Google Git
Sign in
apache / beam-site / aa4899384bfb3460196adf6331c744cb480b96df / . / pydoc / 2.38.0 / _modules / apache_beam / runners / dataflow / dataflow_metrics.html
blob: 5adb0d7a79d7907a9678263c947168743440504b [file] [log] [blame]
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>apache_beam.runners.dataflow.dataflow_metrics &mdash; Apache Beam 2.38.0 documentation</title>
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="index" title="Index" href="../../../../genindex.html" />
<link rel="search" title="Search" href="../../../../search.html" />
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../../../../index.html" class="icon icon-home"> Apache Beam
</a>
<div class="version">
2.38.0
</div>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.coders.html">apache_beam.coders package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.dataframe.html">apache_beam.dataframe package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.io.html">apache_beam.io package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.metrics.html">apache_beam.metrics package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.ml.html">apache_beam.ml package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.options.html">apache_beam.options package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.portability.html">apache_beam.portability package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.runners.html">apache_beam.runners package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.transforms.html">apache_beam.transforms package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.typehints.html">apache_beam.typehints package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.utils.html">apache_beam.utils package</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.error.html">apache_beam.error module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../../index.html">Apache Beam</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../../index.html">Module code</a> &raquo;</li>
<li>apache_beam.runners.dataflow.dataflow_metrics</li>
<li class="wy-breadcrumbs-aside">
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<h1>Source code for apache_beam.runners.dataflow.dataflow_metrics</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;</span>
<span class="sd">DataflowRunner implementation of MetricResults. It is in charge of</span>
<span class="sd">responding to queries of current metrics by going to the dataflow</span>
<span class="sd">service.</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="c1"># pytype: skip-file</span>
<span class="kn">import</span> <span class="nn">argparse</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">numbers</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <span class="n">defaultdict</span>
<span class="kn">from</span> <span class="nn">apache_beam.metrics.cells</span> <span class="kn">import</span> <span class="n">DistributionData</span>
<span class="kn">from</span> <span class="nn">apache_beam.metrics.cells</span> <span class="kn">import</span> <span class="n">DistributionResult</span>
<span class="kn">from</span> <span class="nn">apache_beam.metrics.execution</span> <span class="kn">import</span> <span class="n">MetricKey</span>
<span class="kn">from</span> <span class="nn">apache_beam.metrics.execution</span> <span class="kn">import</span> <span class="n">MetricResult</span>
<span class="kn">from</span> <span class="nn">apache_beam.metrics.metric</span> <span class="kn">import</span> <span class="n">MetricResults</span>
<span class="kn">from</span> <span class="nn">apache_beam.metrics.metricbase</span> <span class="kn">import</span> <span class="n">MetricName</span>
<span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">GoogleCloudOptions</span>
<span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">PipelineOptions</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>
<span class="k">def</span> <span class="nf">_get_match</span><span class="p">(</span><span class="n">proto</span><span class="p">,</span> <span class="n">filter_fn</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Finds and returns the first element that matches a query.</span>
<span class="sd"> If no element matches the query, it throws ValueError.</span>
<span class="sd"> If more than one element matches the query, it returns only the first.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">query</span> <span class="o">=</span> <span class="p">[</span><span class="n">elm</span> <span class="k">for</span> <span class="n">elm</span> <span class="ow">in</span> <span class="n">proto</span> <span class="k">if</span> <span class="n">filter_fn</span><span class="p">(</span><span class="n">elm</span><span class="p">)]</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">query</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Could not find element&#39;</span><span class="p">)</span>
<span class="k">elif</span> <span class="nb">len</span><span class="p">(</span><span class="n">query</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">1</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Too many matches&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">query</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="c1"># V1b3 MetricStructuredName keys to accept and copy to the MetricKey labels.</span>
