blob: e5423db9986c48520513839a2bdd03dc40f5efa5 [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.utils.shared module &mdash; Apache Beam 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" />
<link rel="next" title="apache_beam.utils.subprocess_server module" href="apache_beam.utils.subprocess_server.html" />
<link rel="prev" title="apache_beam.utils.sharded_key module" href="apache_beam.utils.sharded_key.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 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 class="current">
<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.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 current"><a class="reference internal" href="apache_beam.utils.html">apache_beam.utils package</a><ul class="current">
<li class="toctree-l2 current"><a class="reference internal" href="apache_beam.utils.html#submodules">Submodules</a><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="apache_beam.utils.annotations.html">apache_beam.utils.annotations module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.utils.histogram.html">apache_beam.utils.histogram module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.utils.interactive_utils.html">apache_beam.utils.interactive_utils module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.utils.plugin.html">apache_beam.utils.plugin module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.utils.processes.html">apache_beam.utils.processes module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.utils.profiler.html">apache_beam.utils.profiler module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.utils.proto_utils.html">apache_beam.utils.proto_utils module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.utils.retry.html">apache_beam.utils.retry module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.utils.sentinel.html">apache_beam.utils.sentinel module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.utils.sharded_key.html">apache_beam.utils.sharded_key module</a></li>
<li class="toctree-l3 current"><a class="current reference internal" href="#">apache_beam.utils.shared module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.utils.subprocess_server.html">apache_beam.utils.subprocess_server module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.utils.thread_pool_executor.html">apache_beam.utils.thread_pool_executor module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.utils.timestamp.html">apache_beam.utils.timestamp module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.utils.urns.html">apache_beam.utils.urns module</a></li>
</ul>
</li>
</ul>
</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="apache_beam.utils.html">apache_beam.utils package</a> &raquo;</li>
<li>apache_beam.utils.shared module</li>
<li class="wy-breadcrumbs-aside">
<a href="_sources/apache_beam.utils.shared.rst.txt" rel="nofollow"> View page source</a>
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<div class="section" id="module-apache_beam.utils.shared">
<span id="apache-beam-utils-shared-module"></span><h1>apache_beam.utils.shared module<a class="headerlink" href="#module-apache_beam.utils.shared" title="Permalink to this headline"></a></h1>
<p>Shared class.</p>
<p>Shared class for managing a single instance of an object shared by multiple
threads within the same process. Shared is a serializable object that can be
shared by all threads of each worker process, which will be initialized as
necessary by calls to acquire.</p>
<p>Example usage:</p>
<p>To share a very large list across all threads of each worker in a DoFn:</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="c1"># Shared is a helper class for managing a single instance of an object</span>
<span class="c1"># shared by multiple threads within the same process. Instances of Shared</span>
<span class="c1"># are serializable objects that can be shared by all threads of each worker</span>
<span class="c1"># process. A Shared object encapsulates a weak reference to a singleton</span>
<span class="c1"># instance of the shared resource. The singleton is lazily initialized by</span>
<span class="c1"># calls to Shared.acquire().</span>
<span class="c1">#</span>
<span class="c1"># Several built-in types such as list and dict do not directly support weak</span>
<span class="c1"># references but can add support through subclassing:</span>
<span class="c1"># https://docs.python.org/3/library/weakref.html</span>
<span class="k">class</span> <span class="nc">WeakRefList</span><span class="p">(</span><span class="nb">list</span><span class="p">):</span>
<span class="k">pass</span>
<span class="k">class</span> <span class="nc">GetNthStringFn</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">shared_handle</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_shared_handle</span> <span class="o">=</span> <span class="n">shared_handle</span>
<span class="k">def</span> <span class="nf">setup</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="c1"># setup is a good place to initialize transient in-memory resources.</span>
<span class="k">def</span> <span class="nf">initialize_list</span><span class="p">():</span>
<span class="c1"># Build the giant initial list.</span>
<span class="k">return</span> <span class="n">WeakRefList</span><span class="p">([</span><span class="nb">str</span><span class="p">(</span><span class="n">i</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="mi">1000000</span><span class="p">)])</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_giant_list</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_shared_handle</span><span class="o">.</span><span class="n">acquire</span><span class="p">(</span><span class="n">initialize_list</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">element</span><span class="p">):</span>
<span class="k">yield</span> <span class="bp">self</span><span class="o">.</span><span class="n">_giant_list</span><span class="p">[</span><span class="n">element</span><span class="p">]</span>
<span class="n">p</span> <span class="o">=</span> <span class="n">beam</span><span class="o">.</span><span class="n">Pipeline</span><span class="p">()</span>
<span class="n">shared_handle</span> <span class="o">=</span> <span class="n">shared</span><span class="o">.</span><span class="n">Shared</span><span class="p">()</span>
<span class="p">(</span><span class="n">p</span> <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">Create</span><span class="p">([</span><span class="mi">2</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">6</span><span class="p">,</span> <span class="mi">8</span><span class="p">])</span>
<span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">ParDo</span><span class="p">(</span><span class="n">GetNthStringFn</span><span class="p">(</span><span class="n">shared_handle</span><span class="p">)))</span>
</pre></div>
</div>
