blob: 2955d841257dc212c62c53f34235a90d0e7aa17e [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.contrib.operators.spark_submit_operator &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 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="../../../../lineage.html">Lineage</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.contrib.operators.spark_submit_operator</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.contrib.operators.spark_submit_operator</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="c1">#</span>
<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.spark_submit_hook</span> <span class="k">import</span> <span class="n">SparkSubmitHook</span>
<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span>
<span class="kn">from</span> <span class="nn">airflow.settings</span> <span class="k">import</span> <span class="n">WEB_COLORS</span>
<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span>
<div class="viewcode-block" id="SparkSubmitOperator"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.spark_submit_operator.SparkSubmitOperator">[docs]</a><span class="k">class</span> <span class="nc">SparkSubmitOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> This hook is a wrapper around the spark-submit binary to kick off a spark-submit job.</span>
<span class="sd"> It requires that the &quot;spark-submit&quot; binary is in the PATH or the spark-home is set</span>
<span class="sd"> in the extra on the connection.</span>
<span class="sd"> :param application: The application that submitted as a job, either jar or</span>
<span class="sd"> py file. (templated)</span>
<span class="sd"> :type application: str</span>
<span class="sd"> :param conf: Arbitrary Spark configuration properties</span>
<span class="sd"> :type conf: dict</span>
<span class="sd"> :param conn_id: The connection id as configured in Airflow administration. When an</span>
<span class="sd"> invalid connection_id is supplied, it will default to yarn.</span>
<span class="sd"> :type conn_id: str</span>
<span class="sd"> :param files: Upload additional files to the executor running the job, separated by a</span>
<span class="sd"> comma. Files will be placed in the working directory of each executor.</span>
<span class="sd"> For example, serialized objects.</span>
<span class="sd"> :type files: str</span>
<span class="sd"> :param py_files: Additional python files used by the job, can be .zip, .egg or .py.</span>
<span class="sd"> :type py_files: str</span>
<span class="sd"> :param jars: Submit additional jars to upload and place them in executor classpath.</span>
<span class="sd"> :param driver_classpath: Additional, driver-specific, classpath settings.</span>
<span class="sd"> :type driver_classpath: str</span>
<span class="sd"> :type jars: str</span>
<span class="sd"> :param java_class: the main class of the Java application</span>
<span class="sd"> :type java_class: str</span>
<span class="sd"> :param packages: Comma-separated list of maven coordinates of jars to include on the</span>
<span class="sd"> driver and executor classpaths. (templated)</span>
<span class="sd"> :type packages: str</span>
<span class="sd"> :param exclude_packages: Comma-separated list of maven coordinates of jars to exclude</span>
<span class="sd"> while resolving the dependencies provided in &#39;packages&#39;</span>
<span class="sd"> :type exclude_packages: str</span>
<span class="sd"> :param repositories: Comma-separated list of additional remote repositories to search</span>
<span class="sd"> for the maven coordinates given with &#39;packages&#39;</span>
<span class="sd"> :type repositories: str</span>
<span class="sd"> :param total_executor_cores: (Standalone &amp; Mesos only) Total cores for all executors</span>
<span class="sd"> (Default: all the available cores on the worker)</span>
<span class="sd"> :type total_executor_cores: int</span>
<span class="sd"> :param executor_cores: (Standalone &amp; YARN only) Number of cores per executor</span>
<span class="sd"> (Default: 2)</span>
<span class="sd"> :type executor_cores: int</span>
<span class="sd"> :param executor_memory: Memory per executor (e.g. 1000M, 2G) (Default: 1G)</span>
<span class="sd"> :type executor_memory: str</span>
<span class="sd"> :param driver_memory: Memory allocated to the driver (e.g. 1000M, 2G) (Default: 1G)</span>
<span class="sd"> :type driver_memory: str</span>
<span class="sd"> :param keytab: Full path to the file that contains the keytab</span>
<span class="sd"> :type keytab: str</span>
<span class="sd"> :param principal: The name of the kerberos principal used for keytab</span>
<span class="sd"> :type principal: str</span>
<span class="sd"> :param name: Name of the job (default airflow-spark). (templated)</span>
<span class="sd"> :type name: str</span>
<span class="sd"> :param num_executors: Number of executors to launch</span>
<span class="sd"> :type num_executors: int</span>
<span class="sd"> :param application_args: Arguments for the application being submitted</span>
<span class="sd"> :type application_args: list</span>
<span class="sd"> :param env_vars: Environment variables for spark-submit. It</span>
<span class="sd"> supports yarn and k8s mode too.</span>
<span class="sd"> :type env_vars: dict</span>
<span class="sd"> :param verbose: Whether to pass the verbose flag to spark-submit process for debugging</span>
<span class="sd"> :type verbose: bool</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;_name&#39;</span><span class="p">,</span> <span class="s1">&#39;_application_args&#39;</span><span class="p">,</span> <span class="s1">&#39;_packages&#39;</span><span class="p">)</span>
<span class="n">ui_color</span> <span class="o">=</span> <span class="n">WEB_COLORS</span><span class="p">[</span><span class="s1">&#39;LIGHTORANGE&#39;</span><span class="p">]</span>
<span class="nd">@apply_defaults</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">application</span><span class="o">=</span><span class="s1">&#39;&#39;</span><span class="p">,</span>
<span class="n">conf</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">conn_id</span><span class="o">=</span><span class="s1">&#39;spark_default&#39;</span><span class="p">,</span>
<span class="n">files</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">py_files</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">driver_classpath</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">jars</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">java_class</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">packages</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">exclude_packages</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">repositories</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">total_executor_cores</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">executor_cores</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">executor_memory</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">driver_memory</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">keytab</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">principal</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">name</span><span class="o">=</span><span class="s1">&#39;airflow-spark&#39;</span><span class="p">,</span>
