blob: 0bf98559ad6a53e1b63ea24c6c424068405cbd95 [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>apache_beam.runners.dataflow.test_dataflow_runner &mdash; Apache Beam 2.47.0 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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></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" />
</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"> Apache Beam
</a>
<div class="version">
2.47.0
</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="../../../../apache_beam.coders.html">apache_beam.coders package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.dataframe.html">apache_beam.dataframe package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.io.html">apache_beam.io package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.metrics.html">apache_beam.metrics package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.ml.html">apache_beam.ml package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.options.html">apache_beam.options package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.portability.html">apache_beam.portability package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.runners.html">apache_beam.runners package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.testing.html">apache_beam.testing package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.transforms.html">apache_beam.transforms package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.typehints.html">apache_beam.typehints package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.utils.html">apache_beam.utils package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.yaml.html">apache_beam.yaml package</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.error.html">apache_beam.error module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pvalue.html">apache_beam.pvalue module</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">Apache Beam</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>apache_beam.runners.dataflow.test_dataflow_runner</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 apache_beam.runners.dataflow.test_dataflow_runner</h1><div class="highlight"><pre>
<span></span><span class="c1">#</span>
<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span>
<span class="c1"># contributor license agreements. See the NOTICE file distributed with</span>
<span class="c1"># this work for additional information regarding copyright ownership.</span>
<span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span>
<span class="c1"># (the &quot;License&quot;); you may not use this file except in compliance with</span>
<span class="c1"># 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, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="c1">#</span>
<span class="sd">&quot;&quot;&quot;Wrapper of Beam runners that&#39;s built for running and verifying e2e tests.&quot;&quot;&quot;</span>
<span class="c1"># pytype: skip-file</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">time</span>
<span class="kn">from</span> <span class="nn">apache_beam.internal</span> <span class="kn">import</span> <span class="n">pickler</span>
<span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">GoogleCloudOptions</span>
<span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">StandardOptions</span>
<span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">TestOptions</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.dataflow.dataflow_runner</span> <span class="kn">import</span> <span class="n">DataflowRunner</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.runner</span> <span class="kn">import</span> <span class="n">PipelineState</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;TestDataflowRunner&#39;</span><span class="p">]</span>
<span class="c1"># Dataflow take up to 10mins for the long tail of starting/stopping worker</span>
<span class="c1"># pool.</span>
<span class="n">WAIT_IN_STATE_TIMEOUT</span> <span class="o">=</span> <span class="mi">10</span> <span class="o">*</span> <span class="mi">60</span>
<span class="n">_LOGGER</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">(</span><span class="vm">__name__</span><span class="p">)</span>
<div class="viewcode-block" id="TestDataflowRunner"><a class="viewcode-back" href="../../../../apache_beam.runners.dataflow.test_dataflow_runner.html#apache_beam.runners.dataflow.test_dataflow_runner.TestDataflowRunner">[docs]</a><span class="k">class</span> <span class="nc">TestDataflowRunner</span><span class="p">(</span><span class="n">DataflowRunner</span><span class="p">):</span>
<div class="viewcode-block" id="TestDataflowRunner.run_pipeline"><a class="viewcode-back" href="../../../../apache_beam.runners.dataflow.test_dataflow_runner.html#apache_beam.runners.dataflow.test_dataflow_runner.TestDataflowRunner.run_pipeline">[docs]</a> <span class="k">def</span> <span class="nf">run_pipeline</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pipeline</span><span class="p">,</span> <span class="n">options</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Execute test pipeline and verify test matcher&quot;&quot;&quot;</span>
<span class="n">test_options</span> <span class="o">=</span> <span class="n">options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">TestOptions</span><span class="p">)</span>
<span class="n">on_success_matcher</span> <span class="o">=</span> <span class="n">test_options</span><span class="o">.</span><span class="n">on_success_matcher</span>
<span class="n">wait_duration</span> <span class="o">=</span> <span class="n">test_options</span><span class="o">.</span><span class="n">wait_until_finish_duration</span>
<span class="n">is_streaming</span> <span class="o">=</span> <span class="n">options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">StandardOptions</span><span class="p">)</span><span class="o">.</span><span class="n">streaming</span>
<span class="c1"># [BEAM-1889] Do not send this to remote workers also, there is no need to</span>
<span class="c1"># send this option to remote executors.</span>
<span class="n">test_options</span><span class="o">.</span><span class="n">on_success_matcher</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">result</span> <span class="o">=</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">run_pipeline</span><span class="p">(</span><span class="n">pipeline</span><span class="p">,</span> <span class="n">options</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">has_job</span><span class="p">:</span>
<span class="c1"># TODO(markflyhigh)(https://github.com/apache/beam/issues/18254): Use</span>
<span class="c1"># print since Nose dosen&#39;t show logs in some cases.</span>
