| |
| |
| |
| |
| <!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>airflow.utils.dag_processing — Airflow Documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="../../../_static/js/modernizr.min.js"></script> |
| |
| |
| <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 type="text/javascript" src="../../../_static/language_data.js"></script> |
| |
| <script type="text/javascript" src="../../../_static/js/theme.js"></script> |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="index" title="Index" href="../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| |
| <script> |
| document.addEventListener('DOMContentLoaded', function() { |
| var el = document.getElementById('changelog'); |
| if (el !== null ) { |
| // [AIRFLOW-...] |
| el.innerHTML = el.innerHTML.replace( |
| /\[(AIRFLOW-[\d]+)\]/g, |
| `<a href="https://issues.apache.org/jira/browse/$1">[$1]</a>` |
| ); |
| // (#...) |
| el.innerHTML = el.innerHTML.replace( |
| /\(#([\d]+)\)/g, |
| `<a href="https://github.com/apache/airflow/pull/$1">(#$1)</a>` |
| ); |
| }; |
| }) |
| </script> |
| <style> |
| .example-header { |
| position: relative; |
| background: #9AAA7A; |
| padding: 8px 16px; |
| margin-bottom: 0; |
| } |
| .example-header--with-button { |
| padding-right: 166px; |
| } |
| .example-header:after{ |
| content: ''; |
| display: table; |
| clear: both; |
| } |
| .example-title { |
| display:block; |
| padding: 4px; |
| margin-right: 16px; |
| color: white; |
| overflow-x: auto; |
| } |
| .example-header-button { |
| top: 8px; |
| right: 16px; |
| position: absolute; |
| } |
| .example-header + .highlight-python { |
| margin-top: 0 !important; |
| } |
| .viewcode-button { |
| display: inline-block; |
| padding: 8px 16px; |
| border: 0; |
| margin: 0; |
| outline: 0; |
| border-radius: 2px; |
| -webkit-box-shadow: 0 3px 5px 0 rgba(0,0,0,.3); |
| box-shadow: 0 3px 6px 0 rgba(0,0,0,.3); |
| color: #404040; |
| background-color: #e7e7e7; |
| cursor: pointer; |
| font-size: 16px; |
| font-weight: 500; |
| line-height: 1; |
| text-decoration: none; |
| text-overflow: ellipsis; |
| overflow: hidden; |
| text-transform: uppercase; |
| -webkit-transition: background-color .2s; |
| transition: background-color .2s; |
| vertical-align: middle; |
| white-space: nowrap; |
| } |
| .viewcode-button:visited { |
| color: #404040; |
| } |
| .viewcode-button:hover, .viewcode-button:focus { |
| color: #404040; |
| background-color: #d6d6d6; |
| } |
| </style> |
| |
| <script type="application/javascript"> |
| window.ga=window.ga||function(){(ga.q=ga.q||[]).push(arguments)};ga.l=+new Date; |
| ga("create", "UA-140539454-1", "auto"); |
| ga("send", "pageview"); |
| </script> |
| <script async src="https://www.google-analytics.com/analytics.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"> Airflow |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 1.10.3 |
| </div> |
| |
| |
| |
| |
| <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"> |
| |
| |
| |
| |
| |
| |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../project.html">Project</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../license.html">License</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../start.html">Quick Start</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../installation.html">Installation</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../tutorial.html">Tutorial</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../howto/index.html">How-to Guides</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../ui.html">UI / Screenshots</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../concepts.html">Concepts</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../profiling.html">Data Profiling</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../cli.html">Command Line Interface</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../scheduler.html">Scheduling & Triggers</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../plugins.html">Plugins</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../security.html">Security</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../timezone.html">Time zones</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../api.html">Experimental Rest API</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../integration.html">Integration</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../metrics.html">Metrics</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../kubernetes.html">Kubernetes</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../lineage.html">Lineage</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../changelog.html">Changelog</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../faq.html">FAQ</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../macros.html">Macros reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../_api/index.html">API Reference</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">Airflow</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> »</li> |
| |
| <li><a href="../../index.html">Module code</a> »</li> |
| |
| <li>airflow.utils.dag_processing</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 airflow.utils.dag_processing</h1><div class="highlight"><pre> |
| <span></span><span class="c1"># -*- coding: utf-8 -*-</span> |
| <span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span> |
| <span class="c1"># or more contributor license agreements. See the NOTICE file</span> |
| <span class="c1"># distributed with this work for additional information</span> |
| <span class="c1"># regarding copyright ownership. The ASF licenses this file</span> |
| <span class="c1"># to you under the Apache License, Version 2.0 (the</span> |
| <span class="c1"># "License"); you may not use this file except in compliance</span> |
| <span class="c1"># with the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing,</span> |
| <span class="c1"># software distributed under the License is distributed on an</span> |
| <span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span> |
| <span class="c1"># KIND, either express or implied. See the License for the</span> |
| <span class="c1"># specific language governing permissions and limitations</span> |
| <span class="c1"># under the License.</span> |
| <span class="c1">#</span> |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">absolute_import</span> |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">division</span> |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">print_function</span> |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">unicode_literals</span> |
| |
| <span class="kn">import</span> <span class="nn">logging</span> |
| <span class="kn">import</span> <span class="nn">multiprocessing</span> |
| <span class="kn">import</span> <span class="nn">os</span> |
| <span class="kn">import</span> <span class="nn">re</span> |
| <span class="kn">import</span> <span class="nn">signal</span> |
| <span class="kn">import</span> <span class="nn">sys</span> |
| <span class="kn">import</span> <span class="nn">time</span> |
| <span class="kn">import</span> <span class="nn">zipfile</span> |
| <span class="kn">from</span> <span class="nn">abc</span> <span class="k">import</span> <span class="n">ABCMeta</span><span class="p">,</span> <span class="n">abstractmethod</span> |
| <span class="kn">from</span> <span class="nn">collections</span> <span class="k">import</span> <span class="n">defaultdict</span> |
| <span class="kn">from</span> <span class="nn">collections</span> <span class="k">import</span> <span class="n">namedtuple</span> |
| <span class="kn">from</span> <span class="nn">datetime</span> <span class="k">import</span> <span class="n">timedelta</span> |
| <span class="kn">from</span> <span class="nn">importlib</span> <span class="k">import</span> <span class="n">import_module</span> |
| <span class="kn">import</span> <span class="nn">enum</span> |
| |
| <span class="kn">import</span> <span class="nn">psutil</span> |
| <span class="kn">from</span> <span class="nn">six.moves</span> <span class="k">import</span> <span class="nb">range</span><span class="p">,</span> <span class="n">reload_module</span> |
| <span class="kn">from</span> <span class="nn">sqlalchemy</span> <span class="k">import</span> <span class="n">or_</span> |
| <span class="kn">from</span> <span class="nn">tabulate</span> <span class="k">import</span> <span class="n">tabulate</span> |
| |
| <span class="c1"># To avoid circular imports</span> |
| <span class="kn">import</span> <span class="nn">airflow.models</span> |
| <span class="kn">from</span> <span class="nn">airflow</span> <span class="k">import</span> <span class="n">configuration</span> <span class="k">as</span> <span class="n">conf</span> |
| <span class="kn">from</span> <span class="nn">airflow.dag.base_dag</span> <span class="k">import</span> <span class="n">BaseDag</span><span class="p">,</span> <span class="n">BaseDagBag</span> |
| <span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="k">import</span> <span class="n">AirflowException</span> |
| <span class="kn">from</span> <span class="nn">airflow.settings</span> <span class="k">import</span> <span class="n">Stats</span> |
| <span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">errors</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils</span> <span class="k">import</span> <span class="n">timezone</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils.db</span> <span class="k">import</span> <span class="n">provide_session</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils.log.logging_mixin</span> <span class="k">import</span> <span class="n">LoggingMixin</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils.state</span> <span class="k">import</span> <span class="n">State</span> |
| |
| |
| <span class="k">class</span> <span class="nc">SimpleDag</span><span class="p">(</span><span class="n">BaseDag</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> A simplified representation of a DAG that contains all attributes</span> |
| <span class="sd"> required for instantiating and scheduling its associated tasks.</span> |
| <span class="sd"> """</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">dag</span><span class="p">,</span> <span class="n">pickle_id</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :param dag: the DAG</span> |
| <span class="sd"> :type dag: airflow.models.DAG</span> |
| <span class="sd"> :param pickle_id: ID associated with the pickled version of this DAG.</span> |
| <span class="sd"> :type pickle_id: unicode</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_dag_id</span> <span class="o">=</span> <span class="n">dag</span><span class="o">.</span><span class="n">dag_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_task_ids</span> <span class="o">=</span> <span class="p">[</span><span class="n">task</span><span class="o">.</span><span class="n">task_id</span> <span class="k">for</span> <span class="n">task</span> <span class="ow">in</span> <span class="n">dag</span><span class="o">.</span><span class="n">tasks</span><span class="p">]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_full_filepath</span> <span class="o">=</span> <span class="n">dag</span><span class="o">.</span><span class="n">full_filepath</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_is_paused</span> <span class="o">=</span> <span class="n">dag</span><span class="o">.</span><span class="n">is_paused</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_concurrency</span> <span class="o">=</span> <span class="n">dag</span><span class="o">.</span><span class="n">concurrency</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_pickle_id</span> <span class="o">=</span> <span class="n">pickle_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_task_special_args</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">for</span> <span class="n">task</span> <span class="ow">in</span> <span class="n">dag</span><span class="o">.</span><span class="n">tasks</span><span class="p">:</span> |
| <span class="n">special_args</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">if</span> <span class="n">task</span><span class="o">.</span><span class="n">task_concurrency</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">special_args</span><span class="p">[</span><span class="s1">'task_concurrency'</span><span class="p">]</span> <span class="o">=</span> <span class="n">task</span><span class="o">.</span><span class="n">task_concurrency</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">special_args</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_task_special_args</span><span class="p">[</span><span class="n">task</span><span class="o">.</span><span class="n">task_id</span><span class="p">]</span> <span class="o">=</span> <span class="n">special_args</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">dag_id</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :return: the DAG ID</span> |
| <span class="sd"> :rtype: unicode</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dag_id</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">task_ids</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :return: A list of task IDs that are in this DAG</span> |
| <span class="sd"> :rtype: list[unicode]</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_task_ids</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">full_filepath</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :return: The absolute path to the file that contains this DAG's definition</span> |
| <span class="sd"> :rtype: unicode</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_full_filepath</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">concurrency</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :return: maximum number of tasks that can run simultaneously from this DAG</span> |
| <span class="sd"> :rtype: int</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_concurrency</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">is_paused</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :return: whether this DAG is paused or not</span> |
| <span class="sd"> :rtype: bool</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_is_paused</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">pickle_id</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :return: The pickle ID for this DAG, if it has one. Otherwise None.</span> |
| <span class="sd"> :rtype: unicode</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pickle_id</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">task_special_args</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_task_special_args</span> |
| |
