p">:</span> <span class="n">name</span><span class="p">}),</span>
<span class="n">spec</span><span class="o">=</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1PodSpec</span><span class="p">(</span>
<span class="n">containers</span><span class="o">=</span><span class="p">[</span><span class="n">container</span><span class="p">],</span>
<span class="n">volumes</span><span class="o">=</span><span class="p">[</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1Volume</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="s2">&quot;nfs-pvc&quot;</span><span class="p">,</span>
<span class="n">persistent_volume_claim</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">nfs_pvc</span>
<span class="p">)],</span>
<span class="n">restart_policy</span><span class="o">=</span><span class="s1">&#39;OnFailure&#39;</span>
<span class="p">),</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">container</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">V1Container</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">,</span>
<span class="n">image</span><span class="o">=</span><span class="n">trainer_params</span><span class="o">.</span><span class="n">image</span><span class="p">,</span>
<span class="n">command</span><span class="o">=</span><span class="n">trainer_params</span><span class="o">.</span><span class="n">command</span><span class="p">,</span>
<span class="n">args</span><span class="o">=</span><span class="n">trainer_params</span><span class="o">.</span><span class="n">arguments</span><span class="p">,</span>
<span class="n">image_pull_policy</span><span class="o">=</span><span class="s1">&#39;Always&#39;</span><span class="p">,</span>
<span class="n">env</span><span class="o">=</span><span class="p">[</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1EnvVar</span><span class="p">(</span><span class="s2">&quot;ACCESS_KEY_ID&quot;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">s3_access_key</span><span class="p">),</span>
<span class="n">k8sclient</span><span class="o">.</span><span class="n">V1EnvVar</span><span class="p">(</span><span class="s2">&quot;SECRET_ACCESS_KEY&quot;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">s3_secret_key</span><span class="p">)],</span>
<span class="n">stdin</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">tty</span><span class="o">=</span><span class="kc">True</span>
<span class="p">)</span>
<span class="n">template</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">V1PodTemplateSpec</span><span class="p">(</span>
<span class="n">metadata</span><span class="o">=</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1ObjectMeta</span><span class="p">(</span><span class="n">labels</span><span class="o">=</span><span class="p">{</span><span class="s1">&#39;app&#39;</span><span class="p">:</span> <span class="n">name</span><span class="p">}),</span>
<span class="n">spec</span><span class="o">=</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1PodSpec</span><span class="p">(</span>
<span class="n">containers</span><span class="o">=</span><span class="p">[</span><span class="n">container</span><span class="p">],</span>
<span class="n">restart_policy</span><span class="o">=</span><span class="s1">&#39;OnFailure&#39;</span>
<span class="p">),</span>
<span class="p">)</span>
<span class="n">job_spec</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">V1JobSpec</span><span class="p">(</span>
<span class="n">completions</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">template</span><span class="o">=</span><span class="n">template</span>
<span class="p">)</span>
<span class="n">job</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">V1Job</span><span class="p">(</span>
<span class="n">api_version</span><span class="o">=</span><span class="s2">&quot;batch/v1&quot;</span><span class="p">,</span>
<span class="n">kind</span><span class="o">=</span><span class="s2">&quot;Job&quot;</span><span class="p">,</span>
<span class="n">metadata</span><span class="o">=</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1ObjectMeta</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">),</span>
<span class="n">spec</span><span class="o">=</span><span class="n">job_spec</span>
<span class="p">)</span>
<span class="n">api_client</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">BatchV1Api</span><span class="p">()</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">api_client</span><span class="o">.</span><span class="n">create_namespaced_job</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">namespace</span><span class="p">,</span> <span class="n">job</span><span class="p">)</span>
<span class="n">trainer_params</span><span class="o">.</span><span class="n">orchestration_params</span><span class="p">[</span><span class="s1">&#39;job_name&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="k">except</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">rest</span><span class="o">.</span><span class="n">ApiException</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Got exception: </span><span class="si">%s</span><span class="se">\n</span><span class="s2"> while creating job&quot;</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="k">def</span> <span class="nf">deploy_worker</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Deploys the rollout worker(s) in Kubernetes.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">worker_params</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">run_type_params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">RunType</span><span class="o">.</span><span class="n">ROLLOUT_WORKER</span><span class="p">),</span> <span class="kc">None</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">worker_params</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="n">worker_params</span><span class="o">.</span><span class="n">command</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">&#39;--memory_backend_params&#39;</span><span class="p">,</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">memory_backend_parameters</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">)]</span>
