| |
| |
| <!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.direct.watermark_manager — Apache Beam documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> |
| |
| |
| |
| |
| |
| <link rel="index" title="Index" |
| href="../../../../genindex.html"/> |
| <link rel="search" title="Search" href="../../../../search.html"/> |
| <link rel="top" title="Apache Beam documentation" href="../../../../index.html"/> |
| <link rel="up" title="Module code" href="../../../index.html"/> |
| |
| |
| <script src="../../../../_static/js/modernizr.min.js"></script> |
| |
| </head> |
| |
| <body class="wy-body-for-nav" role="document"> |
| |
| |
| <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> |
| <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.internal.html">apache_beam.internal 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.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.tools.html">apache_beam.tools 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> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.version.html">apache_beam.version module</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" role="navigation" 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> »</li> |
| |
| <li><a href="../../../index.html">Module code</a> »</li> |
| |
| <li>apache_beam.runners.direct.watermark_manager</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.direct.watermark_manager</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 "License"); 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 "AS IS" 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">"""Manages watermarks of PCollections and AppliedPTransforms."""</span> |
| |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">absolute_import</span> |
| |
| <span class="kn">import</span> <span class="nn">threading</span> |
| <span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">object</span> |
| |
| <span class="kn">from</span> <span class="nn">apache_beam</span> <span class="k">import</span> <span class="n">pipeline</span> |
| <span class="kn">from</span> <span class="nn">apache_beam</span> <span class="k">import</span> <span class="n">pvalue</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.runners.direct.util</span> <span class="k">import</span> <span class="n">TimerFiring</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.utils.timestamp</span> <span class="k">import</span> <span class="n">MAX_TIMESTAMP</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.utils.timestamp</span> <span class="k">import</span> <span class="n">MIN_TIMESTAMP</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.utils.timestamp</span> <span class="k">import</span> <span class="n">TIME_GRANULARITY</span> |
| |
| |
| <div class="viewcode-block" id="WatermarkManager"><a class="viewcode-back" href="../../../../apache_beam.runners.direct.watermark_manager.html#apache_beam.runners.direct.watermark_manager.WatermarkManager">[docs]</a><span class="k">class</span> <span class="nc">WatermarkManager</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""For internal use only; no backwards-compatibility guarantees.</span> |
| |
| <span class="sd"> Tracks and updates watermarks for all AppliedPTransforms."""</span> |
| |
| <span class="n">WATERMARK_POS_INF</span> <span class="o">=</span> <span class="n">MAX_TIMESTAMP</span> |
| <span class="n">WATERMARK_NEG_INF</span> <span class="o">=</span> <span class="n">MIN_TIMESTAMP</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">clock</span><span class="p">,</span> <span class="n">root_transforms</span><span class="p">,</span> <span class="n">value_to_consumers</span><span class="p">,</span> |
| <span class="n">transform_keyed_states</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_clock</span> <span class="o">=</span> <span class="n">clock</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_root_transforms</span> <span class="o">=</span> <span class="n">root_transforms</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_value_to_consumers</span> <span class="o">=</span> <span class="n">value_to_consumers</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_transform_keyed_states</span> <span class="o">=</span> <span class="n">transform_keyed_states</span> |
| <span class="c1"># AppliedPTransform -> TransformWatermarks</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_transform_to_watermarks</span> <span class="o">=</span> <span class="p">{}</span> |
| |
| <span class="k">for</span> <span class="n">root_transform</span> <span class="ow">in</span> <span class="n">root_transforms</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_transform_to_watermarks</span><span class="p">[</span><span class="n">root_transform</span><span class="p">]</span> <span class="o">=</span> <span class="n">_TransformWatermarks</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_clock</span><span class="p">,</span> <span class="n">transform_keyed_states</span><span class="p">[</span><span class="n">root_transform</span><span class="p">],</span> <span class="n">root_transform</span><span class="p">)</span> |
| |
| <span class="k">for</span> <span class="n">consumers</span> <span class="ow">in</span> <span class="n">value_to_consumers</span><span class="o">.</span><span class="n">values</span><span class="p">():</span> |
