You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@metron.apache.org by ma...@apache.org on 2017/12/19 10:59:31 UTC
svn commit: r23800 [7/24] - in /dev/metron/0.4.2-RC2: ./ site-book/
site-book/css/ site-book/images/ site-book/images/logos/
site-book/images/profiles/ site-book/img/ site-book/js/
site-book/metron-analytics/ site-book/metron-analytics/metron-maas-serv...
Added: dev/metron/0.4.2-RC2/site-book/metron-analytics/metron-statistics/index.html
==============================================================================
--- dev/metron/0.4.2-RC2/site-book/metron-analytics/metron-statistics/index.html (added)
+++ dev/metron/0.4.2-RC2/site-book/metron-analytics/metron-statistics/index.html Tue Dec 19 10:59:31 2017
@@ -0,0 +1,971 @@
+<!DOCTYPE html>
+<!--
+ | Generated by Apache Maven Doxia at 2017-12-08
+ | Rendered using Apache Maven Fluido Skin 1.3.0
+-->
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+ <meta charset="UTF-8" />
+ <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+ <meta name="Date-Revision-yyyymmdd" content="20171208" />
+ <meta http-equiv="Content-Language" content="en" />
+ <title>Metron – Statistics and Mathematical Functions</title>
+ <link rel="stylesheet" href="../../css/apache-maven-fluido-1.3.0.min.css" />
+ <link rel="stylesheet" href="../../css/site.css" />
+ <link rel="stylesheet" href="../../css/print.css" media="print" />
+
+
+ <script type="text/javascript" src="../../js/apache-maven-fluido-1.3.0.min.js"></script>
+
+
+
+<script type="text/javascript">$( document ).ready( function() { $( '.carousel' ).carousel( { interval: 3500 } ) } );</script>
+
+ </head>
+ <body class="topBarDisabled">
+
+
+
+
+ <div class="container-fluid">
+ <div id="banner">
+ <div class="pull-left">
+ <a href="http://metron.apache.org/" id="bannerLeft">
+ <img src="../../images/metron-logo.png" alt="Apache Metron" width="148px" height="48px"/>
+ </a>
+ </div>
+ <div class="pull-right"> </div>
+ <div class="clear"><hr/></div>
+ </div>
+
+ <div id="breadcrumbs">
+ <ul class="breadcrumb">
+
+
+ <li class="">
+ <a href="http://www.apache.org" class="externalLink" title="Apache">
+ Apache</a>
+ </li>
+ <li class="divider ">/</li>
+ <li class="">
+ <a href="http://metron.apache.org/" class="externalLink" title="Metron">
+ Metron</a>
+ </li>
+ <li class="divider ">/</li>
+ <li class="">
+ <a href="../../index.html" title="Documentation">
+ Documentation</a>
+ </li>
+ <li class="divider ">/</li>
+ <li class="">Statistics and Mathematical Functions</li>
+
+
+
+ <li id="publishDate" class="pull-right">Last Published: 2017-12-08</li> <li class="divider pull-right">|</li>
+ <li id="projectVersion" class="pull-right">Version: 0.4.2</li>
+
+ </ul>
+ </div>
+
+
+ <div class="row-fluid">
+ <div id="leftColumn" class="span3">
+ <div class="well sidebar-nav">
+
+
+ <ul class="nav nav-list">
+ <li class="nav-header">User Documentation</li>
+
+ <li>
+
+ <a href="../../index.html" title="Metron">
+ <i class="icon-chevron-down"></i>
+ Metron</a>
+ <ul class="nav nav-list">
+
+ <li>
+
+ <a href="../../Upgrading.html" title="Upgrading">
+ <i class="none"></i>
+ Upgrading</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-analytics/index.html" title="Analytics">
+ <i class="icon-chevron-down"></i>
+ Analytics</a>
+ <ul class="nav nav-list">
+
+ <li>
+
+ <a href="../../metron-analytics/metron-maas-service/index.html" title="Maas-service">
+ <i class="none"></i>
+ Maas-service</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-analytics/metron-profiler/index.html" title="Profiler">
+ <i class="none"></i>
+ Profiler</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-analytics/metron-profiler-client/index.html" title="Profiler-client">
+ <i class="none"></i>
+ Profiler-client</a>
+ </li>
+
+ <li class="active">
+
+ <a href="#"><i class="icon-chevron-down"></i>Statistics</a>
+ <ul class="nav nav-list">
+
+ <li>
+
+ <a href="../../metron-analytics/metron-statistics/HLLP.html" title="HLLP">
+ <i class="none"></i>
+ HLLP</a>
+ </li>
+ </ul>
+ </li>
+ </ul>
+ </li>
+
+ <li>
+
+ <a href="../../metron-contrib/metron-docker/index.html" title="Docker">
+ <i class="none"></i>
+ Docker</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-deployment/index.html" title="Deployment">
+ <i class="icon-chevron-right"></i>
+ Deployment</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-interface/metron-alerts/index.html" title="Alerts">
+ <i class="none"></i>
+ Alerts</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-interface/metron-config/index.html" title="Config">
+ <i class="none"></i>
+ Config</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-interface/metron-rest/index.html" title="Rest">
+ <i class="none"></i>
+ Rest</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-platform/index.html" title="Platform">
+ <i class="icon-chevron-right"></i>
+ Platform</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-sensors/index.html" title="Sensors">
+ <i class="icon-chevron-right"></i>
+ Sensors</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-stellar/stellar-3rd-party-example/index.html" title="Stellar-3rd-party-example">
+ <i class="none"></i>
+ Stellar-3rd-party-example</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-stellar/stellar-common/index.html" title="Stellar-common">
+ <i class="icon-chevron-right"></i>
+ Stellar-common</a>
+ </li>
+
+ <li>
+
+ <a href="../../use-cases/index.html" title="Use-cases">
+ <i class="icon-chevron-right"></i>
+ Use-cases</a>
+ </li>
+ </ul>
+ </li>
+ </ul>
+
+
+
+ <hr class="divider" />
+
+ <div id="poweredBy">
+ <div class="clear"></div>
+ <div class="clear"></div>
+ <div class="clear"></div>
+ <a href="http://maven.apache.org/" title="Built by Maven" class="poweredBy">
+ <img class="builtBy" alt="Built by Maven" src="../../images/logos/maven-feather.png" />
+ </a>
+ </div>
+ </div>
+ </div>
+
+
+ <div id="bodyColumn" class="span9" >
+
+ <h1>Statistics and Mathematical Functions</h1>
+<p><a name="Statistics_and_Mathematical_Functions"></a></p>
+<p>A variety of non-trivial and advanced analytics make use of statistics and advanced mathematical functions. Particular, capturing the statistical snapshots in a scalable way can open up doors for more advanced analytics such as outlier analysis. As such, this project is aimed at capturing a robust set of statistical functions and statistical-based algorithms in the form of Stellar functions. These functions can be used from everywhere where Stellar is used.</p>
+<div class="section">
+<h2><a name="Stellar_Functions"></a>Stellar Functions</h2>
+<div class="section">
+<h3><a name="Approximation_Statistics"></a>Approximation Statistics</h3>
+<div class="section">
+<h4><a name="HLLP_ADD"></a><tt>HLLP_ADD</tt></h4>
+
+<ul>
+
+<li>Description: Add value to the HyperLogLogPlus estimator set. See <a href="HLLP.html">HLLP README</a></li>
+
+<li>Input:
+
+<ul>
+
+<li>hyperLogLogPlus - the hllp estimator to add a value to</li>
+
+<li>value+ - value to add to the set. Takes a single item or a list.</li>
+ </ul></li>
+
+<li>Returns: The HyperLogLogPlus set with a new value added</li>
+</ul></div>
+<div class="section">
+<h4><a name="HLLP_CARDINALITY"></a><tt>HLLP_CARDINALITY</tt></h4>
+
+<ul>
+
+<li>Description: Returns HyperLogLogPlus-estimated cardinality for this set. See <a href="HLLP.html">HLLP README</a></li>
+
+<li>Input:
+
+<ul>
+
+<li>hyperLogLogPlus - the hllp set</li>
+ </ul></li>
+
+<li>Returns: Long value representing the cardinality for this set. Cardinality of a null set is 0.</li>
+</ul></div>
+<div class="section">
+<h4><a name="HLLP_INIT"></a><tt>HLLP_INIT</tt></h4>
+
+<ul>
+
