blob: 411f16904bd20aeb0ee4c8c0a34f5075241e5d05 [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.io.gcp.datastore.v1new.util &mdash; Apache Beam 2.38.0 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">
2.38.0
</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.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>
</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.io.gcp.datastore.v1new.util</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.io.gcp.datastore.v1new.util</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="c1"># Utility functions &amp; classes that are _not_ specific to the datastore client.</span>
<span class="c1">#</span>
<span class="c1"># For internal use only; no backwards-compatibility guarantees.</span>
<span class="c1"># pytype: skip-file</span>
<span class="kn">import</span> <span class="nn">math</span>
<span class="c1"># Constants used in batched mutation RPCs:</span>
<span class="n">WRITE_BATCH_INITIAL_SIZE</span> <span class="o">=</span> <span class="mi">50</span>
<span class="c1"># Max allowed Datastore writes per batch, and max bytes per batch.</span>
<span class="c1"># Note that the max bytes per batch set here is lower than the 10MB limit</span>
<span class="c1"># actually enforced by the API, to leave space for the CommitRequest wrapper</span>
<span class="c1"># around the mutations.</span>
<span class="c1"># https://cloud.google.com/datastore/docs/concepts/limits</span>
<span class="n">WRITE_BATCH_MAX_SIZE</span> <span class="o">=</span> <span class="mi">500</span>
<span class="n">WRITE_BATCH_MAX_BYTES_SIZE</span> <span class="o">=</span> <span class="mi">9000000</span>
<span class="n">WRITE_BATCH_MIN_SIZE</span> <span class="o">=</span> <span class="mi">5</span>
<span class="n">WRITE_BATCH_TARGET_LATENCY_MS</span> <span class="o">=</span> <span class="mi">6000</span>
<div class="viewcode-block" id="MovingSum"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.util.html#apache_beam.io.gcp.datastore.v1new.util.MovingSum">[docs]</a><span class="k">class</span> <span class="nc">MovingSum</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Class that keeps track of a rolling window sum.</span>
<span class="sd"> For use in tracking recent performance of the connector.</span>
<span class="sd"> Intended to be similar to</span>
<span class="sd"> org.apache.beam.sdk.util.MovingFunction(..., Sum.ofLongs()), but for</span>
<span class="sd"> convenience we expose the count of entries as well so this doubles as a</span>
<span class="sd"> moving average tracker.</span>
<span class="sd"> &quot;&quot;&quot;</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">window_ms</span><span class="p">,</span> <span class="n">bucket_ms</span><span class="p">):</span>
<span class="k">if</span> <span class="n">window_ms</span> <span class="o">&lt;</span> <span class="n">bucket_ms</span> <span class="ow">or</span> <span class="n">bucket_ms</span> <span class="o">&lt;=</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;window_ms &gt;= bucket_ms &gt; 0 please&quot;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_num_buckets</span> <span class="o">=</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="n">window_ms</span> <span class="o">/</span> <span class="n">bucket_ms</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_bucket_ms</span> <span class="o">=</span> <span class="n">bucket_ms</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_Reset</span><span class="p">(</span><span class="n">now</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span> <span class="c1"># initialize the moving window members</span>
<span class="k">def</span> <span class="nf">_Reset</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">now</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_current_index</span> <span class="o">=</span> <span class="mi">0</span> <span class="c1"># pointer into self._buckets</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_current_ms_since_epoch</span> <span class="o">=</span> <span class="n">math</span><span class="o">.</span><span class="n">floor</span><span class="p">(</span>
<span class="n">now</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">_bucket_ms</span><span class="p">)</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">_bucket_ms</span>
<span class="c1"># _buckets is a list where each element is a list [sum, num_samples]</span>
<span class="c1"># This is a circular buffer where</span>
<span class="c1"># [_current_index] represents the time range</span>
<span class="c1"># [_current_ms_since_epoch, _current_ms_since_epoch+_bucket_ms)</span>
<span class="c1"># [_current_index-1] represents immediatly prior time range</span>
<span class="c1"># [_current_ms_since_epoch-_bucket_ms, _current_ms_since_epoch)</span>
<span class="c1"># etc, wrapping around from the start to the end of the array, so</span>
<span class="c1"># [_current_index+1] is the element representing the oldest bucket.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_buckets</span> <span class="o">=</span> <span class="p">[[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_buckets</span><span class="p">)]</span>
<span class="k">def</span> <span class="nf">_Flush</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">now</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Args:</span>
<span class="sd"> now: int, milliseconds since epoch</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">now</span> <span class="o">&gt;=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_current_ms_since_epoch</span> <span class="o">+</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_bucket_ms</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_buckets</span><span class="p">):</span>
<span class="c1"># Time moved forward so far that all currently held data is outside of</span>
<span class="c1"># the window. It is faster to simply reset our data.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_Reset</span><span class="p">(</span><span class="n">now</span><span class="p">)</span>
<span class="k">return</span>
<span class="k">while</span> <span class="n">now</span> <span class="o">&gt;</span> <span class="bp">self</span><span class="o">.</span><span class="n">_current_ms_since_epoch</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_bucket_ms</span><span class="p">:</span>
<span class="c1"># Advance time by one _bucket_ms, setting the new bucket&#39;s counts to 0.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_current_ms_since_epoch</span> <span class="o">+=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_bucket_ms</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_current_index</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_current_index</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_buckets</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_buckets</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">_current_index</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">]</span>