| <span class="k">for</span> <span class="n">consumer</span> <span class="ow">in</span> <span class="n">consumers</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_transform_to_watermarks</span><span class="p">[</span><span class="n">consumer</span><span class="p">]</span> <span class="o">=</span> <span class="n">_TransformWatermarks</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_clock</span><span class="p">,</span> <span class="n">transform_keyed_states</span><span class="p">[</span><span class="n">consumer</span><span class="p">],</span> <span class="n">consumer</span><span class="p">)</span> |
| |
| <span class="k">for</span> <span class="n">consumers</span> <span class="ow">in</span> <span class="n">value_to_consumers</span><span class="o">.</span><span class="n">values</span><span class="p">():</span> |
| <span class="k">for</span> <span class="n">consumer</span> <span class="ow">in</span> <span class="n">consumers</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_update_input_transform_watermarks</span><span class="p">(</span><span class="n">consumer</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_update_input_transform_watermarks</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">applied_ptransform</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">applied_ptransform</span><span class="p">,</span> <span class="n">pipeline</span><span class="o">.</span><span class="n">AppliedPTransform</span><span class="p">)</span> |
| <span class="n">input_transform_watermarks</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">input_pvalue</span> <span class="ow">in</span> <span class="n">applied_ptransform</span><span class="o">.</span><span class="n">inputs</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="n">input_pvalue</span><span class="o">.</span><span class="n">producer</span> <span class="ow">or</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">input_pvalue</span><span class="p">,</span> <span class="n">pvalue</span><span class="o">.</span><span class="n">PBegin</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">input_pvalue</span><span class="o">.</span><span class="n">producer</span><span class="p">:</span> |
| <span class="n">input_transform_watermarks</span><span class="o">.</span><span class="n">append</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">get_watermarks</span><span class="p">(</span><span class="n">input_pvalue</span><span class="o">.</span><span class="n">producer</span><span class="p">))</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_transform_to_watermarks</span><span class="p">[</span> |
| <span class="n">applied_ptransform</span><span class="p">]</span><span class="o">.</span><span class="n">update_input_transform_watermarks</span><span class="p">(</span> |
| <span class="n">input_transform_watermarks</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="WatermarkManager.get_watermarks"><a class="viewcode-back" href="../../../../apache_beam.runners.direct.watermark_manager.html#apache_beam.runners.direct.watermark_manager.WatermarkManager.get_watermarks">[docs]</a> <span class="k">def</span> <span class="nf">get_watermarks</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">applied_ptransform</span><span class="p">):</span> |
| <span class="sd">"""Gets the input and output watermarks for an AppliedPTransform.</span> |
| |
| <span class="sd"> If the applied_ptransform has not processed any elements, return a</span> |
| <span class="sd"> watermark with minimum value.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> applied_ptransform: AppliedPTransform to get the watermarks for.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> A snapshot (TransformWatermarks) of the input watermark and output</span> |
| <span class="sd"> watermark for the provided transform.</span> |
| <span class="sd"> """</span> |
| |
| <span class="c1"># TODO(altay): Composite transforms should have a composite watermark. Until</span> |
| <span class="c1"># then they are represented by their last transform.</span> |
| <span class="k">while</span> <span class="n">applied_ptransform</span><span class="o">.</span><span class="n">parts</span><span class="p">:</span> |
| <span class="n">applied_ptransform</span> <span class="o">=</span> <span class="n">applied_ptransform</span><span class="o">.</span><span class="n">parts</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> |
| |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_transform_to_watermarks</span><span class="p">[</span><span class="n">applied_ptransform</span><span class="p">]</span></div> |
| |
| <div class="viewcode-block" id="WatermarkManager.update_watermarks"><a class="viewcode-back" href="../../../../apache_beam.runners.direct.watermark_manager.html#apache_beam.runners.direct.watermark_manager.WatermarkManager.update_watermarks">[docs]</a> <span class="k">def</span> <span class="nf">update_watermarks</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">completed_committed_bundle</span><span class="p">,</span> <span class="n">applied_ptransform</span><span class="p">,</span> |
| <span class="n">completed_timers</span><span class="p">,</span> <span class="n">outputs</span><span class="p">,</span> <span class="n">unprocessed_bundles</span><span class="p">,</span> |
| <span class="n">keyed_earliest_holds</span><span class="p">,</span> <span class="n">side_inputs_container</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">applied_ptransform</span><span class="p">,</span> <span class="n">pipeline</span><span class="o">.</span><span class="n">AppliedPTransform</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_update_pending</span><span class="p">(</span> |