| <span class="k">def</span> <span class="nf">get_task_special_arg</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">special_arg_name</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">task_id</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_task_special_args</span> <span class="ow">and</span> <span class="n">special_arg_name</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_task_special_args</span><span class="p">[</span><span class="n">task_id</span><span class="p">]:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_task_special_args</span><span class="p">[</span><span class="n">task_id</span><span class="p">][</span><span class="n">special_arg_name</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| |
| |
| <span class="k">class</span> <span class="nc">SimpleTaskInstance</span><span class="p">(</span><span class="nb">object</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">ti</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_dag_id</span> <span class="o">=</span> <span class="n">ti</span><span class="o">.</span><span class="n">dag_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_task_id</span> <span class="o">=</span> <span class="n">ti</span><span class="o">.</span><span class="n">task_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_execution_date</span> <span class="o">=</span> <span class="n">ti</span><span class="o">.</span><span class="n">execution_date</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_start_date</span> <span class="o">=</span> <span class="n">ti</span><span class="o">.</span><span class="n">start_date</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_end_date</span> <span class="o">=</span> <span class="n">ti</span><span class="o">.</span><span class="n">end_date</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_try_number</span> <span class="o">=</span> <span class="n">ti</span><span class="o">.</span><span class="n">try_number</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_state</span> <span class="o">=</span> <span class="n">ti</span><span class="o">.</span><span class="n">state</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_executor_config</span> <span class="o">=</span> <span class="n">ti</span><span class="o">.</span><span class="n">executor_config</span> |
| <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">ti</span><span class="p">,</span> <span class="s1">'run_as_user'</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_run_as_user</span> <span class="o">=</span> <span class="n">ti</span><span class="o">.</span><span class="n">run_as_user</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_run_as_user</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">ti</span><span class="p">,</span> <span class="s1">'pool'</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_pool</span> <span class="o">=</span> <span class="n">ti</span><span class="o">.</span><span class="n">pool</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_pool</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">ti</span><span class="p">,</span> <span class="s1">'priority_weight'</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_priority_weight</span> <span class="o">=</span> <span class="n">ti</span><span class="o">.</span><span class="n">priority_weight</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_priority_weight</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_queue</span> <span class="o">=</span> <span class="n">ti</span><span class="o">.</span><span class="n">queue</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_key</span> <span class="o">=</span> <span class="n">ti</span><span class="o">.</span><span class="n">key</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">dag_id</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dag_id</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">task_id</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_task_id</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">execution_date</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_execution_date</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">start_date</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_start_date</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">end_date</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end_date</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">try_number</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_try_number</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">state</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_state</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">pool</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pool</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">priority_weight</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_priority_weight</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">queue</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_queue</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">key</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_key</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">executor_config</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_executor_config</span> |
| |
| <span class="nd">@provide_session</span> |
| <span class="k">def</span> <span class="nf">construct_task_instance</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">session</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">lock_for_update</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Construct a TaskInstance from the database based on the primary key</span> |
| |
| <span class="sd"> :param session: DB session.</span> |
| <span class="sd"> :param lock_for_update: if True, indicates that the database should</span> |
| <span class="sd"> lock the TaskInstance (issuing a FOR UPDATE clause) until the</span> |
| <span class="sd"> session is committed.</span> |
| <span class="sd"> """</span> |
| <span class="n">TI</span> <span class="o">=</span> <span class="n">airflow</span><span class="o">.</span><span class="n">models</span><span class="o">.</span><span class="n">TaskInstance</span> |
| |
| <span class="n">qry</span> <span class="o">=</span> <span class="n">session</span><span class="o">.</span><span class="n">query</span><span class="p">(</span><span class="n">TI</span><span class="p">)</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span> |
| <span class="n">TI</span><span class="o">.</span><span class="n">dag_id</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dag_id</span><span class="p">,</span> |
| <span class="n">TI</span><span class="o">.</span><span class="n">task_id</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_task_id</span><span class="p">,</span> |
| <span class="n">TI</span><span class="o">.</span><span class="n">execution_date</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_execution_date</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">lock_for_update</span><span class="p">:</span> |
| <span class="n">ti</span> <span class="o">=</span> <span class="n">qry</span><span class="o">.</span><span class="n">with_for_update</span><span class="p">()</span><span class="o">.</span><span class="n">first</span><span class="p">()</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">ti</span> <span class="o">=</span> <span class="n">qry</span><span class="o">.</span><span class="n">first</span><span class="p">()</span> |
| <span class="k">return</span> <span class="n">ti</span> |
| |
| |
| <span class="k">class</span> <span class="nc">SimpleDagBag</span><span class="p">(</span><span class="n">BaseDagBag</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> A collection of SimpleDag objects with some convenience methods.</span> |
| <span class="sd"> """</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">simple_dags</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Constructor.</span> |
| |
| <span class="sd"> :param simple_dags: SimpleDag objects that should be in this</span> |
| <span class="sd"> :type list(airflow.utils.dag_processing.SimpleDagBag)</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">simple_dags</span> <span class="o">=</span> <span class="n">simple_dags</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dag_id_to_simple_dag</span> <span class="o">=</span> <span class="p">{}</span> |
| |
| <span class="k">for</span> <span class="n">simple_dag</span> <span class="ow">in</span> <span class="n">simple_dags</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dag_id_to_simple_dag</span><span class="p">[</span><span class="n">simple_dag</span><span class="o">.</span><span class="n">dag_id</span><span class="p">]</span> <span class="o">=</span> <span class="n">simple_dag</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">dag_ids</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :return: IDs of all the DAGs in this</span> |
| <span class="sd"> :rtype: list[unicode]</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">dag_id_to_simple_dag</span><span class="o">.</span><span class="n">keys</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">get_dag</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dag_id</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :param dag_id: DAG ID</span> |
| <span class="sd"> :type dag_id: unicode</span> |
| <span class="sd"> :return: if the given DAG ID exists in the bag, return the BaseDag</span> |
| <span class="sd"> corresponding to that ID. Otherwise, throw an Exception</span> |
| <span class="sd"> :rtype: airflow.utils.dag_processing.SimpleDag</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">dag_id</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">dag_id_to_simple_dag</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s2">"Unknown DAG ID </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">dag_id</span><span class="p">))</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">dag_id_to_simple_dag</span><span class="p">[</span><span class="n">dag_id</span><span class="p">]</span> |
| |
| |
| <div class="viewcode-block" id="list_py_file_paths"><a class="viewcode-back" href="../../../_api/airflow/models/index.html#airflow.models.list_py_file_paths">[docs]</a><span class="k">def</span> <span class="nf">list_py_file_paths</span><span class="p">(</span><span class="n">directory</span><span class="p">,</span> <span class="n">safe_mode</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">include_examples</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Traverse a directory and look for Python files.</span> |
| |
| <span class="sd"> :param directory: the directory to traverse</span> |
| <span class="sd"> :type directory: unicode</span> |
| <span class="sd"> :param safe_mode: whether to use a heuristic to determine whether a file</span> |
| <span class="sd"> contains Airflow DAG definitions</span> |
| <span class="sd"> :return: a list of paths to Python files in the specified directory</span> |
| <span class="sd"> :rtype: list[unicode]</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">include_examples</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">include_examples</span> <span class="o">=</span> <span class="n">conf</span><span class="o">.</span><span class="n">getboolean</span><span class="p">(</span><span class="s1">'core'</span><span class="p">,</span> <span class="s1">'LOAD_EXAMPLES'</span><span class="p">)</span> |
| <span class="n">file_paths</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">if</span> <span class="n">directory</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">[]</span> |
| <span class="k">elif</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="n">directory</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">directory</span><span class="p">]</span> |
| <span class="k">elif</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isdir</span><span class="p">(</span><span class="n">directory</span><span class="p">):</span> |
| <span class="n">patterns_by_dir</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">for</span> <span class="n">root</span><span class="p">,</span> <span class="n">dirs</span><span class="p">,</span> <span class="n">files</span> <span class="ow">in</span> <span class="n">os</span><span class="o">.</span><span class="n">walk</span><span class="p">(</span><span class="n">directory</span><span class="p">,</span> <span class="n">followlinks</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span> |
| <span class="n">patterns</span> <span class="o">=</span> <span class="n">patterns_by_dir</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">root</span><span class="p">,</span> <span class="p">[])</span> |
| <span class="n">ignore_file</span> <span class="o">=</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">root</span><span class="p">,</span> <span class="s1">'.airflowignore'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="n">ignore_file</span><span class="p">):</span> |
| <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">ignore_file</span><span class="p">,</span> <span class="s1">'r'</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span> |
| <span class="c1"># If we have new patterns create a copy so we don't change</span> |
| <span class="c1"># the previous list (which would affect other subdirs)</span> |
| <span class="n">patterns</span> <span class="o">=</span> <span class="n">patterns</span> <span class="o">+</span> <span class="p">[</span><span class="n">p</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">f</span><span class="o">.</span><span class="n">read</span><span class="p">()</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="p">)</span> <span class="k">if</span> <span class="n">p</span><span class="p">]</span> |
| |
| <span class="c1"># If we can ignore any subdirs entirely we should - fewer paths</span> |
| <span class="c1"># to walk is better. We have to modify the ``dirs`` array in</span> |
| <span class="c1"># place for this to affect os.walk</span> |
| <span class="n">dirs</span><span class="p">[:]</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="n">d</span> |
| <span class="k">for</span> <span class="n">d</span> <span class="ow">in</span> <span class="n">dirs</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">any</span><span class="p">(</span><span class="n">re</span><span class="o">.</span><span class="n">search</span><span class="p">(</span><span class="n">p</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">root</span><span class="p">,</span> <span class="n">d</span><span class="p">))</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">patterns</span><span class="p">)</span> |
| <span class="p">]</span> |
| |
