blob: c9b89ad244646981eb90763756dc3242ee30dd5c [file] [log] [blame]
<!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.executors.celery_executor &mdash; Airflow Documentation</title>
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
<script src="../../../_static/js/modernizr.min.js"></script>
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search">
<a href="../../../index.html" class="icon icon-home"> Airflow
</a>
<div class="version">
1.10.2
</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 &amp; 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="../../../code.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> &raquo;</li>
<li><a href="../../index.html">Module code</a> &raquo;</li>
<li>airflow.executors.celery_executor</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.executors.celery_executor</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"># &quot;License&quot;); 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"># &quot;AS IS&quot; 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="kn">import</span> <span class="nn">subprocess</span>
<span class="kn">import</span> <span class="nn">time</span>
<span class="kn">import</span> <span class="nn">os</span>
<span class="kn">from</span> <span class="nn">celery</span> <span class="k">import</span> <span class="n">Celery</span>
<span class="kn">from</span> <span class="nn">celery</span> <span class="k">import</span> <span class="n">states</span> <span class="k">as</span> <span class="n">celery_states</span>
<span class="kn">from</span> <span class="nn">airflow.config_templates.default_celery</span> <span class="k">import</span> <span class="n">DEFAULT_CELERY_CONFIG</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.executors.base_executor</span> <span class="k">import</span> <span class="n">BaseExecutor</span>
<span class="kn">from</span> <span class="nn">airflow</span> <span class="k">import</span> <span class="n">configuration</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.module_loading</span> <span class="k">import</span> <span class="n">import_string</span>
<span class="sd">&#39;&#39;&#39;</span>
<span class="sd">To start the celery worker, run the command:</span>
<span class="sd">airflow worker</span>
<span class="sd">&#39;&#39;&#39;</span>
<span class="k">if</span> <span class="n">configuration</span><span class="o">.</span><span class="n">conf</span><span class="o">.</span><span class="n">has_option</span><span class="p">(</span><span class="s1">&#39;celery&#39;</span><span class="p">,</span> <span class="s1">&#39;celery_config_options&#39;</span><span class="p">):</span>
<span class="n">celery_configuration</span> <span class="o">=</span> <span class="n">import_string</span><span class="p">(</span>
<span class="n">configuration</span><span class="o">.</span><span class="n">conf</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;celery&#39;</span><span class="p">,</span> <span class="s1">&#39;celery_config_options&#39;</span><span class="p">)</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">celery_configuration</span> <span class="o">=</span> <span class="n">DEFAULT_CELERY_CONFIG</span>
<span class="n">app</span> <span class="o">=</span> <span class="n">Celery</span><span class="p">(</span>
<span class="n">configuration</span><span class="o">.</span><span class="n">conf</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;celery&#39;</span><span class="p">,</span> <span class="s1">&#39;CELERY_APP_NAME&#39;</span><span class="p">),</span>
<span class="n">config_source</span><span class="o">=</span><span class="n">celery_configuration</span><span class="p">)</span>
<span class="nd">@app</span><span class="o">.</span><span class="n">task</span>
<span class="k">def</span> <span class="nf">execute_command</span><span class="p">(</span><span class="n">command</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">info</span><span class="p">(</span><span class="s2">&quot;Executing command in Celery: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">command</span><span class="p">)</span>
<span class="n">env</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">subprocess</span><span class="o">.</span><span class="n">check_call</span><span class="p">(</span><span class="n">command</span><span class="p">,</span> <span class="n">shell</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">stderr</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">STDOUT</span><span class="p">,</span>
<span class="n">close_fds</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">env</span><span class="o">=</span><span class="n">env</span><span class="p">)</span>
<span class="k">except</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">CalledProcessError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="n">log</span><span class="o">.</span><span class="n">exception</span><span class="p">(</span><span class="s1">&#39;execute_command encountered a CalledProcessError&#39;</span><span class="p">)</span>
<span class="n">log</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="n">e</span><span class="o">.</span><span class="n">output</span><span class="p">)</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">&#39;Celery command failed&#39;</span><span class="p">)</span>
<div class="viewcode-block" id="CeleryExecutor"><a class="viewcode-back" href="../../../code.html#airflow.executors.celery_executor.CeleryExecutor">[docs]</a><span class="k">class</span> <span class="nc">CeleryExecutor</span><span class="p">(</span><span class="n">BaseExecutor</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> CeleryExecutor is recommended for production use of Airflow. It allows</span>
<span class="sd"> distributing the execution of task instances to multiple worker nodes.</span>
<span class="sd"> Celery is a simple, flexible and reliable distributed system to process</span>
<span class="sd"> vast amounts of messages, while providing operations with the tools</span>
<span class="sd"> required to maintain such a system.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="CeleryExecutor.start"><a class="viewcode-back" href="../../../code.html#airflow.executors.celery_executor.CeleryExecutor.start">[docs]</a> <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="bp">self</span><span class="o">.</span><span class="n">tasks</span> <span class="o">=</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">last_state</span> <span class="o">=</span> <span class="p">{}</span></div>