| <span class="n">completed_committed_bundle</span><span class="p">,</span> <span class="n">applied_ptransform</span><span class="p">,</span> <span class="n">completed_timers</span><span class="p">,</span> |
| <span class="n">outputs</span><span class="p">,</span> <span class="n">unprocessed_bundles</span><span class="p">)</span> |
| <span class="n">tw</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_watermarks</span><span class="p">(</span><span class="n">applied_ptransform</span><span class="p">)</span> |
| <span class="n">tw</span><span class="o">.</span><span class="n">hold</span><span class="p">(</span><span class="n">keyed_earliest_holds</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_refresh_watermarks</span><span class="p">(</span><span class="n">applied_ptransform</span><span class="p">,</span> <span class="n">side_inputs_container</span><span class="p">)</span></div> |
| |
| <span class="k">def</span> <span class="nf">_update_pending</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_committed_bundle</span><span class="p">,</span> <span class="n">applied_ptransform</span><span class="p">,</span> |
| <span class="n">completed_timers</span><span class="p">,</span> <span class="n">output_committed_bundles</span><span class="p">,</span> |
| <span class="n">unprocessed_bundles</span><span class="p">):</span> |
| <span class="sd">"""Updated list of pending bundles for the given AppliedPTransform."""</span> |
| |
| <span class="c1"># Update pending elements. Filter out empty bundles. They do not impact</span> |
| <span class="c1"># watermarks and should not trigger downstream execution.</span> |
| <span class="k">for</span> <span class="n">output</span> <span class="ow">in</span> <span class="n">output_committed_bundles</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">output</span><span class="o">.</span><span class="n">has_elements</span><span class="p">():</span> |
| <span class="k">if</span> <span class="n">output</span><span class="o">.</span><span class="n">pcollection</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_value_to_consumers</span><span class="p">:</span> |
| <span class="n">consumers</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_value_to_consumers</span><span class="p">[</span><span class="n">output</span><span class="o">.</span><span class="n">pcollection</span><span class="p">]</span> |
| <span class="k">for</span> <span class="n">consumer</span> <span class="ow">in</span> <span class="n">consumers</span><span class="p">:</span> |
| <span class="n">consumer_tw</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_transform_to_watermarks</span><span class="p">[</span><span class="n">consumer</span><span class="p">]</span> |
| <span class="n">consumer_tw</span><span class="o">.</span><span class="n">add_pending</span><span class="p">(</span><span class="n">output</span><span class="p">)</span> |
| |
| <span class="n">completed_tw</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_transform_to_watermarks</span><span class="p">[</span><span class="n">applied_ptransform</span><span class="p">]</span> |
| <span class="n">completed_tw</span><span class="o">.</span><span class="n">update_timers</span><span class="p">(</span><span class="n">completed_timers</span><span class="p">)</span> |
| |
| <span class="k">for</span> <span class="n">unprocessed_bundle</span> <span class="ow">in</span> <span class="n">unprocessed_bundles</span><span class="p">:</span> |
| <span class="n">completed_tw</span><span class="o">.</span><span class="n">add_pending</span><span class="p">(</span><span class="n">unprocessed_bundle</span><span class="p">)</span> |
| |
| <span class="k">assert</span> <span class="n">input_committed_bundle</span> <span class="ow">or</span> <span class="n">applied_ptransform</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_root_transforms</span> |
| <span class="k">if</span> <span class="n">input_committed_bundle</span> <span class="ow">and</span> <span class="n">input_committed_bundle</span><span class="o">.</span><span class="n">has_elements</span><span class="p">():</span> |
| <span class="n">completed_tw</span><span class="o">.</span><span class="n">remove_pending</span><span class="p">(</span><span class="n">input_committed_bundle</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_refresh_watermarks</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">applied_ptransform</span><span class="p">,</span> <span class="n">side_inputs_container</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">applied_ptransform</span><span class="p">,</span> <span class="n">pipeline</span><span class="o">.</span><span class="n">AppliedPTransform</span><span class="p">)</span> |
| <span class="n">unblocked_tasks</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">tw</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_watermarks</span><span class="p">(</span><span class="n">applied_ptransform</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">tw</span><span class="o">.</span><span class="n">refresh</span><span class="p">():</span> |
| <span class="k">for</span> <span class="n">pval</span> <span class="ow">in</span> <span class="n">applied_ptransform</span><span class="o">.</span><span class="n">outputs</span><span class="o">.</span><span class="n">values</span><span class="p">():</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">pval</span><span class="p">,</span> <span class="n">pvalue</span><span class="o">.</span><span class="n">DoOutputsTuple</span><span class="p">):</span> |