<span class="n">STEP_LABEL</span> <span class="o">=</span> <span class="s1">&#39;step&#39;</span>
<span class="n">STRUCTURED_NAME_LABELS</span> <span class="o">=</span> <span class="nb">set</span><span class="p">(</span>
<span class="p">[</span><span class="s1">&#39;execution_step&#39;</span><span class="p">,</span> <span class="s1">&#39;original_name&#39;</span><span class="p">,</span> <span class="s1">&#39;output_user_name&#39;</span><span class="p">])</span>
<div class="viewcode-block" id="DataflowMetrics"><a class="viewcode-back" href="../../../../apache_beam.runners.dataflow.dataflow_metrics.html#apache_beam.runners.dataflow.dataflow_metrics.DataflowMetrics">[docs]</a><span class="k">class</span> <span class="nc">DataflowMetrics</span><span class="p">(</span><span class="n">MetricResults</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Implementation of MetricResults class for the Dataflow runner.&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">dataflow_client</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">job_result</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">job_graph</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initialize the Dataflow metrics object.</span>
<span class="sd"> Args:</span>
<span class="sd"> dataflow_client: apiclient.DataflowApplicationClient to interact with the</span>
<span class="sd"> dataflow service.</span>
<span class="sd"> job_result: DataflowPipelineResult with the state and id information of</span>
<span class="sd"> the job.</span>
<span class="sd"> job_graph: apiclient.Job instance to be able to translate between internal</span>
<span class="sd"> step names (e.g. &quot;s2&quot;), and user step names (e.g. &quot;split&quot;).</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_dataflow_client</span> <span class="o">=</span> <span class="n">dataflow_client</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job_result</span> <span class="o">=</span> <span class="n">job_result</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_queried_after_termination</span> <span class="o">=</span> <span class="kc">False</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cached_metrics</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_job_graph</span> <span class="o">=</span> <span class="n">job_graph</span>
<span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">_is_counter</span><span class="p">(</span><span class="n">metric_result</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">metric_result</span><span class="o">.</span><span class="n">attempted</span><span class="p">,</span> <span class="n">numbers</span><span class="o">.</span><span class="n">Number</span><span class="p">)</span>
<span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">_is_distribution</span><span class="p">(</span><span class="n">metric_result</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">metric_result</span><span class="o">.</span><span class="n">attempted</span><span class="p">,</span> <span class="n">DistributionResult</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_translate_step_name</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">internal_name</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Translate between internal step names (e.g. &quot;s1&quot;) and user step names.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_graph</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s1">&#39;Could not translate the internal step name </span><span class="si">%r</span><span class="s1"> since job graph is &#39;</span>
<span class="s1">&#39;not available.&#39;</span> <span class="o">%</span> <span class="n">internal_name</span><span class="p">)</span>
<span class="n">user_step_name</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_job_graph</span> <span class="ow">and</span> <span class="n">internal_name</span> <span class="ow">in</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_job_graph</span><span class="o">.</span><span class="n">proto_pipeline</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">transforms</span><span class="o">.</span><span class="n">keys</span><span class="p">()):</span>
<span class="c1"># Dataflow Runner v2 with portable job submission uses proto transform map</span>
<span class="c1"># IDs for step names. Also PTransform.unique_name maps to user step names.</span>
<span class="c1"># Hence we lookup user step names based on the proto.</span>
<span class="n">user_step_name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_graph</span><span class="o">.</span><span class="n">proto_pipeline</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">transforms</span><span class="p">[</span>
<span class="n">internal_name</span><span class="p">]</span><span class="o">.</span><span class="n">unique_name</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">step</span> <span class="o">=</span> <span class="n">_get_match</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_job_graph</span><span class="o">.</span><span class="n">proto</span><span class="o">.</span><span class="n">steps</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">name</span> <span class="o">==</span> <span class="n">internal_name</span><span class="p">)</span>
