blob: f22fd2920914cc0322df3128495fb75463c07d9c [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.dataproc.dataproc_cluster_manager &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.dataproc.dataproc_cluster_manager</li>
<li class="wy-breadcrumbs-aside">
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<h1>Source code for apache_beam.runners.interactive.dataproc.dataproc_cluster_manager</h1><div class="highlight"><pre>
<span></span><span class="c1">#</span>
<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span>
<span class="c1"># contributor license agreements. See the NOTICE file distributed with</span>
<span class="c1"># this work for additional information regarding copyright ownership.</span>
<span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span>
<span class="c1"># (the &quot;License&quot;); you may not use this file except in compliance with</span>
<span class="c1"># the License. You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="c1">#</span>
<span class="c1"># pytype: skip-file</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">re</span>
<span class="kn">import</span> <span class="nn">time</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Optional</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Tuple</span>
<span class="kn">from</span> <span class="nn">apache_beam</span> <span class="kn">import</span> <span class="n">version</span> <span class="k">as</span> <span class="n">beam_version</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="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.dataproc.types</span> <span class="kn">import</span> <span class="n">ClusterMetadata</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.interactive.utils</span> <span class="kn">import</span> <span class="n">obfuscate</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.interactive.utils</span> <span class="kn">import</span> <span class="n">progress_indicated</span>
<span class="k">try</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">google.cloud</span> <span class="kn">import</span> <span class="n">dataproc_v1</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.gcp</span> <span class="kn">import</span> <span class="n">gcsfilesystem</span> <span class="c1">#pylint: disable=ungrouped-imports</span>
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
<span class="k">class</span> <span class="nc">UnimportedDataproc</span><span class="p">:</span>
<span class="n">Cluster</span> <span class="o">=</span> <span class="kc">None</span>
<span class="n">dataproc_v1</span> <span class="o">=</span> <span class="n">UnimportedDataproc</span><span class="p">()</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="c1"># Name of the log file auto-generated by Dataproc. We use it to locate the</span>
<span class="c1"># startup output of the Flink daemon to retrieve master url and dashboard</span>
<span class="c1"># information.</span>
<span class="n">DATAPROC_STAGING_LOG_NAME</span> <span class="o">=</span> <span class="s1">&#39;dataproc-initialization-script-0_output&#39;</span>
<span class="c1"># Home dir of os user yarn.</span>
<span class="n">YARN_HOME</span> <span class="o">=</span> <span class="s1">&#39;/var/lib/hadoop-yarn&#39;</span>
<span class="c1"># Configures the os user yarn to use gcloud as the docker credHelper.</span>
<span class="c1"># Also sets some taskmanager configurations for better parallelism.</span>
<span class="c1"># Finally starts the yarn application: flink cluster in session mode.</span>
<span class="n">INIT_ACTION</span> <span class="o">=</span> <span class="s2">&quot;&quot;&quot;#!/bin/bash</span>
<span class="s2">sudo -u yarn gcloud auth configure-docker --quiet</span>
<span class="s2">readonly FLINK_INSTALL_DIR=&#39;/usr/lib/flink&#39;</span>
<span class="s2">readonly MASTER_HOSTNAME=&quot;$(/usr/share/google/get_metadata_value attributes/dataproc-master)&quot;</span>
<span class="s2">cat &lt;&lt;EOF &gt;&gt;$</span><span class="si">{FLINK_INSTALL_DIR}</span><span class="s2">/conf/flink-conf.yaml</span>
<span class="s2">taskmanager.memory.network.fraction: 0.2</span>
<span class="s2">taskmanager.memory.network.min: 64mb</span>
<span class="s2">taskmanager.memory.network.max: 1gb</span>
<span class="s2">EOF</span>
<span class="s2">sed -i </span><span class="se">\</span>
<span class="s2"> &quot;s/^taskmanager.network.numberOfBuffers: 2048/taskmanager.network.numberOfBuffers: 8192/&quot; </span><span class="se">\</span>
<span class="s2"> $</span><span class="si">{FLINK_INSTALL_DIR}</span><span class="s2">/conf/flink-conf.yaml</span>
<span class="s2">if [[ &quot;$</span><span class="si">{HOSTNAME}</span><span class="s2">&quot; == &quot;$</span><span class="si">{MASTER_HOSTNAME}</span><span class="s2">&quot; ]]; then</span>
<span class="s2"> . /usr/bin/flink-yarn-daemon</span>
<span class="s2">fi</span>
<span class="s2">&quot;&quot;&quot;</span>