+<li>Description: Initializes the HyperLogLogPlus estimator set. p must be a value between 4 and sp and sp must be less than 32 and greater than 4. See <a href="HLLP.html">HLLP README</a></li>
+
+<li>Input:
+
+<ul>
+
+<li>p - the precision value for the normal set</li>
+
+<li>sp - the precision value for the sparse set. If p is set, but sp is 0 or not specified, the sparse set will be disabled.</li>
+ </ul></li>
+
+<li>Returns: A new HyperLogLogPlus set</li>
+</ul></div>
+<div class="section">
+<h4><a name="HLLP_MERGE"></a><tt>HLLP_MERGE</tt></h4>
+
+<ul>
+
+<li>Description: Merge hllp sets together. The resulting estimator is initialized with p and sp precision values from the first provided hllp estimator set. See <a href="HLLP.html">HLLP README</a></li>
+
+<li>Input:
+
+<ul>
+
+<li>hllp - List of hllp estimators to merge. Takes a single hllp set or a list.</li>
+ </ul></li>
+
+<li>Returns: A new merged HyperLogLogPlus estimator set. Passing an empty list returns null.</li>
+</ul></div></div>
+<div class="section">
+<h3><a name="Mathematical_Functions"></a>Mathematical Functions</h3>
+<div class="section">
+<h4><a name="ABS"></a><tt>ABS</tt></h4>
+
+<ul>
+
+<li>Description: Returns the absolute value of a number.</li>
+
+<li>Input:
+
+<ul>
+
+<li>number - The number to take the absolute value of</li>
+ </ul></li>
+
+<li>Returns: The absolute value of the number passed in.</li>
+</ul></div>
+<div class="section">
+<h4><a name="BIN"></a><tt>BIN</tt></h4>
+
+<ul>
+
+<li>Description: Computes the bin that the value is in given a set of bounds.</li>
+
+<li>Input:
+
+<ul>
+
+<li>value - The value to bin</li>
+
+<li>bounds - A list of value bounds (excluding min and max) in sorted order.</li>
+ </ul></li>
+
+<li>Returns: Which bin N the value falls in such that bound(N-1) < value <= bound(N). No min and max bounds are provided, so values smaller than the 0’th bound go in the 0’th bin, and values greater than the last bound go in the M’th bin.</li>
+</ul></div></div>
+<div class="section">
+<h3><a name="Distributional_Statistics"></a>Distributional Statistics</h3>
+<div class="section">
+<h4><a name="STATS_ADD"></a><tt>STATS_ADD</tt></h4>
+
+<ul>
+
+<li>Description: Adds one or more input values to those that are used to calculate the summary statistics.</li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object. If null, then a new one is initialized.</li>
+
+<li>value+ - One or more items to add. Each item may be a number or a list of numbers. If an item is a list, each number in the list will be added.</li>
+ </ul></li>
+
+<li>Returns: A Stellar statistics object</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_BIN"></a><tt>STATS_BIN</tt></h4>
+
+<ul>
+
+<li>Description: Computes the bin that the value is in based on the statistical distribution.</li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+
+<li>value - The value to bin</li>
+
+<li>bounds? - A list of percentile bin bounds (excluding min and max) or a string representing a known and common set of bins. For convenience, we have provided QUARTILE, QUINTILE, and DECILE which you can pass in as a string arg. If this argument is omitted, then we assume a Quartile bin split.</li>
+ </ul></li>
+
+<li>Returns: "Which bin N the value falls in such that bound(N-1) < value <= bound(N). No min and max bounds are provided, so values smaller than the 0’th bound go in the 0’th bin, and values greater than the last bound go in the M’th bin.</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_COUNT"></a><tt>STATS_COUNT</tt></h4>
+
+<ul>
+
+<li>Description: Calculates the count of the values accumulated (or in the window if a window is used).</li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+ </ul></li>
+
+<li>Returns: The count of the values in the window or NaN if the statistics object is null.</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_GEOMETRIC_MEAN"></a><tt>STATS_GEOMETRIC_MEAN</tt></h4>
+
+<ul>
+
+<li>Description: Calculates the geometric mean of the accumulated values (or in the window if a window is used). See <a class="externalLink" href="http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics">http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics</a></li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+ </ul></li>
+
+<li>Returns: The geometric mean of the values in the window or NaN if the statistics object is null.</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_INIT"></a><tt>STATS_INIT</tt></h4>
+
+<ul>
+
+<li>Description: Initializes a statistics object</li>
+
+<li>Input:
+
+<ul>
+
+<li>window_size - The number of input data values to maintain in a rolling window in memory. If window_size is equal to 0, then no rolling window is maintained. Using no rolling window is less memory intensive, but cannot calculate certain statistics like percentiles and kurtosis.</li>
+ </ul></li>
+
+<li>Returns: A Stellar statistics object</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_KURTOSIS"></a><tt>STATS_KURTOSIS</tt></h4>
+
+<ul>
+
+<li>Description: Calculates the kurtosis of the accumulated values (or in the window if a window is used). See <a class="externalLink" href="http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics">http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics</a></li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+ </ul></li>
+
+<li>Returns: The kurtosis of the values in the window or NaN if the statistics object is null.</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_MAX"></a><tt>STATS_MAX</tt></h4>
+
+<ul>
+
+<li>Description: Calculates the maximum of the accumulated values (or in the window if a window is used).</li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+ </ul></li>
+
+<li>Returns: The maximum of the accumulated values in the window or NaN if the statistics object is null.</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_MEAN"></a><tt>STATS_MEAN</tt></h4>
+
+<ul>
+
+<li>Description: Calculates the mean of the accumulated values (or in the window if a window is used).</li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+ </ul></li>
+
+<li>Returns: The mean of the values in the window or NaN if the statistics object is null.</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_MERGE"></a><tt>STATS_MERGE</tt></h4>
+
+<ul>
+
+<li>Description: Merges statistics objects.</li>
+
+<li>Input:
+
+<ul>
+
+<li>statistics - A list of statistics objects</li>
+ </ul></li>
+
+<li>Returns: A Stellar statistics object</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_MIN"></a><tt>STATS_MIN</tt></h4>
+
+<ul>
+
+<li>Description: Calculates the minimum of the accumulated values (or in the window if a window is used).</li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+ </ul></li>
+
+<li>Returns: The minimum of the accumulated values in the window or NaN if the statistics object is null.</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_PERCENTILE"></a><tt>STATS_PERCENTILE</tt></h4>
+
+<ul>
+
+<li>Description: Computes the p’th percentile of the accumulated values (or in the window if a window is used).</li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+
+<li>p - a double where 0 <= p < 1 representing the percentile</li>
+ </ul></li>
+
+<li>Returns: The p’th percentile of the data or NaN if the statistics object is null</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_POPULATION_VARIANCE"></a><tt>STATS_POPULATION_VARIANCE</tt></h4>
+
+<ul>
+
+<li>Description: Calculates the population variance of the accumulated values (or in the window if a window is used). See <a class="externalLink" href="http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics">http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics</a></li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+ </ul></li>
