blob: 44b6a54a4903f56e9522995b6f0b203d78972298 [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.interactive.background_caching_job &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.interactive.background_caching_job</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.interactive.background_caching_job</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;Module to build and run background source recording jobs.</span>
<span class="sd">For internal use only; no backwards-compatibility guarantees.</span>
<span class="sd">A background source recording job is a job that records events for all</span>
<span class="sd">recordable sources of a given pipeline. With Interactive Beam, one such job is</span>
<span class="sd">started when a pipeline run happens (which produces a main job in contrast to</span>
<span class="sd">the background source recording job) and meets the following conditions:</span>
<span class="sd"> #. The pipeline contains recordable sources, configured through</span>
<span class="sd"> interactive_beam.options.recordable_sources.</span>
<span class="sd"> #. No such background job is running.</span>
<span class="sd"> #. No such background job has completed successfully and the cached events are</span>
<span class="sd"> still valid (invalidated when recordable sources change in the pipeline).</span>
<span class="sd">Once started, the background source recording job runs asynchronously until it</span>
<span class="sd">hits some recording limit configured in interactive_beam.options. Meanwhile,</span>
<span class="sd">the main job and future main jobs from the pipeline will run using the</span>
<span class="sd">deterministic replayable recorded events until they are invalidated.</span>
<span class="sd">&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">threading</span>
<span class="kn">import</span> <span class="nn">time</span>
<span class="kn">import</span> <span class="nn">apache_beam</span> <span class="k">as</span> <span class="nn">beam</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.interactive</span> <span class="kn">import</span> <span class="n">interactive_environment</span> <span class="k">as</span> <span class="n">ie</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.interactive</span> <span class="kn">import</span> <span class="n">utils</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.interactive.caching</span> <span class="kn">import</span> <span class="n">streaming_cache</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">_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="BackgroundCachingJob"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.background_caching_job.html#apache_beam.runners.interactive.background_caching_job.BackgroundCachingJob">[docs]</a><span class="k">class</span> <span class="nc">BackgroundCachingJob</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;A simple abstraction that controls necessary components of a timed and</span>
<span class="sd"> space limited background source recording job.</span>
<span class="sd"> A background source recording job successfully completes source data</span>
<span class="sd"> recording in 2 conditions:</span>
<span class="sd"> #. The job is finite and runs into DONE state;</span>
<span class="sd"> #. The job is infinite but hits an interactive_beam.options configured limit</span>
<span class="sd"> and gets cancelled into CANCELLED/CANCELLING state.</span>
<span class="sd"> In both situations, the background source recording job should be treated as</span>
<span class="sd"> done successfully.</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">pipeline_result</span><span class="p">,</span> <span class="n">limiters</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pipeline_result</span> <span class="o">=</span> <span class="n">pipeline_result</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_result_lock</span> <span class="o">=</span> <span class="n">threading</span><span class="o">.</span><span class="n">RLock</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_condition_checker</span> <span class="o">=</span> <span class="n">threading</span><span class="o">.</span><span class="n">Thread</span><span class="p">(</span>
<span class="n">target</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_background_caching_job_condition_checker</span><span class="p">,</span> <span class="n">daemon</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="c1"># Limiters are checks s.t. if any are triggered then the background caching</span>
<span class="c1"># job gets cancelled.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_limiters</span> <span class="o">=</span> <span class="n">limiters</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_condition_checker</span><span class="o">.</span><span class="n">start</span><span class="p">()</span>
<span class="k">def</span> <span class="nf">_background_caching_job_condition_checker</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
<span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_result_lock</span><span class="p">:</span>
<span class="k">if</span> <span class="n">PipelineState</span><span class="o">.</span><span class="n">is_terminal</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_pipeline_result</span><span class="o">.</span><span class="n">state</span><span class="p">):</span>
<span class="k">break</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_should_end_condition_checker</span><span class="p">():</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cancel</span><span class="p">()</span>
<span class="k">break</span>