<span class="nb">print</span><span class="p">(</span><span class="s1">&#39;Worker logs: </span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">build_console_url</span><span class="p">(</span><span class="n">options</span><span class="p">))</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">&#39;Console log: &#39;</span><span class="p">)</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">build_console_url</span><span class="p">(</span><span class="n">options</span><span class="p">))</span>
<span class="k">try</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">wait_until_in_state</span><span class="p">(</span><span class="n">PipelineState</span><span class="o">.</span><span class="n">RUNNING</span><span class="p">)</span>
<span class="k">if</span> <span class="n">is_streaming</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">wait_duration</span><span class="p">:</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s1">&#39;Waiting indefinitely for streaming job.&#39;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">wait_until_finish</span><span class="p">(</span><span class="n">duration</span><span class="o">=</span><span class="n">wait_duration</span><span class="p">)</span>
<span class="k">if</span> <span class="n">on_success_matcher</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">hamcrest</span> <span class="kn">import</span> <span class="n">assert_that</span> <span class="k">as</span> <span class="n">hc_assert_that</span>
<span class="n">hc_assert_that</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="p">,</span> <span class="n">pickler</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">on_success_matcher</span><span class="p">))</span>
<span class="k">finally</span><span class="p">:</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">is_in_terminal_state</span><span class="p">():</span>
<span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">cancel</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">wait_until_in_state</span><span class="p">(</span><span class="n">PipelineState</span><span class="o">.</span><span class="n">CANCELLED</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">result</span></div>
<div class="viewcode-block" id="TestDataflowRunner.build_console_url"><a class="viewcode-back" href="../../../../apache_beam.runners.dataflow.test_dataflow_runner.html#apache_beam.runners.dataflow.test_dataflow_runner.TestDataflowRunner.build_console_url">[docs]</a> <span class="k">def</span> <span class="nf">build_console_url</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">options</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Build a console url of Dataflow job.&quot;&quot;&quot;</span>
<span class="n">project</span> <span class="o">=</span> <span class="n">options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">GoogleCloudOptions</span><span class="p">)</span><span class="o">.</span><span class="n">project</span>
<span class="n">region_id</span> <span class="o">=</span> <span class="n">options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">GoogleCloudOptions</span><span class="p">)</span><span class="o">.</span><span class="n">region</span>
<span class="n">job_id</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">job_id</span><span class="p">()</span>
<span class="k">return</span> <span class="p">(</span>
<span class="s1">&#39;https://console.cloud.google.com/dataflow/jobs/</span><span class="si">%s</span><span class="s1">/</span><span class="si">%s</span><span class="s1">?project=</span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span>
<span class="p">(</span><span class="n">region_id</span><span class="p">,</span> <span class="n">job_id</span><span class="p">,</span> <span class="n">project</span><span class="p">))</span></div>
<div class="viewcode-block" id="TestDataflowRunner.wait_until_in_state"><a class="viewcode-back" href="../../../../apache_beam.runners.dataflow.test_dataflow_runner.html#apache_beam.runners.dataflow.test_dataflow_runner.TestDataflowRunner.wait_until_in_state">[docs]</a> <span class="k">def</span> <span class="nf">wait_until_in_state</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">expected_state</span><span class="p">,</span> <span class="n">timeout</span><span class="o">=</span><span class="n">WAIT_IN_STATE_TIMEOUT</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Wait until Dataflow pipeline enters a certain state.&quot;&quot;&quot;</span>
<span class="n">consoleUrl</span> <span class="o">=</span> <span class="p">(</span>
<span class="s2">&quot;Console URL: https://console.cloud.google.com/dataflow/&quot;</span>
<span class="sa">f</span><span class="s2">&quot;&lt;regionId&gt;/</span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">job_id</span><span class="p">()</span><span class="si">}</span><span class="s2">?project=&lt;projectId&gt;&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">has_job</span><span class="p">:</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="n">consoleUrl</span><span class="p">)</span>
<span class="k">raise</span> <span class="ne">IOError</span><span class="p">(</span><span class="s1">&#39;Failed to get the Dataflow job id.&#39;</span><span class="p">)</span>
<span class="n">start_time</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span>
<span class="k">while</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">start_time</span> <span class="o">&lt;=</span> <span class="n">timeout</span><span class="p">:</span>
<span class="n">job_state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">result</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">result</span><span class="o">.</span><span class="n">is_in_terminal_state</span><span class="p">()</span> <span class="ow">or</span> <span class="n">job_state</span> <span class="o">==</span> <span class="n">expected_state</span><span class="p">:</span>
<span class="k">return</span> <span class="n">job_state</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="n">_LOGGER</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="n">consoleUrl</span><span class="p">)</span>
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span>
<span class="s1">&#39;Timeout after </span><span class="si">%d</span><span class="s1"> seconds while waiting for job </span><span class="si">%s</span><span class="s1"> &#39;</span>
<span class="s1">&#39;enters expected state </span><span class="si">%s</span><span class="s1">. Current state is </span><span class="si">%s</span><span class="s1">.&#39;</span> <span class="o">%</span>
<span class="p">(</span><span class="n">timeout</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">job_id</span><span class="p">(),</span> <span class="n">expected_state</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">state</span><span class="p">))</span></div></div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
&copy; Copyright
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>