<span class="n">user_step_name</span> <span class="o">=</span> <span class="n">_get_match</span><span class="p">(</span>
<span class="n">step</span><span class="o">.</span><span class="n">properties</span><span class="o">.</span><span class="n">additionalProperties</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">key</span> <span class="o">==</span> <span class="s1">&#39;user_name&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">value</span><span class="o">.</span><span class="n">string_value</span>
<span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span>
<span class="k">pass</span> <span class="c1"># Exception is handled below.</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">user_step_name</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s1">&#39;Could not translate the internal step name </span><span class="si">%r</span><span class="s1">.&#39;</span> <span class="o">%</span> <span class="n">internal_name</span><span class="p">)</span>
<span class="k">return</span> <span class="n">user_step_name</span>
<span class="k">def</span> <span class="nf">_get_metric_key</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">metric</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Populate the MetricKey object for a queried metric result.&quot;&quot;&quot;</span>
<span class="n">step</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span>
<span class="n">name</span> <span class="o">=</span> <span class="n">metric</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">name</span> <span class="c1"># Always extract a name</span>
<span class="n">labels</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">try</span><span class="p">:</span> <span class="c1"># Try to extract the user step name.</span>
<span class="c1"># If ValueError is thrown within this try-block, it is because of</span>
<span class="c1"># one of the following:</span>
<span class="c1"># 1. Unable to translate the step name. Only happening with improperly</span>
<span class="c1"># formatted job graph (unlikely), or step name not being the internal</span>
<span class="c1"># step name (only happens for unstructured-named metrics).</span>
<span class="c1"># 2. Unable to unpack [step] or [namespace]; which should only happen</span>
<span class="c1"># for unstructured names.</span>
<span class="n">step</span> <span class="o">=</span> <span class="n">_get_match</span><span class="p">(</span>
<span class="n">metric</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">context</span><span class="o">.</span><span class="n">additionalProperties</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">key</span> <span class="o">==</span> <span class="n">STEP_LABEL</span><span class="p">)</span><span class="o">.</span><span class="n">value</span>
<span class="n">step</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_translate_step_name</span><span class="p">(</span><span class="n">step</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span>
<span class="k">pass</span>
<span class="n">namespace</span> <span class="o">=</span> <span class="s2">&quot;dataflow/v1b3&quot;</span> <span class="c1"># Try to extract namespace or add a default.</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">namespace</span> <span class="o">=</span> <span class="n">_get_match</span><span class="p">(</span>
<span class="n">metric</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">context</span><span class="o">.</span><span class="n">additionalProperties</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">key</span> <span class="o">==</span> <span class="s1">&#39;namespace&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">value</span>
<span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span>
<span class="k">pass</span>
<span class="k">for</span> <span class="n">kv</span> <span class="ow">in</span> <span class="n">metric</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">context</span><span class="o">.</span><span class="n">additionalProperties</span><span class="p">:</span>
<span class="k">if</span> <span class="n">kv</span><span class="o">.</span><span class="n">key</span> <span class="ow">in</span> <span class="n">STRUCTURED_NAME_LABELS</span><span class="p">:</span>
<span class="n">labels</span><span class="p">[</span><span class="n">kv</span><span class="o">.</span><span class="n">key</span><span class="p">]</span> <span class="o">=</span> <span class="n">kv</span><span class="o">.</span><span class="n">value</span>
<span class="c1"># Package everything besides namespace and name the labels as well,</span>
<span class="c1"># including unmodified step names to assist in integration the exact</span>
<span class="c1"># unmodified values which come from dataflow.</span>
<span class="k">return</span> <span class="n">MetricKey</span><span class="p">(</span><span class="n">step</span><span class="p">,</span> <span class="n">MetricName</span><span class="p">(</span><span class="n">namespace</span><span class="p">,</span> <span class="n">name</span><span class="p">),</span> <span class="n">labels</span><span class="o">=</span><span class="n">labels</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_populate_metrics</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">response</span><span class="p">,</span> <span class="n">result</span><span class="p">,</span> <span class="n">user_metrics</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Move metrics from response to results as MetricResults.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">user_metrics</span><span class="p">:</span>