| <span class="c1"># We want patterns defined in a parent folder's .airflowignore to</span> |
| <span class="c1"># apply to subdirs too</span> |
| <span class="k">for</span> <span class="n">d</span> <span class="ow">in</span> <span class="n">dirs</span><span class="p">:</span> |
| <span class="n">patterns_by_dir</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">root</span><span class="p">,</span> <span class="n">d</span><span class="p">)]</span> <span class="o">=</span> <span class="n">patterns</span> |
| |
| <span class="k">for</span> <span class="n">f</span> <span class="ow">in</span> <span class="n">files</span><span class="p">:</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">file_path</span> <span class="o">=</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">root</span><span class="p">,</span> <span class="n">f</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">isfile</span><span class="p">(</span><span class="n">file_path</span><span class="p">):</span> |
| <span class="k">continue</span> |
| <span class="n">mod_name</span><span class="p">,</span> <span class="n">file_ext</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">splitext</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">split</span><span class="p">(</span><span class="n">file_path</span><span class="p">)[</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span> |
| <span class="k">if</span> <span class="n">file_ext</span> <span class="o">!=</span> <span class="s1">'.py'</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">zipfile</span><span class="o">.</span><span class="n">is_zipfile</span><span class="p">(</span><span class="n">file_path</span><span class="p">):</span> |
| <span class="k">continue</span> |
| <span class="k">if</span> <span class="nb">any</span><span class="p">([</span><span class="n">re</span><span class="o">.</span><span class="n">findall</span><span class="p">(</span><span class="n">p</span><span class="p">,</span> <span class="n">file_path</span><span class="p">)</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">patterns</span><span class="p">]):</span> |
| <span class="k">continue</span> |
| |
| <span class="c1"># Heuristic that guesses whether a Python file contains an</span> |
| <span class="c1"># Airflow DAG definition.</span> |
| <span class="n">might_contain_dag</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">if</span> <span class="n">safe_mode</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">zipfile</span><span class="o">.</span><span class="n">is_zipfile</span><span class="p">(</span><span class="n">file_path</span><span class="p">):</span> |
| <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">file_path</span><span class="p">,</span> <span class="s1">'rb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span> |
| <span class="n">content</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">read</span><span class="p">()</span> |
| <span class="n">might_contain_dag</span> <span class="o">=</span> <span class="nb">all</span><span class="p">(</span> |
| <span class="p">[</span><span class="n">s</span> <span class="ow">in</span> <span class="n">content</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="p">(</span><span class="sa">b</span><span class="s1">'DAG'</span><span class="p">,</span> <span class="sa">b</span><span class="s1">'airflow'</span><span class="p">)])</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">might_contain_dag</span><span class="p">:</span> |
| <span class="k">continue</span> |
| |
| <span class="n">file_paths</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">file_path</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">Exception</span><span class="p">:</span> |
| <span class="n">log</span> <span class="o">=</span> <span class="n">LoggingMixin</span><span class="p">()</span><span class="o">.</span><span class="n">log</span> |
| <span class="n">log</span><span class="o">.</span><span class="n">exception</span><span class="p">(</span><span class="s2">"Error while examining </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">f</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">include_examples</span><span class="p">:</span> |
| <span class="kn">import</span> <span class="nn">airflow.example_dags</span> |
| <span class="n">example_dag_folder</span> <span class="o">=</span> <span class="n">airflow</span><span class="o">.</span><span class="n">example_dags</span><span class="o">.</span><span class="n">__path__</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="n">file_paths</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">list_py_file_paths</span><span class="p">(</span><span class="n">example_dag_folder</span><span class="p">,</span> <span class="n">safe_mode</span><span class="p">,</span> <span class="kc">False</span><span class="p">))</span> |
| <span class="k">return</span> <span class="n">file_paths</span></div> |
| |
| |
| <span class="k">class</span> <span class="nc">AbstractDagFileProcessor</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Processes a DAG file. See SchedulerJob.process_file() for more details.</span> |
| <span class="sd"> """</span> |
| <span class="n">__metaclass__</span> <span class="o">=</span> <span class="n">ABCMeta</span> |
| |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">start</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Launch the process to process the file</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span> |
| |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">terminate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sigkill</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Terminate (and then kill) the process launched to process the file</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">pid</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :return: the PID of the process launched to process the given file</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">exit_code</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> After the process is finished, this can be called to get the return code</span> |
| <span class="sd"> :return: the exit code of the process</span> |
| <span class="sd"> :rtype: int</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">done</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Check if the process launched to process this file is done.</span> |
| <span class="sd"> :return: whether the process is finished running</span> |
| <span class="sd"> :rtype: bool</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">result</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :return: result of running SchedulerJob.process_file()</span> |
| <span class="sd"> :rtype: list[airflow.utils.dag_processing.SimpleDag]</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">start_time</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :return: When this started to process the file</span> |
| <span class="sd"> :rtype: datetime</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">file_path</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :return: the path to the file that this is processing</span> |
| <span class="sd"> :rtype: unicode</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span> |
| |
| |
| <span class="n">DagParsingStat</span> <span class="o">=</span> <span class="n">namedtuple</span><span class="p">(</span><span class="s1">'DagParsingStat'</span><span class="p">,</span> |
| <span class="p">[</span><span class="s1">'file_paths'</span><span class="p">,</span> <span class="s1">'all_pids'</span><span class="p">,</span> <span class="s1">'done'</span><span class="p">,</span> |
| <span class="s1">'all_files_processed'</span><span class="p">,</span> <span class="s1">'result_count'</span><span class="p">])</span> |
| |
| |
| <span class="k">class</span> <span class="nc">DagParsingSignal</span><span class="p">(</span><span class="n">enum</span><span class="o">.</span><span class="n">Enum</span><span class="p">):</span> |
| <span class="n">AGENT_HEARTBEAT</span> <span class="o">=</span> <span class="s1">'agent_heartbeat'</span> |
| <span class="n">MANAGER_DONE</span> <span class="o">=</span> <span class="s1">'manager_done'</span> |
| <span class="n">TERMINATE_MANAGER</span> <span class="o">=</span> <span class="s1">'terminate_manager'</span> |
| <span class="n">END_MANAGER</span> <span class="o">=</span> <span class="s1">'end_manager'</span> |
| |
| |
| <span class="k">class</span> <span class="nc">DagFileProcessorAgent</span><span class="p">(</span><span class="n">LoggingMixin</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Agent for DAG file processing. It is responsible for all DAG parsing</span> |
| <span class="sd"> related jobs in scheduler process. Mainly it can spin up DagFileProcessorManager</span> |
| <span class="sd"> in a subprocess, collect DAG parsing results from it and communicate</span> |
| <span class="sd"> signal/DAG parsing stat with it.</span> |
| <span class="sd"> """</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">dag_directory</span><span class="p">,</span> |
| <span class="n">file_paths</span><span class="p">,</span> |
| <span class="n">max_runs</span><span class="p">,</span> |
| <span class="n">processor_factory</span><span class="p">,</span> |
| <span class="n">async_mode</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :param dag_directory: Directory where DAG definitions are kept. All</span> |
| <span class="sd"> files in file_paths should be under this directory</span> |
| <span class="sd"> :type dag_directory: unicode</span> |
| <span class="sd"> :param file_paths: list of file paths that contain DAG definitions</span> |
| <span class="sd"> :type file_paths: list[unicode]</span> |
| <span class="sd"> :param max_runs: The number of times to parse and schedule each file. -1</span> |
| <span class="sd"> for unlimited.</span> |
| <span class="sd"> :type max_runs: int</span> |
| <span class="sd"> :param processor_factory: function that creates processors for DAG</span> |
| <span class="sd"> definition files. Arguments are (dag_definition_path, log_file_path)</span> |
| <span class="sd"> :type processor_factory: (unicode, unicode, list) -> (AbstractDagFileProcessor)</span> |
| <span class="sd"> :param async_mode: Whether to start agent in async mode</span> |
| <span class="sd"> :type async_mode: bool</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span> <span class="o">=</span> <span class="n">file_paths</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_file_path_queue</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_dag_directory</span> <span class="o">=</span> <span class="n">dag_directory</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_max_runs</span> <span class="o">=</span> <span class="n">max_runs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_processor_factory</span> <span class="o">=</span> <span class="n">processor_factory</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_async_mode</span> <span class="o">=</span> <span class="n">async_mode</span> |
| <span class="c1"># Map from file path to the processor</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="c1"># Map from file path to the last runtime</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_last_runtime</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="c1"># Map from file path to the last finish time</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_last_finish_time</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="c1"># Map from file path to the number of runs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_run_count</span> <span class="o">=</span> <span class="n">defaultdict</span><span class="p">(</span><span class="nb">int</span><span class="p">)</span> |
| <span class="c1"># Pids of DAG parse</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_all_pids</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="c1"># Pipe for communicating signals</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_parent_signal_conn</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_child_signal_conn</span> <span class="o">=</span> <span class="n">multiprocessing</span><span class="o">.</span><span class="n">Pipe</span><span class="p">()</span> |
| <span class="c1"># Pipe for communicating DagParsingStat</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_stat_queue</span> <span class="o">=</span> <span class="n">multiprocessing</span><span class="o">.</span><span class="n">Queue</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_result_queue</span> <span class="o">=</span> <span class="n">multiprocessing</span><span class="o">.</span><span class="n">Queue</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_process</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_done</span> <span class="o">=</span> <span class="kc">False</span> |
| <span class="c1"># Initialized as true so we do not deactivate w/o any actual DAG parsing.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_all_files_processed</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_result_count</span> <span class="o">=</span> <span class="mi">0</span> |
| |
| <span class="k">def</span> <span class="nf">start</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Launch DagFileProcessorManager processor and start DAG parsing loop in manager.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_process</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_launch_process</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_dag_directory</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_max_runs</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_processor_factory</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_child_signal_conn</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_stat_queue</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_result_queue</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_async_mode</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Launched DagFileProcessorManager with pid: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_process</span><span class="o">.</span><span class="n">pid</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">heartbeat</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Should only be used when launched DAG file processor manager in sync mode.</span> |
| <span class="sd"> Send agent heartbeat signal to the manager.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_parent_signal_conn</span><span class="o">.</span><span class="n">send</span><span class="p">(</span><span class="n">DagParsingSignal</span><span class="o">.</span><span class="n">AGENT_HEARTBEAT</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">wait_until_finished</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Should only be used when launched DAG file processor manager in sync mode.</span> |
