Add Spark 1.6.0 docs

author: Michael Armbrust <marmbrus@apache.org> 2016-01-04 17:53:21 +0000
committer: Michael Armbrust <marmbrus@apache.org> 2016-01-04 17:53:21 +0000
commit: 0d824b0442707b6842ef19a589cb8a2af997273b (patch)
tree: 4ac1758b478ee6cb74382733fd3eb3157b6c3161 /site/docs/1.6.0/configuration.html
parent: ebcd167cbcb4ba33d8926b66850eff0cce12d365 (diff)
download: spark-website-0d824b0442707b6842ef19a589cb8a2af997273b.tar.gz
spark-website-0d824b0442707b6842ef19a589cb8a2af997273b.tar.bz2
spark-website-0d824b0442707b6842ef19a589cb8a2af997273b.zip
1 files changed, 1908 insertions, 0 deletions
diff --git a/site/docs/1.6.0/configuration.html b/site/docs/1.6.0/configuration.html
new file mode 100644
index 000000000..11cef7f39
--- /dev/null
+++ b/site/docs/1.6.0/configuration.html
@@ -0,0 +1,1908 @@
+
+<!DOCTYPE html>
+<!--[if lt IE 7]>      <html class="no-js lt-ie9 lt-ie8 lt-ie7"> <![endif]-->
+<!--[if IE 7]>         <html class="no-js lt-ie9 lt-ie8"> <![endif]-->
+<!--[if IE 8]>         <html class="no-js lt-ie9"> <![endif]-->
+<!--[if gt IE 8]><!--> <html class="no-js"> <!--<![endif]-->
+    <head>
+        <meta charset="utf-8">
+        <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">
+        <title>Configuration - Spark 1.6.0 Documentation</title>
+        
+
+        
+
+        <link rel="stylesheet" href="css/bootstrap.min.css">
+        <style>
+            body {
+                padding-top: 60px;
+                padding-bottom: 40px;
+            }
+        </style>
+        <meta name="viewport" content="width=device-width">
+        <link rel="stylesheet" href="css/bootstrap-responsive.min.css">
+        <link rel="stylesheet" href="css/main.css">
+
+        <script src="js/vendor/modernizr-2.6.1-respond-1.1.0.min.js"></script>
+
+        <link rel="stylesheet" href="css/pygments-default.css">
+
+        
+        <!-- Google analytics script -->
+        <script type="text/javascript">
+          var _gaq = _gaq || [];
+          _gaq.push(['_setAccount', 'UA-32518208-2']);
+          _gaq.push(['_trackPageview']);
+
+          (function() {
+            var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
+            ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
+            var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
+          })();
+        </script>
+        
+
+    </head>
+    <body>
+        <!--[if lt IE 7]>
+            <p class="chromeframe">You are using an outdated browser. <a href="http://browsehappy.com/">Upgrade your browser today</a> or <a href="http://www.google.com/chromeframe/?redirect=true">install Google Chrome Frame</a> to better experience this site.</p>
+        <![endif]-->
+
+        <!-- This code is taken from http://twitter.github.com/bootstrap/examples/hero.html -->
+
+        <div class="navbar navbar-fixed-top" id="topbar">
+            <div class="navbar-inner">
+                <div class="container">
+                    <div class="brand"><a href="index.html">
+                      <img src="img/spark-logo-hd.png" style="height:50px;"/></a><span class="version">1.6.0</span>
+                    </div>
+                    <ul class="nav">
+                        <!--TODO(andyk): Add class="active" attribute to li some how.-->
+                        <li><a href="index.html">Overview</a></li>
+
+                        <li class="dropdown">
+                            <a href="#" class="dropdown-toggle" data-toggle="dropdown">Programming Guides<b class="caret"></b></a>
+                            <ul class="dropdown-menu">
+                                <li><a href="quick-start.html">Quick Start</a></li>
+                                <li><a href="programming-guide.html">Spark Programming Guide</a></li>
+                                <li class="divider"></li>
+                                <li><a href="streaming-programming-guide.html">Spark Streaming</a></li>
+                                <li><a href="sql-programming-guide.html">DataFrames, Datasets and SQL</a></li>
+                                <li><a href="mllib-guide.html">MLlib (Machine Learning)</a></li>
+                                <li><a href="graphx-programming-guide.html">GraphX (Graph Processing)</a></li>
+                                <li><a href="bagel-programming-guide.html">Bagel (Pregel on Spark)</a></li>
+                                <li><a href="sparkr.html">SparkR (R on Spark)</a></li>
+                            </ul>
+                        </li>
+
+                        <li class="dropdown">
+                            <a href="#" class="dropdown-toggle" data-toggle="dropdown">API Docs<b class="caret"></b></a>
+                            <ul class="dropdown-menu">
+                                <li><a href="api/scala/index.html#org.apache.spark.package">Scala</a></li>
+                                <li><a href="api/java/index.html">Java</a></li>
+                                <li><a href="api/python/index.html">Python</a></li>
+                                <li><a href="api/R/index.html">R</a></li>
+                            </ul>
+                        </li>
+
+                        <li class="dropdown">
+                            <a href="#" class="dropdown-toggle" data-toggle="dropdown">Deploying<b class="caret"></b></a>
+                            <ul class="dropdown-menu">
+                                <li><a href="cluster-overview.html">Overview</a></li>
+                                <li><a href="submitting-applications.html">Submitting Applications</a></li>
+                                <li class="divider"></li>
+                                <li><a href="spark-standalone.html">Spark Standalone</a></li>
+                                <li><a href="running-on-mesos.html">Mesos</a></li>
+                                <li><a href="running-on-yarn.html">YARN</a></li>
+                                <li class="divider"></li>
+                                <li><a href="ec2-scripts.html">Amazon EC2</a></li>
+                            </ul>
+                        </li>
+
+                        <li class="dropdown">
+                            <a href="api.html" class="dropdown-toggle" data-toggle="dropdown">More<b class="caret"></b></a>
+                            <ul class="dropdown-menu">
+                                <li><a href="configuration.html">Configuration</a></li>
+                                <li><a href="monitoring.html">Monitoring</a></li>
+                                <li><a href="tuning.html">Tuning Guide</a></li>
+                                <li><a href="job-scheduling.html">Job Scheduling</a></li>
+                                <li><a href="security.html">Security</a></li>
+                                <li><a href="hardware-provisioning.html">Hardware Provisioning</a></li>
+                                <li class="divider"></li>
+                                <li><a href="building-spark.html">Building Spark</a></li>
+                                <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">Contributing to Spark</a></li>
+                                <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Supplemental+Spark+Projects">Supplemental Projects</a></li>
+                            </ul>
+                        </li>
+                    </ul>
+                    <!--<p class="navbar-text pull-right"><span class="version-text">v1.6.0</span></p>-->
+                </div>
+            </div>
+        </div>
+
+        <div class="container-wrapper">
+
+            
+                <div class="content" id="content">
+                    
+                        <h1 class="title">Spark Configuration</h1>
+                    
+
+                    <ul id="markdown-toc">
+  <li><a href="#spark-properties" id="markdown-toc-spark-properties">Spark Properties</a>    <ul>
+      <li><a href="#dynamically-loading-spark-properties" id="markdown-toc-dynamically-loading-spark-properties">Dynamically Loading Spark Properties</a></li>
+      <li><a href="#viewing-spark-properties" id="markdown-toc-viewing-spark-properties">Viewing Spark Properties</a></li>
+      <li><a href="#available-properties" id="markdown-toc-available-properties">Available Properties</a>        <ul>
+          <li><a href="#application-properties" id="markdown-toc-application-properties">Application Properties</a></li>
+          <li><a href="#runtime-environment" id="markdown-toc-runtime-environment">Runtime Environment</a></li>
+          <li><a href="#shuffle-behavior" id="markdown-toc-shuffle-behavior">Shuffle Behavior</a></li>
+          <li><a href="#spark-ui" id="markdown-toc-spark-ui">Spark UI</a></li>
+          <li><a href="#compression-and-serialization" id="markdown-toc-compression-and-serialization">Compression and Serialization</a></li>
+          <li><a href="#memory-management" id="markdown-toc-memory-management">Memory Management</a></li>
+          <li><a href="#execution-behavior" id="markdown-toc-execution-behavior">Execution Behavior</a></li>
+          <li><a href="#networking" id="markdown-toc-networking">Networking</a></li>
+          <li><a href="#scheduling" id="markdown-toc-scheduling">Scheduling</a></li>
+          <li><a href="#dynamic-allocation" id="markdown-toc-dynamic-allocation">Dynamic Allocation</a></li>
+          <li><a href="#security" id="markdown-toc-security">Security</a></li>
+          <li><a href="#encryption" id="markdown-toc-encryption">Encryption</a></li>
+          <li><a href="#spark-streaming" id="markdown-toc-spark-streaming">Spark Streaming</a></li>
+          <li><a href="#sparkr" id="markdown-toc-sparkr">SparkR</a></li>
+          <li><a href="#cluster-managers" id="markdown-toc-cluster-managers">Cluster Managers</a>            <ul>
+              <li><a href="#yarnrunning-on-yarnhtmlconfiguration" id="markdown-toc-yarnrunning-on-yarnhtmlconfiguration"><a href="running-on-yarn.html#configuration">YARN</a></a></li>