<span class="n">num_executors</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">application_args</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">env_vars</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="o">*</span><span class="n">args</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">SparkSubmitOperator</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="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_application</span> <span class="o">=</span> <span class="n">application</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_conf</span> <span class="o">=</span> <span class="n">conf</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_files</span> <span class="o">=</span> <span class="n">files</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_py_files</span> <span class="o">=</span> <span class="n">py_files</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_driver_classpath</span> <span class="o">=</span> <span class="n">driver_classpath</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_jars</span> <span class="o">=</span> <span class="n">jars</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_java_class</span> <span class="o">=</span> <span class="n">java_class</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_packages</span> <span class="o">=</span> <span class="n">packages</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_exclude_packages</span> <span class="o">=</span> <span class="n">exclude_packages</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_repositories</span> <span class="o">=</span> <span class="n">repositories</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_total_executor_cores</span> <span class="o">=</span> <span class="n">total_executor_cores</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_executor_cores</span> <span class="o">=</span> <span class="n">executor_cores</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_executor_memory</span> <span class="o">=</span> <span class="n">executor_memory</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_driver_memory</span> <span class="o">=</span> <span class="n">driver_memory</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_keytab</span> <span class="o">=</span> <span class="n">keytab</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_principal</span> <span class="o">=</span> <span class="n">principal</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_name</span> <span class="o">=</span> <span class="n">name</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_num_executors</span> <span class="o">=</span> <span class="n">num_executors</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_application_args</span> <span class="o">=</span> <span class="n">application_args</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_env_vars</span> <span class="o">=</span> <span class="n">env_vars</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_verbose</span> <span class="o">=</span> <span class="n">verbose</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_hook</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_conn_id</span> <span class="o">=</span> <span class="n">conn_id</span>
<div class="viewcode-block" id="SparkSubmitOperator.execute"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.spark_submit_operator.SparkSubmitOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Call the SparkSubmitHook to run the provided spark job</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_hook</span> <span class="o">=</span> <span class="n">SparkSubmitHook</span><span class="p">(</span>
<span class="n">conf</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_conf</span><span class="p">,</span>
<span class="n">conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_conn_id</span><span class="p">,</span>
<span class="n">files</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_files</span><span class="p">,</span>
<span class="n">py_files</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_py_files</span><span class="p">,</span>
<span class="n">driver_classpath</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_driver_classpath</span><span class="p">,</span>
<span class="n">jars</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_jars</span><span class="p">,</span>
<span class="n">java_class</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_java_class</span><span class="p">,</span>
<span class="n">packages</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_packages</span><span class="p">,</span>
<span class="n">exclude_packages</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_exclude_packages</span><span class="p">,</span>
<span class="n">repositories</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_repositories</span><span class="p">,</span>
<span class="n">total_executor_cores</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_total_executor_cores</span><span class="p">,</span>
<span class="n">executor_cores</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_executor_cores</span><span class="p">,</span>
<span class="n">executor_memory</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_executor_memory</span><span class="p">,</span>
<span class="n">driver_memory</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_driver_memory</span><span class="p">,</span>
<span class="n">keytab</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_keytab</span><span class="p">,</span>
<span class="n">principal</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_principal</span><span class="p">,</span>
<span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_name</span><span class="p">,</span>
<span class="n">num_executors</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_num_executors</span><span class="p">,</span>
<span class="n">application_args</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_application_args</span><span class="p">,</span>
<span class="n">env_vars</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_env_vars</span><span class="p">,</span>
<span class="n">verbose</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_verbose</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_hook</span><span class="o">.</span><span class="n">submit</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_application</span><span class="p">)</span></div>
<div class="viewcode-block" id="SparkSubmitOperator.on_kill"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.spark_submit_operator.SparkSubmitOperator.on_kill">[docs]</a> <span class="k">def</span> <span class="nf">on_kill</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">_hook</span><span class="o">.</span><span class="n">on_kill</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/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>