+
+<li>Returns: The population variance of the values in the window or NaN if the statistics object is null.</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_QUADRATIC_MEAN"></a><tt>STATS_QUADRATIC_MEAN</tt></h4>
+
+<ul>
+
+<li>Description: Calculates the quadratic mean of the accumulated values (or in the window if a window is used). See <a class="externalLink" href="http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics">http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics</a></li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+ </ul></li>
+
+<li>Returns: The quadratic mean of the values in the window or NaN if the statistics object is null.</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_SD"></a><tt>STATS_SD</tt></h4>
+
+<ul>
+
+<li>Description: Calculates the standard deviation of the accumulated values (or in the window if a window is used). See <a class="externalLink" href="http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics">http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics</a></li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+ </ul></li>
+
+<li>Returns: The standard deviation of the values in the window or NaN if the statistics object is null.</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_SKEWNESS"></a><tt>STATS_SKEWNESS</tt></h4>
+
+<ul>
+
+<li>Description: Calculates the skewness of the accumulated values (or in the window if a window is used). See <a class="externalLink" href="http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics">http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics</a></li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+ </ul></li>
+
+<li>Returns: The skewness of the values in the window or NaN if the statistics object is null.</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_SUM"></a><tt>STATS_SUM</tt></h4>
+
+<ul>
+
+<li>Description: Calculates the sum of the accumulated values (or in the window if a window is used).</li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+ </ul></li>
+
+<li>Returns: The sum of the values in the window or NaN if the statistics object is null.</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_SUM_LOGS"></a><tt>STATS_SUM_LOGS</tt></h4>
+
+<ul>
+
+<li>Description: Calculates the sum of the (natural) log of the accumulated values (or in the window if a window is used). See <a class="externalLink" href="http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics">http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics</a></li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+ </ul></li>
+
+<li>Returns: The sum of the (natural) log of the values in the window or NaN if the statistics object is null.</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_SUM_SQUARES"></a><tt>STATS_SUM_SQUARES</tt></h4>
+
+<ul>
+
+<li>Description: Calculates the sum of the squares of the accumulated values (or in the window if a window is used).</li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+ </ul></li>
+
+<li>Returns: The sum of the squares of the values in the window or NaN if the statistics object is null.</li>
+</ul></div>
+<div class="section">
+<h4><a name="STATS_VARIANCE"></a><tt>STATS_VARIANCE</tt></h4>
+
+<ul>
+
+<li>Description: Calculates the variance of the accumulated values (or in the window if a window is used). See <a class="externalLink" href="http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics">http://commons.apache.org/proper/commons-math/userguide/stat.html#a1.2_Descriptive_statistics</a></li>
+
+<li>Input:
+
+<ul>
+
+<li>stats - The Stellar statistics object</li>
+ </ul></li>
+
+<li>Returns: The variance of the values in the window or NaN if the statistics object is null.</li>
+</ul></div></div>
+<div class="section">
+<h3><a name="Statistical_Outlier_Detection"></a>Statistical Outlier Detection</h3>
+<div class="section">
+<h4><a name="OUTLIER_MAD_STATE_MERGE"></a><tt>OUTLIER_MAD_STATE_MERGE</tt></h4>
+
+<ul>
+
+<li>Description: Update the statistical state required to compute the Median Absolute Deviation.</li>
+
+<li>Input:
+
+<ul>
+
+<li>[state] - A list of Median Absolute Deviation States to merge. Generally these are states across time.</li>
+
+<li>currentState? - The current state (optional)</li>
+ </ul></li>
+
+<li>Returns: The Median Absolute Deviation state</li>
+</ul></div>
+<div class="section">
+<h4><a name="OUTLIER_MAD_ADD"></a><tt>OUTLIER_MAD_ADD</tt></h4>
+
+<ul>
+
+<li>Description: Add a piece of data to the state.</li>
+
+<li>Input:
+
+<ul>
+
+<li>state - The MAD state</li>
+
+<li>value - The numeric value to add</li>
+ </ul></li>
+
+<li>Returns: The MAD state</li>
+</ul></div>
+<div class="section">
+<h4><a name="OUTLIER_MAD_SCORE"></a><tt>OUTLIER_MAD_SCORE</tt></h4>
+
+<ul>
+
+<li>Description: Get the modified z-score normalized by the MAD: scale * | x_i - median(X) | / MAD. See the first page of <a class="externalLink" href="http://web.ipac.caltech.edu/staff/fmasci/home/astro_refs/BetterThanMAD.pdf">http://web.ipac.caltech.edu/staff/fmasci/home/astro_refs/BetterThanMAD.pdf</a></li>
+
+<li>Input:
+
+<ul>
+
+<li>state - The MAD state</li>
+
+<li>value - The numeric value to score</li>
+
+<li>scale? - Optionally the scale to use when computing the modified z-score. Default is <tt>0.6745</tt>, see the first page of <a class="externalLink" href="http://web.ipac.caltech.edu/staff/fmasci/home/astro_refs/BetterThanMAD.pdf">http://web.ipac.caltech.edu/staff/fmasci/home/astro_refs/BetterThanMAD.pdf</a></li>
+ </ul></li>
+
+<li>Returns: The modified z-score</li>
+</ul>
+<p><a name="Outlier_Analysis"></a></p>
+<h1>Outlier Analysis</h1>
+<p>A common desire is to find anomalies in numerical data. To that end, we have some simple statistical anomaly detectors.</p></div></div></div>
+<div class="section">
+<h2><a name="Median_Absolute_Deviation"></a>Median Absolute Deviation</h2>
+<p>Much has been written about this robust estimator. See the first page of <a class="externalLink" href="http://web.ipac.caltech.edu/staff/fmasci/home/astro_refs/BetterThanMAD.pdf">http://web.ipac.caltech.edu/staff/fmasci/home/astro_refs/BetterThanMAD.pdf</a> for a good coverage of the good and the bad of MAD. The usage, however is fairly straightforward:</p>
+
+<ul>
+
+<li>Gather the statistical state required to compute the MAD
+
+<ul>
+
+<li>The distribution of the values of a univariate random variable over time.</li>
+
+<li>The distribution of the absolute deviations of the values from the median.</li>
+ </ul></li>
+
+<li>Use this statistical state to score unseen values. The higher the score, the more unlike the previously seen data the value is.</li>
+</ul>
+<p>There are a couple of issues which make MAD a bit hard to compute. First, the statistical state requires computing median, which can be computationally expensive to compute exactly. To get around this, we use the OnlineStatisticalProvider to compute a sketch rather than the exact median. Secondly, the statistical state for seasonal data should be limited to a fixed, trailing window. We do this by ensuring that the MAD state is mergeable and able to be queried from within the Profiler.</p>
+<div class="section">
+<h3><a name="Example"></a>Example</h3>
+<p>We will create a dummy data stream of gaussian noise to illustrate how to use the MAD functionality along with the profiler to tag messages as outliers or not.</p>
+<p>To do this, we will create a </p>
+
+<ul>
+
+<li>data generator</li>
+
+<li>parser</li>
+
+<li>profiler profile</li>
+
