blob: 7c73959a3b43e0b74fbcbf4dbc66d21196be287f [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>
<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>
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-140539454-1']);
_gaq.push(['_trackPageview']);
</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>
</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">
1.10.5
</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 Reference</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">REST API Reference</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">Python API Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../privacy_notice.html">Privacy Notice</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><a href="../executors.html">airflow.executors</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">math</span>
<span class="kn">import</span> <span class="nn">os</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">traceback</span>
<span class="kn">from</span> <span class="nn">multiprocessing</span> <span class="k">import</span> <span class="n">Pool</span><span class="p">,</span> <span class="n">cpu_count</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</span> <span class="k">import</span> <span class="n">configuration</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.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="kn">from</span> <span class="nn">airflow.utils.timeout</span> <span class="k">import</span> <span class="n">timeout</span>
<span class="c1"># Make it constant for unit test.</span>
<div class="viewcode-block" id="CELERY_FETCH_ERR_MSG_HEADER"><a class="viewcode-back" href="../../../_api/airflow/executors/celery_executor/index.html#airflow.executors.celery_executor.CELERY_FETCH_ERR_MSG_HEADER">[docs]</a><span class="n">CELERY_FETCH_ERR_MSG_HEADER</span> <span class="o">=</span> <span class="s1">&#39;Error fetching Celery task state&#39;</span></div>
<div class="viewcode-block" id="CELERY_SEND_ERR_MSG_HEADER"><a class="viewcode-back" href="../../../_api/airflow/executors/celery_executor/index.html#airflow.executors.celery_executor.CELERY_SEND_ERR_MSG_HEADER">[docs]</a><span class="n">CELERY_SEND_ERR_MSG_HEADER</span> <span class="o">=</span> <span class="s1">&#39;Error sending Celery task&#39;</span></div>
<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>
<div class="viewcode-block" id="celery_configuration"><a class="viewcode-back" href="../../../_api/airflow/executors/celery_executor/index.html#airflow.executors.celery_executor.celery_configuration">[docs]</a> <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></div>
<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>
<div class="viewcode-block" id="app"><a class="viewcode-back" href="../../../_api/airflow/executors/celery_executor/index.html#airflow.executors.celery_executor.app">[docs]</a><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></div>
<span class="nd">@app</span><span class="o">.</span><span class="n">task</span>
<div class="viewcode-block" id="execute_command"><a class="viewcode-back" href="../../../_api/airflow/executors/celery_executor/index.html#airflow.executors.celery_executor.execute_command">[docs]</a><span class="k">def</span> <span class="nf">execute_command</span><span class="p">(</span><span class="n">command_to_exec</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_to_exec</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_to_exec</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>
<div class="viewcode-block" id="ExceptionWithTraceback"><a class="viewcode-back" href="../../../_api/airflow/executors/celery_executor/index.html#airflow.executors.celery_executor.ExceptionWithTraceback">[docs]</a><span class="k">class</span> <span class="nc">ExceptionWithTraceback</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Wrapper class used to propagate exceptions to parent processes from subprocesses.</span>
<span class="sd"> :param exception: The exception to wrap</span>
<span class="sd"> :type exception: Exception</span>
<span class="sd"> :param exception_traceback: The stacktrace to wrap</span>
<span class="sd"> :type exception_traceback: str</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">exception</span><span class="p">,</span> <span class="n">exception_traceback</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">exception</span> <span class="o">=</span> <span class="n">exception</span>
<span class="bp">self</span><span class="o">.</span><span class="n">traceback</span> <span class="o">=</span> <span class="n">exception_traceback</span></div>
<div class="viewcode-block" id="fetch_celery_task_state"><a class="viewcode-back" href="../../../_api/airflow/executors/celery_executor/index.html#airflow.executors.celery_executor.fetch_celery_task_state">[docs]</a><span class="k">def</span> <span class="nf">fetch_celery_task_state</span><span class="p">(</span><span class="n">celery_task</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Fetch and return the state of the given celery task. The scope of this function is</span>
<span class="sd"> global so that it can be called by subprocesses in the pool.</span>
<span class="sd"> :param celery_task: a tuple of the Celery task key and the async Celery object used</span>
<span class="sd"> to fetch the task&#39;s state</span>
<span class="sd"> :type celery_task: tuple(str, celery.result.AsyncResult)</span>
<span class="sd"> :return: a tuple of the Celery task key and the Celery state of the task</span>
<span class="sd"> :rtype: tuple[str, str]</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">try</span><span class="p">:</span>
<span class="k">with</span> <span class="n">timeout</span><span class="p">(</span><span class="n">seconds</span><span class="o">=</span><span class="mi">2</span><span class="p">):</span>