| <span class="n">pvals</span> <span class="o">=</span> <span class="p">(</span><span class="n">v</span> <span class="k">for</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">pval</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">pvals</span> <span class="o">=</span> <span class="p">(</span><span class="n">pval</span><span class="p">,)</span> |
| <span class="k">for</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">pvals</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">v</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_value_to_consumers</span><span class="p">:</span> <span class="c1"># If there are downstream consumers</span> |
| <span class="n">consumers</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_value_to_consumers</span><span class="p">[</span><span class="n">v</span><span class="p">]</span> |
| <span class="k">for</span> <span class="n">consumer</span> <span class="ow">in</span> <span class="n">consumers</span><span class="p">:</span> |
| <span class="n">unblocked_tasks</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_refresh_watermarks</span><span class="p">(</span><span class="n">consumer</span><span class="p">,</span> <span class="n">side_inputs_container</span><span class="p">))</span> |
| <span class="c1"># Notify the side_inputs_container.</span> |
| <span class="n">unblocked_tasks</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span> |
| <span class="n">side_inputs_container</span> |
| <span class="o">.</span><span class="n">update_watermarks_for_transform_and_unblock_tasks</span><span class="p">(</span> |
| <span class="n">applied_ptransform</span><span class="p">,</span> <span class="n">tw</span><span class="p">))</span> |
| <span class="k">return</span> <span class="n">unblocked_tasks</span> |
| |
| <div class="viewcode-block" id="WatermarkManager.extract_all_timers"><a class="viewcode-back" href="../../../../apache_beam.runners.direct.watermark_manager.html#apache_beam.runners.direct.watermark_manager.WatermarkManager.extract_all_timers">[docs]</a> <span class="k">def</span> <span class="nf">extract_all_timers</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Extracts fired timers for all transforms</span> |
| <span class="sd"> and reports if there are any timers set."""</span> |
| <span class="n">all_timers</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">has_realtime_timer</span> <span class="o">=</span> <span class="kc">False</span> |
| <span class="k">for</span> <span class="n">applied_ptransform</span><span class="p">,</span> <span class="n">tw</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_transform_to_watermarks</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">fired_timers</span><span class="p">,</span> <span class="n">had_realtime_timer</span> <span class="o">=</span> <span class="n">tw</span><span class="o">.</span><span class="n">extract_transform_timers</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">fired_timers</span><span class="p">:</span> |
| <span class="n">all_timers</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">applied_ptransform</span><span class="p">,</span> <span class="n">fired_timers</span><span class="p">))</span> |
| <span class="k">if</span> <span class="p">(</span><span class="n">had_realtime_timer</span> |
| <span class="ow">and</span> <span class="n">tw</span><span class="o">.</span><span class="n">output_watermark</span> <span class="o"><</span> <span class="n">WatermarkManager</span><span class="o">.</span><span class="n">WATERMARK_POS_INF</span><span class="p">):</span> |
| <span class="n">has_realtime_timer</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">return</span> <span class="n">all_timers</span><span class="p">,</span> <span class="n">has_realtime_timer</span></div></div> |
| |
| |
| <span class="k">class</span> <span class="nc">_TransformWatermarks</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""Tracks input and output watermarks for an AppliedPTransform."""</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">clock</span><span class="p">,</span> <span class="n">keyed_states</span><span class="p">,</span> <span class="n">transform</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_clock</span> <span class="o">=</span> <span class="n">clock</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_keyed_states</span> <span class="o">=</span> <span class="n">keyed_states</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_input_transform_watermarks</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_input_watermark</span> <span class="o">=</span> <span class="n">WatermarkManager</span><span class="o">.</span><span class="n">WATERMARK_NEG_INF</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_output_watermark</span> <span class="o">=</span> <span class="n">WatermarkManager</span><span class="o">.</span><span class="n">WATERMARK_NEG_INF</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_keyed_earliest_holds</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_pending</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span> <span class="c1"># Scheduled bundles targeted for this transform.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_fired_timers</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span> <span class="o">=</span> <span class="n">threading</span><span class="o">.</span><span class="n">Lock</span><span class="p">()</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_label</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">transform</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">update_input_transform_watermarks</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_transform_watermarks</span><span class="p">):</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_input_transform_watermarks</span> <span class="o">=</span> <span class="n">input_transform_watermarks</span> |