<span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mf">0.5</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_should_end_condition_checker</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">any</span><span class="p">(</span><span class="n">l</span><span class="o">.</span><span class="n">is_triggered</span><span class="p">()</span> <span class="k">for</span> <span class="n">l</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_limiters</span><span class="p">)</span>
<div class="viewcode-block" id="BackgroundCachingJob.is_done"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.background_caching_job.html#apache_beam.runners.interactive.background_caching_job.BackgroundCachingJob.is_done">[docs]</a> <span class="k">def</span> <span class="nf">is_done</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">_result_lock</span><span class="p">:</span>
<span class="n">is_terminated</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pipeline_result</span><span class="o">.</span><span class="n">state</span> <span class="ow">in</span> <span class="p">(</span>
<span class="n">PipelineState</span><span class="o">.</span><span class="n">DONE</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="n">is_triggered</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_should_end_condition_checker</span><span class="p">()</span>
<span class="n">is_cancelling</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pipeline_result</span><span class="o">.</span><span class="n">state</span> <span class="ow">is</span> <span class="n">PipelineState</span><span class="o">.</span><span class="n">CANCELLING</span>
<span class="k">return</span> <span class="n">is_terminated</span> <span class="ow">or</span> <span class="p">(</span><span class="n">is_triggered</span> <span class="ow">and</span> <span class="n">is_cancelling</span><span class="p">)</span></div>
<div class="viewcode-block" id="BackgroundCachingJob.is_running"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.background_caching_job.html#apache_beam.runners.interactive.background_caching_job.BackgroundCachingJob.is_running">[docs]</a> <span class="k">def</span> <span class="nf">is_running</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">_result_lock</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pipeline_result</span><span class="o">.</span><span class="n">state</span> <span class="ow">is</span> <span class="n">PipelineState</span><span class="o">.</span><span class="n">RUNNING</span></div>
<div class="viewcode-block" id="BackgroundCachingJob.cancel"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.background_caching_job.html#apache_beam.runners.interactive.background_caching_job.BackgroundCachingJob.cancel">[docs]</a> <span class="k">def</span> <span class="nf">cancel</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Cancels this background source recording job.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_result_lock</span><span class="p">:</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">PipelineState</span><span class="o">.</span><span class="n">is_terminal</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_pipeline_result</span><span class="o">.</span><span class="n">state</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">_pipeline_result</span><span class="o">.</span><span class="n">cancel</span><span class="p">()</span>
<span class="k">except</span> <span class="ne">NotImplementedError</span><span class="p">:</span>
<span class="c1"># Ignore the cancel invocation if it is never implemented by the</span>
<span class="c1"># runner.</span>
<span class="k">pass</span></div>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">state</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">_result_lock</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pipeline_result</span><span class="o">.</span><span class="n">state</span></div>
<div class="viewcode-block" id="attempt_to_run_background_caching_job"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.background_caching_job.html#apache_beam.runners.interactive.background_caching_job.attempt_to_run_background_caching_job">[docs]</a><span class="k">def</span> <span class="nf">attempt_to_run_background_caching_job</span><span class="p">(</span>
<span class="n">runner</span><span class="p">,</span> <span class="n">user_pipeline</span><span class="p">,</span> <span class="n">options</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">limiters</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Attempts to run a background source recording job for a user-defined</span>
<span class="sd"> pipeline.</span>
<span class="sd"> Returns True if a job was started, False otherwise.</span>
<span class="sd"> The pipeline result is automatically tracked by Interactive Beam in case</span>
<span class="sd"> future cancellation/cleanup is needed.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">is_background_caching_job_needed</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">):</span>
<span class="c1"># Cancel non-terminal jobs if there is any before starting a new one.</span>
<span class="n">attempt_to_cancel_background_caching_job</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">)</span>
<span class="c1"># Cancel the gRPC server serving the test stream if there is one.</span>
<span class="n">attempt_to_stop_test_stream_service</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">)</span>
<span class="c1"># TODO(BEAM-8335): refactor background source recording job logic from</span>
<span class="c1"># pipeline_instrument module to this module and aggregate tests.</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.interactive</span> <span class="kn">import</span> <span class="n">pipeline_instrument</span> <span class="k">as</span> <span class="n">instr</span>