<span class="c1"># Accessing state property of celery task will make actual network request</span>
<span class="c1"># to get the current state of the task.</span>
<span class="n">res</span> <span class="o">=</span> <span class="p">(</span><span class="n">celery_task</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">celery_task</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">state</span><span class="p">)</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="n">exception_traceback</span> <span class="o">=</span> <span class="s2">&quot;Celery Task ID: </span><span class="si">{}</span><span class="se">\n</span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">celery_task</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
<span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">())</span>
<span class="n">res</span> <span class="o">=</span> <span class="n">ExceptionWithTraceback</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="n">exception_traceback</span><span class="p">)</span>
<span class="k">return</span> <span class="n">res</span></div>
<div class="viewcode-block" id="send_task_to_executor"><a class="viewcode-back" href="../../../_api/airflow/executors/celery_executor/index.html#airflow.executors.celery_executor.send_task_to_executor">[docs]</a><span class="k">def</span> <span class="nf">send_task_to_executor</span><span class="p">(</span><span class="n">task_tuple</span><span class="p">):</span>
<span class="n">key</span><span class="p">,</span> <span class="n">simple_ti</span><span class="p">,</span> <span class="n">command</span><span class="p">,</span> <span class="n">queue</span><span class="p">,</span> <span class="n">task</span> <span class="o">=</span> <span class="n">task_tuple</span>
<span class="k">try</span><span class="p">:</span>
<span class="k">with</span> <span class="n">timeout</span><span class="p">(</span><span class="n">seconds</span><span class="o">=</span><span class="mi">2</span><span class="p">):</span>
<span class="n">result</span> <span class="o">=</span> <span class="n">task</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="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="n">exception_traceback</span> <span class="o">=</span> <span class="s2">&quot;Celery Task ID: </span><span class="si">{}</span><span class="se">\n</span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">key</span><span class="p">,</span>
<span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">())</span>
<span class="n">result</span> <span class="o">=</span> <span class="n">ExceptionWithTraceback</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="n">exception_traceback</span><span class="p">)</span>
<span class="k">return</span> <span class="n">key</span><span class="p">,</span> <span class="n">command</span><span class="p">,</span> <span class="n">result</span></div>
<div class="viewcode-block" id="CeleryExecutor"><a class="viewcode-back" href="../../../_api/airflow/executors/celery_executor/index.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>
<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="nb">super</span><span class="p">(</span><span class="n">CeleryExecutor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="c1"># Celery doesn&#39;t support querying the state of multiple tasks in parallel</span>
<span class="c1"># (which can become a bottleneck on bigger clusters) so we use</span>
<span class="c1"># a multiprocessing pool to speed this up.</span>
<span class="c1"># How many worker processes are created for checking celery task state.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sync_parallelism</span> <span class="o">=</span> <span class="n">configuration</span><span class="o">.</span><span class="n">getint</span><span class="p">(</span><span class="s1">&#39;celery&#39;</span><span class="p">,</span> <span class="s1">&#39;SYNC_PARALLELISM&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sync_parallelism</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">_sync_parallelism</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">cpu_count</span><span class="p">()</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">_sync_pool</span> <span class="o">=</span> <span class="kc">None</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 class="viewcode-block" id="CeleryExecutor.start"><a class="viewcode-back" href="../../../_api/airflow/executors/celery_executor/index.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">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span>
<span class="s1">&#39;Starting Celery Executor using </span><span class="si">%s</span><span class="s1"> processes for syncing&#39;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sync_parallelism</span></div>
<span class="p">)</span>
<div class="viewcode-block" id="CeleryExecutor._num_tasks_per_send_process"><a class="viewcode-back" href="../../../_api/airflow/executors/celery_executor/index.html#airflow.executors.celery_executor.CeleryExecutor._num_tasks_per_send_process">[docs]</a> <span class="k">def</span> <span class="nf">_num_tasks_per_send_process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">to_send_count</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> How many Celery tasks should each worker process send.</span>
<span class="sd"> :return: Number of tasks that should be sent per process</span>
<span class="sd"> :rtype: int</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="nb">max</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span>
<span class="nb">int</span><span class="p">(</span><span class="n">math</span><span class="o">.</span><span class="n">ceil</span><span class="p">(</span><span class="mf">1.0</span> <span class="o">*</span> <span class="n">to_send_count</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sync_parallelism</span><span class="p">)))</span></div>