<p>Real-world uses will typically involve using a side-input to a DoFn to
initialize the shared resource in a way that can’t be done with just its
constructor:</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">class</span> <span class="nc">RainbowTableLookupFn</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">shared_handle</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_shared_handle</span> <span class="o">=</span> <span class="n">shared_handle</span>
<span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">element</span><span class="p">,</span> <span class="n">table_elements</span><span class="p">):</span>
<span class="k">def</span> <span class="nf">construct_table</span><span class="p">():</span>
<span class="c1"># Construct the rainbow table from the table elements.</span>
<span class="c1"># The table contains lines in the form &quot;string::hash&quot;</span>
<span class="n">result</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span>
<span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">table_elements</span><span class="p">:</span>
<span class="n">result</span><span class="p">[</span><span class="n">value</span><span class="p">]</span> <span class="o">=</span> <span class="n">key</span>
<span class="k">return</span> <span class="n">result</span>
<span class="n">rainbow_table</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_shared_handle</span><span class="o">.</span><span class="n">acquire</span><span class="p">(</span><span class="n">construct_table</span><span class="p">)</span>
<span class="n">unhashed_str</span> <span class="o">=</span> <span class="n">rainbow_table</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">element</span><span class="p">)</span>
<span class="k">if</span> <span class="n">unhashed_str</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">yield</span> <span class="n">unhashed_str</span>
<span class="n">p</span> <span class="o">=</span> <span class="n">beam</span><span class="o">.</span><span class="n">Pipeline</span><span class="p">()</span>
<span class="n">shared_handle</span> <span class="o">=</span> <span class="n">shared</span><span class="o">.</span><span class="n">Shared</span><span class="p">()</span>
<span class="n">reverse_hash_table</span> <span class="o">=</span> <span class="n">p</span> <span class="o">|</span> <span class="s2">&quot;ReverseHashTable&quot;</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">Create</span><span class="p">([</span>
<span class="p">(</span><span class="s1">&#39;a&#39;</span><span class="p">,</span> <span class="s1">&#39;0cc175b9c0f1b6a831c399e269772661&#39;</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;b&#39;</span><span class="p">,</span> <span class="s1">&#39;92eb5ffee6ae2fec3ad71c777531578f&#39;</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;c&#39;</span><span class="p">,</span> <span class="s1">&#39;4a8a08f09d37b73795649038408b5f33&#39;</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;d&#39;</span><span class="p">,</span> <span class="s1">&#39;8277e0910d750195b448797616e091ad&#39;</span><span class="p">)])</span>
<span class="n">unhashed</span> <span class="o">=</span> <span class="p">(</span><span class="n">p</span>
<span class="o">|</span> <span class="s1">&#39;Hashes&#39;</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">Create</span><span class="p">([</span>
<span class="s1">&#39;0cc175b9c0f1b6a831c399e269772661&#39;</span><span class="p">,</span>
<span class="s1">&#39;8277e0910d750195b448797616e091ad&#39;</span><span class="p">])</span>
<span class="o">|</span> <span class="s1">&#39;Unhash&#39;</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">ParDo</span><span class="p">(</span>
<span class="n">RainbowTableLookupFn</span><span class="p">(</span><span class="n">shared_handle</span><span class="p">),</span> <span class="n">reverse_hash_table</span><span class="p">))</span>
</pre></div>
</div>
<dl class="class">
<dt id="apache_beam.utils.shared.Shared">
<em class="property">class </em><code class="descclassname">apache_beam.utils.shared.</code><code class="descname">Shared</code><a class="reference internal" href="_modules/apache_beam/utils/shared.html#Shared"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.utils.shared.Shared" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <a class="reference external" href="https://docs.python.org/3/library/functions.html#object" title="(in Python v3.9)"><code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></a></p>
<p>Handle for managing shared per-process objects.</p>
<p>Each instance of a Shared object represents a distinct handle to a distinct
object. Example usage is described in the file comment of shared.py.</p>
<p>This object has the following limitations:
* A shared object won’t be GC’ed if there isn’t another acquire called for
a different shared object.
* Each stage can only use exactly one Shared token, otherwise only one
Shared token, <em>NOT NECESSARILY THE LATEST</em>, will be “kept-alive”.
* If there are two different stages using separate Shared tokens, but which
get fused together, only one Shared token will be “kept-alive”.</p>
<p>(See documentation of _SharedMap for details.)</p>
<dl class="method">
<dt id="apache_beam.utils.shared.Shared.acquire">
<code class="descname">acquire</code><span class="sig-paren">(</span><em>constructor_fn</em>, <em>tag=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/utils/shared.html#Shared.acquire"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.utils.shared.Shared.acquire" title="Permalink to this definition"></a></dt>
<dd><p>Acquire a reference to the object associated with this Shared handle.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>constructor_fn</strong> – function that initialises / constructs the object if not
present in the cache. This function should take no arguments. It should
return an initialised object, or None if the object could not be
initialised / constructed.</li>
<li><strong>tag</strong> – an optional indentifier to store with the cached object. If
subsequent calls to acquire use different tags, the object will be
reloaded rather than returned from cache.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first last">A reference to an initialised object, either from the cache, or
newly-constructed.</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>
</dd></dl>
</div>
</div>
</div>
<footer>
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="apache_beam.utils.subprocess_server.html" class="btn btn-neutral float-right" title="apache_beam.utils.subprocess_server module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
<a href="apache_beam.utils.sharded_key.html" class="btn btn-neutral float-left" title="apache_beam.utils.sharded_key module" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
</div>
<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>