+              <li><a href="#mesosrunning-on-mesoshtmlconfiguration" id="markdown-toc-mesosrunning-on-mesoshtmlconfiguration"><a href="running-on-mesos.html#configuration">Mesos</a></a></li>
+              <li><a href="#standalone-modespark-standalonehtmlcluster-launch-scripts" id="markdown-toc-standalone-modespark-standalonehtmlcluster-launch-scripts"><a href="spark-standalone.html#cluster-launch-scripts">Standalone Mode</a></a></li>
+            </ul>
+          </li>
+        </ul>
+      </li>
+    </ul>
+  </li>
+  <li><a href="#environment-variables" id="markdown-toc-environment-variables">Environment Variables</a></li>
+  <li><a href="#configuring-logging" id="markdown-toc-configuring-logging">Configuring Logging</a></li>
+  <li><a href="#overriding-configuration-directory" id="markdown-toc-overriding-configuration-directory">Overriding configuration directory</a></li>
+  <li><a href="#inheriting-hadoop-cluster-configuration" id="markdown-toc-inheriting-hadoop-cluster-configuration">Inheriting Hadoop Cluster Configuration</a></li>
+</ul>
+
+<p>Spark provides three locations to configure the system:</p>
+
+<ul>
+  <li><a href="#spark-properties">Spark properties</a> control most application parameters and can be set by using
+a <a href="api/scala/index.html#org.apache.spark.SparkConf">SparkConf</a> object, or through Java
+system properties.</li>
+  <li><a href="#environment-variables">Environment variables</a> can be used to set per-machine settings, such as
+the IP address, through the <code>conf/spark-env.sh</code> script on each node.</li>
+  <li><a href="#configuring-logging">Logging</a> can be configured through <code>log4j.properties</code>.</li>
+</ul>
+
+<h1 id="spark-properties">Spark Properties</h1>
+
+<p>Spark properties control most application settings and are configured separately for each
+application. These properties can be set directly on a
+<a href="api/scala/index.html#org.apache.spark.SparkConf">SparkConf</a> passed to your
+<code>SparkContext</code>. <code>SparkConf</code> allows you to configure some of the common properties
+(e.g. master URL and application name), as well as arbitrary key-value pairs through the
+<code>set()</code> method. For example, we could initialize an application with two threads as follows:</p>
+
+<p>Note that we run with local[2], meaning two threads - which represents &#8220;minimal&#8221; parallelism,
+which can help detect bugs that only exist when we run in a distributed context.</p>
+
+<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">val</span> <span class="n">conf</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">SparkConf</span><span class="o">()</span>
+             <span class="o">.</span><span class="n">setMaster</span><span class="o">(</span><span class="s">&quot;local[2]&quot;</span><span class="o">)</span>
+             <span class="o">.</span><span class="n">setAppName</span><span class="o">(</span><span class="s">&quot;CountingSheep&quot;</span><span class="o">)</span>
+<span class="k">val</span> <span class="n">sc</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">SparkContext</span><span class="o">(</span><span class="n">conf</span><span class="o">)</span></code></pre></div>
+
+<p>Note that we can have more than 1 thread in local mode, and in cases like Spark Streaming, we may
+actually require more than 1 thread to prevent any sort of starvation issues.</p>
+
+<p>Properties that specify some time duration should be configured with a unit of time.
+The following format is accepted:</p>
+
+<pre><code>25ms (milliseconds)
+5s (seconds)
+10m or 10min (minutes)
+3h (hours)
+5d (days)
+1y (years)
+</code></pre>
+
+<p>Properties that specify a byte size should be configured with a unit of size.<br />
+The following format is accepted:</p>
+
+<pre><code>1b (bytes)
+1k or 1kb (kibibytes = 1024 bytes)
+1m or 1mb (mebibytes = 1024 kibibytes)
+1g or 1gb (gibibytes = 1024 mebibytes)
+1t or 1tb (tebibytes = 1024 gibibytes)
+1p or 1pb (pebibytes = 1024 tebibytes)
+</code></pre>
+
+<h2 id="dynamically-loading-spark-properties">Dynamically Loading Spark Properties</h2>
+<p>In some cases, you may want to avoid hard-coding certain configurations in a <code>SparkConf</code>. For
+instance, if you&#8217;d like to run the same application with different masters or different
+amounts of memory. Spark allows you to simply create an empty conf:</p>
+
+<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">val</span> <span class="n">sc</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">SparkContext</span><span class="o">(</span><span class="k">new</span> <span class="nc">SparkConf</span><span class="o">())</span></code></pre></div>
+
+<p>Then, you can supply configuration values at runtime:</p>
+
+<div class="highlight"><pre><code class="language-bash" data-lang="bash">./bin/spark-submit --name <span class="s2">&quot;My app&quot;</span> --master <span class="nb">local</span><span class="o">[</span>4<span class="o">]</span> --conf spark.eventLog.enabled<span class="o">=</span><span class="nb">false</span>
+  --conf <span class="s2">&quot;spark.executor.extraJavaOptions=-XX:+PrintGCDetails -XX:+PrintGCTimeStamps&quot;</span> myApp.jar</code></pre></div>
+
+<p>The Spark shell and <a href="submitting-applications.html"><code>spark-submit</code></a>
+tool support two ways to load configurations dynamically. The first are command line options,
+such as <code>--master</code>, as shown above. <code>spark-submit</code> can accept any Spark property using the <code>--conf</code>
+flag, but uses special flags for properties that play a part in launching the Spark application.
+Running <code>./bin/spark-submit --help</code> will show the entire list of these options.</p>
+
+<p><code>bin/spark-submit</code> will also read configuration options from <code>conf/spark-defaults.conf</code>, in which
+each line consists of a key and a value separated by whitespace. For example:</p>
+
+<pre><code>spark.master            spark://5.6.7.8:7077
+spark.executor.memory   4g
+spark.eventLog.enabled  true
+spark.serializer        org.apache.spark.serializer.KryoSerializer
+</code></pre>
+
+<p>Any values specified as flags or in the properties file will be passed on to the application
+and merged with those specified through SparkConf. Properties set directly on the SparkConf
+take highest precedence, then flags passed to <code>spark-submit</code> or <code>spark-shell</code>, then options
+in the <code>spark-defaults.conf</code> file. A few configuration keys have been renamed since earlier
+versions of Spark; in such cases, the older key names are still accepted, but take lower
+precedence than any instance of the newer key.</p>
+
+<h2 id="viewing-spark-properties">Viewing Spark Properties</h2>
+
+<p>The application web UI at <code>http://&lt;driver&gt;:4040</code> lists Spark properties in the &#8220;Environment&#8221; tab.
+This is a useful place to check to make sure that your properties have been set correctly. Note
+that only values explicitly specified through <code>spark-defaults.conf</code>, <code>SparkConf</code>, or the command
+line will appear. For all other configuration properties, you can assume the default value is used.</p>
+
+<h2 id="available-properties">Available Properties</h2>
+
+<p>Most of the properties that control internal settings have reasonable default values. Some
+of the most common options to set are:</p>
+
+<h4 id="application-properties">Application Properties</h4>
+<table class="table">
+<tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr>
+<tr>
+  <td><code>spark.app.name</code></td>
+  <td>(none)</td>
+  <td>
+    The name of your application. This will appear in the UI and in log data.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.driver.cores</code></td>
+  <td>1</td>
+  <td>
+    Number of cores to use for the driver process, only in cluster mode.
+  </td>
+</tr>
+  <td><code>spark.driver.maxResultSize</code></td>
+  <td>1g</td>
+  <td>
+    Limit of total size of serialized results of all partitions for each Spark action (e.g. collect).
+    Should be at least 1M, or 0 for unlimited. Jobs will be aborted if the total size
+    is above this limit.
+    Having a high limit may cause out-of-memory errors in driver (depends on spark.driver.memory
+    and memory overhead of objects in JVM). Setting a proper limit can protect the driver from
+    out-of-memory errors.
+  </td>
+
+<tr>
+  <td><code>spark.driver.memory</code></td>
+  <td>1g</td>
+  <td>
+    Amount of memory to use for the driver process, i.e. where SparkContext is initialized.
+    (e.g. <code>1g</code>, <code>2g</code>).
+
+    <br /><em>Note:</em> In client mode, this config must not be set through the <code>SparkConf</code>
+    directly in your application, because the driver JVM has already started at that point.
+    Instead, please set this through the <code>--driver-memory</code> command line option
+    or in your default properties file.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.executor.memory</code></td>
+  <td>1g</td>
+  <td>
+    Amount of memory to use per executor process (e.g. <code>2g</code>, <code>8g</code>).
+  </td>
+</tr>
+<tr>
+  <td><code>spark.extraListeners</code></td>
+  <td>(none)</td>
+  <td>
+    A comma-separated list of classes that implement <code>SparkListener</code>; when initializing
+    SparkContext, instances of these classes will be created and registered with Spark's listener
+    bus.  If a class has a single-argument constructor that accepts a SparkConf, that constructor
+    will be called; otherwise, a zero-argument constructor will be called. If no valid constructor
+    can be found, the SparkContext creation will fail with an exception.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.local.dir</code></td>
+  <td>/tmp</td>
+  <td>
+    Directory to use for "scratch" space in Spark, including map output files and RDDs that get
+    stored on disk. This should be on a fast, local disk in your system. It can also be a
+    comma-separated list of multiple directories on different disks.