<span class="n">worker_params</span><span class="o">.</span><span class="n">command</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">&#39;--data_store_params&#39;</span><span class="p">,</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">data_store_params</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">)]</span>
<span class="n">worker_params</span><span class="o">.</span><span class="n">command</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">&#39;--num_workers&#39;</span><span class="p">,</span> <span class="s1">&#39;</span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">worker_params</span><span class="o">.</span><span class="n">num_replicas</span><span class="p">)]</span>
<span class="n">name</span> <span class="o">=</span> <span class="s2">&quot;</span><span class="si">{}</span><span class="s2">-</span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">worker_params</span><span class="o">.</span><span class="n">run_type</span><span class="p">,</span> <span class="n">uuid</span><span class="o">.</span><span class="n">uuid4</span><span class="p">())</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">data_store_params</span><span class="o">.</span><span class="n">store_type</span> <span class="o">==</span> <span class="s2">&quot;nfs&quot;</span><span class="p">:</span>
<span class="n">container</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">V1Container</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">,</span>
<span class="n">image</span><span class="o">=</span><span class="n">worker_params</span><span class="o">.</span><span class="n">image</span><span class="p">,</span>
<span class="n">command</span><span class="o">=</span><span class="n">worker_params</span><span class="o">.</span><span class="n">command</span><span class="p">,</span>
<span class="n">args</span><span class="o">=</span><span class="n">worker_params</span><span class="o">.</span><span class="n">arguments</span><span class="p">,</span>
<span class="n">image_pull_policy</span><span class="o">=</span><span class="s1">&#39;Always&#39;</span><span class="p">,</span>
<span class="n">volume_mounts</span><span class="o">=</span><span class="p">[</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1VolumeMount</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="s1">&#39;nfs-pvc&#39;</span><span class="p">,</span>
<span class="n">mount_path</span><span class="o">=</span><span class="n">worker_params</span><span class="o">.</span><span class="n">checkpoint_dir</span>
<span class="p">)],</span>
<span class="n">stdin</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">tty</span><span class="o">=</span><span class="kc">True</span>
<span class="p">)</span>
<span class="n">template</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">V1PodTemplateSpec</span><span class="p">(</span>
<span class="n">metadata</span><span class="o">=</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1ObjectMeta</span><span class="p">(</span><span class="n">labels</span><span class="o">=</span><span class="p">{</span><span class="s1">&#39;app&#39;</span><span class="p">:</span> <span class="n">name</span><span class="p">}),</span>
<span class="n">spec</span><span class="o">=</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1PodSpec</span><span class="p">(</span>
<span class="n">containers</span><span class="o">=</span><span class="p">[</span><span class="n">container</span><span class="p">],</span>
<span class="n">volumes</span><span class="o">=</span><span class="p">[</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1Volume</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="s2">&quot;nfs-pvc&quot;</span><span class="p">,</span>
<span class="n">persistent_volume_claim</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">nfs_pvc</span>
<span class="p">)],</span>
<span class="n">restart_policy</span><span class="o">=</span><span class="s1">&#39;OnFailure&#39;</span>
<span class="p">),</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">container</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">V1Container</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">,</span>
<span class="n">image</span><span class="o">=</span><span class="n">worker_params</span><span class="o">.</span><span class="n">image</span><span class="p">,</span>
<span class="n">command</span><span class="o">=</span><span class="n">worker_params</span><span class="o">.</span><span class="n">command</span><span class="p">,</span>
<span class="n">args</span><span class="o">=</span><span class="n">worker_params</span><span class="o">.</span><span class="n">arguments</span><span class="p">,</span>
<span class="n">image_pull_policy</span><span class="o">=</span><span class="s1">&#39;Always&#39;</span><span class="p">,</span>
<span class="n">env</span><span class="o">=</span><span class="p">[</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1EnvVar</span><span class="p">(</span><span class="s2">&quot;ACCESS_KEY_ID&quot;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">s3_access_key</span><span class="p">),</span>
<span class="n">k8sclient</span><span class="o">.</span><span class="n">V1EnvVar</span><span class="p">(</span><span class="s2">&quot;SECRET_ACCESS_KEY&quot;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">s3_secret_key</span><span class="p">)],</span>
<span class="n">stdin</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">tty</span><span class="o">=</span><span class="kc">True</span>
<span class="p">)</span>
<span class="n">template</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">V1PodTemplateSpec</span><span class="p">(</span>