<div class="viewcode-block" id="DataprocClusterManager"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.html#apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.DataprocClusterManager">[docs]</a><span class="k">class</span> <span class="nc">DataprocClusterManager</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Self-contained cluster manager that controls the lifecyle of a Dataproc</span>
<span class="sd"> cluster connected by one or more pipelines under Interactive Beam.</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">cluster_metadata</span><span class="p">:</span> <span class="n">ClusterMetadata</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Initializes the DataprocClusterManager with properties required</span>
<span class="sd"> to interface with the Dataproc ClusterControllerClient.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span> <span class="o">=</span> <span class="n">cluster_metadata</span>
<span class="c1"># Pipelines whose jobs are executed on the cluster.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">pipelines</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cluster_client</span> <span class="o">=</span> <span class="n">dataproc_v1</span><span class="o">.</span><span class="n">ClusterControllerClient</span><span class="p">(</span>
<span class="n">client_options</span><span class="o">=</span><span class="p">{</span>
<span class="s1">&#39;api_endpoint&#39;</span><span class="p">:</span> \
<span class="sa">f</span><span class="s1">&#39;</span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">region</span><span class="si">}</span><span class="s1">-dataproc.googleapis.com:443&#39;</span>
<span class="p">})</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fs</span> <span class="o">=</span> <span class="n">gcsfilesystem</span><span class="o">.</span><span class="n">GCSFileSystem</span><span class="p">(</span><span class="n">PipelineOptions</span><span class="p">())</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_staging_directory</span> <span class="o">=</span> <span class="kc">None</span>
<span class="n">cache_dir</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="ow">not</span> <span class="n">cache_dir</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="n">error_msg</span> <span class="o">=</span> <span class="p">(</span>
<span class="s1">&#39;ib.options.cache_root needs to be a Cloud Storage &#39;</span>
<span class="s1">&#39;Bucket to cache source recording and PCollections in current &#39;</span>
<span class="sa">f</span><span class="s1">&#39;interactive setup, instead </span><span class="se">\&#39;</span><span class="si">{</span><span class="n">cache_dir</span><span class="si">}</span><span class="se">\&#39;</span><span class="s1"> is assigned.&#39;</span><span class="p">)</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="n">error_msg</span><span class="p">)</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="n">error_msg</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cache_root</span> <span class="o">=</span> <span class="n">cache_dir</span><span class="o">.</span><span class="n">rstrip</span><span class="p">(</span><span class="s1">&#39;/&#39;</span><span class="p">)</span>
<div class="viewcode-block" id="DataprocClusterManager.stage_init_action"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.html#apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.DataprocClusterManager.stage_init_action">[docs]</a> <span class="k">def</span> <span class="nf">stage_init_action</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Stages the initialization action script to GCS cache root to set up</span>
<span class="sd"> Dataproc clusters.</span>
<span class="sd"> Returns the staged gcs file path.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># Versionizes the initialization action script.</span>
<span class="n">init_action_ver</span> <span class="o">=</span> <span class="n">obfuscate</span><span class="p">(</span><span class="n">INIT_ACTION</span><span class="p">)</span>
<span class="n">path</span> <span class="o">=</span> <span class="sa">f</span><span class="s1">&#39;</span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">_cache_root</span><span class="si">}</span><span class="s1">/dataproc-init-action-</span><span class="si">{</span><span class="n">init_action_ver</span><span class="si">}</span><span class="s1">.sh&#39;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fs</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">path</span><span class="p">):</span>
<span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fs</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> <span class="k">as</span> <span class="n">bwriter</span><span class="p">:</span>
<span class="n">bwriter</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">INIT_ACTION</span><span class="o">.</span><span class="n">encode</span><span class="p">())</span>
<span class="k">return</span> <span class="n">path</span></div>
<div class="viewcode-block" id="DataprocClusterManager.create_cluster"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.html#apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.DataprocClusterManager.create_cluster">[docs]</a> <span class="nd">@progress_indicated</span>