+
+    NOTE: In Spark 1.0 and later this will be overriden by SPARK_LOCAL_DIRS (Standalone, Mesos) or
+    LOCAL_DIRS (YARN) environment variables set by the cluster manager.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.logConf</code></td>
+  <td>false</td>
+  <td>
+    Logs the effective SparkConf as INFO when a SparkContext is started.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.master</code></td>
+  <td>(none)</td>
+  <td>
+    The cluster manager to connect to. See the list of
+    <a href="submitting-applications.html#master-urls"> allowed master URL's</a>.
+  </td>
+</tr>
+</table>
+
+<p>Apart from these, the following properties are also available, and may be useful in some situations:</p>
+
+<h4 id="runtime-environment">Runtime Environment</h4>
+<table class="table">
+<tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr>
+<tr>
+  <td><code>spark.driver.extraClassPath</code></td>
+  <td>(none)</td>
+  <td>
+    Extra classpath entries to prepend to the classpath of the driver.
+
+    <br /><em>Note:</em> In client mode, this config must not be set through the <code>SparkConf</code>
+    directly in your application, because the driver JVM has already started at that point.
+    Instead, please set this through the <code>--driver-class-path</code> command line option or in
+    your default properties file.</td>
+  
+</tr>
+<tr>
+  <td><code>spark.driver.extraJavaOptions</code></td>
+  <td>(none)</td>
+  <td>
+    A string of extra JVM options to pass to the driver. For instance, GC settings or other logging.
+
+    <br /><em>Note:</em> In client mode, this config must not be set through the <code>SparkConf</code>
+    directly in your application, because the driver JVM has already started at that point.
+    Instead, please set this through the <code>--driver-java-options</code> command line option or in
+    your default properties file.</td>
+  
+</tr>
+<tr>
+  <td><code>spark.driver.extraLibraryPath</code></td>
+  <td>(none)</td>
+  <td>
+    Set a special library path to use when launching the driver JVM.
+
+    <br /><em>Note:</em> In client mode, this config must not be set through the <code>SparkConf</code>
+    directly in your application, because the driver JVM has already started at that point.
+    Instead, please set this through the <code>--driver-library-path</code> command line option or in
+    your default properties file.</td>
+  
+</tr>
+<tr>
+  <td><code>spark.driver.userClassPathFirst</code></td>
+  <td>false</td>
+  <td>
+    (Experimental) Whether to give user-added jars precedence over Spark's own jars when loading
+    classes in the the driver. This feature can be used to mitigate conflicts between Spark's
+    dependencies and user dependencies. It is currently an experimental feature.
+
+    This is used in cluster mode only.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.executor.extraClassPath</code></td>
+  <td>(none)</td>
+  <td>
+    Extra classpath entries to prepend to the classpath of executors. This exists primarily for
+    backwards-compatibility with older versions of Spark. Users typically should not need to set
+    this option.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.executor.extraJavaOptions</code></td>
+  <td>(none)</td>
+  <td>
+    A string of extra JVM options to pass to executors. For instance, GC settings or other logging.
+    Note that it is illegal to set Spark properties or heap size settings with this option. Spark
+    properties should be set using a SparkConf object or the spark-defaults.conf file used with the
+    spark-submit script. Heap size settings can be set with spark.executor.memory.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.executor.extraLibraryPath</code></td>
+  <td>(none)</td>
+  <td>
+    Set a special library path to use when launching executor JVM's.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.executor.logs.rolling.maxRetainedFiles</code></td>
+  <td>(none)</td>
+  <td>
+    Sets the number of latest rolling log files that are going to be retained by the system.
+    Older log files will be deleted. Disabled by default.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.executor.logs.rolling.maxSize</code></td>
+  <td>(none)</td>
+  <td>
+    Set the max size of the file by which the executor logs will be rolled over.
+    Rolling is disabled by default. See <code>spark.executor.logs.rolling.maxRetainedFiles</code>
+    for automatic cleaning of old logs.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.executor.logs.rolling.strategy</code></td>
+  <td>(none)</td>
+  <td>
+    Set the strategy of rolling of executor logs. By default it is disabled. It can
+    be set to "time" (time-based rolling) or "size" (size-based rolling). For "time",
+    use <code>spark.executor.logs.rolling.time.interval</code> to set the rolling interval.
+    For "size", use <code>spark.executor.logs.rolling.size.maxBytes</code> to set
+    the maximum file size for rolling.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.executor.logs.rolling.time.interval</code></td>
+  <td>daily</td>
+  <td>
+    Set the time interval by which the executor logs will be rolled over.
+    Rolling is disabled by default. Valid values are <code>daily</code>, <code>hourly</code>, <code>minutely</code> or
+    any interval in seconds. See <code>spark.executor.logs.rolling.maxRetainedFiles</code>
+    for automatic cleaning of old logs.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.executor.userClassPathFirst</code></td>
+  <td>false</td>
+  <td>
+    (Experimental) Same functionality as <code>spark.driver.userClassPathFirst</code>, but
+    applied to executor instances.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.executorEnv.[EnvironmentVariableName]</code></td>
+  <td>(none)</td>
+  <td>
+    Add the environment variable specified by <code>EnvironmentVariableName</code> to the Executor
+    process. The user can specify multiple of these to set multiple environment variables.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.python.profile</code></td>
+  <td>false</td>
+  <td>
+    Enable profiling in Python worker, the profile result will show up by <code>sc.show_profiles()</code>,
+    or it will be displayed before the driver exiting. It also can be dumped into disk by
+    <code>sc.dump_profiles(path)</code>. If some of the profile results had been displayed manually,
+    they will not be displayed automatically before driver exiting.
+
+    By default the <code>pyspark.profiler.BasicProfiler</code> will be used, but this can be overridden by
+    passing a profiler class in as a parameter to the <code>SparkContext</code> constructor.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.python.profile.dump</code></td>
+  <td>(none)</td>
+  <td>
+    The directory which is used to dump the profile result before driver exiting.
+    The results will be dumped as separated file for each RDD. They can be loaded
+    by ptats.Stats(). If this is specified, the profile result will not be displayed
+    automatically.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.python.worker.memory</code></td>
+  <td>512m</td>
+  <td>
+    Amount of memory to use per python worker process during aggregation, in the same
+    format as JVM memory strings (e.g. <code>512m</code>, <code>2g</code>). If the memory
+    used during aggregation goes above this amount, it will spill the data into disks.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.python.worker.reuse</code></td>
+  <td>true</td>
+  <td>
+    Reuse Python worker or not. If yes, it will use a fixed number of Python workers,
+    does not need to fork() a Python process for every tasks. It will be very useful
+    if there is large broadcast, then the broadcast will not be needed to transfered
+    from JVM to Python worker for every task.
+  </td>
+</tr>
+</table>
+
+<h4 id="shuffle-behavior">Shuffle Behavior</h4>
+<table class="table">
+<tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr>
+<tr>
+  <td><code>spark.reducer.maxSizeInFlight</code></td>
+  <td>48m</td>
+  <td>
+    Maximum size of map outputs to fetch simultaneously from each reduce task. Since
+    each output requires us to create a buffer to receive it, this represents a fixed memory
+    overhead per reduce task, so keep it small unless you have a large amount of memory.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.shuffle.compress</code></td>
+  <td>true</td>
+  <td>
+    Whether to compress map output files. Generally a good idea. Compression will use
+    <code>spark.io.compression.codec</code>.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.shuffle.file.buffer</code></td>
+  <td>32k</td>
+  <td>
+    Size of the in-memory buffer for each shuffle file output stream. These buffers
+    reduce the number of disk seeks and system calls made in creating intermediate shuffle files.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.shuffle.io.maxRetries</code></td>
+  <td>3</td>
+  <td>
+    (Netty only) Fetches that fail due to IO-related exceptions are automatically retried if this is
+    set to a non-zero value. This retry logic helps stabilize large shuffles in the face of long GC
+    pauses or transient network connectivity issues.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.shuffle.io.numConnectionsPerPeer</code></td>
+  <td>1</td>
+  <td>
+    (Netty only) Connections between hosts are reused in order to reduce connection buildup for
+    large clusters. For clusters with many hard disks and few hosts, this may result in insufficient
+    concurrency to saturate all disks, and so users may consider increasing this value.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.shuffle.io.preferDirectBufs</code></td>
+  <td>true</td>
+  <td>
+    (Netty only) Off-heap buffers are used to reduce garbage collection during shuffle and cache
+    block transfer. For environments where off-heap memory is tightly limited, users may wish to
+    turn this off to force all allocations from Netty to be on-heap.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.shuffle.io.retryWait</code></td>
+  <td>5s</td>
+  <td>
+    (Netty only) How long to wait between retries of fetches. The maximum delay caused by retrying
+    is 15 seconds by default, calculated as <code>maxRetries * retryWait</code>.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.shuffle.manager</code></td>
+  <td>sort</td>
+  <td>
+    Implementation to use for shuffling data. There are two implementations available:
+    <code>sort</code> and <code>hash</code>.