<span class="c1"># Intentional dead reckoning here; we don&#39;t care about staying precisely</span>
<span class="c1"># aligned with multiples of _bucket_ms since the epoch, we just need our</span>
<span class="c1"># buckets to represent the most recent _window_ms time window.</span>
<div class="viewcode-block" id="MovingSum.sum"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.util.html#apache_beam.io.gcp.datastore.v1new.util.MovingSum.sum">[docs]</a> <span class="k">def</span> <span class="nf">sum</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">now</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_Flush</span><span class="p">(</span><span class="n">now</span><span class="p">)</span>
<span class="k">return</span> <span class="nb">sum</span><span class="p">(</span><span class="n">bucket</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">bucket</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_buckets</span><span class="p">)</span></div>
<div class="viewcode-block" id="MovingSum.add"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.util.html#apache_beam.io.gcp.datastore.v1new.util.MovingSum.add">[docs]</a> <span class="k">def</span> <span class="nf">add</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">now</span><span class="p">,</span> <span class="n">inc</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_Flush</span><span class="p">(</span><span class="n">now</span><span class="p">)</span>
<span class="n">bucket</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_buckets</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">_current_index</span><span class="p">]</span>
<span class="n">bucket</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+=</span> <span class="n">inc</span>
<span class="n">bucket</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">+=</span> <span class="mi">1</span></div>
<div class="viewcode-block" id="MovingSum.count"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.util.html#apache_beam.io.gcp.datastore.v1new.util.MovingSum.count">[docs]</a> <span class="k">def</span> <span class="nf">count</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">now</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_Flush</span><span class="p">(</span><span class="n">now</span><span class="p">)</span>
<span class="k">return</span> <span class="nb">sum</span><span class="p">(</span><span class="n">bucket</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">bucket</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_buckets</span><span class="p">)</span></div>
<div class="viewcode-block" id="MovingSum.has_data"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.util.html#apache_beam.io.gcp.datastore.v1new.util.MovingSum.has_data">[docs]</a> <span class="k">def</span> <span class="nf">has_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">now</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="n">now</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span></div></div>
<div class="viewcode-block" id="DynamicBatchSizer"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.util.html#apache_beam.io.gcp.datastore.v1new.util.DynamicBatchSizer">[docs]</a><span class="k">class</span> <span class="nc">DynamicBatchSizer</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Determines request sizes for future Datastore RPCs.&quot;&quot;&quot;</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="bp">self</span><span class="o">.</span><span class="n">_commit_time_per_entity_ms</span> <span class="o">=</span> <span class="n">MovingSum</span><span class="p">(</span>
<span class="n">window_ms</span><span class="o">=</span><span class="mi">120000</span><span class="p">,</span> <span class="n">bucket_ms</span><span class="o">=</span><span class="mi">10000</span><span class="p">)</span>
<div class="viewcode-block" id="DynamicBatchSizer.get_batch_size"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.util.html#apache_beam.io.gcp.datastore.v1new.util.DynamicBatchSizer.get_batch_size">[docs]</a> <span class="k">def</span> <span class="nf">get_batch_size</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">now</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Returns the recommended size for datastore RPCs at this time.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_commit_time_per_entity_ms</span><span class="o">.</span><span class="n">has_data</span><span class="p">(</span><span class="n">now</span><span class="p">):</span>
<span class="k">return</span> <span class="n">WRITE_BATCH_INITIAL_SIZE</span>
<span class="n">recent_mean_latency_ms</span> <span class="o">=</span> <span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_commit_time_per_entity_ms</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">now</span><span class="p">)</span> <span class="o">//</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_commit_time_per_entity_ms</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="n">now</span><span class="p">))</span>
<span class="k">return</span> <span class="nb">max</span><span class="p">(</span>
<span class="n">WRITE_BATCH_MIN_SIZE</span><span class="p">,</span>
<span class="nb">min</span><span class="p">(</span>
<span class="n">WRITE_BATCH_MAX_SIZE</span><span class="p">,</span>
<span class="n">WRITE_BATCH_TARGET_LATENCY_MS</span> <span class="o">//</span> <span class="nb">max</span><span class="p">(</span><span class="n">recent_mean_latency_ms</span><span class="p">,</span> <span class="mi">1</span><span class="p">)))</span></div>
<div class="viewcode-block" id="DynamicBatchSizer.report_latency"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.util.html#apache_beam.io.gcp.datastore.v1new.util.DynamicBatchSizer.report_latency">[docs]</a> <span class="k">def</span> <span class="nf">report_latency</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">now</span><span class="p">,</span> <span class="n">latency_ms</span><span class="p">,</span> <span class="n">num_mutations</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Report the latency of a Datastore RPC.</span>
<span class="sd"> Args:</span>
<span class="sd"> now: double, completion time of the RPC as seconds since the epoch.</span>
<span class="sd"> latency_ms: double, the observed latency in milliseconds for this RPC.</span>
<span class="sd"> num_mutations: int, number of mutations contained in the RPC.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_commit_time_per_entity_ms</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">now</span><span class="p">,</span> <span class="n">latency_ms</span> <span class="o">/</span> <span class="n">num_mutations</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>