<span class="k">def</span> <span class="nf">create_cluster</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cluster</span><span class="p">:</span> <span class="nb">dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Attempts to create a cluster using attributes that were</span>
<span class="sd"> initialized with the DataprocClusterManager instance.</span>
<span class="sd"> Args:</span>
<span class="sd"> cluster: Dictionary representing Dataproc cluster. Read more about the</span>
<span class="sd"> schema for clusters here:</span>
<span class="sd"> https://cloud.google.com/python/docs/reference/dataproc/latest/google.cloud.dataproc_v1.types.Cluster</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">master_url</span><span class="p">:</span>
<span class="k">return</span>
<span class="k">try</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cluster_client</span><span class="o">.</span><span class="n">create_cluster</span><span class="p">(</span>
<span class="n">request</span><span class="o">=</span><span class="p">{</span>
<span class="s1">&#39;project_id&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span>
<span class="s1">&#39;region&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">region</span><span class="p">,</span>
<span class="s1">&#39;cluster&#39;</span><span class="p">:</span> <span class="n">cluster</span>
<span class="p">})</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">code</span> <span class="o">==</span> <span class="mi">409</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;Cluster </span><span class="si">%s</span><span class="s1"> already exists. Continuing...&#39;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">e</span><span class="o">.</span><span class="n">code</span> <span class="o">==</span> <span class="mi">403</span><span class="p">:</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">error</span><span class="p">(</span>
<span class="s1">&#39;Due to insufficient project permissions, &#39;</span>
<span class="s1">&#39;unable to create cluster: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">)</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s1">&#39;You cannot create a cluster in project: </span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">project_id</span><span class="p">))</span>
<span class="k">elif</span> <span class="n">e</span><span class="o">.</span><span class="n">code</span> <span class="o">==</span> <span class="mi">501</span><span class="p">:</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">error</span><span class="p">(</span>
<span class="s1">&#39;Invalid region provided: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">region</span><span class="p">)</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s1">&#39;Region </span><span class="si">{}</span><span class="s1"> does not exist!&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">region</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">error</span><span class="p">(</span>
<span class="s1">&#39;Unable to create cluster: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">)</span>
<span class="k">raise</span> <span class="n">e</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;Cluster created successfully: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_staging_directory</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_staging_location</span><span class="p">()</span>
<span class="n">master_url</span><span class="p">,</span> <span class="n">dashboard</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_master_url_and_dashboard</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">master_url</span> <span class="o">=</span> <span class="n">master_url</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">dashboard</span> <span class="o">=</span> <span class="n">dashboard</span></div>
<div class="viewcode-block" id="DataprocClusterManager.create_flink_cluster"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.html#apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.DataprocClusterManager.create_flink_cluster">[docs]</a> <span class="k">def</span> <span class="nf">create_flink_cluster</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Calls _create_cluster with a configuration that enables FlinkRunner.&quot;&quot;&quot;</span>
<span class="n">init_action_path</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">stage_init_action</span><span class="p">()</span>
<span class="n">cluster</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">&#39;project_id&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span>
<span class="s1">&#39;cluster_name&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">,</span>
<span class="s1">&#39;config&#39;</span><span class="p">:</span> <span class="p">{</span>
<span class="s1">&#39;software_config&#39;</span><span class="p">:</span> <span class="p">{</span>
<span class="c1"># TODO(https://github.com/apache/beam/issues/21527): Uncomment</span>
<span class="c1"># these lines when a Dataproc image is released with previously</span>