+    Sort-based shuffle is more memory-efficient and is the default option starting in 1.2.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.shuffle.service.enabled</code></td>
+  <td>false</td>
+  <td>
+    Enables the external shuffle service. This service preserves the shuffle files written by
+    executors so the executors can be safely removed. This must be enabled if
+    <code>spark.dynamicAllocation.enabled</code> is "true". The external shuffle service
+    must be set up in order to enable it. See
+    <a href="job-scheduling.html#configuration-and-setup">dynamic allocation
+    configuration and setup documentation</a> for more information.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.shuffle.service.port</code></td>
+  <td>7337</td>
+  <td>
+    Port on which the external shuffle service will run.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.shuffle.sort.bypassMergeThreshold</code></td>
+  <td>200</td>
+  <td>
+    (Advanced) In the sort-based shuffle manager, avoid merge-sorting data if there is no
+    map-side aggregation and there are at most this many reduce partitions.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.shuffle.spill.compress</code></td>
+  <td>true</td>
+  <td>
+    Whether to compress data spilled during shuffles. Compression will use
+    <code>spark.io.compression.codec</code>.
+  </td>
+</tr>
+</table>
+
+<h4 id="spark-ui">Spark UI</h4>
+<table class="table">
+<tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr>
+<tr>
+  <td><code>spark.eventLog.compress</code></td>
+  <td>false</td>
+  <td>
+    Whether to compress logged events, if <code>spark.eventLog.enabled</code> is true.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.eventLog.dir</code></td>
+  <td>file:///tmp/spark-events</td>
+  <td>
+    Base directory in which Spark events are logged, if <code>spark.eventLog.enabled</code> is true.
+    Within this base directory, Spark creates a sub-directory for each application, and logs the
+    events specific to the application in this directory. Users may want to set this to
+    a unified location like an HDFS directory so history files can be read by the history server.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.eventLog.enabled</code></td>
+  <td>false</td>
+  <td>
+    Whether to log Spark events, useful for reconstructing the Web UI after the application has
+    finished.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.ui.killEnabled</code></td>
+  <td>true</td>
+  <td>
+    Allows stages and corresponding jobs to be killed from the web ui.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.ui.port</code></td>
+  <td>4040</td>
+  <td>
+    Port for your application's dashboard, which shows memory and workload data.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.ui.retainedJobs</code></td>
+  <td>1000</td>
+  <td>
+    How many jobs the Spark UI and status APIs remember before garbage
+    collecting.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.ui.retainedStages</code></td>
+  <td>1000</td>
+  <td>
+    How many stages the Spark UI and status APIs remember before garbage
+    collecting.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.worker.ui.retainedExecutors</code></td>
+  <td>1000</td>
+  <td>
+    How many finished executors the Spark UI and status APIs remember before garbage collecting.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.worker.ui.retainedDrivers</code></td>
+  <td>1000</td>
+  <td>
+    How many finished drivers the Spark UI and status APIs remember before garbage collecting.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.sql.ui.retainedExecutions</code></td>
+  <td>1000</td>
+  <td>
+    How many finished executions the Spark UI and status APIs remember before garbage collecting.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.streaming.ui.retainedBatches</code></td>
+  <td>1000</td>
+  <td>
+    How many finished batches the Spark UI and status APIs remember before garbage collecting.
+  </td>
+</tr>
+</table>
+
+<h4 id="compression-and-serialization">Compression and Serialization</h4>
+<table class="table">
+<tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr>
+<tr>
+  <td><code>spark.broadcast.compress</code></td>
+  <td>true</td>
+  <td>
+    Whether to compress broadcast variables before sending them. Generally a good idea.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.closure.serializer</code></td>
+  <td>org.apache.spark.serializer.<br />JavaSerializer</td>
+  <td>
+    Serializer class to use for closures. Currently only the Java serializer is supported.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.io.compression.codec</code></td>
+  <td>snappy</td>
+  <td>
+    The codec used to compress internal data such as RDD partitions, broadcast variables and
+    shuffle outputs. By default, Spark provides three codecs: <code>lz4</code>, <code>lzf</code>,
+    and <code>snappy</code>. You can also use fully qualified class names to specify the codec,
+    e.g.
+    <code>org.apache.spark.io.LZ4CompressionCodec</code>,
+    <code>org.apache.spark.io.LZFCompressionCodec</code>,
+    and <code>org.apache.spark.io.SnappyCompressionCodec</code>.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.io.compression.lz4.blockSize</code></td>
+  <td>32k</td>
+  <td>
+    Block size used in LZ4 compression, in the case when LZ4 compression codec
+    is used. Lowering this block size will also lower shuffle memory usage when LZ4 is used.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.io.compression.snappy.blockSize</code></td>
+  <td>32k</td>
+  <td>
+    Block size used in Snappy compression, in the case when Snappy compression codec
+    is used. Lowering this block size will also lower shuffle memory usage when Snappy is used.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.kryo.classesToRegister</code></td>
+  <td>(none)</td>
+  <td>
+    If you use Kryo serialization, give a comma-separated list of custom class names to register
+    with Kryo.
+    See the <a href="tuning.html#data-serialization">tuning guide</a> for more details.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.kryo.referenceTracking</code></td>
+  <td>true (false when using Spark SQL Thrift Server)</td>
+  <td>
+    Whether to track references to the same object when serializing data with Kryo, which is
+    necessary if your object graphs have loops and useful for efficiency if they contain multiple
+    copies of the same object. Can be disabled to improve performance if you know this is not the
+    case.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.kryo.registrationRequired</code></td>
+  <td>false</td>
+  <td>
+    Whether to require registration with Kryo. If set to 'true', Kryo will throw an exception
+    if an unregistered class is serialized. If set to false (the default), Kryo will write
+    unregistered class names along with each object. Writing class names can cause
+    significant performance overhead, so enabling this option can enforce strictly that a
+    user has not omitted classes from registration.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.kryo.registrator</code></td>
+  <td>(none)</td>
+  <td>
+    If you use Kryo serialization, set this class to register your custom classes with Kryo. This
+    property is useful if you need to register your classes in a custom way, e.g. to specify a custom
+    field serializer. Otherwise <code>spark.kryo.classesToRegister</code> is simpler. It should be
+    set to a class that extends
+    <a href="api/scala/index.html#org.apache.spark.serializer.KryoRegistrator">
+    <code>KryoRegistrator</code></a>.
+    See the <a href="tuning.html#data-serialization">tuning guide</a> for more details.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.kryoserializer.buffer.max</code></td>
+  <td>64m</td>
+  <td>
+    Maximum allowable size of Kryo serialization buffer. This must be larger than any
+    object you attempt to serialize. Increase this if you get a "buffer limit exceeded" exception
+    inside Kryo.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.kryoserializer.buffer</code></td>
+  <td>64k</td>
+  <td>
+    Initial size of Kryo's serialization buffer. Note that there will be one buffer
+     <i>per core</i> on each worker. This buffer will grow up to
+     <code>spark.kryoserializer.buffer.max</code> if needed.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.rdd.compress</code></td>
+  <td>false</td>
+  <td>
+    Whether to compress serialized RDD partitions (e.g. for
+    <code>StorageLevel.MEMORY_ONLY_SER</code>). Can save substantial space at the cost of some
+    extra CPU time.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.serializer</code></td>
+  <td>
+    org.apache.spark.serializer.<br />JavaSerializer (org.apache.spark.serializer.<br />
+    KryoSerializer when using Spark SQL Thrift Server)
+  </td>
+  <td>
+    Class to use for serializing objects that will be sent over the network or need to be cached
+    in serialized form. The default of Java serialization works with any Serializable Java object
+    but is quite slow, so we recommend <a href="tuning.html">using
+    <code>org.apache.spark.serializer.KryoSerializer</code> and configuring Kryo serialization</a>
+    when speed is necessary. Can be any subclass of
+    <a href="api/scala/index.html#org.apache.spark.serializer.Serializer">
+    <code>org.apache.spark.Serializer</code></a>.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.serializer.objectStreamReset</code></td>
+  <td>100</td>
+  <td>
+    When serializing using org.apache.spark.serializer.JavaSerializer, the serializer caches
+    objects to prevent writing redundant data, however that stops garbage collection of those
+    objects. By calling 'reset' you flush that info from the serializer, and allow old
+    objects to be collected. To turn off this periodic reset set it to -1.
+    By default it will reset the serializer every 100 objects.
+  </td>
+</tr>
+</table>
+
+<h4 id="memory-management">Memory Management</h4>
+<table class="table">
+<tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr>
+<tr>
+  <td><code>spark.memory.fraction</code></td>
+  <td>0.75</td>
+  <td>
+    Fraction of (heap space - 300MB) used for execution and storage. The lower this is, the
+    more frequently spills and cached data eviction occur. The purpose of this config is to set
+    aside memory for internal metadata, user data structures, and imprecise size estimation
+    in the case of sparse, unusually large records. Leaving this at the default value is
+    recommended. For more detail, see <a href="tuning.html#memory-management-overview">
+    this description</a>.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.memory.storageFraction</code></td>
+  <td>0.5</td>
+  <td>
+    Amount of storage memory immune to eviction, expressed as a fraction of the size of the
+    region set aside by <code>spark.memory.fraction</code>. The higher this is, the less
+    working memory may be available to execution and tasks may spill to disk more often.