<div class="viewcode-block" id="CeleryExecutor._num_tasks_per_fetch_process"><a class="viewcode-back" href="../../../_api/airflow/executors/celery_executor/index.html#airflow.executors.celery_executor.CeleryExecutor._num_tasks_per_fetch_process">[docs]</a> <span class="k">def</span> <span class="nf">_num_tasks_per_fetch_process</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> How many Celery tasks should be sent to each worker process.</span>
<span class="sd"> :return: Number of tasks that should be used per process</span>
<span class="sd"> :rtype: int</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="nb">max</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span>
<span class="nb">int</span><span class="p">(</span><span class="n">math</span><span class="o">.</span><span class="n">ceil</span><span class="p">(</span><span class="mf">1.0</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">tasks</span><span class="p">)</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sync_parallelism</span><span class="p">)))</span></div>
<div class="viewcode-block" id="CeleryExecutor.trigger_tasks"><a class="viewcode-back" href="../../../_api/airflow/executors/celery_executor/index.html#airflow.executors.celery_executor.CeleryExecutor.trigger_tasks">[docs]</a> <span class="k">def</span> <span class="nf">trigger_tasks</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">open_slots</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Overwrite trigger_tasks function from BaseExecutor</span>
<span class="sd"> :param open_slots: Number of open slots</span>
<span class="sd"> :return:</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">sorted_queue</span> <span class="o">=</span> <span class="nb">sorted</span><span class="p">(</span>
<span class="p">[(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">queued_tasks</span><span class="o">.</span><span class="n">items</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">1</span><span class="p">][</span><span class="mi">1</span><span class="p">],</span>
<span class="n">reverse</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">task_tuples_to_send</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">min</span><span class="p">((</span><span class="n">open_slots</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">queued_tasks</span><span class="p">)))):</span>
<span class="n">key</span><span class="p">,</span> <span class="p">(</span><span class="n">command</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">queue</span><span class="p">,</span> <span class="n">simple_ti</span><span class="p">)</span> <span class="o">=</span> <span class="n">sorted_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">task_tuples_to_send</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">key</span><span class="p">,</span> <span class="n">simple_ti</span><span class="p">,</span> <span class="n">command</span><span class="p">,</span> <span class="n">queue</span><span class="p">,</span>
<span class="n">execute_command</span><span class="p">))</span>
<span class="n">cached_celery_backend</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">task_tuples_to_send</span><span class="p">:</span>
<span class="n">tasks</span> <span class="o">=</span> <span class="p">[</span><span class="n">t</span><span class="p">[</span><span class="mi">4</span><span class="p">]</span> <span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="n">task_tuples_to_send</span><span class="p">]</span>
<span class="c1"># Celery state queries will stuck if we do not use one same backend</span>
<span class="c1"># for all tasks.</span>
<span class="n">cached_celery_backend</span> <span class="o">=</span> <span class="n">tasks</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">backend</span>
<span class="k">if</span> <span class="n">task_tuples_to_send</span><span class="p">:</span>
<span class="c1"># Use chunking instead of a work queue to reduce context switching</span>
<span class="c1"># since tasks are roughly uniform in size</span>
<span class="n">chunksize</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_tasks_per_send_process</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">task_tuples_to_send</span><span class="p">))</span>
<span class="n">num_processes</span> <span class="o">=</span> <span class="nb">min</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">task_tuples_to_send</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sync_parallelism</span><span class="p">)</span>
<span class="n">send_pool</span> <span class="o">=</span> <span class="n">Pool</span><span class="p">(</span><span class="n">processes</span><span class="o">=</span><span class="n">num_processes</span><span class="p">)</span>
<span class="n">key_and_async_results</span> <span class="o">=</span> <span class="n">send_pool</span><span class="o">.</span><span class="n">map</span><span class="p">(</span>
<span class="n">send_task_to_executor</span><span class="p">,</span>
<span class="n">task_tuples_to_send</span><span class="p">,</span>
<span class="n">chunksize</span><span class="o">=</span><span class="n">chunksize</span><span class="p">)</span>
<span class="n">send_pool</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
<span class="n">send_pool</span><span class="o">.</span><span class="n">join</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="s1">&#39;Sent all tasks.&#39;</span><span class="p">)</span>