| <span class="sd"> Wait for done signal from the manager.</span> |
| <span class="sd"> """</span> |
| <span class="k">while</span> <span class="kc">True</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parent_signal_conn</span><span class="o">.</span><span class="n">recv</span><span class="p">()</span> <span class="o">==</span> <span class="n">DagParsingSignal</span><span class="o">.</span><span class="n">MANAGER_DONE</span><span class="p">:</span> |
| <span class="k">break</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_launch_process</span><span class="p">(</span><span class="n">dag_directory</span><span class="p">,</span> |
| <span class="n">file_paths</span><span class="p">,</span> |
| <span class="n">max_runs</span><span class="p">,</span> |
| <span class="n">processor_factory</span><span class="p">,</span> |
| <span class="n">signal_conn</span><span class="p">,</span> |
| <span class="n">_stat_queue</span><span class="p">,</span> |
| <span class="n">result_queue</span><span class="p">,</span> |
| <span class="n">async_mode</span><span class="p">):</span> |
| <span class="k">def</span> <span class="nf">helper</span><span class="p">():</span> |
| <span class="c1"># Reload configurations and settings to avoid collision with parent process.</span> |
| <span class="c1"># Because this process may need custom configurations that cannot be shared,</span> |
| <span class="c1"># e.g. RotatingFileHandler. And it can cause connection corruption if we</span> |
| <span class="c1"># do not recreate the SQLA connection pool.</span> |
| <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'CONFIG_PROCESSOR_MANAGER_LOGGER'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'True'</span> |
| <span class="c1"># Replicating the behavior of how logging module was loaded</span> |
| <span class="c1"># in logging_config.py</span> |
| <span class="n">reload_module</span><span class="p">(</span><span class="n">import_module</span><span class="p">(</span><span class="n">airflow</span><span class="o">.</span><span class="n">settings</span><span class="o">.</span><span class="n">LOGGING_CLASS_PATH</span><span class="o">.</span><span class="n">rsplit</span><span class="p">(</span><span class="s1">'.'</span><span class="p">,</span> <span class="mi">1</span><span class="p">)[</span><span class="mi">0</span><span class="p">]))</span> |
| <span class="n">reload_module</span><span class="p">(</span><span class="n">airflow</span><span class="o">.</span><span class="n">settings</span><span class="p">)</span> |
| <span class="n">airflow</span><span class="o">.</span><span class="n">settings</span><span class="o">.</span><span class="n">initialize</span><span class="p">()</span> |
| <span class="k">del</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'CONFIG_PROCESSOR_MANAGER_LOGGER'</span><span class="p">]</span> |
| <span class="n">processor_manager</span> <span class="o">=</span> <span class="n">DagFileProcessorManager</span><span class="p">(</span><span class="n">dag_directory</span><span class="p">,</span> |
| <span class="n">file_paths</span><span class="p">,</span> |
| <span class="n">max_runs</span><span class="p">,</span> |
| <span class="n">processor_factory</span><span class="p">,</span> |
| <span class="n">signal_conn</span><span class="p">,</span> |
| <span class="n">_stat_queue</span><span class="p">,</span> |
| <span class="n">result_queue</span><span class="p">,</span> |
| <span class="n">async_mode</span><span class="p">)</span> |
| |
| <span class="n">processor_manager</span><span class="o">.</span><span class="n">start</span><span class="p">()</span> |
| |
| <span class="n">p</span> <span class="o">=</span> <span class="n">multiprocessing</span><span class="o">.</span><span class="n">Process</span><span class="p">(</span><span class="n">target</span><span class="o">=</span><span class="n">helper</span><span class="p">,</span> |
| <span class="n">args</span><span class="o">=</span><span class="p">(),</span> |
| <span class="n">name</span><span class="o">=</span><span class="s2">"DagFileProcessorManager"</span><span class="p">)</span> |
| <span class="n">p</span><span class="o">.</span><span class="n">start</span><span class="p">()</span> |
| <span class="k">return</span> <span class="n">p</span> |
| |
| <span class="k">def</span> <span class="nf">harvest_simple_dags</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Harvest DAG parsing results from result queue and sync metadata from stat queue.</span> |
| <span class="sd"> :return: List of parsing result in SimpleDag format.</span> |
| <span class="sd"> """</span> |
| <span class="c1"># Metadata and results to be harvested can be inconsistent,</span> |
| <span class="c1"># but it should not be a big problem.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_sync_metadata</span><span class="p">()</span> |
| <span class="c1"># Heartbeating after syncing metadata so we do not restart manager</span> |
| <span class="c1"># if it processed all files for max_run times and exit normally.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_heartbeat_manager</span><span class="p">()</span> |
| <span class="n">simple_dags</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="c1"># multiprocessing.Queue().qsize will not work on MacOS.</span> |
| <span class="k">if</span> <span class="n">sys</span><span class="o">.</span><span class="n">platform</span> <span class="o">==</span> <span class="s2">"darwin"</span><span class="p">:</span> |
| <span class="n">qsize</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_result_count</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">qsize</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_result_queue</span><span class="o">.</span><span class="n">qsize</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">qsize</span><span class="p">):</span> |
| <span class="n">simple_dags</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_result_queue</span><span class="o">.</span><span class="n">get</span><span class="p">())</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_result_count</span> <span class="o">=</span> <span class="mi">0</span> |
| |
| <span class="k">return</span> <span class="n">simple_dags</span> |
| |
| <span class="k">def</span> <span class="nf">_heartbeat_manager</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Heartbeat DAG file processor and start it if it is not alive.</span> |
| <span class="sd"> :return:</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_process</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_process</span><span class="o">.</span><span class="n">is_alive</span><span class="p">()</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">done</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">start</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">_sync_metadata</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sync metadata from stat queue and only keep the latest stat.</span> |
| <span class="sd"> :return:</span> |
| <span class="sd"> """</span> |
| <span class="k">while</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_stat_queue</span><span class="o">.</span><span class="n">empty</span><span class="p">():</span> |
| <span class="n">stat</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_stat_queue</span><span class="o">.</span><span class="n">get</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span> <span class="o">=</span> <span class="n">stat</span><span class="o">.</span><span class="n">file_paths</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_all_pids</span> <span class="o">=</span> <span class="n">stat</span><span class="o">.</span><span class="n">all_pids</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_done</span> <span class="o">=</span> <span class="n">stat</span><span class="o">.</span><span class="n">done</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_all_files_processed</span> <span class="o">=</span> <span class="n">stat</span><span class="o">.</span><span class="n">all_files_processed</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_result_count</span> <span class="o">+=</span> <span class="n">stat</span><span class="o">.</span><span class="n">result_count</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">file_paths</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">done</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_done</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">all_files_processed</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_all_files_processed</span> |
| |
| <span class="k">def</span> <span class="nf">terminate</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Send termination signal to DAG parsing processor manager</span> |
| <span class="sd"> and expect it to terminate all DAG file processors.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Sending termination message to manager."</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_child_signal_conn</span><span class="o">.</span><span class="n">send</span><span class="p">(</span><span class="n">DagParsingSignal</span><span class="o">.</span><span class="n">TERMINATE_MANAGER</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">end</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Terminate (and then kill) the manager process launched.</span> |
| <span class="sd"> :return:</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_process</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s1">'Ending without manager process.'</span><span class="p">)</span> |
| <span class="k">return</span> |
| <span class="n">this_process</span> <span class="o">=</span> <span class="n">psutil</span><span class="o">.</span><span class="n">Process</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">getpid</span><span class="p">())</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">manager_process</span> <span class="o">=</span> <span class="n">psutil</span><span class="o">.</span><span class="n">Process</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_process</span><span class="o">.</span><span class="n">pid</span><span class="p">)</span> |
| <span class="k">except</span> <span class="n">psutil</span><span class="o">.</span><span class="n">NoSuchProcess</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Manager process not running."</span><span class="p">)</span> |
| <span class="k">return</span> |
| |
| <span class="c1"># First try SIGTERM</span> |
| <span class="k">if</span> <span class="n">manager_process</span><span class="o">.</span><span class="n">is_running</span><span class="p">()</span> \ |
| <span class="ow">and</span> <span class="n">manager_process</span><span class="o">.</span><span class="n">pid</span> <span class="ow">in</span> <span class="p">[</span><span class="n">x</span><span class="o">.</span><span class="n">pid</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">this_process</span><span class="o">.</span><span class="n">children</span><span class="p">()]:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Terminating manager process: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">manager_process</span><span class="o">.</span><span class="n">pid</span><span class="p">)</span> |
| <span class="n">manager_process</span><span class="o">.</span><span class="n">terminate</span><span class="p">()</span> |
| <span class="c1"># TODO: Remove magic number</span> |
| <span class="n">timeout</span> <span class="o">=</span> <span class="mi">5</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Waiting up to </span><span class="si">%s</span><span class="s2">s for manager process to exit..."</span><span class="p">,</span> <span class="n">timeout</span><span class="p">)</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">psutil</span><span class="o">.</span><span class="n">wait_procs</span><span class="p">({</span><span class="n">manager_process</span><span class="p">},</span> <span class="n">timeout</span><span class="p">)</span> |
| <span class="k">except</span> <span class="n">psutil</span><span class="o">.</span><span class="n">TimeoutExpired</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Ran out of time while waiting for "</span> |
| <span class="s2">"processes to exit"</span><span class="p">)</span> |
| |
| <span class="c1"># Then SIGKILL</span> |
| <span class="k">if</span> <span class="n">manager_process</span><span class="o">.</span><span class="n">is_running</span><span class="p">()</span> \ |
| <span class="ow">and</span> <span class="n">manager_process</span><span class="o">.</span><span class="n">pid</span> <span class="ow">in</span> <span class="p">[</span><span class="n">x</span><span class="o">.</span><span class="n">pid</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">this_process</span><span class="o">.</span><span class="n">children</span><span class="p">()]:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Killing manager process: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">manager_process</span><span class="o">.</span><span class="n">pid</span><span class="p">)</span> |
| <span class="n">manager_process</span><span class="o">.</span><span class="n">kill</span><span class="p">()</span> |
| <span class="n">manager_process</span><span class="o">.</span><span class="n">wait</span><span class="p">()</span> |
| |
| |
| <span class="k">class</span> <span class="nc">DagFileProcessorManager</span><span class="p">(</span><span class="n">LoggingMixin</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Given a list of DAG definition files, this kicks off several processors</span> |
| <span class="sd"> in parallel to process them and put the results to a multiprocessing.Queue</span> |
| <span class="sd"> for DagFileProcessorAgent to harvest. The parallelism is limited and as the</span> |
| <span class="sd"> processors finish, more are launched. The files are processed over and</span> |
| <span class="sd"> over again, but no more often than the specified interval.</span> |
| |
| <span class="sd"> :type _file_path_queue: list[unicode]</span> |
| <span class="sd"> :type _processors: dict[unicode, AbstractDagFileProcessor]</span> |
| <span class="sd"> :type _last_runtime: dict[unicode, float]</span> |
| <span class="sd"> :type _last_finish_time: dict[unicode, datetime.datetime]</span> |
| <span class="sd"> """</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">dag_directory</span><span class="p">,</span> |
| <span class="n">file_paths</span><span class="p">,</span> |
| <span class="n">max_runs</span><span class="p">,</span> |