+    Leaving this at the default value is recommended. For more detail, see
+    <a href="tuning.html#memory-management-overview">this description</a>.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.memory.offHeap.enabled</code></td>
+  <td>true</td>
+  <td>
+    If true, Spark will attempt to use off-heap memory for certain operations. If off-heap memory use is enabled, then <code>spark.memory.offHeap.size</code> must be positive.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.memory.offHeap.size</code></td>
+  <td>0</td>
+  <td>
+    The absolute amount of memory which can be used for off-heap allocation.
+    This setting has no impact on heap memory usage, so if your executors' total memory consumption must fit within some hard limit then be sure to shrink your JVM heap size accordingly.
+    This must be set to a positive value when <code>spark.memory.offHeap.enabled=true</code>.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.memory.useLegacyMode</code></td>
+  <td>false</td>
+  <td>
+    Whether to enable the legacy memory management mode used in Spark 1.5 and before.
+    The legacy mode rigidly partitions the heap space into fixed-size regions,
+    potentially leading to excessive spilling if the application was not tuned.
+    The following deprecated memory fraction configurations are not read unless this is enabled:
+    <code>spark.shuffle.memoryFraction</code><br />
+    <code>spark.storage.memoryFraction</code><br />
+    <code>spark.storage.unrollFraction</code>
+  </td>
+</tr>
+<tr>
+  <td><code>spark.shuffle.memoryFraction</code></td>
+  <td>0.2</td>
+  <td>
+    (deprecated) This is read only if <code>spark.memory.useLegacyMode</code> is enabled.
+    Fraction of Java heap to use for aggregation and cogroups during shuffles.
+    At any given time, the collective size of
+    all in-memory maps used for shuffles is bounded by this limit, beyond which the contents will
+    begin to spill to disk. If spills are often, consider increasing this value at the expense of
+    <code>spark.storage.memoryFraction</code>.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.storage.memoryFraction</code></td>
+  <td>0.6</td>
+  <td>
+    (deprecated) This is read only if <code>spark.memory.useLegacyMode</code> is enabled.
+    Fraction of Java heap to use for Spark's memory cache. This should not be larger than the "old"
+    generation of objects in the JVM, which by default is given 0.6 of the heap, but you can
+    increase it if you configure your own old generation size.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.storage.unrollFraction</code></td>
+  <td>0.2</td>
+  <td>
+    (deprecated) This is read only if <code>spark.memory.useLegacyMode</code> is enabled.
+    Fraction of <code>spark.storage.memoryFraction</code> to use for unrolling blocks in memory.
+    This is dynamically allocated by dropping existing blocks when there is not enough free
+    storage space to unroll the new block in its entirety.
+  </td>
+</tr>
+</table>
+
+<h4 id="execution-behavior">Execution Behavior</h4>
+<table class="table">
+<tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr>
+<tr>
+  <td><code>spark.broadcast.blockSize</code></td>
+  <td>4m</td>
+  <td>
+    Size of each piece of a block for <code>TorrentBroadcastFactory</code>.
+    Too large a value decreases parallelism during broadcast (makes it slower); however, if it is
+    too small, <code>BlockManager</code> might take a performance hit.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.broadcast.factory</code></td>
+  <td>org.apache.spark.broadcast.<br />TorrentBroadcastFactory</td>
+  <td>
+    Which broadcast implementation to use.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.cleaner.ttl</code></td>
+  <td>(infinite)</td>
+  <td>
+    Duration (seconds) of how long Spark will remember any metadata (stages generated, tasks
+    generated, etc.). Periodic cleanups will ensure that metadata older than this duration will be
+    forgotten. This is useful for running Spark for many hours / days (for example, running 24/7 in
+    case of Spark Streaming applications). Note that any RDD that persists in memory for more than
+    this duration will be cleared as well.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.executor.cores</code></td>
+  <td>1 in YARN mode, all the available cores on the worker in standalone mode.</td>
+  <td>
+    The number of cores to use on each executor. For YARN and standalone mode only.
+
+    In standalone mode, setting this parameter allows an application to run multiple executors on
+    the same worker, provided that there are enough cores on that worker. Otherwise, only one
+    executor per application will run on each worker.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.default.parallelism</code></td>
+  <td>
+    For distributed shuffle operations like <code>reduceByKey</code> and <code>join</code>, the
+    largest number of partitions in a parent RDD.  For operations like <code>parallelize</code>
+    with no parent RDDs, it depends on the cluster manager:
+    <ul>
+      <li>Local mode: number of cores on the local machine</li>
+      <li>Mesos fine grained mode: 8</li>
+      <li>Others: total number of cores on all executor nodes or 2, whichever is larger</li>
+    </ul>
+  </td>
+  <td>
+    Default number of partitions in RDDs returned by transformations like <code>join</code>,
+    <code>reduceByKey</code>, and <code>parallelize</code> when not set by user.
+  </td>
+</tr>
+<tr>
+    <td><code>spark.executor.heartbeatInterval</code></td>
+    <td>10s</td>
+    <td>Interval between each executor's heartbeats to the driver.  Heartbeats let
+    the driver know that the executor is still alive and update it with metrics for in-progress
+    tasks.</td>
+</tr>
+<tr>
+  <td><code>spark.files.fetchTimeout</code></td>
+  <td>60s</td>
+  <td>
+    Communication timeout to use when fetching files added through SparkContext.addFile() from
+    the driver.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.files.useFetchCache</code></td>
+  <td>true</td>
+  <td>
+    If set to true (default), file fetching will use a local cache that is shared by executors
+    that belong to the same application, which can improve task launching performance when
+    running many executors on the same host. If set to false, these caching optimizations will
+    be disabled and all executors will fetch their own copies of files. This optimization may be
+    disabled in order to use Spark local directories that reside on NFS filesystems (see
+    <a href="https://issues.apache.org/jira/browse/SPARK-6313">SPARK-6313</a> for more details).
+  </td>
+</tr>
+<tr>
+  <td><code>spark.files.overwrite</code></td>
+  <td>false</td>
+  <td>
+    Whether to overwrite files added through SparkContext.addFile() when the target file exists and
+    its contents do not match those of the source.
+  </td>
+</tr>
+<tr>
+    <td><code>spark.hadoop.cloneConf</code></td>
+    <td>false</td>
+    <td>If set to true, clones a new Hadoop <code>Configuration</code> object for each task.  This
+    option should be enabled to work around <code>Configuration</code> thread-safety issues (see
+    <a href="https://issues.apache.org/jira/browse/SPARK-2546">SPARK-2546</a> for more details).
+    This is disabled by default in order to avoid unexpected performance regressions for jobs that
+    are not affected by these issues.</td>
+</tr>
+<tr>
+    <td><code>spark.hadoop.validateOutputSpecs</code></td>
+    <td>true</td>
+    <td>If set to true, validates the output specification (e.g. checking if the output directory already exists)
+    used in saveAsHadoopFile and other variants. This can be disabled to silence exceptions due to pre-existing
+    output directories. We recommend that users do not disable this except if trying to achieve compatibility with
+    previous versions of Spark. Simply use Hadoop's FileSystem API to delete output directories by hand.
+    This setting is ignored for jobs generated through Spark Streaming's StreamingContext, since
+    data may need to be rewritten to pre-existing output directories during checkpoint recovery.</td>
+</tr>
+<tr>
+  <td><code>spark.storage.memoryMapThreshold</code></td>
+  <td>2m</td>
+  <td>
+    Size of a block above which Spark memory maps when reading a block from disk.
+    This prevents Spark from memory mapping very small blocks. In general, memory
+    mapping has high overhead for blocks close to or below the page size of the operating system.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.externalBlockStore.blockManager</code></td>
+  <td>org.apache.spark.storage.TachyonBlockManager</td>
+  <td>
+    Implementation of external block manager (file system) that store RDDs. The file system's URL is set by
+    <code>spark.externalBlockStore.url</code>.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.externalBlockStore.baseDir</code></td>
+  <td>System.getProperty("java.io.tmpdir")</td>
+  <td>
+    Directories of the external block store that store RDDs. The file system's URL is set by
+   <code>spark.externalBlockStore.url</code> It can also be a comma-separated list of multiple
+    directories on Tachyon file system.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.externalBlockStore.url</code></td>
+  <td>tachyon://localhost:19998 for Tachyon</td>
+  <td>
+    The URL of the underlying external blocker file system in the external block store.
+  </td>
+</tr>
+</table>
+
+<h4 id="networking">Networking</h4>
+<table class="table">
+<tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr>
+<tr>
+  <td><code>spark.akka.frameSize</code></td>
+  <td>128</td>
+  <td>
+    Maximum message size (in MB) to allow in "control plane" communication; generally only applies to map
+    output size information sent between executors and the driver. Increase this if you are running
+    jobs with many thousands of map and reduce tasks and see messages about the frame size.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.akka.heartbeat.interval</code></td>
+  <td>1000s</td>
+  <td>
+    This is set to a larger value to disable the transport failure detector that comes built in to
+    Akka. It can be enabled again, if you plan to use this feature (Not recommended). A larger
+    interval value reduces network overhead and a smaller value ( ~ 1 s) might be more
+    informative for Akka's failure detector. Tune this in combination of <code>spark.akka.heartbeat.pauses</code>
+    if you need to. A likely positive use case for using failure detector would be: a sensistive
+    failure detector can help evict rogue executors quickly. However this is usually not the case
+    as GC pauses and network lags are expected in a real Spark cluster. Apart from that enabling
+    this leads to a lot of exchanges of heart beats between nodes leading to flooding the network
+    with those.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.akka.heartbeat.pauses</code></td>
+  <td>6000s</td>
+  <td>
+     This is set to a larger value to disable the transport failure detector that comes built in to Akka.