| |
| <span class="k">def</span> <span class="nf">update_timers</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">completed_timers</span><span class="p">):</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">timer_firing</span> <span class="ow">in</span> <span class="n">completed_timers</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_fired_timers</span><span class="o">.</span><span class="n">remove</span><span class="p">(</span><span class="n">timer_firing</span><span class="p">)</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">input_watermark</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_watermark</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">output_watermark</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_output_watermark</span> |
| |
| <span class="k">def</span> <span class="nf">hold</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">keyed_earliest_holds</span><span class="p">):</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">hold_value</span> <span class="ow">in</span> <span class="n">keyed_earliest_holds</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_keyed_earliest_holds</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="o">=</span> <span class="n">hold_value</span> |
| <span class="k">if</span> <span class="p">(</span><span class="n">hold_value</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> |
| <span class="n">hold_value</span> <span class="o">==</span> <span class="n">WatermarkManager</span><span class="o">.</span><span class="n">WATERMARK_POS_INF</span><span class="p">):</span> |
| <span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">_keyed_earliest_holds</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> |
| |
| <span class="k">def</span> <span class="nf">add_pending</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pending</span><span class="p">):</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_pending</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">pending</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">remove_pending</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">completed</span><span class="p">):</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span><span class="p">:</span> |
| <span class="c1"># Ignore repeated removes. This will happen if a transform has a repeated</span> |
| <span class="c1"># input.</span> |
| <span class="k">if</span> <span class="n">completed</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pending</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_pending</span><span class="o">.</span><span class="n">remove</span><span class="p">(</span><span class="n">completed</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">refresh</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span><span class="p">:</span> |
| <span class="n">min_pending_timestamp</span> <span class="o">=</span> <span class="n">WatermarkManager</span><span class="o">.</span><span class="n">WATERMARK_POS_INF</span> |
| <span class="n">has_pending_elements</span> <span class="o">=</span> <span class="kc">False</span> |
| <span class="k">for</span> <span class="n">input_bundle</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pending</span><span class="p">:</span> |
| <span class="c1"># TODO(ccy): we can have the Bundle class keep track of the minimum</span> |
| <span class="c1"># timestamp so we don't have to do an iteration here.</span> |
| <span class="k">for</span> <span class="n">wv</span> <span class="ow">in</span> <span class="n">input_bundle</span><span class="o">.</span><span class="n">get_elements_iterable</span><span class="p">():</span> |
| <span class="n">has_pending_elements</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">if</span> <span class="n">wv</span><span class="o">.</span><span class="n">timestamp</span> <span class="o"><</span> <span class="n">min_pending_timestamp</span><span class="p">:</span> |
| <span class="n">min_pending_timestamp</span> <span class="o">=</span> <span class="n">wv</span><span class="o">.</span><span class="n">timestamp</span> |
| |
| <span class="c1"># If there is a pending element with a certain timestamp, we can at most</span> |
| <span class="c1"># advance our watermark to the maximum timestamp less than that</span> |
| <span class="c1"># timestamp.</span> |
| <span class="n">pending_holder</span> <span class="o">=</span> <span class="n">WatermarkManager</span><span class="o">.</span><span class="n">WATERMARK_POS_INF</span> |
| <span class="k">if</span> <span class="n">has_pending_elements</span><span class="p">:</span> |
| <span class="n">pending_holder</span> <span class="o">=</span> <span class="n">min_pending_timestamp</span> <span class="o">-</span> <span class="n">TIME_GRANULARITY</span> |
| |