| <span class="n">processor_factory</span><span class="p">,</span> |
| <span class="n">signal_conn</span><span class="p">,</span> |
| <span class="n">stat_queue</span><span class="p">,</span> |
| <span class="n">result_queue</span><span class="p">,</span> |
| <span class="n">async_mode</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :param dag_directory: Directory where DAG definitions are kept. All</span> |
| <span class="sd"> files in file_paths should be under this directory</span> |
| <span class="sd"> :type dag_directory: unicode</span> |
| <span class="sd"> :param file_paths: list of file paths that contain DAG definitions</span> |
| <span class="sd"> :type file_paths: list[unicode]</span> |
| <span class="sd"> :param max_runs: The number of times to parse and schedule each file. -1</span> |
| <span class="sd"> for unlimited.</span> |
| <span class="sd"> :type max_runs: int</span> |
| <span class="sd"> :param processor_factory: function that creates processors for DAG</span> |
| <span class="sd"> definition files. Arguments are (dag_definition_path)</span> |
| <span class="sd"> :type processor_factory: (unicode, unicode, list) -> (AbstractDagFileProcessor)</span> |
| <span class="sd"> :param signal_conn: connection to communicate signal with processor agent.</span> |
| <span class="sd"> :type signal_conn: airflow.models.connection.Connection</span> |
| <span class="sd"> :param stat_queue: the queue to use for passing back parsing stat to agent.</span> |
| <span class="sd"> :type stat_queue: multiprocessing.Queue</span> |
| <span class="sd"> :param result_queue: the queue to use for passing back the result to agent.</span> |
| <span class="sd"> :type result_queue: multiprocessing.Queue</span> |
| <span class="sd"> :param async_mode: whether to start the manager in async mode</span> |
| <span class="sd"> :type async_mode: bool</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span> <span class="o">=</span> <span class="n">file_paths</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_file_path_queue</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_dag_directory</span> <span class="o">=</span> <span class="n">dag_directory</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_max_runs</span> <span class="o">=</span> <span class="n">max_runs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_processor_factory</span> <span class="o">=</span> <span class="n">processor_factory</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_signal_conn</span> <span class="o">=</span> <span class="n">signal_conn</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_stat_queue</span> <span class="o">=</span> <span class="n">stat_queue</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_result_queue</span> <span class="o">=</span> <span class="n">result_queue</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_async_mode</span> <span class="o">=</span> <span class="n">async_mode</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_parallelism</span> <span class="o">=</span> <span class="n">conf</span><span class="o">.</span><span class="n">getint</span><span class="p">(</span><span class="s1">'scheduler'</span><span class="p">,</span> <span class="s1">'max_threads'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="s1">'sqlite'</span> <span class="ow">in</span> <span class="n">conf</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'core'</span><span class="p">,</span> <span class="s1">'sql_alchemy_conn'</span><span class="p">)</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parallelism</span> <span class="o">></span> <span class="mi">1</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">"Cannot use more than 1 thread when using sqlite. "</span> |
| <span class="s2">"Setting parallelism to 1"</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_parallelism</span> <span class="o">=</span> <span class="mi">1</span> |
| |
| <span class="c1"># Parse and schedule each file no faster than this interval.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_file_process_interval</span> <span class="o">=</span> <span class="n">conf</span><span class="o">.</span><span class="n">getint</span><span class="p">(</span><span class="s1">'scheduler'</span><span class="p">,</span> |
| <span class="s1">'min_file_process_interval'</span><span class="p">)</span> |
| <span class="c1"># How often to print out DAG file processing stats to the log. Default to</span> |
| <span class="c1"># 30 seconds.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">print_stats_interval</span> <span class="o">=</span> <span class="n">conf</span><span class="o">.</span><span class="n">getint</span><span class="p">(</span><span class="s1">'scheduler'</span><span class="p">,</span> |
| <span class="s1">'print_stats_interval'</span><span class="p">)</span> |
| <span class="c1"># How many seconds do we wait for tasks to heartbeat before mark them as zombies.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_zombie_threshold_secs</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">conf</span><span class="o">.</span><span class="n">getint</span><span class="p">(</span><span class="s1">'scheduler'</span><span class="p">,</span> <span class="s1">'scheduler_zombie_task_threshold'</span><span class="p">))</span> |
| <span class="c1"># Map from file path to the processor</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="c1"># Map from file path to the last runtime</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_last_runtime</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="c1"># Map from file path to the last finish time</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_last_finish_time</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_last_zombie_query_time</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> |
| <span class="c1"># Last time that the DAG dir was traversed to look for files</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">last_dag_dir_refresh_time</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> |
| <span class="c1"># Last time stats were printed</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">last_stat_print_time</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">datetime</span><span class="p">(</span><span class="mi">2000</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span> |
| <span class="c1"># TODO: Remove magic number</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_zombie_query_interval</span> <span class="o">=</span> <span class="mi">10</span> |
| <span class="c1"># Map from file path to the number of runs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_run_count</span> <span class="o">=</span> <span class="n">defaultdict</span><span class="p">(</span><span class="nb">int</span><span class="p">)</span> |
| <span class="c1"># Manager heartbeat key.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_heart_beat_key</span> <span class="o">=</span> <span class="s1">'heart-beat'</span> |
| |
| <span class="c1"># How often to scan the DAGs directory for new files. Default to 5 minutes.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dag_dir_list_interval</span> <span class="o">=</span> <span class="n">conf</span><span class="o">.</span><span class="n">getint</span><span class="p">(</span><span class="s1">'scheduler'</span><span class="p">,</span> |
| <span class="s1">'dag_dir_list_interval'</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_log</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">(</span><span class="s1">'airflow.processor_manager'</span><span class="p">)</span> |
| |
| <span class="n">signal</span><span class="o">.</span><span class="n">signal</span><span class="p">(</span><span class="n">signal</span><span class="o">.</span><span class="n">SIGINT</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_exit_gracefully</span><span class="p">)</span> |
| <span class="n">signal</span><span class="o">.</span><span class="n">signal</span><span class="p">(</span><span class="n">signal</span><span class="o">.</span><span class="n">SIGTERM</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_exit_gracefully</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_exit_gracefully</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">signum</span><span class="p">,</span> <span class="n">frame</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Helper method to clean up DAG file processors to avoid leaving orphan processes.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Exiting gracefully upon receiving signal </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">signum</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">terminate</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">end</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Finished terminating DAG processors."</span><span class="p">)</span> |
| <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">EX_OK</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">start</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Use multiple processes to parse and generate tasks for the</span> |
| <span class="sd"> DAGs in parallel. By processing them in separate processes,</span> |
| <span class="sd"> we can get parallelism and isolation from potentially harmful</span> |
| <span class="sd"> user code.</span> |
| <span class="sd"> """</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Processing files using up to </span><span class="si">%s</span><span class="s2"> processes at a time "</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parallelism</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Process each file at most once every </span><span class="si">%s</span><span class="s2"> seconds"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_file_process_interval</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s2">"Checking for new files in </span><span class="si">%s</span><span class="s2"> every </span><span class="si">%s</span><span class="s2"> seconds"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dag_directory</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">dag_dir_list_interval</span> |
| <span class="p">)</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_async_mode</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Starting DagFileProcessorManager in async mode"</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">start_in_async</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">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Starting DagFileProcessorManager in sync mode"</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">start_in_sync</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">start_in_async</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Parse DAG files repeatedly in a standalone loop.</span> |
| <span class="sd"> """</span> |
| <span class="k">while</span> <span class="kc">True</span><span class="p">:</span> |
| <span class="n">loop_start_time</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_signal_conn</span><span class="o">.</span><span class="n">poll</span><span class="p">():</span> |
| <span class="n">agent_signal</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_signal_conn</span><span class="o">.</span><span class="n">recv</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">agent_signal</span> <span class="o">==</span> <span class="n">DagParsingSignal</span><span class="o">.</span><span class="n">TERMINATE_MANAGER</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">terminate</span><span class="p">()</span> |
| <span class="k">break</span> |
| <span class="k">elif</span> <span class="n">agent_signal</span> <span class="o">==</span> <span class="n">DagParsingSignal</span><span class="o">.</span><span class="n">END_MANAGER</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">end</span><span class="p">()</span> |
| <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">EX_OK</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_refresh_dag_dir</span><span class="p">()</span> |
| |
| <span class="n">simple_dags</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">heartbeat</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">simple_dag</span> <span class="ow">in</span> <span class="n">simple_dags</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_result_queue</span><span class="o">.</span><span class="n">put</span><span class="p">(</span><span class="n">simple_dag</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_print_stat</span><span class="p">()</span> |
| |
| <span class="n">all_files_processed</span> <span class="o">=</span> <span class="nb">all</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_last_finish_time</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">file_paths</span><span class="p">)</span> |
| <span class="n">max_runs_reached</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_runs_reached</span><span class="p">()</span> |
| |
| <span class="n">dag_parsing_stat</span> <span class="o">=</span> <span class="n">DagParsingStat</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">get_all_pids</span><span class="p">(),</span> |
| <span class="n">max_runs_reached</span><span class="p">,</span> |
| <span class="n">all_files_processed</span><span class="p">,</span> |
| <span class="nb">len</span><span class="p">(</span><span class="n">simple_dags</span><span class="p">))</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_stat_queue</span><span class="o">.</span><span class="n">put</span><span class="p">(</span><span class="n">dag_parsing_stat</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">max_runs_reached</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Exiting dag parsing loop as all files "</span> |
| <span class="s2">"have been processed </span><span class="si">%s</span><span class="s2"> times"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_runs</span><span class="p">)</span> |
| <span class="k">break</span> |
| |
| <span class="n">loop_duration</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">loop_start_time</span> |
| <span class="k">if</span> <span class="n">loop_duration</span> <span class="o"><</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="n">sleep_length</span> <span class="o">=</span> <span class="mi">1</span> <span class="o">-</span> <span class="n">loop_duration</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Sleeping for </span><span class="si">%.2f</span><span class="s2"> seconds to prevent excessive logging"</span><span class="p">,</span> <span class="n">sleep_length</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="n">sleep_length</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">start_in_sync</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Parse DAG files in a loop controlled by DagParsingSignal.</span> |