<span class="n">metrics</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">metric</span> <span class="k">for</span> <span class="n">metric</span> <span class="ow">in</span> <span class="n">response</span><span class="o">.</span><span class="n">metrics</span> <span class="k">if</span> <span class="n">metric</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">origin</span> <span class="o">==</span> <span class="s1">&#39;user&#39;</span>
<span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">metrics</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">metric</span> <span class="k">for</span> <span class="n">metric</span> <span class="ow">in</span> <span class="n">response</span><span class="o">.</span><span class="n">metrics</span>
<span class="k">if</span> <span class="n">metric</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">origin</span> <span class="o">==</span> <span class="s1">&#39;dataflow/v1b3&#39;</span>
<span class="p">]</span>
<span class="c1"># Get the tentative/committed versions of every metric together.</span>
<span class="n">metrics_by_name</span> <span class="o">=</span> <span class="n">defaultdict</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="p">{})</span>
<span class="k">for</span> <span class="n">metric</span> <span class="ow">in</span> <span class="n">metrics</span><span class="p">:</span>
<span class="k">if</span> <span class="p">(</span><span class="n">metric</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;_MIN&#39;</span><span class="p">)</span> <span class="ow">or</span>
<span class="n">metric</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;_MAX&#39;</span><span class="p">)</span> <span class="ow">or</span>
<span class="n">metric</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;_MEAN&#39;</span><span class="p">)</span> <span class="ow">or</span>
<span class="n">metric</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;_COUNT&#39;</span><span class="p">)):</span>
<span class="c1"># The Dataflow Service presents distribution metrics in two ways:</span>
<span class="c1"># One way is as a single distribution object with all its fields, and</span>
<span class="c1"># another way is as four different scalar metrics labeled as _MIN,</span>
<span class="c1"># _MAX, _COUNT_, _MEAN.</span>
<span class="c1"># TODO(pabloem) remove these when distributions are not being broken up</span>
<span class="c1"># in the service.</span>
<span class="c1"># The second way is only useful for the UI, and should be ignored.</span>
<span class="k">continue</span>
<span class="n">is_tentative</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">prop</span> <span class="k">for</span> <span class="n">prop</span> <span class="ow">in</span> <span class="n">metric</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">context</span><span class="o">.</span><span class="n">additionalProperties</span>
<span class="k">if</span> <span class="n">prop</span><span class="o">.</span><span class="n">key</span> <span class="o">==</span> <span class="s1">&#39;tentative&#39;</span> <span class="ow">and</span> <span class="n">prop</span><span class="o">.</span><span class="n">value</span> <span class="o">==</span> <span class="s1">&#39;true&#39;</span>
<span class="p">]</span>
<span class="n">tentative_or_committed</span> <span class="o">=</span> <span class="s1">&#39;tentative&#39;</span> <span class="k">if</span> <span class="n">is_tentative</span> <span class="k">else</span> <span class="s1">&#39;committed&#39;</span>
<span class="n">metric_key</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_metric_key</span><span class="p">(</span><span class="n">metric</span><span class="p">)</span>
<span class="k">if</span> <span class="n">metric_key</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">continue</span>
<span class="n">metrics_by_name</span><span class="p">[</span><span class="n">metric_key</span><span class="p">][</span><span class="n">tentative_or_committed</span><span class="p">]</span> <span class="o">=</span> <span class="n">metric</span>
<span class="c1"># Now we create the MetricResult elements.</span>
<span class="k">for</span> <span class="n">metric_key</span><span class="p">,</span> <span class="n">metric</span> <span class="ow">in</span> <span class="n">metrics_by_name</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
<span class="n">attempted</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_metric_value</span><span class="p">(</span><span class="n">metric</span><span class="p">[</span><span class="s1">&#39;tentative&#39;</span><span class="p">])</span>
<span class="n">committed</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_metric_value</span><span class="p">(</span><span class="n">metric</span><span class="p">[</span><span class="s1">&#39;committed&#39;</span><span class="p">])</span>
<span class="n">result</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