| <span class="n">input_watermarks</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="n">tw</span><span class="o">.</span><span class="n">output_watermark</span> <span class="k">for</span> <span class="n">tw</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_transform_watermarks</span><span class="p">]</span> |
| <span class="n">input_watermarks</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">WatermarkManager</span><span class="o">.</span><span class="n">WATERMARK_POS_INF</span><span class="p">)</span> |
| <span class="n">producer_watermark</span> <span class="o">=</span> <span class="nb">min</span><span class="p">(</span><span class="n">input_watermarks</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_input_watermark</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_input_watermark</span><span class="p">,</span> |
| <span class="nb">min</span><span class="p">(</span><span class="n">pending_holder</span><span class="p">,</span> <span class="n">producer_watermark</span><span class="p">))</span> |
| <span class="n">earliest_hold</span> <span class="o">=</span> <span class="n">WatermarkManager</span><span class="o">.</span><span class="n">WATERMARK_POS_INF</span> |
| <span class="k">for</span> <span class="n">hold</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_keyed_earliest_holds</span><span class="o">.</span><span class="n">values</span><span class="p">():</span> |
| <span class="k">if</span> <span class="n">hold</span> <span class="o"><</span> <span class="n">earliest_hold</span><span class="p">:</span> |
| <span class="n">earliest_hold</span> <span class="o">=</span> <span class="n">hold</span> |
| <span class="n">new_output_watermark</span> <span class="o">=</span> <span class="nb">min</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_input_watermark</span><span class="p">,</span> <span class="n">earliest_hold</span><span class="p">)</span> |
| |
| <span class="n">advanced</span> <span class="o">=</span> <span class="n">new_output_watermark</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">_output_watermark</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_output_watermark</span> <span class="o">=</span> <span class="n">new_output_watermark</span> |
| <span class="k">return</span> <span class="n">advanced</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">synchronized_processing_output_time</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_clock</span><span class="o">.</span><span class="n">time</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">extract_transform_timers</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Extracts fired timers and reports of any timers set per transform."""</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span><span class="p">:</span> |
| <span class="n">fired_timers</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">has_realtime_timer</span> <span class="o">=</span> <span class="kc">False</span> |
| <span class="k">for</span> <span class="n">encoded_key</span><span class="p">,</span> <span class="n">state</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_keyed_states</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">timers</span><span class="p">,</span> <span class="n">had_realtime_timer</span> <span class="o">=</span> <span class="n">state</span><span class="o">.</span><span class="n">get_timers</span><span class="p">(</span> |
| <span class="n">watermark</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_input_watermark</span><span class="p">,</span> |
| <span class="n">processing_time</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_clock</span><span class="o">.</span><span class="n">time</span><span class="p">())</span> |
| <span class="k">if</span> <span class="n">had_realtime_timer</span><span class="p">:</span> |
| <span class="n">has_realtime_timer</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">for</span> <span class="n">expired</span> <span class="ow">in</span> <span class="n">timers</span><span class="p">:</span> |
| <span class="n">window</span><span class="p">,</span> <span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">time_domain</span><span class="p">,</span> <span class="n">timestamp</span><span class="p">)</span> <span class="o">=</span> <span class="n">expired</span> |
| <span class="n">fired_timers</span><span class="o">.</span><span class="n">append</span><span class="p">(</span> |
| <span class="n">TimerFiring</span><span class="p">(</span><span class="n">encoded_key</span><span class="p">,</span> <span class="n">window</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">time_domain</span><span class="p">,</span> <span class="n">timestamp</span><span class="p">))</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_fired_timers</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">fired_timers</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">fired_timers</span><span class="p">,</span> <span class="n">has_realtime_timer</span> |
| </pre></div> |
| |
| </div> |
| <div class="articleComments"> |
| |
| </div> |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| © Copyright . |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/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"> |
| var DOCUMENTATION_OPTIONS = { |
| URL_ROOT:'../../../../', |
| VERSION:'', |
| COLLAPSE_INDEX:false, |
| FILE_SUFFIX:'.html', |
| HAS_SOURCE: true, |
| SOURCELINK_SUFFIX: '.txt' |
| }; |
| </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.StickyNav.enable(); |
| }); |
| </script> |
| |
| |
| </body> |
| </html> |