+     It can be enabled again, if you plan to use this feature (Not recommended). Acceptable heart
+     beat pause for Akka. This can be used to control sensitivity to GC pauses. Tune
+     this along with <code>spark.akka.heartbeat.interval</code> if you need to.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.akka.threads</code></td>
+  <td>4</td>
+  <td>
+    Number of actor threads to use for communication. Can be useful to increase on large clusters
+    when the driver has a lot of CPU cores.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.akka.timeout</code></td>
+  <td>100s</td>
+  <td>
+    Communication timeout between Spark nodes.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.blockManager.port</code></td>
+  <td>(random)</td>
+  <td>
+    Port for all block managers to listen on. These exist on both the driver and the executors.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.broadcast.port</code></td>
+  <td>(random)</td>
+  <td>
+    Port for the driver's HTTP broadcast server to listen on.
+    This is not relevant for torrent broadcast.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.driver.host</code></td>
+  <td>(local hostname)</td>
+  <td>
+    Hostname or IP address for the driver to listen on.
+    This is used for communicating with the executors and the standalone Master.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.driver.port</code></td>
+  <td>(random)</td>
+  <td>
+    Port for the driver to listen on.
+    This is used for communicating with the executors and the standalone Master.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.executor.port</code></td>
+  <td>(random)</td>
+  <td>
+    Port for the executor to listen on. This is used for communicating with the driver.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.fileserver.port</code></td>
+  <td>(random)</td>
+  <td>
+    Port for the driver's HTTP file server to listen on.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.network.timeout</code></td>
+  <td>120s</td>
+  <td>
+    Default timeout for all network interactions. This config will be used in place of
+    <code>spark.core.connection.ack.wait.timeout</code>, <code>spark.akka.timeout</code>,
+    <code>spark.storage.blockManagerSlaveTimeoutMs</code>,
+    <code>spark.shuffle.io.connectionTimeout</code>, <code>spark.rpc.askTimeout</code> or
+    <code>spark.rpc.lookupTimeout</code> if they are not configured.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.port.maxRetries</code></td>
+  <td>16</td>
+  <td>
+    Maximum number of retries when binding to a port before giving up.
+    When a port is given a specific value (non 0), each subsequent retry will
+    increment the port used in the previous attempt by 1 before retrying. This
+    essentially allows it to try a range of ports from the start port specified
+    to port + maxRetries.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.replClassServer.port</code></td>
+  <td>(random)</td>
+  <td>
+    Port for the driver's HTTP class server to listen on.
+    This is only relevant for the Spark shell.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.rpc.numRetries</code></td>
+  <td>3</td>
+  <td>
+    Number of times to retry before an RPC task gives up.
+    An RPC task will run at most times of this number.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.rpc.retry.wait</code></td>
+  <td>3s</td>
+  <td>
+    Duration for an RPC ask operation to wait before retrying.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.rpc.askTimeout</code></td>
+  <td>120s</td>
+  <td>
+    Duration for an RPC ask operation to wait before timing out.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.rpc.lookupTimeout</code></td>
+  <td>120s</td>
+  <td>
+    Duration for an RPC remote endpoint lookup operation to wait before timing out.  
+  </td>
+</tr>
+</table>
+
+<h4 id="scheduling">Scheduling</h4>
+<table class="table">
+<tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr>
+<tr>
+  <td><code>spark.cores.max</code></td>
+  <td>(not set)</td>
+  <td>
+    When running on a <a href="spark-standalone.html">standalone deploy cluster</a> or a
+    <a href="running-on-mesos.html#mesos-run-modes">Mesos cluster in "coarse-grained"
+    sharing mode</a>, the maximum amount of CPU cores to request for the application from
+    across the cluster (not from each machine). If not set, the default will be
+    <code>spark.deploy.defaultCores</code> on Spark's standalone cluster manager, or
+    infinite (all available cores) on Mesos.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.locality.wait</code></td>
+  <td>3s</td>
+  <td>
+    How long to wait to launch a data-local task before giving up and launching it
+    on a less-local node. The same wait will be used to step through multiple locality levels
+    (process-local, node-local, rack-local and then any). It is also possible to customize the
+    waiting time for each level by setting <code>spark.locality.wait.node</code>, etc.
+    You should increase this setting if your tasks are long and see poor locality, but the
+    default usually works well.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.locality.wait.node</code></td>
+  <td>spark.locality.wait</td>
+  <td>
+    Customize the locality wait for node locality. For example, you can set this to 0 to skip
+    node locality and search immediately for rack locality (if your cluster has rack information).
+  </td>
+</tr>
+<tr>
+  <td><code>spark.locality.wait.process</code></td>
+  <td>spark.locality.wait</td>
+  <td>
+    Customize the locality wait for process locality. This affects tasks that attempt to access
+    cached data in a particular executor process.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.locality.wait.rack</code></td>
+  <td>spark.locality.wait</td>
+  <td>
+    Customize the locality wait for rack locality.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.scheduler.maxRegisteredResourcesWaitingTime</code></td>
+  <td>30s</td>
+  <td>
+    Maximum amount of time to wait for resources to register before scheduling begins.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.scheduler.minRegisteredResourcesRatio</code></td>
+  <td>0.8 for YARN mode; 0.0 for standalone mode and Mesos coarse-grained mode</td>
+  <td>
+    The minimum ratio of registered resources (registered resources / total expected resources)
+    (resources are executors in yarn mode, CPU cores in standalone mode and Mesos coarsed-grained
+     mode ['spark.cores.max' value is total expected resources for Mesos coarse-grained mode] )
+    to wait for before scheduling begins. Specified as a double between 0.0 and 1.0.
+    Regardless of whether the minimum ratio of resources has been reached,
+    the maximum amount of time it will wait before scheduling begins is controlled by config
+    <code>spark.scheduler.maxRegisteredResourcesWaitingTime</code>.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.scheduler.mode</code></td>
+  <td>FIFO</td>
+  <td>
+    The <a href="job-scheduling.html#scheduling-within-an-application">scheduling mode</a> between
+    jobs submitted to the same SparkContext. Can be set to <code>FAIR</code>
+    to use fair sharing instead of queueing jobs one after another. Useful for
+    multi-user services.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.scheduler.revive.interval</code></td>
+  <td>1s</td>
+  <td>
+    The interval length for the scheduler to revive the worker resource offers to run tasks.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.speculation</code></td>
+  <td>false</td>
+  <td>
+    If set to "true", performs speculative execution of tasks. This means if one or more tasks are
+    running slowly in a stage, they will be re-launched.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.speculation.interval</code></td>
+  <td>100ms</td>
+  <td>
+    How often Spark will check for tasks to speculate.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.speculation.multiplier</code></td>
+  <td>1.5</td>
+  <td>
+    How many times slower a task is than the median to be considered for speculation.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.speculation.quantile</code></td>
+  <td>0.75</td>
+  <td>
+    Percentage of tasks which must be complete before speculation is enabled for a particular stage.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.task.cpus</code></td>
+  <td>1</td>
+  <td>
+    Number of cores to allocate for each task.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.task.maxFailures</code></td>
+  <td>4</td>
+  <td>
+    Number of individual task failures before giving up on the job.
+    Should be greater than or equal to 1. Number of allowed retries = this value - 1.
+  </td>
+</tr>
+</table>
+
+<h4 id="dynamic-allocation">Dynamic Allocation</h4>
+<table class="table">
+<tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr>
+<tr>
+  <td><code>spark.dynamicAllocation.enabled</code></td>
+  <td>false</td>
+  <td>
+    Whether to use dynamic resource allocation, which scales the number of executors registered
+    with this application up and down based on the workload. Note that this is currently only
+    available on YARN mode. For more detail, see the description
+    <a href="job-scheduling.html#dynamic-resource-allocation">here</a>.
+    <br /><br />
+    This requires <code>spark.shuffle.service.enabled</code> to be set.