<div class="viewcode-block" id="CeleryExecutor.execute_async"><a class="viewcode-back" href="../../../code.html#airflow.executors.celery_executor.CeleryExecutor.execute_async">[docs]</a> <span class="k">def</span> <span class="nf">execute_async</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">command</span><span class="p">,</span>
<span class="n">queue</span><span class="o">=</span><span class="n">DEFAULT_CELERY_CONFIG</span><span class="p">[</span><span class="s1">&#39;task_default_queue&#39;</span><span class="p">],</span>
<span class="n">executor_config</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;[celery] queuing </span><span class="si">{key}</span><span class="s2"> through celery, &quot;</span>
<span class="s2">&quot;queue=</span><span class="si">{queue}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="nb">locals</span><span class="p">()))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tasks</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="o">=</span> <span class="n">execute_command</span><span class="o">.</span><span class="n">apply_async</span><span class="p">(</span>
<span class="n">args</span><span class="o">=</span><span class="p">[</span><span class="n">command</span><span class="p">],</span> <span class="n">queue</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">last_state</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="o">=</span> <span class="n">celery_states</span><span class="o">.</span><span class="n">PENDING</span></div>
<div class="viewcode-block" id="CeleryExecutor.sync"><a class="viewcode-back" href="../../../code.html#airflow.executors.celery_executor.CeleryExecutor.sync">[docs]</a> <span class="k">def</span> <span class="nf">sync</span><span class="p">(</span><span class="bp">self</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">&quot;Inquiring about </span><span class="si">%s</span><span class="s2"> celery task(s)&quot;</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">tasks</span><span class="p">))</span>
<span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">task</span> <span class="ow">in</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">tasks</span><span class="o">.</span><span class="n">items</span><span class="p">()):</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">state</span> <span class="o">=</span> <span class="n">task</span><span class="o">.</span><span class="n">state</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_state</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="o">!=</span> <span class="n">state</span><span class="p">:</span>
<span class="k">if</span> <span class="n">state</span> <span class="o">==</span> <span class="n">celery_states</span><span class="o">.</span><span class="n">SUCCESS</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">success</span><span class="p">(</span><span class="n">key</span><span class="p">)</span>
<span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">tasks</span><span class="p">[</span><span class="n">key</span><span class="p">]</span>
<span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_state</span><span class="p">[</span><span class="n">key</span><span class="p">]</span>
<span class="k">elif</span> <span class="n">state</span> <span class="o">==</span> <span class="n">celery_states</span><span class="o">.</span><span class="n">FAILURE</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fail</span><span class="p">(</span><span class="n">key</span><span class="p">)</span>
<span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">tasks</span><span class="p">[</span><span class="n">key</span><span class="p">]</span>
<span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_state</span><span class="p">[</span><span class="n">key</span><span class="p">]</span>
<span class="k">elif</span> <span class="n">state</span> <span class="o">==</span> <span class="n">celery_states</span><span class="o">.</span><span class="n">REVOKED</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fail</span><span class="p">(</span><span class="n">key</span><span class="p">)</span>
<span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">tasks</span><span class="p">[</span><span class="n">key</span><span class="p">]</span>
<span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_state</span><span class="p">[</span><span class="n">key</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">info</span><span class="p">(</span><span class="s2">&quot;Unexpected state: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">state</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">last_state</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="o">=</span> <span class="n">state</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</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">&quot;Error syncing the celery executor, ignoring it:&quot;</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="n">e</span><span class="p">)</span></div>
<div class="viewcode-block" id="CeleryExecutor.end"><a class="viewcode-back" href="../../../code.html#airflow.executors.celery_executor.CeleryExecutor.end">[docs]</a> <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="n">synchronous</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="k">if</span> <span class="n">synchronous</span><span class="p">:</span>
<span class="k">while</span> <span class="nb">any</span><span class="p">([</span>
<span class="n">task</span><span class="o">.</span><span class="n">state</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">celery_states</span><span class="o">.</span><span class="n">READY_STATES</span>
<span class="k">for</span> <span class="n">task</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">tasks</span><span class="o">.</span><span class="n">values</span><span class="p">()]):</span>
<span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">5</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sync</span><span class="p">()</span></div></div>
</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" 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>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>