<span class="n">runner_pipeline</span> <span class="o">=</span> <span class="n">beam</span><span class="o">.</span><span class="n">pipeline</span><span class="o">.</span><span class="n">Pipeline</span><span class="o">.</span><span class="n">from_runner_api</span><span class="p">(</span>
<span class="n">user_pipeline</span><span class="o">.</span><span class="n">to_runner_api</span><span class="p">(),</span> <span class="n">runner</span><span class="p">,</span> <span class="n">options</span><span class="p">)</span>
<span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">add_derived_pipeline</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">,</span> <span class="n">runner_pipeline</span><span class="p">)</span>
<span class="n">background_caching_job_result</span> <span class="o">=</span> <span class="n">beam</span><span class="o">.</span><span class="n">pipeline</span><span class="o">.</span><span class="n">Pipeline</span><span class="o">.</span><span class="n">from_runner_api</span><span class="p">(</span>
<span class="n">instr</span><span class="o">.</span><span class="n">build_pipeline_instrument</span><span class="p">(</span>
<span class="n">runner_pipeline</span><span class="p">)</span><span class="o">.</span><span class="n">background_caching_pipeline_proto</span><span class="p">(),</span>
<span class="n">runner</span><span class="p">,</span>
<span class="n">options</span><span class="p">)</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
<span class="n">recording_limiters</span> <span class="o">=</span> <span class="p">(</span>
<span class="n">limiters</span>
<span class="k">if</span> <span class="n">limiters</span> <span class="k">else</span> <span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">options</span><span class="o">.</span><span class="n">capture_control</span><span class="o">.</span><span class="n">limiters</span><span class="p">())</span>
<span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">set_background_caching_job</span><span class="p">(</span>
<span class="n">user_pipeline</span><span class="p">,</span>
<span class="n">BackgroundCachingJob</span><span class="p">(</span>
<span class="n">background_caching_job_result</span><span class="p">,</span> <span class="n">limiters</span><span class="o">=</span><span class="n">recording_limiters</span><span class="p">))</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="k">return</span> <span class="kc">False</span></div>
<div class="viewcode-block" id="is_background_caching_job_needed"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.background_caching_job.html#apache_beam.runners.interactive.background_caching_job.is_background_caching_job_needed">[docs]</a><span class="k">def</span> <span class="nf">is_background_caching_job_needed</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Determines if a background source recording job needs to be started.</span>
<span class="sd"> It does several state checks and recording state changes throughout the</span>
<span class="sd"> process. It is not idempotent to simplify the usage.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">job</span> <span class="o">=</span> <span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">get_background_caching_job</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">)</span>
<span class="c1"># Checks if the pipeline contains any source that needs to be cached.</span>
<span class="n">need_cache</span> <span class="o">=</span> <span class="n">has_source_to_cache</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">)</span>
<span class="c1"># If this is True, we can invalidate a previous done/running job if there is</span>
<span class="c1"># one.</span>
<span class="n">cache_changed</span> <span class="o">=</span> <span class="n">is_source_to_cache_changed</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">)</span>
<span class="c1"># When recording replay is disabled, cache is always needed for recordable</span>
<span class="c1"># sources (if any).</span>
<span class="k">if</span> <span class="n">need_cache</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">options</span><span class="o">.</span><span class="n">enable_recording_replay</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.interactive.options</span> <span class="kn">import</span> <span class="n">capture_control</span>
<span class="n">capture_control</span><span class="o">.</span><span class="n">evict_captured_data</span><span class="p">()</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="k">return</span> <span class="p">(</span>
<span class="n">need_cache</span> <span class="ow">and</span>
<span class="c1"># Checks if it&#39;s the first time running a job from the pipeline.</span>
<span class="p">(</span>
<span class="ow">not</span> <span class="n">job</span> <span class="ow">or</span>
<span class="c1"># Or checks if there is no previous job.</span>
<span class="c1"># DONE means a previous job has completed successfully and the</span>
<span class="c1"># cached events might still be valid.</span>
<span class="ow">not</span> <span class="p">(</span>
<span class="n">job</span><span class="o">.</span><span class="n">is_done</span><span class="p">()</span> <span class="ow">or</span>
<span class="c1"># RUNNING means a previous job has been started and is still</span>
<span class="c1"># running.</span>
<span class="n">job</span><span class="o">.</span><span class="n">is_running</span><span class="p">())</span> <span class="ow">or</span>
<span class="c1"># Or checks if we can invalidate the previous job.</span>
<span class="n">cache_changed</span><span class="p">))</span></div>