<span class="n">metadata</span><span class="o">=</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1ObjectMeta</span><span class="p">(</span><span class="n">labels</span><span class="o">=</span><span class="p">{</span><span class="s1">&#39;app&#39;</span><span class="p">:</span> <span class="n">name</span><span class="p">}),</span>
<span class="n">spec</span><span class="o">=</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1PodSpec</span><span class="p">(</span>
<span class="n">containers</span><span class="o">=</span><span class="p">[</span><span class="n">container</span><span class="p">],</span>
<span class="n">restart_policy</span><span class="o">=</span><span class="s1">&#39;OnFailure&#39;</span>
<span class="p">)</span>
<span class="p">)</span>
<span class="n">job_spec</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">V1JobSpec</span><span class="p">(</span>
<span class="n">completions</span><span class="o">=</span><span class="n">worker_params</span><span class="o">.</span><span class="n">num_replicas</span><span class="p">,</span>
<span class="n">parallelism</span><span class="o">=</span><span class="n">worker_params</span><span class="o">.</span><span class="n">num_replicas</span><span class="p">,</span>
<span class="n">template</span><span class="o">=</span><span class="n">template</span>
<span class="p">)</span>
<span class="n">job</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">V1Job</span><span class="p">(</span>
<span class="n">api_version</span><span class="o">=</span><span class="s2">&quot;batch/v1&quot;</span><span class="p">,</span>
<span class="n">kind</span><span class="o">=</span><span class="s2">&quot;Job&quot;</span><span class="p">,</span>
<span class="n">metadata</span><span class="o">=</span><span class="n">k8sclient</span><span class="o">.</span><span class="n">V1ObjectMeta</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">),</span>
<span class="n">spec</span><span class="o">=</span><span class="n">job_spec</span>
<span class="p">)</span>
<span class="n">api_client</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">BatchV1Api</span><span class="p">()</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">api_client</span><span class="o">.</span><span class="n">create_namespaced_job</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">namespace</span><span class="p">,</span> <span class="n">job</span><span class="p">)</span>
<span class="n">worker_params</span><span class="o">.</span><span class="n">orchestration_params</span><span class="p">[</span><span class="s1">&#39;job_name&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="k">except</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">rest</span><span class="o">.</span><span class="n">ApiException</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Got exception: </span><span class="si">%s</span><span class="se">\n</span><span class="s2"> while creating Job&quot;</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="k">def</span> <span class="nf">worker_logs</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="o">=</span><span class="s1">&#39;./logs&#39;</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> :param path: Path to store the worker logs.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">worker_params</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">run_type_params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">RunType</span><span class="o">.</span><span class="n">ROLLOUT_WORKER</span><span class="p">),</span> <span class="kc">None</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">worker_params</span><span class="p">:</span>
<span class="k">return</span>
<span class="n">api_client</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">CoreV1Api</span><span class="p">()</span>
<span class="n">pods</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">pods</span> <span class="o">=</span> <span class="n">api_client</span><span class="o">.</span><span class="n">list_namespaced_pod</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">namespace</span><span class="p">,</span> <span class="n">label_selector</span><span class="o">=</span><span class="s1">&#39;app=</span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="n">worker_params</span><span class="o">.</span><span class="n">orchestration_params</span><span class="p">[</span><span class="s1">&#39;job_name&#39;</span><span class="p">]</span>
<span class="p">))</span>
<span class="c1"># pod = pods.items[0]</span>
<span class="k">except</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">rest</span><span class="o">.</span><span class="n">ApiException</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Got exception: </span><span class="si">%s</span><span class="se">\n</span><span class="s2"> while reading pods&quot;</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span>
<span class="k">return</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">pods</span> <span class="ow">or</span> <span class="nb">len</span><span class="p">(</span><span class="n">pods</span><span class="o">.</span><span class="n">items</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">return</span>
<span class="k">for</span> <span class="n">pod</span> <span class="ow">in</span> <span class="n">pods</span><span class="o">.</span><span class="n">items</span><span class="p">:</span>
<span class="n">Process</span><span class="p">(</span><span class="n">target</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_tail_log_file</span><span class="p">,</span> <span class="n">args</span><span class="o">=</span><span class="p">(</span><span class="n">pod</span><span class="o">.</span><span class="n">metadata</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">api_client</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">namespace</span><span class="p">,</span> <span class="n">path</span><span class="p">))</span><span class="o">.</span><span class="n">start</span><span class="p">()</span>