+    The following configurations are also relevant:
+    <code>spark.dynamicAllocation.minExecutors</code>,
+    <code>spark.dynamicAllocation.maxExecutors</code>, and
+    <code>spark.dynamicAllocation.initialExecutors</code>
+  </td>
+</tr>
+<tr>
+  <td><code>spark.dynamicAllocation.executorIdleTimeout</code></td>
+  <td>60s</td>
+  <td>
+    If dynamic allocation is enabled and an executor has been idle for more than this duration,
+    the executor will be removed. For more detail, see this
+    <a href="job-scheduling.html#resource-allocation-policy">description</a>.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.dynamicAllocation.cachedExecutorIdleTimeout</code></td>
+  <td>infinity</td>
+  <td>
+    If dynamic allocation is enabled and an executor which has cached data blocks has been idle for more than this duration,
+    the executor will be removed. For more details, see this
+    <a href="job-scheduling.html#resource-allocation-policy">description</a>.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.dynamicAllocation.initialExecutors</code></td>
+  <td><code>spark.dynamicAllocation.minExecutors</code></td>
+  <td>
+    Initial number of executors to run if dynamic allocation is enabled.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.dynamicAllocation.maxExecutors</code></td>
+  <td>infinity</td>
+  <td>
+    Upper bound for the number of executors if dynamic allocation is enabled.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.dynamicAllocation.minExecutors</code></td>
+  <td>0</td>
+  <td>
+    Lower bound for the number of executors if dynamic allocation is enabled.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.dynamicAllocation.schedulerBacklogTimeout</code></td>
+  <td>1s</td>
+  <td>
+    If dynamic allocation is enabled and there have been pending tasks backlogged for more than
+    this duration, new executors will be requested. For more detail, see this
+    <a href="job-scheduling.html#resource-allocation-policy">description</a>.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.dynamicAllocation.sustainedSchedulerBacklogTimeout</code></td>
+  <td><code>schedulerBacklogTimeout</code></td>
+  <td>
+    Same as <code>spark.dynamicAllocation.schedulerBacklogTimeout</code>, but used only for
+    subsequent executor requests. For more detail, see this
+    <a href="job-scheduling.html#resource-allocation-policy">description</a>.
+  </td>
+</tr>
+</table>
+
+<h4 id="security">Security</h4>
+<table class="table">
+<tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr>
+<tr>
+  <td><code>spark.acls.enable</code></td>
+  <td>false</td>
+  <td>
+    Whether Spark acls should are enabled. If enabled, this checks to see if the user has
+    access permissions to view or modify the job.  Note this requires the user to be known,
+    so if the user comes across as null no checks are done. Filters can be used with the UI
+    to authenticate and set the user.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.admin.acls</code></td>
+  <td>Empty</td>
+  <td>
+    Comma separated list of users/administrators that have view and modify access to all Spark jobs.
+    This can be used if you run on a shared cluster and have a set of administrators or devs who
+    help debug when things work. Putting a "*" in the list means any user can have the priviledge
+    of admin.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.authenticate</code></td>
+  <td>false</td>
+  <td>
+    Whether Spark authenticates its internal connections. See
+    <code>spark.authenticate.secret</code> if not running on YARN.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.authenticate.secret</code></td>
+  <td>None</td>
+  <td>
+    Set the secret key used for Spark to authenticate between components. This needs to be set if
+    not running on YARN and authentication is enabled.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.authenticate.enableSaslEncryption</code></td>
+  <td>false</td>
+  <td>
+    Enable encrypted communication when authentication is enabled. This option is currently
+    only supported by the block transfer service.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.network.sasl.serverAlwaysEncrypt</code></td>
+  <td>false</td>
+  <td>
+    Disable unencrypted connections for services that support SASL authentication. This is
+    currently supported by the external shuffle service.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.core.connection.ack.wait.timeout</code></td>
+  <td>60s</td>
+  <td>
+    How long for the connection to wait for ack to occur before timing
+    out and giving up. To avoid unwilling timeout caused by long pause like GC,
+    you can set larger value.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.core.connection.auth.wait.timeout</code></td>
+  <td>30s</td>
+  <td>
+    How long for the connection to wait for authentication to occur before timing
+    out and giving up.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.modify.acls</code></td>
+  <td>Empty</td>
+  <td>
+    Comma separated list of users that have modify access to the Spark job. By default only the
+    user that started the Spark job has access to modify it (kill it for example). Putting a "*" in
+    the list means any user can have access to modify it.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.ui.filters</code></td>
+  <td>None</td>
+  <td>
+    Comma separated list of filter class names to apply to the Spark web UI. The filter should be a
+    standard <a href="http://docs.oracle.com/javaee/6/api/javax/servlet/Filter.html">
+    javax servlet Filter</a>. Parameters to each filter can also be specified by setting a
+    java system property of: <br />
+    <code>spark.&lt;class name of filter&gt;.params='param1=value1,param2=value2'</code><br />
+    For example: <br />
+    <code>-Dspark.ui.filters=com.test.filter1</code> <br />
+    <code>-Dspark.com.test.filter1.params='param1=foo,param2=testing'</code>
+  </td>
+</tr>
+<tr>
+  <td><code>spark.ui.view.acls</code></td>
+  <td>Empty</td>
+  <td>
+    Comma separated list of users that have view access to the Spark web ui. By default only the
+    user that started the Spark job has view access. Putting a "*" in the list means any user can
+    have view access to this Spark job.
+  </td>
+</tr>
+</table>
+
+<h4 id="encryption">Encryption</h4>
+
+<table class="table">
+    <tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr>
+    <tr>
+        <td><code>spark.ssl.enabled</code></td>
+        <td>false</td>
+        <td>
+            <p>Whether to enable SSL connections on all supported protocols.</p>
+
+            <p>All the SSL settings like <code>spark.ssl.xxx</code> where <code>xxx</code> is a
+            particular configuration property, denote the global configuration for all the supported
+            protocols. In order to override the global configuration for the particular protocol,
+            the properties must be overwritten in the protocol-specific namespace.</p>
+
+            <p>Use <code>spark.ssl.YYY.XXX</code> settings to overwrite the global configuration for
+            particular protocol denoted by <code>YYY</code>. Currently <code>YYY</code> can be
+            either <code>akka</code> for Akka based connections or <code>fs</code> for broadcast and
+            file server.</p>
+        </td>
+    </tr>
+    <tr>
+        <td><code>spark.ssl.enabledAlgorithms</code></td>
+        <td>Empty</td>
+        <td>
+            A comma separated list of ciphers. The specified ciphers must be supported by JVM.
+            The reference list of protocols one can find on
+            <a href="https://blogs.oracle.com/java-platform-group/entry/diagnosing_tls_ssl_and_https">this</a>
+            page.
+        </td>
+    </tr>
+    <tr>
+        <td><code>spark.ssl.keyPassword</code></td>
+        <td>None</td>
+        <td>
+            A password to the private key in key-store.
+        </td>
+    </tr>
+    <tr>
+        <td><code>spark.ssl.keyStore</code></td>
+        <td>None</td>
+        <td>
+            A path to a key-store file. The path can be absolute or relative to the directory where
+            the component is started in.
+        </td>
+    </tr>
+    <tr>
+        <td><code>spark.ssl.keyStorePassword</code></td>
+        <td>None</td>
+        <td>
+            A password to the key-store.
+        </td>
+    </tr>
+    <tr>
+        <td><code>spark.ssl.protocol</code></td>
+        <td>None</td>
+        <td>
+            A protocol name. The protocol must be supported by JVM. The reference list of protocols
+            one can find on <a href="https://blogs.oracle.com/java-platform-group/entry/diagnosing_tls_ssl_and_https">this</a>
+            page.
+        </td>
+    </tr>
+    <tr>
+        <td><code>spark.ssl.trustStore</code></td>
+        <td>None</td>
+        <td>
+            A path to a trust-store file. The path can be absolute or relative to the directory
+            where the component is started in.
+        </td>
+    </tr>
+    <tr>
+        <td><code>spark.ssl.trustStorePassword</code></td>
+        <td>None</td>
+        <td>
+            A password to the trust-store.
+        </td>
+    </tr>
+</table>
+
+<h4 id="spark-streaming">Spark Streaming</h4>
+<table class="table">
+<tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr>
+<tr>
+  <td><code>spark.streaming.backpressure.enabled</code></td>
+  <td>false</td>
+  <td>
+    Enables or disables Spark Streaming's internal backpressure mechanism (since 1.5).
+    This enables the Spark Streaming to control the receiving rate based on the
+    current batch scheduling delays and processing times so that the system receives
+    only as fast as the system can process. Internally, this dynamically sets the
+    maximum receiving rate of receivers. This rate is upper bounded by the values
+    <code>spark.streaming.receiver.maxRate</code> and <code>spark.streaming.kafka.maxRatePerPartition</code>
+    if they are set (see below).
+  </td>
+</tr>
+<tr>
+  <td><code>spark.streaming.blockInterval</code></td>
+  <td>200ms</td>
+  <td>
+    Interval at which data received by Spark Streaming receivers is chunked
+    into blocks of data before storing them in Spark. Minimum recommended - 50 ms. See the
+    <a href="streaming-programming-guide.html#level-of-parallelism-in-data-receiving">performance
+     tuning</a> section in the Spark Streaming programing guide for more details.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.streaming.receiver.maxRate</code></td>
+  <td>not set</td>
+  <td>
+    Maximum rate (number of records per second) at which each receiver will receive data.
+    Effectively, each stream will consume at most this number of records per second.
+    Setting this configuration to 0 or a negative number will put no limit on the rate.
+    See the <a href="streaming-programming-guide.html#deploying-applications">deployment guide</a>
+    in the Spark Streaming programing guide for mode details.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.streaming.receiver.writeAheadLog.enable</code></td>
+  <td>false</td>
+  <td>
+    Enable write ahead logs for receivers. All the input data received through receivers
+    will be saved to write ahead logs that will allow it to be recovered after driver failures.