+<li>enrichment and threat triage</li>
+</ul>
+<div class="section">
+<h4><a name="Data_Generator"></a>Data Generator</h4>
+<p>We can create a simple python script to generate a stream of gaussian noise at the frequency of one message per second as a python script which should be saved at <tt>~/rand_gen.py</tt>:</p>
+
+<div class="source">
+<div class="source">
+<pre>#!/usr/bin/python
+import random
+import sys
+import time
+def main():
+ mu = float(sys.argv[1])
+ sigma = float(sys.argv[2])
+ freq_s = int(sys.argv[3])
+ while True:
+ print str(random.gauss(mu, sigma))
+ sys.stdout.flush()
+ time.sleep(freq_s)
+
+if __name__ == '__main__':
+ main()
+</pre></div></div>
+<p>This script will take the following as arguments:</p>
+
+<ul>
+
+<li>The mean of the data generated</li>
+
+<li>The standard deviation of the data generated</li>
+
+<li>The frequency (in seconds) of the data generated</li>
+</ul>
+<p>If, however, you’d like to test a longer tailed distribution, like the student t-distribution and have numpy installed, you can use the following as <tt>~/rand_gen.py</tt>:</p>
+
+<div class="source">
+<div class="source">
+<pre>#!/usr/bin/python
+import random
+import sys
+import time
+import numpy as np
+
+def main():
+ df = float(sys.argv[1])
+ freq_s = int(sys.argv[2])
+ while True:
+ print str(np.random.standard_t(df))
+ sys.stdout.flush()
+ time.sleep(freq_s)
+
+if __name__ == '__main__':
+ main()
+</pre></div></div>
+<p>This script will take the following as arguments:</p>
+
+<ul>
+
+<li>The degrees of freedom for the distribution</li>
+
+<li>The frequency (in seconds) of the data generated</li>
+</ul></div>
+<div class="section">
+<h4><a name="The_Parser"></a>The Parser</h4>
+<p>We will create a parser that will take the single numbers in and create a message with a field called <tt>value</tt> in them using the <tt>CSVParser</tt>.</p>
+<p>Add the following file to <tt>$METRON_HOME/config/zookeeper/parsers/mad.json</tt>:</p>
+
+<div class="source">
+<div class="source">
+<pre>{
+ "parserClassName" : "org.apache.metron.parsers.csv.CSVParser"
+ ,"sensorTopic" : "mad"
+ ,"parserConfig" : {
+ "columns" : {
+ "value_str" : 0
+ }
+ }
+ ,"fieldTransformations" : [
+ {
+ "transformation" : "STELLAR"
+ ,"output" : [ "value" ]
+ ,"config" : {
+ "value" : "TO_DOUBLE(value_str)"
+ }
+ }
+ ]
+}
+</pre></div></div></div>
+<div class="section">
+<h4><a name="Enrichment_and_Threat_Intel"></a>Enrichment and Threat Intel</h4>
+<p>We will set a threat triage level of <tt>10</tt> if a message generates a outlier score of more than 3.5. This cutoff will depend on your data and should be adjusted based on the assumed underlying distribution. Note that under the assumptions of normality, MAD will act as a robust estimator of the standard deviation, so the cutoff should be considered the number of standard deviations away. For other distributions, there are other interpretations which will make sense in the context of measuring the “degree different”. See <a class="externalLink" href="http://eurekastatistics.com/using-the-median-absolute-deviation-to-find-outliers/">http://eurekastatistics.com/using-the-median-absolute-deviation-to-find-outliers/</a> for a brief discussion of this.</p>
+<p>Create the following in <tt>$METRON_HOME/config/zookeeper/enrichments/mad.json</tt>:</p>
+
+<div class="source">
+<div class="source">
+<pre>{
+ "enrichment": {
+ "fieldMap": {
+ "stellar" : {
+ "config" : {
+ "parser_score" : "OUTLIER_MAD_SCORE(OUTLIER_MAD_STATE_MERGE(
+PROFILE_GET( 'sketchy_mad', 'global', PROFILE_FIXED(10, 'MINUTES')) ), value)"
+ ,"is_alert" : "if parser_score > 3.5 then true else is_alert"
+ }
+ }
+ }
+ ,"fieldToTypeMap": { }
+ },
+ "threatIntel": {
+ "fieldMap": { },
+ "fieldToTypeMap": { },
+ "triageConfig" : {
+ "riskLevelRules" : [
+ {
+ "rule" : "parser_score > 3.5",
+ "score" : 10
+ }
+ ],
+ "aggregator" : "MAX"
+ }
+ }
+}
+</pre></div></div>
+<p>We also need an indexing configuration. Create the following in <tt>$METRON_HOME/config/zookeeper/indexing/mad.json</tt>:</p>
+
+<div class="source">
+<div class="source">
+<pre>{
+ "hdfs" : {
+ "index": "mad",
+ "batchSize": 1,
+ "enabled" : true
+ },
+ "elasticsearch" : {
+ "index": "mad",
+ "batchSize": 1,
+ "enabled" : true
+ }
+}
+</pre></div></div></div>
+<div class="section">
+<h4><a name="The_Profiler"></a>The Profiler</h4>
+<p>We can set up the profiler to track the MAD statistical state required to compute MAD. For the purposes of this demonstration, we will configure the profiler to capture statistics on the minute mark. We will capture a global statistical state for the <tt>value</tt> field and we will look back for a 5 minute window when computing the median.</p>
+<p>Create the following file at <tt>$METRON_HOME/config/zookeeper/profiler.json</tt>:</p>
+
+<div class="source">
+<div class="source">
+<pre>{
+ "profiles": [
+ {
+ "profile": "sketchy_mad",
+ "foreach": "'global'",
+ "onlyif": "true",
+ "init" : {
+ "s": "OUTLIER_MAD_STATE_MERGE(PROFILE_GET('sketchy_mad',
+'global', PROFILE_FIXED(5, 'MINUTES')))"
+ },
+ "update": {
+ "s": "OUTLIER_MAD_ADD(s, value)"
+ },
+ "result": "s"
+ }
+ ]
+}
+</pre></div></div>
+<p>Adjust <tt>$METRON_HOME/config/zookeeper/global.json</tt> to adjust the capture duration:</p>
+
+<div class="source">
+<div class="source">
+<pre> "profiler.client.period.duration" : "1",
+ "profiler.client.period.duration.units" : "MINUTES"
+</pre></div></div>
+<p>Adjust <tt>$METRON_HOME/config/profiler.properties</tt> to adjust the capture duration by changing <tt>profiler.period.duration=15</tt> to <tt>profiler.period.duration=1</tt></p></div>
+<div class="section">
+<h4><a name="Execute_the_Flow"></a>Execute the Flow</h4>
+
+<ol style="list-style-type: decimal">
+
+<li>
+<p>Install the elasticsearch head plugin by executing: <tt>/usr/share/elasticsearch/bin/plugin install mobz/elasticsearch-head</tt></p></li>
+
+<li>
+<p>Stopping all other parser topologies via monit</p></li>
+
+<li>
+<p>Create the <tt>mad</tt> kafka topic by executing: <tt>/usr/hdp/current/kafka-broker/bin/kafka-topics.sh --zookeeper node1:2181 --create --topic mad --partitions 1 --replication-factor 1</tt></p></li>
+
+<li>
+<p>Push the modified configs by executing: <tt>$METRON_HOME/bin/zk_load_configs.sh --mode PUSH -z node1:2181 -i $METRON_HOME/config/zookeeper/</tt></p></li>
+
+<li>
+<p>Start the profiler by executing: <tt>$METRON_HOME/bin/start_profiler_topology.sh</tt></p></li>
+
+<li>
+<p>Start the parser topology by executing: <tt>$METRON_HOME/bin/start_parser_topology.sh -k node1:6667 -z node1:2181 -s mad</tt></p></li>
+
+<li>
+<p>Ensure that the enrichment and indexing topologies are started. If not, then start those via monit or by hand.</p></li>
+
+<li>
+<p>Generate data into kafka by executing the following for at least 10 minutes: <tt>~/rand_gen.py 0 1 1 | /usr/hdp/current/kafka-broker/bin/kafka-console-producer.sh --broker-list node1:6667 --topic mad</tt> Note: if you chose the use the t-distribution script above, you would adjust the parameters of the <tt>rand_gen.py</tt> script accordingly.</p></li>
+
+<li>
+<p>Stop the above with ctrl-c and send in an obvious outlier into kafka: <tt>echo "1000" | /usr/hdp/current/kafka-broker/bin/kafka-console-producer.sh --broker-list node1:6667 --topic mad</tt></p></li>
+</ol>
+<p>You should be able to find the outlier via the elasticsearch head plugin by searching for the messages where <tt>is_alert</tt> is <tt>true</tt>.</p></div></div></div>
+ </div>
+ </div>
+ </div>
+
+ <hr/>
+
+ <footer>
+ <div class="container-fluid">
+ <div class="row span12">Copyright © 2017
+ <a href="https://www.apache.org">The Apache Software Foundation</a>.