<span class="k">def</span> <span class="nf">_tail_log_file</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pod_name</span><span class="p">,</span> <span class="n">api_client</span><span class="p">,</span> <span class="n">namespace</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">path</span><span class="p">):</span>
<span class="n">os</span><span class="o">.</span><span class="n">mkdir</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
<span class="n">sys</span><span class="o">.</span><span class="n">stdout</span> <span class="o">=</span> <span class="nb">open</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">pod_name</span><span class="p">),</span> <span class="s1">&#39;w&#39;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tail_log</span><span class="p">(</span><span class="n">pod_name</span><span class="p">,</span> <span class="n">api_client</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">trainer_logs</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Get the logs from trainer.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">trainer_params</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">run_type_params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">RunType</span><span class="o">.</span><span class="n">TRAINER</span><span class="p">),</span> <span class="kc">None</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">trainer_params</span><span class="p">:</span>
<span class="k">return</span>
<span class="n">api_client</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">CoreV1Api</span><span class="p">()</span>
<span class="n">pod</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">pods</span> <span class="o">=</span> <span class="n">api_client</span><span class="o">.</span><span class="n">list_namespaced_pod</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">namespace</span><span class="p">,</span> <span class="n">label_selector</span><span class="o">=</span><span class="s1">&#39;app=</span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="n">trainer_params</span><span class="o">.</span><span class="n">orchestration_params</span><span class="p">[</span><span class="s1">&#39;job_name&#39;</span><span class="p">]</span>
<span class="p">))</span>
<span class="n">pod</span> <span class="o">=</span> <span class="n">pods</span><span class="o">.</span><span class="n">items</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="k">except</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">rest</span><span class="o">.</span><span class="n">ApiException</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Got exception: </span><span class="si">%s</span><span class="se">\n</span><span class="s2"> while reading pods&quot;</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span>
<span class="k">return</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">pod</span><span class="p">:</span>
<span class="k">return</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tail_log</span><span class="p">(</span><span class="n">pod</span><span class="o">.</span><span class="n">metadata</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">api_client</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">tail_log</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pod_name</span><span class="p">,</span> <span class="n">corev1_api</span><span class="p">):</span>
<span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
<span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">10</span><span class="p">)</span>
<span class="c1"># Try to tail the pod logs</span>
<span class="k">try</span><span class="p">:</span>
<span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">corev1_api</span><span class="o">.</span><span class="n">read_namespaced_pod_log</span><span class="p">(</span>
<span class="n">pod_name</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">namespace</span><span class="p">,</span> <span class="n">follow</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">_preload_content</span><span class="o">=</span><span class="kc">False</span>
<span class="p">):</span>
<span class="nb">print</span><span class="p">(</span><span class="n">line</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s1">&#39;utf-8&#39;</span><span class="p">),</span> <span class="n">flush</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">end</span><span class="o">=</span><span class="s1">&#39;&#39;</span><span class="p">)</span>
<span class="k">except</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">rest</span><span class="o">.</span><span class="n">ApiException</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">pass</span>
<span class="c1"># This part will get executed if the pod is one of the following phases: not ready, failed or terminated.</span>
<span class="c1"># Check if the pod has errored out, else just try again.</span>
<span class="c1"># Get the pod</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">pod</span> <span class="o">=</span> <span class="n">corev1_api</span><span class="o">.</span><span class="n">read_namespaced_pod</span><span class="p">(</span><span class="n">pod_name</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">namespace</span><span class="p">)</span>
<span class="k">except</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">rest</span><span class="o">.</span><span class="n">ApiException</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">continue</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">pod</span><span class="p">,</span> <span class="s1">&#39;status&#39;</span><span class="p">)</span> <span class="ow">or</span> <span class="ow">not</span> <span class="n">pod</span><span class="o">.</span><span class="n">status</span><span class="p">:</span>