<span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">command</span><span class="p">,</span> <span class="n">result</span> <span class="ow">in</span> <span class="n">key_and_async_results</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">ExceptionWithTraceback</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="n">CELERY_SEND_ERR_MSG_HEADER</span> <span class="o">+</span> <span class="s2">&quot;:</span><span class="si">%s</span><span class="se">\n</span><span class="si">%s</span><span class="se">\n</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">result</span><span class="o">.</span><span class="n">exception</span><span class="p">,</span> <span class="n">result</span><span class="o">.</span><span class="n">traceback</span>
<span class="p">)</span>
<span class="k">elif</span> <span class="n">result</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="c1"># Only pops when enqueued successfully, otherwise keep it</span>
<span class="c1"># and expect scheduler loop to deal with it.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">queued_tasks</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="n">key</span><span class="p">)</span>
<span class="n">result</span><span class="o">.</span><span class="n">backend</span> <span class="o">=</span> <span class="n">cached_celery_backend</span>
<span class="bp">self</span><span class="o">.</span><span class="n">running</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="o">=</span> <span class="n">command</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">result</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="../../../_api/airflow/executors/celery_executor/index.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="n">num_processes</span> <span class="o">=</span> <span class="nb">min</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="bp">self</span><span class="o">.</span><span class="n">_sync_parallelism</span><span class="p">)</span>
<span class="k">if</span> <span class="n">num_processes</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">debug</span><span class="p">(</span><span class="s2">&quot;No task to query celery, skipping sync&quot;</span><span class="p">)</span>
<span class="k">return</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) using </span><span class="si">%s</span><span class="s2"> processes&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="n">num_processes</span><span class="p">)</span>
<span class="c1"># Recreate the process pool each sync in case processes in the pool die</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sync_pool</span> <span class="o">=</span> <span class="n">Pool</span><span class="p">(</span><span class="n">processes</span><span class="o">=</span><span class="n">num_processes</span><span class="p">)</span>
<span class="c1"># Use chunking instead of a work queue to reduce context switching since tasks are</span>
<span class="c1"># roughly uniform in size</span>
<span class="n">chunksize</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_tasks_per_fetch_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">debug</span><span class="p">(</span><span class="s2">&quot;Waiting for inquiries to complete...&quot;</span><span class="p">)</span>
<span class="n">task_keys_to_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sync_pool</span><span class="o">.</span><span class="n">map</span><span class="p">(</span>
<span class="n">fetch_celery_task_state</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="n">chunksize</span><span class="o">=</span><span class="n">chunksize</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sync_pool</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sync_pool</span><span class="o">.</span><span class="n">join</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;Inquiries completed.&quot;</span><span class="p">)</span>
<span class="k">for</span> <span class="n">key_and_state</span> <span class="ow">in</span> <span class="n">task_keys_to_states</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">key_and_state</span><span class="p">,</span> <span class="n">ExceptionWithTraceback</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="n">CELERY_FETCH_ERR_MSG_HEADER</span> <span class="o">+</span> <span class="s2">&quot;, ignoring it:</span><span class="si">%s</span><span class="se">\n</span><span class="si">%s</span><span class="se">\n</span><span class="s2">&quot;</span><span class="p">,</span>
<span class="nb">repr</span><span class="p">(</span><span class="n">key_and_state</span><span class="o">.</span><span class="n">exception</span><span class="p">),</span> <span class="n">key_and_state</span><span class="o">.</span><span class="n">traceback</span>
<span class="p">)</span>
<span class="k">continue</span>
<span class="n">key</span><span class="p">,</span> <span class="n">state</span> <span class="o">=</span> <span class="n">key_and_state</span>
<span class="k">try</span><span class="p">:</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="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">&quot;Error syncing the Celery executor, ignoring it.&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="CeleryExecutor.end"><a class="viewcode-back" href="../../../_api/airflow/executors/celery_executor/index.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>.
<div class="footer">This page uses <a href="https://analytics.google.com/">
Google Analytics</a> to collect statistics. You can disable it by blocking
the JavaScript coming from www.google-analytics.com. Check our
<a href="../../../privacy_notice.html">Privacy Policy</a>
for more details.
<script type="text/javascript">
(function() {
var ga = document.createElement('script');
ga.src = ('https:' == document.location.protocol ?
'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
ga.setAttribute('async', 'true');
var nodes = document.documentElement.childNodes;
var i = -1;
var node;
do {
i++;
node = nodes[i]
} while(node.nodeType !== Node.ELEMENT_NODE);
node.appendChild(ga);
})();
</script>
</div>
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>