<div class="viewcode-block" id="is_cache_complete"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.background_caching_job.html#apache_beam.runners.interactive.background_caching_job.is_cache_complete">[docs]</a><span class="k">def</span> <span class="nf">is_cache_complete</span><span class="p">(</span><span class="n">pipeline_id</span><span class="p">):</span>
<span class="c1"># type: (str) -&gt; bool</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns True if the backgrond cache for the given pipeline is done.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">user_pipeline</span> <span class="o">=</span> <span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">pipeline_id_to_pipeline</span><span class="p">(</span><span class="n">pipeline_id</span><span class="p">)</span>
<span class="n">job</span> <span class="o">=</span> <span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">get_background_caching_job</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">)</span>
<span class="n">is_done</span> <span class="o">=</span> <span class="n">job</span> <span class="ow">and</span> <span class="n">job</span><span class="o">.</span><span class="n">is_done</span><span class="p">()</span>
<span class="n">cache_changed</span> <span class="o">=</span> <span class="n">is_source_to_cache_changed</span><span class="p">(</span>
<span class="n">user_pipeline</span><span class="p">,</span> <span class="n">update_cached_source_signature</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="c1"># Stop reading from the cache if the background job is done or the underlying</span>
<span class="c1"># cache signature changed that requires a new background source recording job.</span>
<span class="k">return</span> <span class="n">is_done</span> <span class="ow">or</span> <span class="n">cache_changed</span></div>
<div class="viewcode-block" id="has_source_to_cache"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.background_caching_job.html#apache_beam.runners.interactive.background_caching_job.has_source_to_cache">[docs]</a><span class="k">def</span> <span class="nf">has_source_to_cache</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Determines if a user-defined pipeline contains any source that need to be</span>
<span class="sd"> cached. If so, also immediately wrap current cache manager held by current</span>
<span class="sd"> interactive environment into a streaming cache if this has not been done.</span>
<span class="sd"> The wrapping doesn&#39;t invalidate existing cache in any way.</span>
<span class="sd"> This can help determining if a background source recording job is needed to</span>
<span class="sd"> write cache for sources and if a test stream service is needed to serve the</span>
<span class="sd"> cache.</span>
<span class="sd"> Throughout the check, if source-to-cache has changed from the last check, it</span>
<span class="sd"> also cleans up the invalidated cache early on.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># TODO(BEAM-8335): we temporarily only cache replaceable unbounded sources.</span>
<span class="c1"># Add logic for other cacheable sources here when they are available.</span>
<span class="n">has_cache</span> <span class="o">=</span> <span class="n">utils</span><span class="o">.</span><span class="n">has_unbounded_sources</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">)</span>
<span class="k">if</span> <span class="n">has_cache</span><span class="p">:</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">get_cache_manager</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">,</span>
<span class="n">create_if_absent</span><span class="o">=</span><span class="kc">True</span><span class="p">),</span>
<span class="n">streaming_cache</span><span class="o">.</span><span class="n">StreamingCache</span><span class="p">):</span>
<span class="n">file_based_cm</span> <span class="o">=</span> <span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">get_cache_manager</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">)</span>
<span class="n">cache_dir</span> <span class="o">=</span> <span class="n">file_based_cm</span><span class="o">.</span><span class="n">_cache_dir</span>
<span class="n">cache_root</span> <span class="o">=</span> <span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">options</span><span class="o">.</span><span class="n">cache_root</span>
<span class="k">if</span> <span class="n">cache_root</span><span class="p">:</span>
<span class="k">if</span> <span class="n">cache_root</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;gs://&#39;</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s1">&#39;GCS cache paths are not currently supported for &#39;</span>
<span class="s1">&#39;streaming pipelines.&#39;</span><span class="p">)</span>
<span class="n">cache_dir</span> <span class="o">=</span> <span class="n">cache_root</span>
<span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">set_cache_manager</span><span class="p">(</span>
<span class="n">streaming_cache</span><span class="o">.</span><span class="n">StreamingCache</span><span class="p">(</span>
<span class="n">cache_dir</span><span class="p">,</span>
<span class="n">is_cache_complete</span><span class="o">=</span><span class="n">is_cache_complete</span><span class="p">,</span>
<span class="n">sample_resolution_sec</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span>
<span class="n">saved_pcoders</span><span class="o">=</span><span class="n">file_based_cm</span><span class="o">.</span><span class="n">_saved_pcoders</span><span class="p">),</span>
<span class="n">user_pipeline</span><span class="p">)</span>
<span class="k">return</span> <span class="n">has_cache</span></div>