<span class="c1"># missing dependencies.</span>
<span class="c1"># &#39;image_version&#39;: ie.current_env().clusters.</span>
<span class="c1"># DATAPROC_IMAGE_VERSION,</span>
<span class="s1">&#39;optional_components&#39;</span><span class="p">:</span> <span class="p">[</span><span class="s1">&#39;DOCKER&#39;</span><span class="p">,</span> <span class="s1">&#39;FLINK&#39;</span><span class="p">],</span>
<span class="s1">&#39;properties&#39;</span><span class="p">:</span> <span class="p">{</span>
<span class="c1"># Enforces HOME dir for user yarn.</span>
<span class="s1">&#39;yarn:yarn.nodemanager.user-home-dir&#39;</span><span class="p">:</span> <span class="n">YARN_HOME</span>
<span class="p">}</span>
<span class="p">},</span>
<span class="s1">&#39;initialization_actions&#39;</span><span class="p">:</span> <span class="p">[{</span>
<span class="s1">&#39;executable_file&#39;</span><span class="p">:</span> <span class="n">init_action_path</span>
<span class="p">}],</span>
<span class="s1">&#39;gce_cluster_config&#39;</span><span class="p">:</span> <span class="p">{</span>
<span class="s1">&#39;metadata&#39;</span><span class="p">:</span> <span class="p">{</span>
<span class="s1">&#39;flink-start-yarn-session&#39;</span><span class="p">:</span> <span class="s1">&#39;false&#39;</span>
<span class="p">},</span>
<span class="s1">&#39;service_account_scopes&#39;</span><span class="p">:</span> <span class="p">[</span>
<span class="s1">&#39;https://www.googleapis.com/auth/cloud-platform&#39;</span>
<span class="p">]</span>
<span class="p">},</span>
<span class="s1">&#39;master_config&#39;</span><span class="p">:</span> <span class="p">{</span>
<span class="c1"># There must be 1 and only 1 instance of master.</span>
<span class="s1">&#39;num_instances&#39;</span><span class="p">:</span> <span class="mi">1</span>
<span class="p">},</span>
<span class="s1">&#39;worker_config&#39;</span><span class="p">:</span> <span class="p">{},</span>
<span class="s1">&#39;endpoint_config&#39;</span><span class="p">:</span> <span class="p">{</span>
<span class="s1">&#39;enable_http_port_access&#39;</span><span class="p">:</span> <span class="kc">True</span>
<span class="p">}</span>
<span class="p">},</span>
<span class="s1">&#39;labels&#39;</span><span class="p">:</span> <span class="p">{</span>
<span class="s1">&#39;goog-dataflow-notebook&#39;</span><span class="p">:</span> <span class="n">beam_version</span><span class="o">.</span><span class="n">__version__</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span>
<span class="s1">&#39;.&#39;</span><span class="p">,</span> <span class="s1">&#39;_&#39;</span><span class="p">)</span>
<span class="p">}</span>
<span class="p">}</span>
<span class="c1"># Additional gce_cluster_config.</span>
<span class="n">gce_cluster_config</span> <span class="o">=</span> <span class="n">cluster</span><span class="p">[</span><span class="s1">&#39;config&#39;</span><span class="p">][</span><span class="s1">&#39;gce_cluster_config&#39;</span><span class="p">]</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">subnetwork</span><span class="p">:</span>
<span class="n">gce_cluster_config</span><span class="p">[</span><span class="s1">&#39;subnetwork_uri&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">subnetwork</span>
<span class="c1"># Additional InstanceGroupConfig for master and workers.</span>
<span class="n">master_config</span> <span class="o">=</span> <span class="n">cluster</span><span class="p">[</span><span class="s1">&#39;config&#39;</span><span class="p">][</span><span class="s1">&#39;master_config&#39;</span><span class="p">]</span>
<span class="n">worker_config</span> <span class="o">=</span> <span class="n">cluster</span><span class="p">[</span><span class="s1">&#39;config&#39;</span><span class="p">][</span><span class="s1">&#39;worker_config&#39;</span><span class="p">]</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">num_workers</span><span class="p">:</span>
<span class="n">worker_config</span><span class="p">[</span><span class="s1">&#39;num_instances&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">num_workers</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">machine_type</span><span class="p">:</span>
<span class="n">master_config</span><span class="p">[</span><span class="s1">&#39;machine_type_uri&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">machine_type</span>
<span class="n">worker_config</span><span class="p">[</span><span class="s1">&#39;machine_type_uri&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">machine_type</span>
<span class="bp">self</span><span class="o">.</span><span class="n">create_cluster</span><span class="p">(</span><span class="n">cluster</span><span class="p">)</span></div>
<div class="viewcode-block" id="DataprocClusterManager.cleanup"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.html#apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.DataprocClusterManager.cleanup">[docs]</a> <span class="k">def</span> <span class="nf">cleanup</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Deletes the cluster that uses the attributes initialized</span>