<span class="n">MetricResult</span><span class="p">(</span><span class="n">metric_key</span><span class="p">,</span> <span class="n">attempted</span><span class="o">=</span><span class="n">attempted</span><span class="p">,</span> <span class="n">committed</span><span class="o">=</span><span class="n">committed</span><span class="p">))</span>
<span class="k">def</span> <span class="nf">_get_metric_value</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">metric</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Get a metric result object from a MetricUpdate from Dataflow API.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">metric</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">metric</span><span class="o">.</span><span class="n">scalar</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">return</span> <span class="n">metric</span><span class="o">.</span><span class="n">scalar</span><span class="o">.</span><span class="n">integer_value</span>
<span class="k">elif</span> <span class="n">metric</span><span class="o">.</span><span class="n">distribution</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">dist_count</span> <span class="o">=</span> <span class="n">_get_match</span><span class="p">(</span>
<span class="n">metric</span><span class="o">.</span><span class="n">distribution</span><span class="o">.</span><span class="n">object_value</span><span class="o">.</span><span class="n">properties</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">key</span> <span class="o">==</span> <span class="s1">&#39;count&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">value</span><span class="o">.</span><span class="n">integer_value</span>
<span class="n">dist_min</span> <span class="o">=</span> <span class="n">_get_match</span><span class="p">(</span>
<span class="n">metric</span><span class="o">.</span><span class="n">distribution</span><span class="o">.</span><span class="n">object_value</span><span class="o">.</span><span class="n">properties</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">key</span> <span class="o">==</span> <span class="s1">&#39;min&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">value</span><span class="o">.</span><span class="n">integer_value</span>
<span class="n">dist_max</span> <span class="o">=</span> <span class="n">_get_match</span><span class="p">(</span>
<span class="n">metric</span><span class="o">.</span><span class="n">distribution</span><span class="o">.</span><span class="n">object_value</span><span class="o">.</span><span class="n">properties</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">key</span> <span class="o">==</span> <span class="s1">&#39;max&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">value</span><span class="o">.</span><span class="n">integer_value</span>
<span class="n">dist_sum</span> <span class="o">=</span> <span class="n">_get_match</span><span class="p">(</span>
<span class="n">metric</span><span class="o">.</span><span class="n">distribution</span><span class="o">.</span><span class="n">object_value</span><span class="o">.</span><span class="n">properties</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">key</span> <span class="o">==</span> <span class="s1">&#39;sum&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">value</span><span class="o">.</span><span class="n">integer_value</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">dist_sum</span><span class="p">:</span>
<span class="c1"># distribution metric is not meant to use on large values, but in case</span>
<span class="c1"># it is, the value can overflow and become double_value, the correctness</span>
<span class="c1"># of the value may not be guaranteed.</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
<span class="s2">&quot;Distribution metric sum value seems to have &quot;</span>
<span class="s2">&quot;overflowed integer_value range, the correctness of sum or mean &quot;</span>
<span class="s2">&quot;value may not be guaranteed: </span><span class="si">%s</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">metric</span><span class="o">.</span><span class="n">distribution</span><span class="p">)</span>
<span class="n">dist_sum</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span>
<span class="n">_get_match</span><span class="p">(</span>
<span class="n">metric</span><span class="o">.</span><span class="n">distribution</span><span class="o">.</span><span class="n">object_value</span><span class="o">.</span><span class="n">properties</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">key</span> <span class="o">==</span> <span class="s1">&#39;sum&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">value</span><span class="o">.</span><span class="n">double_value</span><span class="p">)</span>
<span class="k">return</span> <span class="n">DistributionResult</span><span class="p">(</span>
<span class="n">DistributionData</span><span class="p">(</span><span class="n">dist_sum</span><span class="p">,</span> <span class="n">dist_count</span><span class="p">,</span> <span class="n">dist_min</span><span class="p">,</span> <span class="n">dist_max</span><span class="p">))</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">None</span>