+    See the <a href="streaming-programming-guide.html#deploying-applications">deployment guide</a>
+    in the Spark Streaming programing guide for more details.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.streaming.unpersist</code></td>
+  <td>true</td>
+  <td>
+    Force RDDs generated and persisted by Spark Streaming to be automatically unpersisted from
+    Spark's memory. The raw input data received by Spark Streaming is also automatically cleared.
+    Setting this to false will allow the raw data and persisted RDDs to be accessible outside the
+    streaming application as they will not be cleared automatically. But it comes at the cost of
+    higher memory usage in Spark.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.streaming.stopGracefullyOnShutdown</code></td>
+  <td>false</td>
+  <td>
+    If <code>true</code>, Spark shuts down the <code>StreamingContext</code> gracefully on JVM 
+    shutdown rather than immediately.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.streaming.kafka.maxRatePerPartition</code></td>
+  <td>not set</td>
+  <td>
+    Maximum rate (number of records per second) at which data will be read from each Kafka
+    partition when using the new Kafka direct stream API. See the
+    <a href="streaming-kafka-integration.html">Kafka Integration guide</a>
+    for more details.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.streaming.kafka.maxRetries</code></td>
+  <td>1</td>
+  <td>
+    Maximum number of consecutive retries the driver will make in order to find
+    the latest offsets on the leader of each partition (a default value of 1
+    means that the driver will make a maximum of 2 attempts). Only applies to
+    the new Kafka direct stream API.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.streaming.ui.retainedBatches</code></td>
+  <td>1000</td>
+  <td>
+    How many batches the Spark Streaming UI and status APIs remember before garbage collecting.
+  </td>
+</tr>
+</table>
+
+<h4 id="sparkr">SparkR</h4>
+<table class="table">
+<tr><th>Property Name</th><th>Default</th><th>Meaning</th></tr>
+<tr>
+  <td><code>spark.r.numRBackendThreads</code></td>
+  <td>2</td>
+  <td>
+    Number of threads used by RBackend to handle RPC calls from SparkR package.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.r.command</code></td>
+  <td>Rscript</td>
+  <td>
+    Executable for executing R scripts in cluster modes for both driver and workers.
+  </td>
+</tr>
+<tr>
+  <td><code>spark.r.driver.command</code></td>
+  <td>spark.r.command</td>
+  <td>
+    Executable for executing R scripts in client modes for driver. Ignored in cluster modes.
+  </td>
+</tr>
+</table>
+
+<h4 id="cluster-managers">Cluster Managers</h4>
+<p>Each cluster manager in Spark has additional configuration options. Configurations
+can be found on the pages for each mode:</p>
+
+<h5 id="yarnrunning-on-yarnhtmlconfiguration"><a href="running-on-yarn.html#configuration">YARN</a></h5>
+
+<h5 id="mesosrunning-on-mesoshtmlconfiguration"><a href="running-on-mesos.html#configuration">Mesos</a></h5>
+
+<h5 id="standalone-modespark-standalonehtmlcluster-launch-scripts"><a href="spark-standalone.html#cluster-launch-scripts">Standalone Mode</a></h5>
+
+<h1 id="environment-variables">Environment Variables</h1>
+
+<p>Certain Spark settings can be configured through environment variables, which are read from the
+<code>conf/spark-env.sh</code> script in the directory where Spark is installed (or <code>conf/spark-env.cmd</code> on
+Windows). In Standalone and Mesos modes, this file can give machine specific information such as
+hostnames. It is also sourced when running local Spark applications or submission scripts.</p>
+
+<p>Note that <code>conf/spark-env.sh</code> does not exist by default when Spark is installed. However, you can
+copy <code>conf/spark-env.sh.template</code> to create it. Make sure you make the copy executable.</p>
+
+<p>The following variables can be set in <code>spark-env.sh</code>:</p>
+
+<table class="table">
+  <tr><th style="width:21%">Environment Variable</th><th>Meaning</th></tr>
+  <tr>
+    <td><code>JAVA_HOME</code></td>
+    <td>Location where Java is installed (if it's not on your default <code>PATH</code>).</td>
+  </tr>
+  <tr>
+    <td><code>PYSPARK_PYTHON</code></td>
+    <td>Python binary executable to use for PySpark in both driver and workers (default is <code>python</code>).</td>
+  </tr>
+  <tr>
+    <td><code>PYSPARK_DRIVER_PYTHON</code></td>
+    <td>Python binary executable to use for PySpark in driver only (default is <code>PYSPARK_PYTHON</code>).</td>
+  </tr>
+  <tr>
+    <td><code>SPARKR_DRIVER_R</code></td>
+    <td>R binary executable to use for SparkR shell (default is <code>R</code>).</td>
+  </tr>
+  <tr>
+    <td><code>SPARK_LOCAL_IP</code></td>
+    <td>IP address of the machine to bind to.</td>
+  </tr>
+  <tr>
+    <td><code>SPARK_PUBLIC_DNS</code></td>
+    <td>Hostname your Spark program will advertise to other machines.</td>
+  </tr>
+</table>
+
+<p>In addition to the above, there are also options for setting up the Spark
+<a href="spark-standalone.html#cluster-launch-scripts">standalone cluster scripts</a>, such as number of cores
+to use on each machine and maximum memory.</p>
+
+<p>Since <code>spark-env.sh</code> is a shell script, some of these can be set programmatically &#8211; for example, you might
+compute <code>SPARK_LOCAL_IP</code> by looking up the IP of a specific network interface.</p>
+
+<h1 id="configuring-logging">Configuring Logging</h1>
+
+<p>Spark uses <a href="http://logging.apache.org/log4j/">log4j</a> for logging. You can configure it by adding a
+<code>log4j.properties</code> file in the <code>conf</code> directory. One way to start is to copy the existing
+<code>log4j.properties.template</code> located there.</p>
+
+<h1 id="overriding-configuration-directory">Overriding configuration directory</h1>
+
+<p>To specify a different configuration directory other than the default &#8220;SPARK_HOME/conf&#8221;,
+you can set SPARK_CONF_DIR. Spark will use the the configuration files (spark-defaults.conf, spark-env.sh, log4j.properties, etc)
+from this directory.</p>
+
+<h1 id="inheriting-hadoop-cluster-configuration">Inheriting Hadoop Cluster Configuration</h1>
+
+<p>If you plan to read and write from HDFS using Spark, there are two Hadoop configuration files that
+should be included on Spark&#8217;s classpath:</p>
+
+<ul>
+  <li><code>hdfs-site.xml</code>, which provides default behaviors for the HDFS client.</li>
+  <li><code>core-site.xml</code>, which sets the default filesystem name.</li>
+</ul>
+
+<p>The location of these configuration files varies across CDH and HDP versions, but
+a common location is inside of <code>/etc/hadoop/conf</code>. Some tools, such as Cloudera Manager, create
+configurations on-the-fly, but offer a mechanisms to download copies of them.</p>
+
+<p>To make these files visible to Spark, set <code>HADOOP_CONF_DIR</code> in <code>$SPARK_HOME/spark-env.sh</code>
+to a location containing the configuration files.</p>
+
+
+                </div>
+            
+             <!-- /container -->
+        </div>
+
+        <script src="js/vendor/jquery-1.8.0.min.js"></script>
+        <script src="js/vendor/bootstrap.min.js"></script>
+        <script src="js/vendor/anchor.min.js"></script>
+        <script src="js/main.js"></script>
+
+        <!-- MathJax Section -->
+        <script type="text/x-mathjax-config">
+            MathJax.Hub.Config({
+                TeX: { equationNumbers: { autoNumber: "AMS" } }
+            });
+        </script>
+        <script>
+            // Note that we load MathJax this way to work with local file (file://), HTTP and HTTPS.
+            // We could use "//cdn.mathjax...", but that won't support "file://".
+            (function(d, script) {
+                script = d.createElement('script');
+                script.type = 'text/javascript';
+                script.async = true;
+                script.onload = function(){
+                    MathJax.Hub.Config({
+                        tex2jax: {
+                            inlineMath: [ ["$", "$"], ["\\\\(","\\\\)"] ],
+                            displayMath: [ ["$$","$$"], ["\\[", "\\]"] ],
+                            processEscapes: true,
+                            skipTags: ['script', 'noscript', 'style', 'textarea', 'pre']
+                        }
+                    });
+                };
+                script.src = ('https:' == document.location.protocol ? 'https://' : 'http://') +
+                    'cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML';
+                d.getElementsByTagName('head')[0].appendChild(script);
+            }(document));
+        </script>
+    </body>
+</html>
author	Michael Armbrust <marmbrus@apache.org>	2016-01-04 17:53:21 +0000
committer	Michael Armbrust <marmbrus@apache.org>	2016-01-04 17:53:21 +0000
commit	0d824b0442707b6842ef19a589cb8a2af997273b (patch)
tree	4ac1758b478ee6cb74382733fd3eb3157b6c3161 /site/docs/1.6.0/configuration.html
parent	ebcd167cbcb4ba33d8926b66850eff0cce12d365 (diff)
download	spark-website-0d824b0442707b6842ef19a589cb8a2af997273b.tar.gz spark-website-0d824b0442707b6842ef19a589cb8a2af997273b.tar.bz2 spark-website-0d824b0442707b6842ef19a589cb8a2af997273b.zip