+ All Rights Reserved.
+
+ </div>
+
+
+
+ </div>
+ </footer>
+ </body>
+</html>
Added: dev/metron/0.4.2-RC2/site-book/metron-contrib/metron-docker/index.html
==============================================================================
--- dev/metron/0.4.2-RC2/site-book/metron-contrib/metron-docker/index.html (added)
+++ dev/metron/0.4.2-RC2/site-book/metron-contrib/metron-docker/index.html Tue Dec 19 10:59:31 2017
@@ -0,0 +1,516 @@
+<!DOCTYPE html>
+<!--
+ | Generated by Apache Maven Doxia at 2017-12-08
+ | Rendered using Apache Maven Fluido Skin 1.3.0
+-->
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+ <meta charset="UTF-8" />
+ <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+ <meta name="Date-Revision-yyyymmdd" content="20171208" />
+ <meta http-equiv="Content-Language" content="en" />
+ <title>Metron – Metron Docker</title>
+ <link rel="stylesheet" href="../../css/apache-maven-fluido-1.3.0.min.css" />
+ <link rel="stylesheet" href="../../css/site.css" />
+ <link rel="stylesheet" href="../../css/print.css" media="print" />
+
+
+ <script type="text/javascript" src="../../js/apache-maven-fluido-1.3.0.min.js"></script>
+
+
+
+<script type="text/javascript">$( document ).ready( function() { $( '.carousel' ).carousel( { interval: 3500 } ) } );</script>
+
+ </head>
+ <body class="topBarDisabled">
+
+
+
+
+ <div class="container-fluid">
+ <div id="banner">
+ <div class="pull-left">
+ <a href="http://metron.apache.org/" id="bannerLeft">
+ <img src="../../images/metron-logo.png" alt="Apache Metron" width="148px" height="48px"/>
+ </a>
+ </div>
+ <div class="pull-right"> </div>
+ <div class="clear"><hr/></div>
+ </div>
+
+ <div id="breadcrumbs">
+ <ul class="breadcrumb">
+
+
+ <li class="">
+ <a href="http://www.apache.org" class="externalLink" title="Apache">
+ Apache</a>
+ </li>
+ <li class="divider ">/</li>
+ <li class="">
+ <a href="http://metron.apache.org/" class="externalLink" title="Metron">
+ Metron</a>
+ </li>
+ <li class="divider ">/</li>
+ <li class="">
+ <a href="../../index.html" title="Documentation">
+ Documentation</a>
+ </li>
+ <li class="divider ">/</li>
+ <li class="">Metron Docker</li>
+
+
+
+ <li id="publishDate" class="pull-right">Last Published: 2017-12-08</li> <li class="divider pull-right">|</li>
+ <li id="projectVersion" class="pull-right">Version: 0.4.2</li>
+
+ </ul>
+ </div>
+
+
+ <div class="row-fluid">
+ <div id="leftColumn" class="span3">
+ <div class="well sidebar-nav">
+
+
+ <ul class="nav nav-list">
+ <li class="nav-header">User Documentation</li>
+
+ <li>
+
+ <a href="../../index.html" title="Metron">
+ <i class="icon-chevron-down"></i>
+ Metron</a>
+ <ul class="nav nav-list">
+
+ <li>
+
+ <a href="../../Upgrading.html" title="Upgrading">
+ <i class="none"></i>
+ Upgrading</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-analytics/index.html" title="Analytics">
+ <i class="icon-chevron-right"></i>
+ Analytics</a>
+ </li>
+
+ <li class="active">
+
+ <a href="#"><i class="none"></i>Docker</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-deployment/index.html" title="Deployment">
+ <i class="icon-chevron-right"></i>
+ Deployment</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-interface/metron-alerts/index.html" title="Alerts">
+ <i class="none"></i>
+ Alerts</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-interface/metron-config/index.html" title="Config">
+ <i class="none"></i>
+ Config</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-interface/metron-rest/index.html" title="Rest">
+ <i class="none"></i>
+ Rest</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-platform/index.html" title="Platform">
+ <i class="icon-chevron-right"></i>
+ Platform</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-sensors/index.html" title="Sensors">
+ <i class="icon-chevron-right"></i>
+ Sensors</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-stellar/stellar-3rd-party-example/index.html" title="Stellar-3rd-party-example">
+ <i class="none"></i>
+ Stellar-3rd-party-example</a>
+ </li>
+
+ <li>
+
+ <a href="../../metron-stellar/stellar-common/index.html" title="Stellar-common">
+ <i class="icon-chevron-right"></i>
+ Stellar-common</a>
+ </li>
+
+ <li>
+
+ <a href="../../use-cases/index.html" title="Use-cases">
+ <i class="icon-chevron-right"></i>
+ Use-cases</a>
+ </li>
+ </ul>
+ </li>
+ </ul>
+
+
+
+ <hr class="divider" />
+
+ <div id="poweredBy">
+ <div class="clear"></div>
+ <div class="clear"></div>
+ <div class="clear"></div>
+ <a href="http://maven.apache.org/" title="Built by Maven" class="poweredBy">
+ <img class="builtBy" alt="Built by Maven" src="../../images/logos/maven-feather.png" />
+ </a>
+ </div>
+ </div>
+ </div>
+
+
+ <div id="bodyColumn" class="span9" >
+
+ <h1>Metron Docker</h1>
+<p><a name="Metron_Docker"></a></p>
+<p>Metron Docker is a <a class="externalLink" href="https://docs.docker.com/compose/overview/">Docker Compose</a> application that is intended only for development and integration testing of Metron. These images can quickly spin-up the underlying components on which Apache Metron runs.</p>
+<p>None of the core Metron components are setup or launched automatically with these Docker images. You will need to manually setup and start the Metron components that you require. You should not expect to see telemetry being parsed, enriched, or indexed. If you are looking to try-out, experiment or demo Metron capabilities on a single node, then the <a href="../../metron-deployment/vagrant/full-dev-platform/index.html">Vagrant-driven VM</a> is what you need. Use this instead of Vagrant when:</p>
+
+<ul>
+
+<li>You want an environment that can be built and spun up quickly</li>
+
+<li>You need to frequently rebuild and restart services</li>
+
+<li>You only need to test, troubleshoot or develop against a subset of services</li>
+</ul>
+<p>Metron Docker includes these images that have been customized for Metron:</p>