<span class="k">def</span> <span class="nf">_get_metrics_from_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">job_id</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Return cached metrics or query the dataflow service.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">job_id</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">job_id</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">job_result</span><span class="o">.</span><span class="n">job_id</span><span class="p">()</span>
<span class="k">except</span> <span class="ne">AttributeError</span><span class="p">:</span>
<span class="n">job_id</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">job_id</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Can not query metrics. Job id is unknown.&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cached_metrics</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cached_metrics</span>
<span class="n">job_metrics</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dataflow_client</span><span class="o">.</span><span class="n">get_job_metrics</span><span class="p">(</span><span class="n">job_id</span><span class="p">)</span>
<span class="c1"># If we cannot determine that the job has terminated,</span>
<span class="c1"># then metrics will not change and we can cache them.</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">job_result</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">job_result</span><span class="o">.</span><span class="n">is_in_terminal_state</span><span class="p">():</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cached_metrics</span> <span class="o">=</span> <span class="n">job_metrics</span>
<span class="k">return</span> <span class="n">job_metrics</span>
<div class="viewcode-block" id="DataflowMetrics.all_metrics"><a class="viewcode-back" href="../../../../apache_beam.runners.dataflow.dataflow_metrics.html#apache_beam.runners.dataflow.dataflow_metrics.DataflowMetrics.all_metrics">[docs]</a> <span class="k">def</span> <span class="nf">all_metrics</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">job_id</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Return all user and system metrics from the dataflow service.&quot;&quot;&quot;</span>
<span class="n">metric_results</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_metrics_from_dataflow</span><span class="p">(</span><span class="n">job_id</span><span class="o">=</span><span class="n">job_id</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_populate_metrics</span><span class="p">(</span><span class="n">response</span><span class="p">,</span> <span class="n">metric_results</span><span class="p">,</span> <span class="n">user_metrics</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_populate_metrics</span><span class="p">(</span><span class="n">response</span><span class="p">,</span> <span class="n">metric_results</span><span class="p">,</span> <span class="n">user_metrics</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="k">return</span> <span class="n">metric_results</span></div>
<div class="viewcode-block" id="DataflowMetrics.query"><a class="viewcode-back" href="../../../../apache_beam.runners.dataflow.dataflow_metrics.html#apache_beam.runners.dataflow.dataflow_metrics.DataflowMetrics.query">[docs]</a> <span class="k">def</span> <span class="nf">query</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="nb">filter</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">metric_results</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_metrics_from_dataflow</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_populate_metrics</span><span class="p">(</span><span class="n">response</span><span class="p">,</span> <span class="n">metric_results</span><span class="p">,</span> <span class="n">user_metrics</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">return</span> <span class="p">{</span>
<span class="bp">self</span><span class="o">.</span><span class="n">COUNTERS</span><span class="p">:</span> <span class="p">[</span>
<span class="n">elm</span> <span class="k">for</span> <span class="n">elm</span> <span class="ow">in</span> <span class="n">metric_results</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">matches</span><span class="p">(</span><span class="nb">filter</span><span class="p">,</span> <span class="n">elm</span><span class="o">.</span><span class="n">key</span><span class="p">)</span> <span class="ow">and</span>
<span class="n">DataflowMetrics</span><span class="o">.</span><span class="n">_is_counter</span><span class="p">(</span><span class="n">elm</span><span class="p">)</span>
<span class="p">],</span>
<span class="bp">self</span><span class="o">.</span><span class="n">DISTRIBUTIONS</span><span class="p">:</span> <span class="p">[</span>
<span class="n">elm</span> <span class="k">for</span> <span class="n">elm</span> <span class="ow">in</span> <span class="n">metric_results</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">matches</span><span class="p">(</span><span class="nb">filter</span><span class="p">,</span> <span class="n">elm</span><span class="o">.</span><span class="n">key</span><span class="p">)</span> <span class="ow">and</span>
<span class="n">DataflowMetrics</span><span class="o">.</span><span class="n">_is_distribution</span><span class="p">(</span><span class="n">elm</span><span class="p">)</span>
<span class="p">],</span>
<span class="bp">self</span><span class="o">.</span><span class="n">GAUGES</span><span class="p">:</span> <span class="p">[]</span>