<span class="k">continue</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">pod</span><span class="o">.</span><span class="n">status</span><span class="p">,</span> <span class="s1">&#39;container_statuses&#39;</span><span class="p">)</span> <span class="ow">or</span> <span class="ow">not</span> <span class="n">pod</span><span class="o">.</span><span class="n">status</span><span class="o">.</span><span class="n">container_statuses</span><span class="p">:</span>
<span class="k">continue</span>
<span class="k">for</span> <span class="n">container_status</span> <span class="ow">in</span> <span class="n">pod</span><span class="o">.</span><span class="n">status</span><span class="o">.</span><span class="n">container_statuses</span><span class="p">:</span>
<span class="k">if</span> <span class="n">container_status</span><span class="o">.</span><span class="n">state</span><span class="o">.</span><span class="n">waiting</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">if</span> <span class="n">container_status</span><span class="o">.</span><span class="n">state</span><span class="o">.</span><span class="n">waiting</span><span class="o">.</span><span class="n">reason</span> <span class="o">==</span> <span class="s1">&#39;Error&#39;</span> <span class="ow">or</span> \
<span class="n">container_status</span><span class="o">.</span><span class="n">state</span><span class="o">.</span><span class="n">waiting</span><span class="o">.</span><span class="n">reason</span> <span class="o">==</span> <span class="s1">&#39;CrashLoopBackOff&#39;</span> <span class="ow">or</span> \
<span class="n">container_status</span><span class="o">.</span><span class="n">state</span><span class="o">.</span><span class="n">waiting</span><span class="o">.</span><span class="n">reason</span> <span class="o">==</span> <span class="s1">&#39;ImagePullBackOff&#39;</span> <span class="ow">or</span> \
<span class="n">container_status</span><span class="o">.</span><span class="n">state</span><span class="o">.</span><span class="n">waiting</span><span class="o">.</span><span class="n">reason</span> <span class="o">==</span> <span class="s1">&#39;ErrImagePull&#39;</span><span class="p">:</span>
<span class="k">return</span>
<span class="k">if</span> <span class="n">container_status</span><span class="o">.</span><span class="n">state</span><span class="o">.</span><span class="n">terminated</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">return</span>
<span class="k">def</span> <span class="nf">undeploy</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Undeploy all the components, such as trainer and rollout worker(s), Redis pub/sub and data store, when required.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">trainer_params</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">run_type_params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">RunType</span><span class="o">.</span><span class="n">TRAINER</span><span class="p">),</span> <span class="kc">None</span><span class="p">)</span>
<span class="n">api_client</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">BatchV1Api</span><span class="p">()</span>
<span class="n">delete_options</span> <span class="o">=</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">V1DeleteOptions</span><span class="p">(</span>
<span class="n">propagation_policy</span><span class="o">=</span><span class="s2">&quot;Foreground&quot;</span>
<span class="p">)</span>
<span class="k">if</span> <span class="n">trainer_params</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">api_client</span><span class="o">.</span><span class="n">delete_namespaced_job</span><span class="p">(</span><span class="n">trainer_params</span><span class="o">.</span><span class="n">orchestration_params</span><span class="p">[</span><span class="s1">&#39;job_name&#39;</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">namespace</span><span class="p">,</span> <span class="n">delete_options</span><span class="p">)</span>
<span class="k">except</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">rest</span><span class="o">.</span><span class="n">ApiException</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Got exception: </span><span class="si">%s</span><span class="se">\n</span><span class="s2"> while deleting trainer&quot;</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span>
<span class="n">worker_params</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">run_type_params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">RunType</span><span class="o">.</span><span class="n">ROLLOUT_WORKER</span><span class="p">),</span> <span class="kc">None</span><span class="p">)</span>
<span class="k">if</span> <span class="n">worker_params</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">api_client</span><span class="o">.</span><span class="n">delete_namespaced_job</span><span class="p">(</span><span class="n">worker_params</span><span class="o">.</span><span class="n">orchestration_params</span><span class="p">[</span><span class="s1">&#39;job_name&#39;</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">namespace</span><span class="p">,</span> <span class="n">delete_options</span><span class="p">)</span>
<span class="k">except</span> <span class="n">k8sclient</span><span class="o">.</span><span class="n">rest</span><span class="o">.</span><span class="n">ApiException</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Got exception: </span><span class="si">%s</span><span class="se">\n</span><span class="s2"> while deleting workers&quot;</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">memory_backend</span><span class="o">.</span><span class="n">undeploy</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">data_store</span><span class="o">.</span><span class="n">undeploy</span><span class="p">()</span></div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
&copy; Copyright 2018, Intel AI Lab
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/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" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>