<span class="sd"> with the DataprocClusterManager instance.&quot;&quot;&quot;</span>
<span class="k">try</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cluster_client</span><span class="o">.</span><span class="n">delete_cluster</span><span class="p">(</span>
<span class="n">request</span><span class="o">=</span><span class="p">{</span>
<span class="s1">&#39;project_id&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span>
<span class="s1">&#39;region&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">region</span><span class="p">,</span>
<span class="s1">&#39;cluster_name&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">,</span>
<span class="p">})</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cleanup_staging_files</span><span class="p">()</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">code</span> <span class="o">==</span> <span class="mi">403</span><span class="p">:</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">error</span><span class="p">(</span>
<span class="s1">&#39;Due to insufficient project permissions, &#39;</span>
<span class="s1">&#39;unable to clean up the default cluster: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">)</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s1">&#39;You cannot delete a cluster in project: </span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">project_id</span><span class="p">))</span>
<span class="k">elif</span> <span class="n">e</span><span class="o">.</span><span class="n">code</span> <span class="o">==</span> <span class="mi">404</span><span class="p">:</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">error</span><span class="p">(</span>
<span class="s1">&#39;Cluster does not exist: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">)</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s1">&#39;Cluster was not found: </span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</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">error</span><span class="p">(</span>
<span class="s1">&#39;Failed to delete cluster: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">)</span>
<span class="k">raise</span> <span class="n">e</span></div>
<div class="viewcode-block" id="DataprocClusterManager.get_cluster_details"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.html#apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.DataprocClusterManager.get_cluster_details">[docs]</a> <span class="k">def</span> <span class="nf">get_cluster_details</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">dataproc_v1</span><span class="o">.</span><span class="n">Cluster</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Gets the Dataproc_v1 Cluster object for the current cluster manager.&quot;&quot;&quot;</span>
<span class="k">try</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cluster_client</span><span class="o">.</span><span class="n">get_cluster</span><span class="p">(</span>
<span class="n">request</span><span class="o">=</span><span class="p">{</span>
<span class="s1">&#39;project_id&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span>
<span class="s1">&#39;region&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">region</span><span class="p">,</span>
<span class="s1">&#39;cluster_name&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span>
<span class="p">})</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">code</span> <span class="o">==</span> <span class="mi">403</span><span class="p">:</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">error</span><span class="p">(</span>
<span class="s1">&#39;Due to insufficient project permissions, &#39;</span>
<span class="s1">&#39;unable to retrieve information for cluster: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">)</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s1">&#39;You cannot view clusters in project: </span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">project_id</span><span class="p">))</span>
<span class="k">elif</span> <span class="n">e</span><span class="o">.</span><span class="n">code</span> <span class="o">==</span> <span class="mi">404</span><span class="p">:</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">error</span><span class="p">(</span>
<span class="s1">&#39;Cluster does not exist: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">)</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s1">&#39;Cluster was not found: </span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</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">error</span><span class="p">(</span>
<span class="s1">&#39;Failed to get information for cluster: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">)</span>
<span class="k">raise</span> <span class="n">e</span></div>