<span class="p">}</span> <span class="c1"># TODO(pabloem): Add Gauge support for dataflow.</span></div></div>
<div class="viewcode-block" id="main"><a class="viewcode-back" href="../../../../apache_beam.runners.dataflow.dataflow_metrics.html#apache_beam.runners.dataflow.dataflow_metrics.main">[docs]</a><span class="k">def</span> <span class="nf">main</span><span class="p">(</span><span class="n">argv</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Print the metric results for a the dataflow --job_id and --project.</span>
<span class="sd"> Instead of running an entire pipeline which takes several minutes, use this</span>
<span class="sd"> main method to display MetricResults for a specific --job_id and --project</span>
<span class="sd"> which takes only a few seconds.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># TODO(BEAM-6833): The MetricResults do not show translated step names as the</span>
<span class="c1"># job_graph is not provided to DataflowMetrics.</span>
<span class="c1"># Import here to avoid adding the dependency for local running scenarios.</span>
<span class="k">try</span><span class="p">:</span>
<span class="c1"># pylint: disable=wrong-import-order, wrong-import-position</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.dataflow.internal</span> <span class="kn">import</span> <span class="n">apiclient</span>
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ImportError</span><span class="p">(</span>
<span class="s1">&#39;Google Cloud Dataflow runner not available, &#39;</span>
<span class="s1">&#39;please install apache_beam[gcp]&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">argv</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="vm">__file__</span><span class="p">:</span>
<span class="n">argv</span> <span class="o">=</span> <span class="n">argv</span><span class="p">[</span><span class="mi">1</span><span class="p">:]</span>
<span class="n">parser</span> <span class="o">=</span> <span class="n">argparse</span><span class="o">.</span><span class="n">ArgumentParser</span><span class="p">()</span>
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
<span class="s1">&#39;-j&#39;</span><span class="p">,</span> <span class="s1">&#39;--job_id&#39;</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s1">&#39;The job id to query metrics for.&#39;</span><span class="p">)</span>
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
<span class="s1">&#39;-p&#39;</span><span class="p">,</span>
<span class="s1">&#39;--project&#39;</span><span class="p">,</span>
<span class="nb">type</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s1">&#39;The project name to query metrics for.&#39;</span><span class="p">)</span>
<span class="n">flags</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">parse_args</span><span class="p">(</span><span class="n">argv</span><span class="p">)</span>
<span class="c1"># Get a Dataflow API client and set its project and job_id in the options.</span>
<span class="n">options</span> <span class="o">=</span> <span class="n">PipelineOptions</span><span class="p">()</span>
<span class="n">gcloud_options</span> <span class="o">=</span> <span class="n">options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">GoogleCloudOptions</span><span class="p">)</span>
<span class="n">gcloud_options</span><span class="o">.</span><span class="n">project</span> <span class="o">=</span> <span class="n">flags</span><span class="o">.</span><span class="n">project</span>
<span class="n">dataflow_client</span> <span class="o">=</span> <span class="n">apiclient</span><span class="o">.</span><span class="n">DataflowApplicationClient</span><span class="p">(</span><span class="n">options</span><span class="p">)</span>
<span class="n">df_metrics</span> <span class="o">=</span> <span class="n">DataflowMetrics</span><span class="p">(</span><span class="n">dataflow_client</span><span class="p">)</span>
<span class="n">all_metrics</span> <span class="o">=</span> <span class="n">df_metrics</span><span class="o">.</span><span class="n">all_metrics</span><span class="p">(</span><span class="n">job_id</span><span class="o">=</span><span class="n">flags</span><span class="o">.</span><span class="n">job_id</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;Printing all MetricResults for </span><span class="si">%s</span><span class="s1"> in </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">flags</span><span class="o">.</span><span class="n">job_id</span><span class="p">,</span> <span class="n">flags</span><span class="o">.</span><span class="n">project</span><span class="p">)</span>
<span class="k">for</span> <span class="n">metric_result</span> <span class="ow">in</span> <span class="n">all_metrics</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="n">metric_result</span><span class="p">)</span></div>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">&#39;__main__&#39;</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">()</span><span class="o">.</span><span class="n">setLevel</span><span class="p">(</span><span class="n">logging</span><span class="o">.</span><span class="n">INFO</span><span class="p">)</span>
<span class="n">main</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">)</span>
</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>