<div class="viewcode-block" id="attempt_to_cancel_background_caching_job"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.background_caching_job.html#apache_beam.runners.interactive.background_caching_job.attempt_to_cancel_background_caching_job">[docs]</a><span class="k">def</span> <span class="nf">attempt_to_cancel_background_caching_job</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Attempts to cancel background source recording job for a user-defined</span>
<span class="sd"> pipeline.</span>
<span class="sd"> If no background source recording job needs to be cancelled, NOOP. Otherwise,</span>
<span class="sd"> cancel such job.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">job</span> <span class="o">=</span> <span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">get_background_caching_job</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">)</span>
<span class="k">if</span> <span class="n">job</span><span class="p">:</span>
<span class="n">job</span><span class="o">.</span><span class="n">cancel</span><span class="p">()</span></div>
<div class="viewcode-block" id="attempt_to_stop_test_stream_service"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.background_caching_job.html#apache_beam.runners.interactive.background_caching_job.attempt_to_stop_test_stream_service">[docs]</a><span class="k">def</span> <span class="nf">attempt_to_stop_test_stream_service</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Attempts to stop the gRPC server/service serving the test stream.</span>
<span class="sd"> If there is no such server started, NOOP. Otherwise, stop it.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">is_a_test_stream_service_running</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">):</span>
<span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">evict_test_stream_service_controller</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">)</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span></div>
<div class="viewcode-block" id="is_a_test_stream_service_running"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.background_caching_job.html#apache_beam.runners.interactive.background_caching_job.is_a_test_stream_service_running">[docs]</a><span class="k">def</span> <span class="nf">is_a_test_stream_service_running</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Checks to see if there is a gPRC server/service running that serves the</span>
<span class="sd"> test stream to any job started from the given user_pipeline.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">get_test_stream_service_controller</span><span class="p">(</span>
<span class="n">user_pipeline</span><span class="p">)</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span></div>
<div class="viewcode-block" id="is_source_to_cache_changed"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.background_caching_job.html#apache_beam.runners.interactive.background_caching_job.is_source_to_cache_changed">[docs]</a><span class="k">def</span> <span class="nf">is_source_to_cache_changed</span><span class="p">(</span>
<span class="n">user_pipeline</span><span class="p">,</span> <span class="n">update_cached_source_signature</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Determines if there is any change in the sources that need to be cached</span>
<span class="sd"> used by the user-defined pipeline.</span>
<span class="sd"> Due to the expensiveness of computations and for the simplicity of usage, this</span>
<span class="sd"> function is not idempotent because Interactive Beam automatically discards</span>
<span class="sd"> previously tracked signature of transforms and tracks the current signature of</span>
<span class="sd"> transforms for the user-defined pipeline if there is any change.</span>
<span class="sd"> When it&#39;s True, there is addition/deletion/mutation of source transforms that</span>
<span class="sd"> requires a new background source recording job.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># By default gets empty set if the user_pipeline is first time seen because</span>
<span class="c1"># we can treat it as adding transforms.</span>
<span class="n">recorded_signature</span> <span class="o">=</span> <span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">get_cached_source_signature</span><span class="p">(</span>
<span class="n">user_pipeline</span><span class="p">)</span>
<span class="n">current_signature</span> <span class="o">=</span> <span class="n">extract_source_to_cache_signature</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">)</span>
<span class="n">is_changed</span> <span class="o">=</span> <span class="ow">not</span> <span class="n">current_signature</span><span class="o">.</span><span class="n">issubset</span><span class="p">(</span><span class="n">recorded_signature</span><span class="p">)</span>
<span class="c1"># The computation of extract_unbounded_source_signature is expensive, track on</span>
<span class="c1"># change by default.</span>
<span class="k">if</span> <span class="n">is_changed</span> <span class="ow">and</span> <span class="n">update_cached_source_signature</span><span class="p">:</span>
<span class="n">options</span> <span class="o">=</span> <span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">options</span>
<span class="c1"># No info needed when recording replay is disabled.</span>
<span class="k">if</span> <span class="n">options</span><span class="o">.</span><span class="n">enable_recording_replay</span><span class="p">:</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">recorded_signature</span><span class="p">:</span>
<span class="k">def</span> <span class="nf">sizeof_fmt</span><span class="p">(</span><span class="n">num</span><span class="p">,</span> <span class="n">suffix</span><span class="o">=</span><span class="s1">&#39;B&#39;</span><span class="p">):</span>