<div class="viewcode-block" id="DataprocClusterManager.wait_for_cluster_to_provision"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.html#apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.DataprocClusterManager.wait_for_cluster_to_provision">[docs]</a> <span class="k">def</span> <span class="nf">wait_for_cluster_to_provision</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">while</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_cluster_details</span><span class="p">()</span><span class="o">.</span><span class="n">status</span><span class="o">.</span><span class="n">state</span><span class="o">.</span><span class="n">name</span> <span class="o">==</span> <span class="s1">&#39;CREATING&#39;</span><span class="p">:</span>
<span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">15</span><span class="p">)</span></div>
<div class="viewcode-block" id="DataprocClusterManager.get_staging_location"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.html#apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.DataprocClusterManager.get_staging_location">[docs]</a> <span class="k">def</span> <span class="nf">get_staging_location</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Gets the staging bucket of an existing Dataproc cluster.&quot;&quot;&quot;</span>
<span class="k">try</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">wait_for_cluster_to_provision</span><span class="p">()</span>
<span class="n">cluster_details</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_cluster_details</span><span class="p">()</span>
<span class="n">bucket_name</span> <span class="o">=</span> <span class="n">cluster_details</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">config_bucket</span>
<span class="n">gcs_path</span> <span class="o">=</span> <span class="s1">&#39;gs://&#39;</span> <span class="o">+</span> <span class="n">bucket_name</span> <span class="o">+</span> <span class="s1">&#39;/google-cloud-dataproc-metainfo/&#39;</span>
<span class="k">for</span> <span class="n">file</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fs</span><span class="o">.</span><span class="n">_list</span><span class="p">(</span><span class="n">gcs_path</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span> <span class="ow">in</span> <span class="n">file</span><span class="o">.</span><span class="n">path</span><span class="p">:</span>
<span class="c1"># this file path split will look something like:</span>
<span class="c1"># [&#39;gs://.../google-cloud-dataproc-metainfo/{staging_dir}/&#39;,</span>
<span class="c1"># &#39;-{node-type}/dataproc-initialization-script-0_output&#39;]</span>
<span class="k">return</span> <span class="n">file</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">error</span><span class="p">(</span>
<span class="s1">&#39;Failed to get </span><span class="si">%s</span><span class="s1"> cluster staging bucket.&#39;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cluster_metadata</span><span class="o">.</span><span class="n">cluster_name</span><span class="p">)</span>
<span class="k">raise</span> <span class="n">e</span></div>
<div class="viewcode-block" id="DataprocClusterManager.parse_master_url_and_dashboard"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.html#apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.DataprocClusterManager.parse_master_url_and_dashboard">[docs]</a> <span class="k">def</span> <span class="nf">parse_master_url_and_dashboard</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">line</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Parses the master_url and YARN application_id of the Flink process from</span>
<span class="sd"> an input line. The line containing both the master_url and application id</span>
<span class="sd"> is always formatted as such:</span>
<span class="sd"> {text} Found Web Interface {master_url} of application</span>
<span class="sd"> &#39;{application_id}&#39;.\\n</span>
<span class="sd"> Truncated example where &#39;...&#39; represents additional text between segments:</span>
<span class="sd"> ... google-dataproc-startup[000]: ... activate-component-flink[0000]:</span>
<span class="sd"> ...org.apache.flink.yarn.YarnClusterDescriptor... [] -</span>
<span class="sd"> Found Web Interface example-master-url:50000 of application</span>
<span class="sd"> &#39;application_123456789000_0001&#39;.</span>
<span class="sd"> Returns the flink_master_url and dashboard link as a tuple.&quot;&quot;&quot;</span>
<span class="n">cluster_details</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_cluster_details</span><span class="p">()</span>
<span class="n">yarn_endpoint</span> <span class="o">=</span> <span class="n">cluster_details</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">endpoint_config</span><span class="o">.</span><span class="n">http_ports</span><span class="p">[</span>
<span class="s1">&#39;YARN ResourceManager&#39;</span><span class="p">]</span>
<span class="n">segment</span> <span class="o">=</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;Found Web Interface &#39;</span><span class="p">)[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39; of application &#39;</span><span class="p">)</span>