| <span class="sd"> Actual DAG parsing loop will run once upon receiving one</span> |
| <span class="sd"> agent heartbeat message and will report done when finished the loop.</span> |
| <span class="sd"> """</span> |
| <span class="k">while</span> <span class="kc">True</span><span class="p">:</span> |
| <span class="n">agent_signal</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_signal_conn</span><span class="o">.</span><span class="n">recv</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">agent_signal</span> <span class="o">==</span> <span class="n">DagParsingSignal</span><span class="o">.</span><span class="n">TERMINATE_MANAGER</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">terminate</span><span class="p">()</span> |
| <span class="k">break</span> |
| <span class="k">elif</span> <span class="n">agent_signal</span> <span class="o">==</span> <span class="n">DagParsingSignal</span><span class="o">.</span><span class="n">END_MANAGER</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">end</span><span class="p">()</span> |
| <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">EX_OK</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">agent_signal</span> <span class="o">==</span> <span class="n">DagParsingSignal</span><span class="o">.</span><span class="n">AGENT_HEARTBEAT</span><span class="p">:</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_refresh_dag_dir</span><span class="p">()</span> |
| |
| <span class="n">simple_dags</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">heartbeat</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">simple_dag</span> <span class="ow">in</span> <span class="n">simple_dags</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_result_queue</span><span class="o">.</span><span class="n">put</span><span class="p">(</span><span class="n">simple_dag</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_print_stat</span><span class="p">()</span> |
| |
| <span class="n">all_files_processed</span> <span class="o">=</span> <span class="nb">all</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_last_finish_time</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">file_paths</span><span class="p">)</span> |
| <span class="n">max_runs_reached</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_runs_reached</span><span class="p">()</span> |
| |
| <span class="n">dag_parsing_stat</span> <span class="o">=</span> <span class="n">DagParsingStat</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">get_all_pids</span><span class="p">(),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">max_runs_reached</span><span class="p">(),</span> |
| <span class="n">all_files_processed</span><span class="p">,</span> |
| <span class="nb">len</span><span class="p">(</span><span class="n">simple_dags</span><span class="p">))</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_stat_queue</span><span class="o">.</span><span class="n">put</span><span class="p">(</span><span class="n">dag_parsing_stat</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">wait_until_finished</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_signal_conn</span><span class="o">.</span><span class="n">send</span><span class="p">(</span><span class="n">DagParsingSignal</span><span class="o">.</span><span class="n">MANAGER_DONE</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">max_runs_reached</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Exiting dag parsing loop as all files "</span> |
| <span class="s2">"have been processed </span><span class="si">%s</span><span class="s2"> times"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_runs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_signal_conn</span><span class="o">.</span><span class="n">send</span><span class="p">(</span><span class="n">DagParsingSignal</span><span class="o">.</span><span class="n">MANAGER_DONE</span><span class="p">)</span> |
| <span class="k">break</span> |
| |
| <span class="k">def</span> <span class="nf">_refresh_dag_dir</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Refresh file paths from dag dir if we haven't done it for too long.</span> |
| <span class="sd"> """</span> |
| <span class="n">elapsed_time_since_refresh</span> <span class="o">=</span> <span class="p">(</span><span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> <span class="o">-</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">last_dag_dir_refresh_time</span><span class="p">)</span><span class="o">.</span><span class="n">total_seconds</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">elapsed_time_since_refresh</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">dag_dir_list_interval</span><span class="p">:</span> |
| <span class="c1"># Build up a list of Python files that could contain DAGs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Searching for files in </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dag_directory</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span> <span class="o">=</span> <span class="n">list_py_file_paths</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_dag_directory</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">last_dag_dir_refresh_time</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"There are </span><span class="si">%s</span><span class="s2"> files in </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dag_directory</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">set_file_paths</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</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">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Removing old import errors"</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">clear_nonexistent_import_errors</span><span class="p">()</span> |
| <span class="k">except</span> <span class="ne">Exception</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">exception</span><span class="p">(</span><span class="s2">"Error removing old import errors"</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_print_stat</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Occasionally print out stats about how fast the files are getting processed</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="p">((</span><span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_stat_print_time</span><span class="p">)</span><span class="o">.</span><span class="n">total_seconds</span><span class="p">()</span> <span class="o">></span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">print_stats_interval</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_log_file_processing_stats</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">last_stat_print_time</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> |
| |
| <span class="nd">@provide_session</span> |
| <span class="k">def</span> <span class="nf">clear_nonexistent_import_errors</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">session</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Clears import errors for files that no longer exist.</span> |
| |
| <span class="sd"> :param session: session for ORM operations</span> |
| <span class="sd"> :type session: sqlalchemy.orm.session.Session</span> |
| <span class="sd"> """</span> |
| <span class="n">query</span> <span class="o">=</span> <span class="n">session</span><span class="o">.</span><span class="n">query</span><span class="p">(</span><span class="n">errors</span><span class="o">.</span><span class="n">ImportError</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span><span class="p">:</span> |
| <span class="n">query</span> <span class="o">=</span> <span class="n">query</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span> |
| <span class="o">~</span><span class="n">errors</span><span class="o">.</span><span class="n">ImportError</span><span class="o">.</span><span class="n">filename</span><span class="o">.</span><span class="n">in_</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="n">query</span><span class="o">.</span><span class="n">delete</span><span class="p">(</span><span class="n">synchronize_session</span><span class="o">=</span><span class="s1">'fetch'</span><span class="p">)</span> |
| <span class="n">session</span><span class="o">.</span><span class="n">commit</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">_log_file_processing_stats</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">known_file_paths</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Print out stats about how files are getting processed.</span> |
| |
| <span class="sd"> :param known_file_paths: a list of file paths that may contain Airflow</span> |
| <span class="sd"> DAG definitions</span> |
| <span class="sd"> :type known_file_paths: list[unicode]</span> |
| <span class="sd"> :return: None</span> |
| <span class="sd"> """</span> |
| |
| <span class="c1"># File Path: Path to the file containing the DAG definition</span> |
| <span class="c1"># PID: PID associated with the process that's processing the file. May</span> |
| <span class="c1"># be empty.</span> |
| <span class="c1"># Runtime: If the process is currently running, how long it's been</span> |
| <span class="c1"># running for in seconds.</span> |
| <span class="c1"># Last Runtime: If the process ran before, how long did it take to</span> |
| <span class="c1"># finish in seconds</span> |
| <span class="c1"># Last Run: When the file finished processing in the previous run.</span> |
| <span class="n">headers</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"File Path"</span><span class="p">,</span> |
| <span class="s2">"PID"</span><span class="p">,</span> |
| <span class="s2">"Runtime"</span><span class="p">,</span> |
| <span class="s2">"Last Runtime"</span><span class="p">,</span> |
| <span class="s2">"Last Run"</span><span class="p">]</span> |
| |
| <span class="n">rows</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">file_path</span> <span class="ow">in</span> <span class="n">known_file_paths</span><span class="p">:</span> |
| <span class="n">last_runtime</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_last_runtime</span><span class="p">(</span><span class="n">file_path</span><span class="p">)</span> |
| <span class="n">file_name</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">basename</span><span class="p">(</span><span class="n">file_path</span><span class="p">)</span> |
| <span class="n">file_name</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">splitext</span><span class="p">(</span><span class="n">file_name</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">sep</span><span class="p">,</span> <span class="s1">'.'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">last_runtime</span><span class="p">:</span> |
| <span class="n">Stats</span><span class="o">.</span><span class="n">gauge</span><span class="p">(</span> |
| <span class="s1">'dag_processing.last_runtime.</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">file_name</span><span class="p">),</span> |
| <span class="n">last_runtime</span> |
| <span class="p">)</span> |
| |
| <span class="n">processor_pid</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_pid</span><span class="p">(</span><span class="n">file_path</span><span class="p">)</span> |
| <span class="n">processor_start_time</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_start_time</span><span class="p">(</span><span class="n">file_path</span><span class="p">)</span> |
| <span class="n">runtime</span> <span class="o">=</span> <span class="p">((</span><span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> <span class="o">-</span> <span class="n">processor_start_time</span><span class="p">)</span><span class="o">.</span><span class="n">total_seconds</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">processor_start_time</span> <span class="k">else</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="n">last_run</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_last_finish_time</span><span class="p">(</span><span class="n">file_path</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">last_run</span><span class="p">:</span> |
| <span class="n">seconds_ago</span> <span class="o">=</span> <span class="p">(</span><span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> <span class="o">-</span> <span class="n">last_run</span><span class="p">)</span><span class="o">.</span><span class="n">total_seconds</span><span class="p">()</span> |
| <span class="n">Stats</span><span class="o">.</span><span class="n">gauge</span><span class="p">(</span> |
| <span class="s1">'dag_processing.last_run.seconds_ago.</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">file_name</span><span class="p">),</span> |
| <span class="n">seconds_ago</span> |
| <span class="p">)</span> |
| |
| <span class="n">rows</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">file_path</span><span class="p">,</span> |
| <span class="n">processor_pid</span><span class="p">,</span> |
| <span class="n">runtime</span><span class="p">,</span> |
| <span class="n">last_runtime</span><span class="p">,</span> |
| <span class="n">last_run</span><span class="p">))</span> |
| |
| <span class="c1"># Sort by longest last runtime. (Can't sort None values in python3)</span> |
| <span class="n">rows</span> <span class="o">=</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">rows</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span> <span class="ow">or</span> <span class="mf">0.0</span><span class="p">)</span> |
| |
| <span class="n">formatted_rows</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">file_path</span><span class="p">,</span> <span class="n">pid</span><span class="p">,</span> <span class="n">runtime</span><span class="p">,</span> <span class="n">last_runtime</span><span class="p">,</span> <span class="n">last_run</span> <span class="ow">in</span> <span class="n">rows</span><span class="p">:</span> |
| <span class="n">formatted_rows</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">file_path</span><span class="p">,</span> |
| <span class="n">pid</span><span class="p">,</span> |
| <span class="s2">"</span><span class="si">{:.2f}</span><span class="s2">s"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">runtime</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">runtime</span> <span class="k">else</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="s2">"</span><span class="si">{:.2f}</span><span class="s2">s"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">last_runtime</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">last_runtime</span> <span class="k">else</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">last_run</span><span class="o">.</span><span class="n">strftime</span><span class="p">(</span><span class="s2">"%Y-%m-</span><span class="si">%d</span><span class="s2">T%H:%M:%S"</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">last_run</span> <span class="k">else</span> <span class="kc">None</span><span class="p">))</span> |