+
+<ul>
+
+<li>Kafka (with Zookeeper)</li>
+
+<li>HBase</li>
+
+<li>Storm</li>
+
+<li>Elasticsearch</li>
+
+<li>Kibana</li>
+
+<li>HDFS</li>
+</ul>
+<div class="section">
+<h2><a name="Setup"></a>Setup</h2>
+<p>Install <a class="externalLink" href="https://docs.docker.com/docker-for-mac/">Docker for Mac</a> or <a class="externalLink" href="https://docs.docker.com/docker-for-windows/">Docker for Windows</a>. The following versions have been tested:</p>
+
+<ul>
+
+<li>Docker version 1.12.0</li>
+
+<li>docker-machine version 0.8.0</li>
+
+<li>docker-compose version 1.8.0</li>
+</ul>
+<p>Build Metron from the top level directory with:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ cd $METRON_HOME
+$ mvn clean install -DskipTests
+</pre></div></div>
+<p>You are welcome to use an existing Docker host but we prefer one with more resources. You can create one of those with this script:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ export METRON_DOCKER_HOME=$METRON_HOME/metron-contrib/metron-docker
+$ cd $METRON_DOCKER_HOME
+$ ./scripts/create-docker-machine.sh
+</pre></div></div>
+<p>This will create a host called “metron-machine”. Anytime you want to run Docker commands against this host, make sure you run this first to set the Docker environment variables:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ eval "$(docker-machine env metron-machine)"
+</pre></div></div>
+<p>If you wish to use a local docker-engine install, please set an environment variable BROKER_IP_ADDR to the IP address of your host machine. This cannot be the loopback address.</p></div>
+<div class="section">
+<h2><a name="Usage"></a>Usage</h2>
+<p>Navigate to the compose application root:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ cd $METRON_DOCKER_HOME/compose/
+</pre></div></div>
+<p>The Metron Docker environment lifecycle is controlled by the <a class="externalLink" href="https://docs.docker.com/compose/reference/overview/">docker-compose</a> command. The service names can be found in the docker-compose.yml file. For example, to build and start the environment run this command:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ eval "$(docker-machine env metron-machine)"
+$ docker-compose up -d
+</pre></div></div>
+<p>After all services have started list the containers and ensure their status is ‘Up’:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ docker ps --format 'table {{.Names}}\t{{.Status}}'
+NAMES STATUS
+metron_storm_1 Up 5 minutes
+metron_hbase_1 Up 5 minutes
+metron_kibana_1 Up 5 minutes
+metron_kafkazk_1 Up 5 minutes
+metron_elasticsearch_1 Up 5 minutes
+</pre></div></div>
+<p>Various services are exposed through http on the Docker host. Get the host ip from the URL property:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ docker-machine ls
+NAME ACTIVE DRIVER STATE URL SWARM DOCKER ERRORS
+metron-machine * virtualbox Running tcp://192.168.99.100:2376 v1.12.5
+</pre></div></div>
+<p>Then, assuming a host ip of <tt>192.168.99.100</tt>, the UIs and APIs are available at:</p>
+
+<ul>
+
+<li>Storm - <a class="externalLink" href="http://192.168.99.100:8080/">http://192.168.99.100:8080/</a></li>
+
+<li>HBase - <a class="externalLink" href="http://192.168.99.100:16010/">http://192.168.99.100:16010/</a></li>
+
+<li>Elasticsearch - <a class="externalLink" href="http://192.168.99.100:9200/_plugin/head/">http://192.168.99.100:9200/_plugin/head/</a></li>
+
+<li>Kibana - <a class="externalLink" href="http://192.168.99.100:5601/">http://192.168.99.100:5601/</a></li>
+
+<li>HDFS (Namenode) - <a class="externalLink" href="http://192.168.99.100:50070/">http://192.168.99.100:50070/</a></li>
+</ul>
+<p>The Storm logs can be useful when troubleshooting topologies. They can be found on the Storm container in <tt>/usr/share/apache-storm/logs</tt>.</p>
+<p>When done using the machine, shut it down with:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ docker-compose down
+</pre></div></div></div>
+<div class="section">
+<h2><a name="Examples"></a>Examples</h2>
+
+<ul>
+
+<li><a href="#Deploy_a_new_parser_class">Deploy a new parser class</a></li>
+
+<li><a href="#Connect_to_a_container">Connect to a container</a></li>
+
+<li><a href="create-a-sensor-from-sample-data/index.html">Create a sensor from sample data</a></li>
+
+<li><a href="upload-configs-to-zookeeper/index.html">Upload configs to Zookeeper</a></li>
+
+<li><a href="manage-a-topology/index.html">Manage a topology</a></li>
+
+<li><a href="run-sensor-data-end-to-end/index.html">Run sensor data end to end</a></li>
+</ul>
+<div class="section">
+<h3><a name="Deploy_a_new_parser_class"></a>Deploy a new parser class</h3>
+<p>After adding a new parser to metron-parsers, build Metron from the top level directory:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ cd $METRON_HOME
+$ mvn clean install -DskipTests
+</pre></div></div>
+<p>Then run these commands to redeploy the parsers to the Storm image:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ cd $METRON_DOCKER_HOME/compose
+$ docker-compose down
+$ docker-compose build storm
+$ docker-compose up -d
+</pre></div></div></div>
+<div class="section">
+<h3><a name="Connect_to_a_container"></a>Connect to a container</h3>
+<p>Suppose there is a problem with Kafka and the logs are needed for further investigation. Run this command to connect and explore the running Kafka container:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ cd $METRON_DOCKER_HOME/compose
+$ docker-compose exec kafkazk bash
+</pre></div></div></div>
+<div class="section">
+<h3><a name="Create_a_sensor_from_sample_data"></a>Create a sensor from sample data</h3>
+<p>A tool for producing test data in Kafka is included with the Kafka/Zookeeper image. It loops through lines in a test data file and outputs them to Kafka at the desired frequency. Create a test data file in <tt>./kafkazk/data/</tt> and rebuild the Kafka/Zookeeper image:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ cd $METRON_DOCKER_HOME/compose