<span class="n">master_url</span> <span class="o">=</span> <span class="n">segment</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">application_id</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="s1">&#39;</span><span class="se">\&#39;</span><span class="s1">|.</span><span class="se">\n</span><span class="s1">&#39;</span><span class="p">,</span> <span class="s1">&#39;&#39;</span><span class="p">,</span> <span class="n">segment</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
<span class="n">dashboard</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span>
<span class="s1">&#39;/yarn/&#39;</span><span class="p">,</span>
<span class="s1">&#39;/gateway/default/yarn/proxy/&#39;</span> <span class="o">+</span> <span class="n">application_id</span> <span class="o">+</span> <span class="s1">&#39;/&#39;</span><span class="p">,</span>
<span class="n">yarn_endpoint</span><span class="p">)</span>
<span class="k">return</span> <span class="n">master_url</span><span class="p">,</span> <span class="n">dashboard</span></div>
<div class="viewcode-block" id="DataprocClusterManager.get_master_url_and_dashboard"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.html#apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.DataprocClusterManager.get_master_url_and_dashboard">[docs]</a> <span class="k">def</span> <span class="nf">get_master_url_and_dashboard</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Tuple</span><span class="p">[</span><span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">],</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns the master_url of the current cluster.&quot;&quot;&quot;</span>
<span class="n">startup_logs</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">file</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fs</span><span class="o">.</span><span class="n">_list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_staging_directory</span><span class="p">):</span>
<span class="k">if</span> <span class="n">DATAPROC_STAGING_LOG_NAME</span> <span class="ow">in</span> <span class="n">file</span><span class="o">.</span><span class="n">path</span><span class="p">:</span>
<span class="n">startup_logs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">file</span><span class="o">.</span><span class="n">path</span><span class="p">)</span>
<span class="k">for</span> <span class="n">log</span> <span class="ow">in</span> <span class="n">startup_logs</span><span class="p">:</span>
<span class="n">content</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fs</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">log</span><span class="p">)</span>
<span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">content</span><span class="o">.</span><span class="n">readlines</span><span class="p">():</span>
<span class="n">decoded_line</span> <span class="o">=</span> <span class="n">line</span><span class="o">.</span><span class="n">decode</span><span class="p">()</span>
<span class="k">if</span> <span class="s1">&#39;Found Web Interface&#39;</span> <span class="ow">in</span> <span class="n">decoded_line</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">parse_master_url_and_dashboard</span><span class="p">(</span><span class="n">decoded_line</span><span class="p">)</span>
<span class="k">return</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span></div>
<div class="viewcode-block" id="DataprocClusterManager.cleanup_staging_files"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.html#apache_beam.runners.interactive.dataproc.dataproc_cluster_manager.DataprocClusterManager.cleanup_staging_files">[docs]</a> <span class="k">def</span> <span class="nf">cleanup_staging_files</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_staging_directory</span><span class="p">:</span>
<span class="n">staging_files</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">file</span><span class="o">.</span><span class="n">path</span> <span class="k">for</span> <span class="n">file</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fs</span><span class="o">.</span><span class="n">_list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_staging_directory</span><span class="p">)</span>
<span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fs</span><span class="o">.</span><span class="n">delete</span><span class="p">(</span><span class="n">staging_files</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cache_root</span><span class="p">:</span>
<span class="n">cache_files</span> <span class="o">=</span> <span class="p">[</span><span class="n">file</span><span class="o">.</span><span class="n">path</span> <span class="k">for</span> <span class="n">file</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fs</span><span class="o">.</span><span class="n">_list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_cache_root</span><span class="p">)]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fs</span><span class="o">.</span><span class="n">delete</span><span class="p">(</span><span class="n">cache_files</span><span class="p">)</span></div></div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
&copy; Copyright
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>