| <span class="n">log_str</span> <span class="o">=</span> <span class="p">(</span><span class="s2">"</span><span class="se">\n</span><span class="s2">"</span> <span class="o">+</span> |
| <span class="s2">"="</span> <span class="o">*</span> <span class="mi">80</span> <span class="o">+</span> |
| <span class="s2">"</span><span class="se">\n</span><span class="s2">"</span> <span class="o">+</span> |
| <span class="s2">"DAG File Processing Stats</span><span class="se">\n\n</span><span class="s2">"</span> <span class="o">+</span> |
| <span class="n">tabulate</span><span class="p">(</span><span class="n">formatted_rows</span><span class="p">,</span> <span class="n">headers</span><span class="o">=</span><span class="n">headers</span><span class="p">)</span> <span class="o">+</span> |
| <span class="s2">"</span><span class="se">\n</span><span class="s2">"</span> <span class="o">+</span> |
| <span class="s2">"="</span> <span class="o">*</span> <span class="mi">80</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="n">log_str</span><span class="p">)</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">file_paths</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span> |
| |
| <span class="k">def</span> <span class="nf">get_pid</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">file_path</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :param file_path: the path to the file that's being processed</span> |
| <span class="sd"> :type file_path: unicode</span> |
| <span class="sd"> :return: the PID of the process processing the given file or None if</span> |
| <span class="sd"> the specified file is not being processed</span> |
| <span class="sd"> :rtype: int</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">file_path</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="p">[</span><span class="n">file_path</span><span class="p">]</span><span class="o">.</span><span class="n">pid</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| |
| <span class="k">def</span> <span class="nf">get_all_pids</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :return: a list of the PIDs for the processors that are running</span> |
| <span class="sd"> :rtype: List[int]</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">x</span><span class="o">.</span><span class="n">pid</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="o">.</span><span class="n">values</span><span class="p">()]</span> |
| |
| <span class="k">def</span> <span class="nf">get_runtime</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">file_path</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :param file_path: the path to the file that's being processed</span> |
| <span class="sd"> :type file_path: unicode</span> |
| <span class="sd"> :return: the current runtime (in seconds) of the process that's</span> |
| <span class="sd"> processing the specified file or None if the file is not currently</span> |
| <span class="sd"> being processed</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">file_path</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="p">[</span><span class="n">file_path</span><span class="p">]</span><span class="o">.</span><span class="n">start_time</span><span class="p">)</span>\ |
| <span class="o">.</span><span class="n">total_seconds</span><span class="p">()</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| |
| <span class="k">def</span> <span class="nf">get_last_runtime</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">file_path</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :param file_path: the path to the file that was processed</span> |
| <span class="sd"> :type file_path: unicode</span> |
| <span class="sd"> :return: the runtime (in seconds) of the process of the last run, or</span> |
| <span class="sd"> None if the file was never processed.</span> |
| <span class="sd"> :rtype: float</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_last_runtime</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">file_path</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">get_last_finish_time</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">file_path</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :param file_path: the path to the file that was processed</span> |
| <span class="sd"> :type file_path: unicode</span> |
| <span class="sd"> :return: the finish time of the process of the last run, or None if the</span> |
| <span class="sd"> file was never processed.</span> |
| <span class="sd"> :rtype: datetime</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_last_finish_time</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">file_path</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">get_start_time</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">file_path</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :param file_path: the path to the file that's being processed</span> |
| <span class="sd"> :type file_path: unicode</span> |
| <span class="sd"> :return: the start time of the process that's processing the</span> |
| <span class="sd"> specified file or None if the file is not currently being processed</span> |
| <span class="sd"> :rtype: datetime</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">file_path</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="p">[</span><span class="n">file_path</span><span class="p">]</span><span class="o">.</span><span class="n">start_time</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| |
| <span class="k">def</span> <span class="nf">set_file_paths</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">new_file_paths</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Update this with a new set of paths to DAG definition files.</span> |
| |
| <span class="sd"> :param new_file_paths: list of paths to DAG definition files</span> |
| <span class="sd"> :type new_file_paths: list[unicode]</span> |
| <span class="sd"> :return: None</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span> <span class="o">=</span> <span class="n">new_file_paths</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_file_path_queue</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_file_path_queue</span> |
| <span class="k">if</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">new_file_paths</span><span class="p">]</span> |
| <span class="c1"># Stop processors that are working on deleted files</span> |
| <span class="n">filtered_processors</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">for</span> <span class="n">file_path</span><span class="p">,</span> <span class="n">processor</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">if</span> <span class="n">file_path</span> <span class="ow">in</span> <span class="n">new_file_paths</span><span class="p">:</span> |
| <span class="n">filtered_processors</span><span class="p">[</span><span class="n">file_path</span><span class="p">]</span> <span class="o">=</span> <span class="n">processor</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s2">"Stopping processor for </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">file_path</span><span class="p">)</span> |
| <span class="n">processor</span><span class="o">.</span><span class="n">terminate</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span> <span class="o">=</span> <span class="n">filtered_processors</span> |
| |
| <span class="k">def</span> <span class="nf">processing_count</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :return: the number of files currently being processed</span> |
| <span class="sd"> :rtype: int</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">wait_until_finished</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sleeps until all the processors are done.</span> |
| <span class="sd"> """</span> |
| <span class="k">for</span> <span class="n">file_path</span><span class="p">,</span> <span class="n">processor</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">while</span> <span class="ow">not</span> <span class="n">processor</span><span class="o">.</span><span class="n">done</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="mf">0.1</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">heartbeat</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> This should be periodically called by the manager loop. This method will</span> |
| <span class="sd"> kick off new processes to process DAG definition files and read the</span> |
| <span class="sd"> results from the finished processors.</span> |
| |
| <span class="sd"> :return: a list of SimpleDags that were produced by processors that</span> |
| <span class="sd"> have finished since the last time this was called</span> |
| <span class="sd"> :rtype: list[airflow.utils.dag_processing.SimpleDag]</span> |
| <span class="sd"> """</span> |
| <span class="n">finished_processors</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="sd">""":type : dict[unicode, AbstractDagFileProcessor]"""</span> |
| <span class="n">running_processors</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="sd">""":type : dict[unicode, AbstractDagFileProcessor]"""</span> |
| |
| <span class="k">for</span> <span class="n">file_path</span><span class="p">,</span> <span class="n">processor</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">if</span> <span class="n">processor</span><span class="o">.</span><span class="n">done</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Processor for </span><span class="si">%s</span><span class="s2"> finished"</span><span class="p">,</span> <span class="n">file_path</span><span class="p">)</span> |
| <span class="n">now</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> |
| <span class="n">finished_processors</span><span class="p">[</span><span class="n">file_path</span><span class="p">]</span> <span class="o">=</span> <span class="n">processor</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_last_runtime</span><span class="p">[</span><span class="n">file_path</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="n">now</span> <span class="o">-</span> |
| <span class="n">processor</span><span class="o">.</span><span class="n">start_time</span><span class="p">)</span><span class="o">.</span><span class="n">total_seconds</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_last_finish_time</span><span class="p">[</span><span class="n">file_path</span><span class="p">]</span> <span class="o">=</span> <span class="n">now</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_run_count</span><span class="p">[</span><span class="n">file_path</span><span class="p">]</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">running_processors</span><span class="p">[</span><span class="n">file_path</span><span class="p">]</span> <span class="o">=</span> <span class="n">processor</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span> <span class="o">=</span> <span class="n">running_processors</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"</span><span class="si">%s</span><span class="s2">/</span><span class="si">%s</span><span class="s2"> DAG parsing processes running"</span><span class="p">,</span> |
| <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parallelism</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"</span><span class="si">%s</span><span class="s2"> file paths queued for processing"</span><span class="p">,</span> |
| <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_file_path_queue</span><span class="p">))</span> |
| |
| <span class="c1"># Collect all the DAGs that were found in the processed files</span> |
| <span class="n">simple_dags</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">file_path</span><span class="p">,</span> <span class="n">processor</span> <span class="ow">in</span> <span class="n">finished_processors</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">if</span> <span class="n">processor</span><span class="o">.</span><span class="n">result</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span> |
| <span class="s2">"Processor for </span><span class="si">%s</span><span class="s2"> exited with return code </span><span class="si">%s</span><span class="s2">."</span><span class="p">,</span> |
| <span class="n">processor</span><span class="o">.</span><span class="n">file_path</span><span class="p">,</span> <span class="n">processor</span><span class="o">.</span><span class="n">exit_code</span> |
| <span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">simple_dag</span> <span class="ow">in</span> <span class="n">processor</span><span class="o">.</span><span class="n">result</span><span class="p">:</span> |
| <span class="n">simple_dags</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">simple_dag</span><span class="p">)</span> |
| |
| <span class="c1"># Generate more file paths to process if we processed all the files</span> |
| <span class="c1"># already.</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_file_path_queue</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="c1"># If the file path is already being processed, or if a file was</span> |
| <span class="c1"># processed recently, wait until the next batch</span> |
| <span class="n">file_paths_in_progress</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="o">.</span><span class="n">keys</span><span class="p">()</span> |
| <span class="n">now</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> |
| <span class="n">file_paths_recently_processed</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">file_path</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span><span class="p">:</span> |
| <span class="n">last_finish_time</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_last_finish_time</span><span class="p">(</span><span class="n">file_path</span><span class="p">)</span> |
| <span class="k">if</span> <span class="p">(</span><span class="n">last_finish_time</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> |
| <span class="p">(</span><span class="n">now</span> <span class="o">-</span> <span class="n">last_finish_time</span><span class="p">)</span><span class="o">.</span><span class="n">total_seconds</span><span class="p">()</span> <span class="o"><</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_file_process_interval</span><span class="p">):</span> |