+$ printf 'first test data\nsecond test data\nthird test data\n' > ./kafkazk/data/TestData.txt
+$ docker-compose down
+$ docker-compose build kafkazk
+$ docker-compose up -d
+</pre></div></div>
+<p>This will deploy the test data file to the Kafka/Zookeeper container. Now that data can be streamed to a Kafka topic:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ docker-compose exec kafkazk ./bin/produce-data.sh
+Usage: produce-data.sh data_path topic [message_delay_in_seconds]
+
+# Stream data in TestData.txt to the 'test' Kafka topic at a frequency of 5 seconds (default is 1 second)
+$ docker-compose exec kafkazk ./bin/produce-data.sh /data/TestData.txt test 5
+</pre></div></div>
+<p>The Kafka/Zookeeper image comes with sample Bro and Squid data:</p>
+
+<div class="source">
+<div class="source">
+<pre># Stream Bro test data every 1 second
+$ docker-compose exec kafkazk ./bin/produce-data.sh /data/BroExampleOutput.txt bro
+
+# Stream Squid test data every 0.1 seconds
+$ docker-compose exec kafkazk ./bin/produce-data.sh /data/SquidExampleOutput.txt squid 0.1
+</pre></div></div></div>
+<div class="section">
+<h3><a name="Upload_configs_to_Zookeeper"></a>Upload configs to Zookeeper</h3>
+<p>Parser configs and a global config configured for this Docker environment are included with the Kafka/Zookeeper image. Load them with:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ docker-compose exec kafkazk bash
+# $METRON_HOME/bin/zk_load_configs.sh -z localhost:2181 -m PUSH -i $METRON_HOME/config/zookeeper
+# exit
+</pre></div></div>
+<p>Dump out the configs with:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ docker-compose exec kafkazk bash
+# $METRON_HOME/bin/zk_load_configs.sh -z localhost:2181 -m DUMP
+# exit
+</pre></div></div></div>
+<div class="section">
+<h3><a name="Manage_a_topology"></a>Manage a topology</h3>
+<p>The Storm image comes with a script to easily start parser topologies:</p>
+
+<div class="source">
+<div class="source">
+<pre>docker-compose exec storm ./bin/start_docker_parser_topology.sh sensor_name
+</pre></div></div>
+<p>The enrichment topology can be started with:</p>
+
+<div class="source">
+<div class="source">
+<pre>docker-compose exec storm ./bin/start_enrichment_topology.sh
+</pre></div></div>
+<p>The indexing topology can be started with:</p>
+
+<div class="source">
+<div class="source">
+<pre>docker-compose exec storm ./bin/start_elasticsearch_topology.sh
+</pre></div></div>
+<p>Topologies can be stopped using the Storm CLI. For example, stop the enrichment topology with:</p>
+
+<div class="source">
+<div class="source">
+<pre>docker-compose exec storm storm kill enrichments -w 0
+</pre></div></div></div>
+<div class="section">
+<h3><a name="Run_sensor_data_end_to_end"></a>Run sensor data end to end</h3>
+<p>First ensure configs were uploaded as described in the previous example. Then start a sensor and leave it running:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ cd $METRON_DOCKER_HOME/compose
+$ docker-compose exec kafkazk ./bin/produce-data.sh /data/BroExampleOutput.txt bro
+</pre></div></div>
+<p>Open a separate console session and verify the sensor is running by consuming a message from Kafka:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ export METRON_DOCKER_HOME=$METRON_HOME/metron-contrib/metron-docker
+$ cd $METRON_DOCKER_HOME/compose
+$ docker-compose exec kafkazk ./bin/kafka-console-consumer.sh --zookeeper localhost:2181 --topic bro
+</pre></div></div>
+<p>A new message should be printed every second. Now kill the consumer and start the Bro parser topology:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ docker-compose exec storm ./bin/start_docker_parser_topology.sh bro
+</pre></div></div>
+<p>Bro data should be flowing through the bro parser topology and into the Kafka enrichments topic. The enrichments topic should be created automatically:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ docker-compose exec kafkazk ./bin/kafka-topics.sh --zookeeper localhost:2181 --list
+bro
+enrichments
+indexing
+</pre></div></div>
+<p>Verify parsed Bro data is in the Kafka enrichments topic:</p>
+
+<div class="source">
+<div class="source">
+<pre>docker-compose exec kafkazk ./bin/kafka-console-consumer.sh --zookeeper localhost:2181 --topic enrichments
+</pre></div></div>
+<p>Now start the enrichment topology:</p>
+
+<div class="source">
+<div class="source">
+<pre>docker-compose exec storm ./bin/start_enrichment_topology.sh
+</pre></div></div>
+<p>Parsed Bro data should be flowing through the enrichment topology and into the Kafka indexing topic. Verify enriched Bro data is in the Kafka indexing topic:</p>
+
+<div class="source">
+<div class="source">
+<pre>docker-compose exec kafkazk ./bin/kafka-console-consumer.sh --zookeeper localhost:2181 --topic indexing
+</pre></div></div>
+<p>Now start the indexing topology:</p>
+
+<div class="source">
+<div class="source">
+<pre>docker-compose exec storm ./bin/start_elasticsearch_topology.sh
+</pre></div></div>
+<p>Enriched Bro data should now be present in the Elasticsearch container:</p>
+
+<div class="source">
+<div class="source">
+<pre>$ docker-machine ls
+NAME ACTIVE DRIVER STATE URL SWARM DOCKER ERRORS
+metron-machine * virtualbox Running tcp://192.168.99.100:2376 v1.12.5
+
+$ curl -XGET http://192.168.99.100:9200/_cat/indices?v
+health status index pri rep docs.count docs.deleted store.size pri.store.size
+yellow open .kibana 1 1 1 0 3.1kb 3.1kb
+yellow open bro_index_2016.12.19.18 5 1 180 0 475kb 475kb
+</pre></div></div></div></div>
+ </div>
+ </div>
+ </div>
+
+ <hr/>
+
+ <footer>
+ <div class="container-fluid">
+ <div class="row span12">Copyright © 2017
+ <a href="https://www.apache.org">The Apache Software Foundation</a>.
+ All Rights Reserved.
+
+ </div>
+
+
+
+ </div>
+ </footer>
+ </body>
+</html>
Added: dev/metron/0.4.2-RC2/site-book/metron-deployment/Kerberos-ambari-setup.html
==============================================================================
--- dev/metron/0.4.2-RC2/site-book/metron-deployment/Kerberos-ambari-setup.html (added)
+++ dev/metron/0.4.2-RC2/site-book/metron-deployment/Kerberos-ambari-setup.html Tue Dec 19 10:59:31 2017
@@ -0,0 +1,317 @@
+<!DOCTYPE html>
+<!--
+ | Generated by Apache Maven Doxia at 2017-12-08
+ | Rendered using Apache Maven Fluido Skin 1.3.0
+-->
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+ <meta charset="UTF-8" />
+ <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+ <meta name="Date-Revision-yyyymmdd" content="20171208" />
+ <meta http-equiv="Content-Language" content="en" />
+ <title>Metron – Setting Up Kerberos in Vagrant Full Dev</title>
+ <link rel="stylesheet" href="../css/apache-maven-fluido-1.3.0.min.css" />
+ <link rel="stylesheet" href="../css/site.css" />
+ <link rel="stylesheet" href="../css/print.css" media="print" />
+
+
+ <script type="text/javascript" src="../js/apache-maven-fluido-1.3.0.min.js"></script>
+
+
+
+<script type="text/javascript">$( document ).ready( function() { $( '.carousel' ).carousel( { interval: 3500 } ) } );</script>
+
+ </head>
+ <body class="topBarDisabled">
+
+
+
+
+ <div class="container-fluid">
+ <div id="banner">
+ <div class="pull-left">
+ <a href="http://metron.apache.org/" id="bannerLeft">
+ <img src="../images/metron-logo.png" alt="Apache Metron" width="148px" height="48px"/>
+ </a>
+ </div>
+ <div class="pull-right"> </div>
+ <div class="clear"><hr/></div>
+ </div>
+
+ <div id="breadcrumbs">
+ <ul class="breadcrumb">
+
+
+ <li class="">
+ <a href="http://www.apache.org" class="externalLink" title="Apache">
+ Apache</a>
+ </li>
+ <li class="divider ">/</li>
+ <li class="">
+ <a href="http://metron.apache.org/" class="externalLink" title="Metron">
+ Metron</a>
+ </li>
+ <li class="divider ">/</li>
+ <li class="">
+ <a href="../index.html" title="Documentation">
+ Documentation</a>
+ </li>
+ <li class="divider ">/</li>
+ <li class="">Setting Up Kerberos in Vagrant Full Dev</li>
+
+
+
+ <li id="publishDate" class="pull-right">Last Published: 2017-12-08</li> <li class="divider pull-right">|</li>
+ <li id="projectVersion" class="pull-right">Version: 0.4.2</li>
+
+ </ul>
+ </div>
+
+
+ <div class="row-fluid">
+ <div id="leftColumn" class="span3">
+ <div class="well sidebar-nav">
+
+
+ <ul class="nav nav-list">
+ <li class="nav-header">User Documentation</li>
+
+ <li>
+
+ <a href="../index.html" title="Metron">
+ <i class="icon-chevron-down"></i>
+ Metron</a>
+ <ul class="nav nav-list">
+
+ <li>
+
+ <a href="../Upgrading.html" title="Upgrading">
+ <i class="none"></i>
+ Upgrading</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-analytics/index.html" title="Analytics">
+ <i class="icon-chevron-right"></i>
+ Analytics</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-contrib/metron-docker/index.html" title="Docker">
+ <i class="none"></i>
+ Docker</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-deployment/index.html" title="Deployment">
+ <i class="icon-chevron-down"></i>
+ Deployment</a>
+ <ul class="nav nav-list">
+
+ <li class="active">
+
+ <a href="#"><i class="none"></i>Kerberos-ambari-setup</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-deployment/Kerberos-manual-setup.html" title="Kerberos-manual-setup">
+ <i class="none"></i>
+ Kerberos-manual-setup</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-deployment/amazon-ec2/index.html" title="Amazon-ec2">
+ <i class="none"></i>
+ Amazon-ec2</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-deployment/other-examples/index.html" title="Other-examples">
+ <i class="icon-chevron-right"></i>
+ Other-examples</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-deployment/packaging/ambari/index.html" title="Ambari">
+ <i class="none"></i>
+ Ambari</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-deployment/packaging/docker/ansible-docker/index.html" title="Ansible-docker">
+ <i class="none"></i>
+ Ansible-docker</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-deployment/packaging/docker/rpm-docker/index.html" title="Rpm-docker">
+ <i class="none"></i>
+ Rpm-docker</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-deployment/packaging/packer-build/index.html" title="Packer-build">
+ <i class="none"></i>
+ Packer-build</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-deployment/roles/index.html" title="Roles">
+ <i class="icon-chevron-right"></i>
+ Roles</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-deployment/vagrant/index.html" title="Vagrant">
+ <i class="icon-chevron-right"></i>
+ Vagrant</a>
+ </li>
+ </ul>
+ </li>
+
+ <li>
+
+ <a href="../metron-interface/metron-alerts/index.html" title="Alerts">
+ <i class="none"></i>
+ Alerts</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-interface/metron-config/index.html" title="Config">
+ <i class="none"></i>
+ Config</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-interface/metron-rest/index.html" title="Rest">
+ <i class="none"></i>
+ Rest</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-platform/index.html" title="Platform">
+ <i class="icon-chevron-right"></i>
+ Platform</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-sensors/index.html" title="Sensors">
+ <i class="icon-chevron-right"></i>
+ Sensors</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-stellar/stellar-3rd-party-example/index.html" title="Stellar-3rd-party-example">
+ <i class="none"></i>
+ Stellar-3rd-party-example</a>
+ </li>
+
+ <li>
+
+ <a href="../metron-stellar/stellar-common/index.html" title="Stellar-common">
+ <i class="icon-chevron-right"></i>
+ Stellar-common</a>
+ </li>
+
+ <li>
+
+ <a href="../use-cases/index.html" title="Use-cases">
+ <i class="icon-chevron-right"></i>
+ Use-cases</a>
+ </li>
+ </ul>
+ </li>
+ </ul>
+
+
+
+ <hr class="divider" />
+
+ <div id="poweredBy">
+ <div class="clear"></div>
+ <div class="clear"></div>
+ <div class="clear"></div>
+ <a href="http://maven.apache.org/" title="Built by Maven" class="poweredBy">
+ <img class="builtBy" alt="Built by Maven" src="../images/logos/maven-feather.png" />
+ </a>
+ </div>
+ </div>
+ </div>
+
+
+ <div id="bodyColumn" class="span9" >
+
+ <h1>Setting Up Kerberos in Vagrant Full Dev</h1>
+<p><a name="Setting_Up_Kerberos_in_Vagrant_Full_Dev"></a></p>
+<p><b>Note:</b> These are instructions for Kerberizing Metron Storm topologies from Kafka to Kafka. This does not cover the sensor connections or MAAS. General Kerberization notes can be found in the metron-deployment <a href="../index.html">README.md</a></p>
+<div class="section">
+<h2><a name="Setup_a_KDC"></a>Setup a KDC</h2>
+<p>See <a href="Kerberos-manual-setup.html#Setup_a_KDC">Setup a KDC</a> and <a href="Kerberos-manual-setup.html#Verify_KDC">Verify KDC</a></p></div>
+<div class="section">
+<h2><a name="Ambari_Setup"></a>Ambari Setup</h2>
+
+<ol style="list-style-type: decimal">
+
+<li>
+<p>Kerberize the cluster via Ambari. More detailed documentation can be found <a class="externalLink" href="http://docs.hortonworks.com/HDPDocuments/HDP2/HDP-2.5.3/bk_security/content/_enabling_kerberos_security_in_ambari.html">here</a>.</p>
+<p>a. For this exercise, choose existing MIT KDC (this is what we setup and installed in the previous steps.)</p>
+<p><img src="../images/enable-kerberos.png" alt="enable keberos" /></p>
+<p><img src="../images/enable-kerberos-started.png" alt="enable keberos get started" /></p>
+<p>b. Setup Kerberos configuration. Realm is EXAMPLE.COM. The admin principal will end up as admin/admin@EXAMPLE.COM when testing the KDC. Use the password you entered during the step for adding the admin principal.</p>
+<p><img src="../images/enable-kerberos-configure-kerberos.png" alt="enable keberos configure" /></p>
+<p>c. Click through to “Start and Test Services.” Let the cluster spin up.</p></li>
+</ol></div>
+<div class="section">
+<h2><a name="Push_Data"></a>Push Data</h2>
+
+<ol style="list-style-type: decimal">
+
+<li>
+<p>Kinit with the metron user</p>
+
+<div class="source">
+<div class="source">
+<pre>kinit -kt /etc/security/keytabs/metron.headless.keytab metron@EXAMPLE.COM
+</pre></div></div></li>
+</ol>
+<p>See <a href="Kerberos-manual-setup.html#Push_Data">Push Data</a></p>
+<div class="section">
+<h3><a name="More_Information"></a>More Information</h3>
+<p>See <a href="Kerberos-manual-setup.html#More_Information">More Information</a></p></div></div>
+ </div>
+ </div>
+ </div>
+
+ <hr/>
+
+ <footer>
+ <div class="container-fluid">
+ <div class="row span12">Copyright © 2017
+ <a href="https://www.apache.org">The Apache Software Foundation</a>.
+ All Rights Reserved.
+
+ </div>
+
+
+
+ </div>
+ </footer>
+ </body>
+</html>