<span class="k">for</span> <span class="n">unit</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">&#39;&#39;</span><span class="p">,</span> <span class="s1">&#39;K&#39;</span><span class="p">,</span> <span class="s1">&#39;M&#39;</span><span class="p">,</span> <span class="s1">&#39;G&#39;</span><span class="p">,</span> <span class="s1">&#39;T&#39;</span><span class="p">,</span> <span class="s1">&#39;P&#39;</span><span class="p">,</span> <span class="s1">&#39;E&#39;</span><span class="p">,</span> <span class="s1">&#39;Z&#39;</span><span class="p">]:</span>
<span class="k">if</span> <span class="nb">abs</span><span class="p">(</span><span class="n">num</span><span class="p">)</span> <span class="o">&lt;</span> <span class="mf">1000.0</span><span class="p">:</span>
<span class="k">return</span> <span class="s2">&quot;</span><span class="si">%3.1f%s%s</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">num</span><span class="p">,</span> <span class="n">unit</span><span class="p">,</span> <span class="n">suffix</span><span class="p">)</span>
<span class="n">num</span> <span class="o">/=</span> <span class="mf">1000.0</span>
<span class="k">return</span> <span class="s2">&quot;</span><span class="si">%.1f%s%s</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">num</span><span class="p">,</span> <span class="s1">&#39;Yi&#39;</span><span class="p">,</span> <span class="n">suffix</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;Interactive Beam has detected unbounded sources in your pipeline. &#39;</span>
<span class="s1">&#39;In order to have a deterministic replay, a segment of data will &#39;</span>
<span class="s1">&#39;be recorded from all sources for </span><span class="si">%s</span><span class="s1"> seconds or until a total of &#39;</span>
<span class="s1">&#39;</span><span class="si">%s</span><span class="s1"> have been written to disk.&#39;</span><span class="p">,</span>
<span class="n">options</span><span class="o">.</span><span class="n">recording_duration</span><span class="o">.</span><span class="n">total_seconds</span><span class="p">(),</span>
<span class="n">sizeof_fmt</span><span class="p">(</span><span class="n">options</span><span class="o">.</span><span class="n">recording_size_limit</span><span class="p">))</span>
<span class="k">else</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;Interactive Beam has detected a new streaming source was &#39;</span>
<span class="s1">&#39;added to the pipeline. In order for the cached streaming &#39;</span>
<span class="s1">&#39;data to start at the same time, all recorded data has been &#39;</span>
<span class="s1">&#39;cleared and a new segment of data will be recorded.&#39;</span><span class="p">)</span>
<span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">cleanup</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">)</span>
<span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">set_cached_source_signature</span><span class="p">(</span>
<span class="n">user_pipeline</span><span class="p">,</span> <span class="n">current_signature</span><span class="p">)</span>
<span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">add_user_pipeline</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">)</span>
<span class="k">return</span> <span class="n">is_changed</span></div>
<div class="viewcode-block" id="extract_source_to_cache_signature"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.background_caching_job.html#apache_beam.runners.interactive.background_caching_job.extract_source_to_cache_signature">[docs]</a><span class="k">def</span> <span class="nf">extract_source_to_cache_signature</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Extracts a set of signature for sources that need to be cached in the</span>
<span class="sd"> user-defined pipeline.</span>
<span class="sd"> A signature is a str representation of urn and payload of a source.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># TODO(BEAM-8335): we temporarily only cache replaceable unbounded sources.</span>
<span class="c1"># Add logic for other cacheable sources here when they are available.</span>
<span class="n">unbounded_sources_as_applied_transforms</span> <span class="o">=</span> <span class="n">utils</span><span class="o">.</span><span class="n">unbounded_sources</span><span class="p">(</span>
<span class="n">user_pipeline</span><span class="p">)</span>
<span class="n">unbounded_sources_as_ptransforms</span> <span class="o">=</span> <span class="nb">set</span><span class="p">(</span>
<span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="o">.</span><span class="n">transform</span><span class="p">,</span> <span class="n">unbounded_sources_as_applied_transforms</span><span class="p">))</span>
<span class="n">_</span><span class="p">,</span> <span class="n">context</span> <span class="o">=</span> <span class="n">user_pipeline</span><span class="o">.</span><span class="n">to_runner_api</span><span class="p">(</span><span class="n">return_context</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">signature</span> <span class="o">=</span> <span class="nb">set</span><span class="p">(</span>
<span class="nb">map</span><span class="p">(</span>
<span class="k">lambda</span> <span class="n">transform</span><span class="p">:</span> <span class="nb">str</span><span class="p">(</span><span class="n">transform</span><span class="o">.</span><span class="n">to_runner_api</span><span class="p">(</span><span class="n">context</span><span class="p">)),</span>
<span class="n">unbounded_sources_as_ptransforms</span><span class="p">))</span>
<span class="k">return</span> <span class="n">signature</span></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>