| <span class="n">file_paths_recently_processed</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">file_path</span><span class="p">)</span> |
| |
| <span class="n">files_paths_at_run_limit</span> <span class="o">=</span> <span class="p">[</span><span class="n">file_path</span> |
| <span class="k">for</span> <span class="n">file_path</span><span class="p">,</span> <span class="n">num_runs</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_run_count</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">num_runs</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_runs</span><span class="p">]</span> |
| |
| <span class="n">files_paths_to_queue</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">set</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span><span class="p">)</span> <span class="o">-</span> |
| <span class="nb">set</span><span class="p">(</span><span class="n">file_paths_in_progress</span><span class="p">)</span> <span class="o">-</span> |
| <span class="nb">set</span><span class="p">(</span><span class="n">file_paths_recently_processed</span><span class="p">)</span> <span class="o">-</span> |
| <span class="nb">set</span><span class="p">(</span><span class="n">files_paths_at_run_limit</span><span class="p">))</span> |
| |
| <span class="k">for</span> <span class="n">file_path</span><span class="p">,</span> <span class="n">processor</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span> |
| <span class="s2">"File path </span><span class="si">%s</span><span class="s2"> is still being processed (started: </span><span class="si">%s</span><span class="s2">)"</span><span class="p">,</span> |
| <span class="n">processor</span><span class="o">.</span><span class="n">file_path</span><span class="p">,</span> <span class="n">processor</span><span class="o">.</span><span class="n">start_time</span><span class="o">.</span><span class="n">isoformat</span><span class="p">()</span> |
| <span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span> |
| <span class="s2">"Queuing the following files for processing:</span><span class="se">\n\t</span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> |
| <span class="s2">"</span><span class="se">\n\t</span><span class="s2">"</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">files_paths_to_queue</span><span class="p">)</span> |
| <span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_file_path_queue</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">files_paths_to_queue</span><span class="p">)</span> |
| |
| <span class="n">zombies</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_find_zombies</span><span class="p">()</span> |
| |
| <span class="c1"># Start more processors if we have enough slots and files to process</span> |
| <span class="k">while</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_parallelism</span> <span class="o">-</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span> <span class="ow">and</span> |
| <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_file_path_queue</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">):</span> |
| <span class="n">file_path</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_file_path_queue</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span> |
| <span class="n">processor</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_processor_factory</span><span class="p">(</span><span class="n">file_path</span><span class="p">,</span> <span class="n">zombies</span><span class="p">)</span> |
| |
| <span class="n">processor</span><span class="o">.</span><span class="n">start</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span> |
| <span class="s2">"Started a process (PID: </span><span class="si">%s</span><span class="s2">) to generate tasks for </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> |
| <span class="n">processor</span><span class="o">.</span><span class="n">pid</span><span class="p">,</span> <span class="n">file_path</span> |
| <span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="p">[</span><span class="n">file_path</span><span class="p">]</span> <span class="o">=</span> <span class="n">processor</span> |
| |
| <span class="c1"># Update heartbeat count.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_run_count</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">_heart_beat_key</span><span class="p">]</span> <span class="o">+=</span> <span class="mi">1</span> |
| |
| <span class="k">return</span> <span class="n">simple_dags</span> |
| |
| <span class="nd">@provide_session</span> |
| <span class="k">def</span> <span class="nf">_find_zombies</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">session</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Find zombie task instances, which are tasks haven't heartbeated for too long.</span> |
| <span class="sd"> :return: Zombie task instances in SimpleTaskInstance format.</span> |
| <span class="sd"> """</span> |
| <span class="n">now</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> |
| <span class="n">zombies</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">if</span> <span class="p">(</span><span class="n">now</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">_last_zombie_query_time</span><span class="p">)</span><span class="o">.</span><span class="n">total_seconds</span><span class="p">()</span> \ |
| <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">_zombie_query_interval</span><span class="p">:</span> |
| <span class="c1"># to avoid circular imports</span> |
| <span class="kn">from</span> <span class="nn">airflow.jobs</span> <span class="k">import</span> <span class="n">LocalTaskJob</span> <span class="k">as</span> <span class="n">LJ</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Finding 'running' jobs without a recent heartbeat"</span><span class="p">)</span> |
| <span class="n">TI</span> <span class="o">=</span> <span class="n">airflow</span><span class="o">.</span><span class="n">models</span><span class="o">.</span><span class="n">TaskInstance</span> |
| <span class="n">limit_dttm</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> <span class="o">-</span> <span class="n">timedelta</span><span class="p">(</span> |
| <span class="n">seconds</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_zombie_threshold_secs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Failing jobs without heartbeat after </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">limit_dttm</span><span class="p">)</span> |
| |
| <span class="n">tis</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">session</span><span class="o">.</span><span class="n">query</span><span class="p">(</span><span class="n">TI</span><span class="p">)</span> |
| <span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">LJ</span><span class="p">,</span> <span class="n">TI</span><span class="o">.</span><span class="n">job_id</span> <span class="o">==</span> <span class="n">LJ</span><span class="o">.</span><span class="n">id</span><span class="p">)</span> |
| <span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">TI</span><span class="o">.</span><span class="n">state</span> <span class="o">==</span> <span class="n">State</span><span class="o">.</span><span class="n">RUNNING</span><span class="p">)</span> |
| <span class="o">.</span><span class="n">filter</span><span class="p">(</span> |
| <span class="n">or_</span><span class="p">(</span> |
| <span class="n">LJ</span><span class="o">.</span><span class="n">state</span> <span class="o">!=</span> <span class="n">State</span><span class="o">.</span><span class="n">RUNNING</span><span class="p">,</span> |
| <span class="n">LJ</span><span class="o">.</span><span class="n">latest_heartbeat</span> <span class="o"><</span> <span class="n">limit_dttm</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">all</span><span class="p">()</span> |
| <span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_last_zombie_query_time</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">ti</span> <span class="ow">in</span> <span class="n">tis</span><span class="p">:</span> |
| <span class="n">zombies</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">SimpleTaskInstance</span><span class="p">(</span><span class="n">ti</span><span class="p">))</span> |
| |
| <span class="k">return</span> <span class="n">zombies</span> |
| |
| <span class="k">def</span> <span class="nf">max_runs_reached</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :return: whether all file paths have been processed max_runs times</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_runs</span> <span class="o">==</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span> <span class="c1"># Unlimited runs.</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| <span class="k">for</span> <span class="n">file_path</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_file_paths</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_run_count</span><span class="p">[</span><span class="n">file_path</span><span class="p">]</span> <span class="o"><</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_runs</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">_run_count</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">_heart_beat_key</span><span class="p">]</span> <span class="o"><</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_runs</span><span class="p">:</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| <span class="k">return</span> <span class="kc">True</span> |
| |
| <span class="k">def</span> <span class="nf">terminate</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Stops all running processors</span> |
| <span class="sd"> :return: None</span> |
| <span class="sd"> """</span> |
| <span class="k">for</span> <span class="n">processor</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_processors</span><span class="o">.</span><span class="n">values</span><span class="p">():</span> |
| <span class="n">processor</span><span class="o">.</span><span class="n">terminate</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">end</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Kill all child processes on exit since we don't want to leave</span> |
| <span class="sd"> them as orphaned.</span> |
| <span class="sd"> """</span> |
| <span class="n">pids_to_kill</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_all_pids</span><span class="p">()</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">pids_to_kill</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="c1"># First try SIGTERM</span> |
| <span class="n">this_process</span> <span class="o">=</span> <span class="n">psutil</span><span class="o">.</span><span class="n">Process</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">getpid</span><span class="p">())</span> |
| <span class="c1"># Only check child processes to ensure that we don't have a case</span> |
| <span class="c1"># where we kill the wrong process because a child process died</span> |
| <span class="c1"># but the PID got reused.</span> |
| <span class="n">child_processes</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">this_process</span><span class="o">.</span><span class="n">children</span><span class="p">(</span><span class="n">recursive</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">x</span><span class="o">.</span><span class="n">is_running</span><span class="p">()</span> <span class="ow">and</span> <span class="n">x</span><span class="o">.</span><span class="n">pid</span> <span class="ow">in</span> <span class="n">pids_to_kill</span><span class="p">]</span> |
| <span class="k">for</span> <span class="n">child</span> <span class="ow">in</span> <span class="n">child_processes</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Terminating child PID: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">child</span><span class="o">.</span><span class="n">pid</span><span class="p">)</span> |
| <span class="n">child</span><span class="o">.</span><span class="n">terminate</span><span class="p">()</span> |
| <span class="c1"># TODO: Remove magic number</span> |
| <span class="n">timeout</span> <span class="o">=</span> <span class="mi">5</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Waiting up to </span><span class="si">%s</span><span class="s2"> seconds for processes to exit..."</span><span class="p">,</span> <span class="n">timeout</span><span class="p">)</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">psutil</span><span class="o">.</span><span class="n">wait_procs</span><span class="p">(</span> |
| <span class="n">child_processes</span><span class="p">,</span> <span class="n">timeout</span><span class="o">=</span><span class="n">timeout</span><span class="p">,</span> |
| <span class="n">callback</span><span class="o">=</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Terminated PID </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">x</span><span class="o">.</span><span class="n">pid</span><span class="p">))</span> |
| <span class="k">except</span> <span class="n">psutil</span><span class="o">.</span><span class="n">TimeoutExpired</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Ran out of time while waiting for processes to exit"</span><span class="p">)</span> |
| |
| <span class="c1"># Then SIGKILL</span> |
| <span class="n">child_processes</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">this_process</span><span class="o">.</span><span class="n">children</span><span class="p">(</span><span class="n">recursive</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">x</span><span class="o">.</span><span class="n">is_running</span><span class="p">()</span> <span class="ow">and</span> <span class="n">x</span><span class="o">.</span><span class="n">pid</span> <span class="ow">in</span> <span class="n">pids_to_kill</span><span class="p">]</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">child_processes</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"SIGKILL processes that did not terminate gracefully"</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">child</span> <span class="ow">in</span> <span class="n">child_processes</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Killing child PID: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">child</span><span class="o">.</span><span class="n">pid</span><span class="p">)</span> |
| <span class="n">child</span><span class="o">.</span><span class="n">kill</span><span class="p">()</span> |
| <span class="n">child</span><span class="o">.</span><span class="n">wait</span><span class="p">()</span> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| |
| </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"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |