616 lines
19 KiB
HTML
616 lines
19 KiB
HTML
<!doctype html>
|
||
<html lang="en">
|
||
<head>
|
||
<meta charset="utf-8">
|
||
<title>Druid for real-time analysis</title>
|
||
<meta name="description" content="Druid for real-time analysis">
|
||
<meta name="author" content="Yann Esposito" />
|
||
<meta name="apple-mobile-web-app-capable" content="yes" />
|
||
<meta name="apple-mobile-web-app-status-bar-style" content="black-translucent" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no">
|
||
<link rel="stylesheet" href="../.reveal.js-3.2.0/css/reveal.css">
|
||
<link rel="stylesheet" href="../.reveal.js-3.2.0/css/theme/solarized-dark.css" id="theme">
|
||
<!-- For syntax highlighting -->
|
||
<link rel="stylesheet" href="../.reveal.js-3.2.0/lib/css/solarized-dark.css">
|
||
<!-- If the query includes 'print-pdf', use the PDF print sheet -->
|
||
<script>
|
||
document.write( '<link rel="stylesheet" href="../.reveal.js-3.2.0/css/print/' +
|
||
( window.location.search.match( /print-pdf/gi ) ? 'pdf' : 'paper' ) +
|
||
'.css" type="text/css" media="print">' );
|
||
</script>
|
||
<!--[if lt IE 9]>
|
||
<script src="../.reveal.js-3.2.0/lib/js/html5shiv.js"></script>
|
||
<![endif]-->
|
||
</head>
|
||
<body>
|
||
|
||
<div class="reveal">
|
||
|
||
<!-- Any section element inside of this container is displayed as a slide -->
|
||
<div class="slides">
|
||
|
||
<section>
|
||
<h1>Druid for real-time analysis</h1>
|
||
<h3>Yann Esposito</h3>
|
||
<p>
|
||
<h4>7 Avril 2016</h4>
|
||
</p>
|
||
</section>
|
||
|
||
|
||
<section id="druid-the-sales-pitch" class="level1">
|
||
<h1>Druid the Sales Pitch</h1>
|
||
<ul>
|
||
<li>Sub-Second Queries</li>
|
||
<li>Real-time Streams</li>
|
||
<li>Scalable to Petabytes</li>
|
||
<li>Deploy Anywhere</li>
|
||
<li>Vibrant Community (Open Source)</li>
|
||
</ul>
|
||
<aside class="notes">
|
||
<ul>
|
||
<li>Ideal for powering user-facing analytic applications</li>
|
||
<li>Deploy anywhere: cloud, on-premise, integrate with Haddop, Spark, Kafka, Storm, Samza</li>
|
||
</ul>
|
||
</aside>
|
||
</section>
|
||
<section id="intro" class="level1">
|
||
<h1>Intro</h1>
|
||
<section id="experience" class="level2">
|
||
<h2>Experience</h2>
|
||
<ul>
|
||
<li>Real Time Social Media Analytics</li>
|
||
</ul>
|
||
</section>
|
||
<section id="real-time" class="level2">
|
||
<h2>Real Time?</h2>
|
||
<ul>
|
||
<li>Ingestion Latency: seconds</li>
|
||
<li>Query Latency: seconds</li>
|
||
</ul>
|
||
</section>
|
||
<section id="demand" class="level2">
|
||
<h2>Demand</h2>
|
||
<ul>
|
||
<li>Twitter: <code>20k msg/s</code>, <code>1msg = 10ko</code> during 24h</li>
|
||
<li>Facebook public: 1000 to 2000 msg/s continuously</li>
|
||
<li>Low Latency</li>
|
||
</ul>
|
||
</section>
|
||
<section id="reality" class="level2">
|
||
<h2>Reality</h2>
|
||
<ul>
|
||
<li>Twitter: 400 msg/s continuously, burst to 1500</li>
|
||
<li>Facebook: 1000 to 2000 msg/s</li>
|
||
</ul>
|
||
</section>
|
||
</section>
|
||
<section id="origin-php" class="level1">
|
||
<h1>Origin (PHP)</h1>
|
||
<p><img src="img/bad_php.jpg" alt="OH NOES PHP!" /> </p>
|
||
</section>
|
||
<section id="st-refactoring-node.js" class="level1">
|
||
<h1>1st Refactoring (Node.js)</h1>
|
||
<ul>
|
||
<li>Ingestion still in PHP</li>
|
||
<li>Node.js, Perl, Java & R for sentiment analysis</li>
|
||
<li>MongoDB</li>
|
||
<li>Manually made time series (Incremental Map/Reduce)</li>
|
||
<li>Manually coded HyperLogLog in js</li>
|
||
</ul>
|
||
</section>
|
||
<section id="return-of-experience" class="level1">
|
||
<h1>Return of Experience</h1>
|
||
<p><img src="img/MongoDB.png" alt="MongoDB the destroyer" /> </p>
|
||
</section>
|
||
<section id="return-of-experience-1" class="level1">
|
||
<h1>Return of Experience</h1>
|
||
<ul>
|
||
<li>Ingestion still in PHP (600 msg/s max)</li>
|
||
<li>Node.js, Perl, Java (10 msg/s max)</li>
|
||
</ul>
|
||
<figure>
|
||
<img src="img/bored.gif" alt="Too Slow, Bored" /><figcaption>Too Slow, Bored</figcaption>
|
||
</figure>
|
||
</section>
|
||
<section id="nd-refactoring" class="level1">
|
||
<h1>2nd Refactoring</h1>
|
||
<ul>
|
||
<li>Haskell</li>
|
||
<li>Clojure / Clojurescript</li>
|
||
<li>Kafka / Zookeeper</li>
|
||
<li>Mesos / Marathon</li>
|
||
<li>Elasticsearch</li>
|
||
<li><strong>Druid</strong></li>
|
||
</ul>
|
||
</section>
|
||
<section id="nd-refactoring-ftw" class="level1">
|
||
<h1>2nd Refactoring (FTW!)</h1>
|
||
<p><img src="img/talking.jpg" alt="Now we're talking" /> </p>
|
||
</section>
|
||
<section id="nd-refactoring-return-of-experience" class="level1">
|
||
<h1>2nd Refactoring return of experience</h1>
|
||
<ul>
|
||
<li>No limit, everything is scalable</li>
|
||
<li>High availability</li>
|
||
<li>Low latency: Ingestion & User faced querying</li>
|
||
<li>Cheap if done correctly</li>
|
||
</ul>
|
||
<p><strong>Thanks Druid!</strong></p>
|
||
</section>
|
||
<section id="demo" class="level1">
|
||
<h1>Demo</h1>
|
||
<ul>
|
||
<li>Low Latency High Volume of Data Analysis</li>
|
||
<li>Typically <code>pulse</code></li>
|
||
</ul>
|
||
<p><a href="http://pulse.vigiglo.be/#/vigiglobe/Earthquake/dashboard" target="_blank"> DEMO Time </a></p>
|
||
</section>
|
||
<section id="pre-considerations" class="level1">
|
||
<h1>Pre Considerations</h1>
|
||
<section id="discovered-vs-invented" class="level2">
|
||
<h2>Discovered vs Invented</h2>
|
||
<p>Try to conceptualize a s.t.</p>
|
||
<ul>
|
||
<li>Ingest Events</li>
|
||
<li>Real-Time Queries</li>
|
||
<li>Scalable</li>
|
||
<li>Highly Available</li>
|
||
</ul>
|
||
<p>Analytics: timeseries, alerting system, top N, etc...</p>
|
||
</section>
|
||
<section id="in-the-end" class="level2">
|
||
<h2>In the End</h2>
|
||
<p>Druid concepts are always emerging naturally</p>
|
||
</section>
|
||
</section>
|
||
<section id="druid" class="level1">
|
||
<h1>Druid</h1>
|
||
<section id="who" class="level2">
|
||
<h2>Who?</h2>
|
||
<p>Metamarkets</p>
|
||
<p><a href="http://druid.io/druid-powered.html"
|
||
target="_blank">Powered by Druid</a></p>
|
||
<ul>
|
||
<li>Alibaba, Cisco, Criteo, eBay, Hulu, Netflix, Paypal...</li>
|
||
</ul>
|
||
</section>
|
||
<section id="goal" class="level2">
|
||
<h2>Goal</h2>
|
||
<blockquote>
|
||
<p>Druid is an open source store designed for real-time exploratory analytics on large data sets.</p>
|
||
</blockquote>
|
||
<blockquote>
|
||
<p>hosted dashboard that would allow users to arbitrarily explore and visualize event streams.</p>
|
||
</blockquote>
|
||
</section>
|
||
<section id="concepts" class="level2">
|
||
<h2>Concepts</h2>
|
||
<ul>
|
||
<li>Column-oriented storage layout</li>
|
||
<li>distributed, shared-nothing architecture</li>
|
||
<li>advanced indexing structure</li>
|
||
</ul>
|
||
</section>
|
||
<section id="key-features" class="level2">
|
||
<h2>Key Features</h2>
|
||
<ul>
|
||
<li>Sub-second OLAP Queries</li>
|
||
<li>Real-time Streaming Ingestion</li>
|
||
<li>Power Analytic Applications</li>
|
||
<li>Cost Effective</li>
|
||
<li>High Available</li>
|
||
<li>Scalable</li>
|
||
</ul>
|
||
</section>
|
||
<section id="right-for-me" class="level2">
|
||
<h2>Right for me?</h2>
|
||
<ul>
|
||
<li>require fast aggregations</li>
|
||
<li>exploratory analytics</li>
|
||
<li>analysis in real-time</li>
|
||
<li>lots of data (trillions of events, petabytes of data)</li>
|
||
<li>no single point of failure</li>
|
||
</ul>
|
||
</section>
|
||
</section>
|
||
<section id="high-level-architecture" class="level1">
|
||
<h1>High Level Architecture</h1>
|
||
<section id="inspiration" class="level2">
|
||
<h2>Inspiration</h2>
|
||
<ul>
|
||
<li>Google's <a href="http://static.googleusercontent.com/media/research.google.com/en/us/pubs/archive/36632.pdf">BigQuery/Dremel</a></li>
|
||
<li>Google's <a href="http://vldb.org/pvldb/vol5/p1436_alexanderhall_vldb2012.pdf">PowerDrill</a></li>
|
||
</ul>
|
||
</section>
|
||
<section id="index-immutability" class="level2">
|
||
<h2>Index / Immutability</h2>
|
||
<p>Druid indexes data to create mostly immutable views.</p>
|
||
</section>
|
||
<section id="storage" class="level2">
|
||
<h2>Storage</h2>
|
||
<p>Store data in custom column format highly optimized for aggregation & filter.</p>
|
||
</section>
|
||
<section id="specialized-nodes" class="level2">
|
||
<h2>Specialized Nodes</h2>
|
||
<ul>
|
||
<li>A Druid cluster is composed of various type of nodes</li>
|
||
<li>Each designed to do a small set of things very well</li>
|
||
<li>Nodes don't need to be deployed on individual hardware</li>
|
||
<li>Many node types can be colocated in production</li>
|
||
</ul>
|
||
</section>
|
||
</section>
|
||
<section id="druid-vs-x" class="level1">
|
||
<h1>Druid vs X</h1>
|
||
<section id="elasticsearch" class="level2">
|
||
<h2>Elasticsearch</h2>
|
||
<ul>
|
||
<li>resource requirement much higher for ingestion & aggregation</li>
|
||
<li>No data summarization (100x in real world data)</li>
|
||
</ul>
|
||
</section>
|
||
<section id="keyvalue-stores-hbasecassandraopentsdb" class="level2">
|
||
<h2>Key/Value Stores (HBase/Cassandra/OpenTSDB)</h2>
|
||
<ul>
|
||
<li>Must Pre-compute Result
|
||
<ul>
|
||
<li>Exponential storage</li>
|
||
<li>Hours of pre-processing time</li>
|
||
</ul></li>
|
||
<li>Use the dimensions as key (like in OpenTSDB)
|
||
<ul>
|
||
<li>No filter index other than range</li>
|
||
<li>Hard for complex predicates</li>
|
||
</ul></li>
|
||
</ul>
|
||
</section>
|
||
<section id="spark" class="level2">
|
||
<h2>Spark</h2>
|
||
<ul>
|
||
<li>Druid can be used to accelerate OLAP queries in Spark</li>
|
||
<li>Druid focuses on the latencies to ingest and serve queries</li>
|
||
<li>Too long for end user to arbitrarily explore data</li>
|
||
</ul>
|
||
</section>
|
||
<section id="sql-on-hadoop-impaladrillspark-sqlpresto" class="level2">
|
||
<h2>SQL-on-Hadoop (Impala/Drill/Spark SQL/Presto)</h2>
|
||
<ul>
|
||
<li>Queries: more data transfer between nodes</li>
|
||
<li>Data Ingestion: bottleneck by backing store</li>
|
||
<li>Query Flexibility: more flexible (full joins)</li>
|
||
</ul>
|
||
</section>
|
||
</section>
|
||
<section id="data" class="level1">
|
||
<h1>Data</h1>
|
||
<section id="concepts-1" class="level2">
|
||
<h2>Concepts</h2>
|
||
<ul>
|
||
<li><strong>Timestamp column</strong>: query centered on time axis</li>
|
||
<li><strong>Dimension columns</strong>: strings (used to filter or to group)</li>
|
||
<li><strong>Metric columns</strong>: used for aggregations (count, sum, mean, etc...)</li>
|
||
</ul>
|
||
</section>
|
||
<section id="indexing" class="level2">
|
||
<h2>Indexing</h2>
|
||
<ul>
|
||
<li>Immutable snapshots of data</li>
|
||
<li>data structure highly optimized for analytic queries</li>
|
||
<li>Each column is stored separately</li>
|
||
<li>Indexes data on a per shard (segment) level</li>
|
||
</ul>
|
||
</section>
|
||
<section id="loading" class="level2">
|
||
<h2>Loading</h2>
|
||
<ul>
|
||
<li>Real-Time</li>
|
||
<li>Batch</li>
|
||
</ul>
|
||
</section>
|
||
<section id="querying" class="level2">
|
||
<h2>Querying</h2>
|
||
<ul>
|
||
<li>JSON over HTTP</li>
|
||
<li>Single Table Operations, no joins.</li>
|
||
</ul>
|
||
</section>
|
||
<section id="segments" class="level2">
|
||
<h2>Segments</h2>
|
||
<ul>
|
||
<li>Per time interval
|
||
<ul>
|
||
<li>skip segments when querying</li>
|
||
</ul></li>
|
||
<li>Immutable
|
||
<ul>
|
||
<li>Cache friendly</li>
|
||
<li>No locking</li>
|
||
</ul></li>
|
||
<li>Versioned
|
||
<ul>
|
||
<li>No locking</li>
|
||
<li>Read-write concurrency</li>
|
||
</ul></li>
|
||
</ul>
|
||
</section>
|
||
</section>
|
||
<section id="roll-up" class="level1">
|
||
<h1>Roll-up</h1>
|
||
<section id="example" class="level2">
|
||
<h2>Example</h2>
|
||
<pre><code>timestamp page ... added deleted
|
||
2011-01-01T00:01:35Z Cthulhu 10 65
|
||
2011-01-01T00:03:63Z Cthulhu 15 62
|
||
2011-01-01T01:04:51Z Cthulhu 32 45
|
||
2011-01-01T01:01:00Z Azatoth 17 87
|
||
2011-01-01T01:02:00Z Azatoth 43 99
|
||
2011-01-01T02:03:00Z Azatoth 12 53</code></pre>
|
||
<pre><code>timestamp page ... nb added deleted
|
||
2011-01-01T00:00:00Z Cthulhu 2 25 127
|
||
2011-01-01T01:00:00Z Cthulhu 1 32 45
|
||
2011-01-01T01:00:00Z Azatoth 2 60 186
|
||
2011-01-01T02:00:00Z Azatoth 1 12 53</code></pre>
|
||
</section>
|
||
<section id="as-sql" class="level2">
|
||
<h2>as SQL</h2>
|
||
<pre><code>GROUP BY timestamp, page, nb, added, deleted
|
||
:: nb = COUNT(1)
|
||
, added = SUM(added)
|
||
, deleted = SUM(deleted)</code></pre>
|
||
<p>In practice can dramatically reduce the size (up to x100)</p>
|
||
</section>
|
||
</section>
|
||
<section id="segments-1" class="level1">
|
||
<h1>Segments</h1>
|
||
<section id="sharding" class="level2">
|
||
<h2>Sharding</h2>
|
||
<p><small><code>sampleData_2011-01-01T01:00:00:00Z_2011-01-01T02:00:00:00Z_v1_0</code></small></p>
|
||
<pre><code>timestamp page ... nb added deleted
|
||
2011-01-01T01:00:00Z Cthulhu 1 20 45
|
||
2011-01-01T01:00:00Z Azatoth 1 30 106</code></pre>
|
||
<p><small><code>sampleData_2011-01-01T01:00:00:00Z_2011-01-01T02:00:00:00Z_v1_0</code></small></p>
|
||
<pre><code>timestamp page ... nb added deleted
|
||
2011-01-01T01:00:00Z Cthulhu 1 12 45
|
||
2011-01-01T01:00:00Z Azatoth 2 30 80</code></pre>
|
||
</section>
|
||
<section id="core-data-structure" class="level2">
|
||
<h2>Core Data Structure</h2>
|
||
<p><img src="img/druid-column-types.png" alt="Segment" /> </p>
|
||
<ul>
|
||
<li>dictionary</li>
|
||
<li>a bitmap for each value</li>
|
||
<li>a list of the columns values encoded using the dictionary</li>
|
||
</ul>
|
||
</section>
|
||
<section id="example-1" class="level2">
|
||
<h2>Example</h2>
|
||
<pre><code>dictionary: { "Cthulhu": 0
|
||
, "Azatoth": 1 }
|
||
|
||
column data: [0, 0, 1, 1]
|
||
|
||
bitmaps (one for each value of the column):
|
||
value="Cthulhu": [1,1,0,0]
|
||
value="Azatoth": [0,0,1,1]</code></pre>
|
||
</section>
|
||
<section id="example-multiple-matches" class="level2">
|
||
<h2>Example (multiple matches)</h2>
|
||
<pre><code>dictionary: { "Cthulhu": 0
|
||
, "Azatoth": 1 }
|
||
|
||
column data: [0, [0,1], 1, 1]
|
||
|
||
bitmaps (one for each value of the column):
|
||
value="Cthulhu": [1,1,0,0]
|
||
value="Azatoth": [0,1,1,1]</code></pre>
|
||
</section>
|
||
<section id="real-time-ingestion" class="level2">
|
||
<h2>Real-time ingestion</h2>
|
||
<ul>
|
||
<li>Via Real-Time Node and Firehose
|
||
<ul>
|
||
<li>No redundancy or HA, thus not recommended</li>
|
||
</ul></li>
|
||
<li>Via Indexing Service and Tranquility API
|
||
<ul>
|
||
<li>Core API</li>
|
||
<li>Integration with Streaming Frameworks</li>
|
||
<li>HTTP Server</li>
|
||
<li><strong>Kafka Consumer</strong></li>
|
||
</ul></li>
|
||
</ul>
|
||
</section>
|
||
<section id="batch-ingestion" class="level2">
|
||
<h2>Batch Ingestion</h2>
|
||
<ul>
|
||
<li>File based (HDFS, S3, ...)</li>
|
||
</ul>
|
||
</section>
|
||
<section id="real-time-ingestion-1" class="level2">
|
||
<h2>Real-time Ingestion</h2>
|
||
<pre><code>Task 1: [ Interval ][ Window ]
|
||
Task 2: [ ]
|
||
----------------------------------------------------->
|
||
time</code></pre>
|
||
</section>
|
||
</section>
|
||
<section id="querying-1" class="level1">
|
||
<h1>Querying</h1>
|
||
<section id="query-types" class="level2">
|
||
<h2>Query types</h2>
|
||
<ul>
|
||
<li>Group by: group by multiple dimensions</li>
|
||
<li>Top N: like grouping by a single dimension</li>
|
||
<li>Timeseries: without grouping over dimensions</li>
|
||
<li>Search: Dimensions lookup</li>
|
||
<li>Time Boundary: Find available data timeframe</li>
|
||
<li>Metadata queries</li>
|
||
</ul>
|
||
</section>
|
||
<section id="examples" class="level2">
|
||
<h2>Example(s)</h2>
|
||
<pre><code>{"queryType": "groupBy",
|
||
"dataSource": "druidtest",
|
||
"granularity": "all",
|
||
"dimensions": [],
|
||
"aggregations": [
|
||
{"type": "count", "name": "rows"},
|
||
{"type": "longSum", "name": "imps", "fieldName": "impressions"},
|
||
{"type": "doubleSum", "name": "wp", "fieldName": "wp"}
|
||
],
|
||
"intervals": ["2010-01-01T00:00/2020-01-01T00"]}</code></pre>
|
||
</section>
|
||
<section id="result" class="level2">
|
||
<h2>Result</h2>
|
||
<pre><code>[ {
|
||
"version" : "v1",
|
||
"timestamp" : "2010-01-01T00:00:00.000Z",
|
||
"event" : {
|
||
"imps" : 5,
|
||
"wp" : 15000.0,
|
||
"rows" : 5
|
||
}
|
||
} ]</code></pre>
|
||
</section>
|
||
<section id="caching" class="level2">
|
||
<h2>Caching</h2>
|
||
<ul>
|
||
<li>Historical node level
|
||
<ul>
|
||
<li>By segment</li>
|
||
</ul></li>
|
||
<li>Broker Level
|
||
<ul>
|
||
<li>By segment and query</li>
|
||
<li><code>groupBy</code> is disabled on purpose!</li>
|
||
</ul></li>
|
||
<li>By default: local caching</li>
|
||
</ul>
|
||
</section>
|
||
</section>
|
||
<section id="druid-components" class="level1">
|
||
<h1>Druid Components</h1>
|
||
<section id="druid-1" class="level2">
|
||
<h2>Druid</h2>
|
||
<ul>
|
||
<li>Real-time Nodes</li>
|
||
<li>Historical Nodes</li>
|
||
<li>Broker Nodes</li>
|
||
<li>Coordinator</li>
|
||
<li>For indexing:
|
||
<ul>
|
||
<li>Overlord</li>
|
||
<li>Middle Manager</li>
|
||
</ul></li>
|
||
</ul>
|
||
</section>
|
||
<section id="also" class="level2">
|
||
<h2>Also</h2>
|
||
<ul>
|
||
<li>Deep Storage (S3, HDFS, ...)</li>
|
||
<li>Metadata Storage (SQL)</li>
|
||
<li>Load Balancer</li>
|
||
<li>Cache</li>
|
||
</ul>
|
||
</section>
|
||
<section id="coordinator" class="level2">
|
||
<h2>Coordinator</h2>
|
||
<ul>
|
||
<li>Real-time Nodes (pull data, index it)</li>
|
||
<li>Historical Nodes (keep old segments)</li>
|
||
<li>Broker Nodes (route queries to RT & Hist. nodes, merge)</li>
|
||
<li>Coordinator (manage segemnts)</li>
|
||
<li>For indexing:
|
||
<ul>
|
||
<li>Overlord (distribute task to the middle manager)</li>
|
||
<li>Middle Manager (execute tasks via Peons)</li>
|
||
</ul></li>
|
||
</ul>
|
||
</section>
|
||
</section>
|
||
<section id="when-not-to-choose-druid" class="level1">
|
||
<h1>When <em>not</em> to choose Druid</h1>
|
||
<ul>
|
||
<li>Data is not time-series</li>
|
||
<li>Cardinality is <em>very</em> high</li>
|
||
<li>Number of dimensions is high</li>
|
||
<li>Setup cost must be avoided</li>
|
||
</ul>
|
||
</section>
|
||
<section id="graphite-metrics" class="level1">
|
||
<h1>Graphite (metrics)</h1>
|
||
<p><img src="img/graphite.png" alt="Graphite" />__</p>
|
||
<p><a href="http://graphite.wikidot.com">Graphite</a></p>
|
||
</section>
|
||
<section id="pivot-exploring-data" class="level1">
|
||
<h1>Pivot (exploring data)</h1>
|
||
<p><img src="img/pivot.gif" alt="Pivot" /> </p>
|
||
<p><a href="https://github.com/implydata/pivot">Pivot</a></p>
|
||
</section>
|
||
<section id="caravel" class="level1">
|
||
<h1>Caravel</h1>
|
||
<p><img src="img/caravel.png" alt="caravel" /> </p>
|
||
<p><a href="https://github.com/airbnb/caravel">Caravel</a></p>
|
||
</section>
|
||
<section id="conclusions" class="level1">
|
||
<h1>Conclusions</h1>
|
||
<section id="precompute-your-time-series" class="level2">
|
||
<h2>Precompute your time series?</h2>
|
||
<p><img src="img/wrong.jpg" alt="You're doing it wrong" /> </p>
|
||
</section>
|
||
<section id="dont-reinvent-it" class="level2">
|
||
<h2>Don't reinvent it</h2>
|
||
<ul>
|
||
<li>need a user facing API</li>
|
||
<li>need time series on many dimensions</li>
|
||
<li>need real-time</li>
|
||
<li>big volume of data</li>
|
||
</ul>
|
||
</section>
|
||
<section id="druid-way-is-the-right-way" class="level2">
|
||
<h2>Druid way is the right way!</h2>
|
||
<ol type="1">
|
||
<li>Push in kafka</li>
|
||
<li>Add the right dimensions</li>
|
||
<li>Push in druid</li>
|
||
<li>???</li>
|
||
<li>Profit!</li>
|
||
</ol>
|
||
</section>
|
||
</section>
|
||
</div>
|
||
|
||
<script src="../.reveal.js-3.2.0/lib/js/head.min.js"></script>
|
||
<script src="../.reveal.js-3.2.0/js/reveal.js"></script>
|
||
|
||
<script>
|
||
// Full list of configuration options available here:
|
||
// https://github.com/hakimel/reveal.js#configuration
|
||
Reveal.initialize({
|
||
controls: true,
|
||
progress: true,
|
||
history: true,
|
||
center: false,
|
||
|
||
// available themes are in /css/theme
|
||
theme: Reveal.getQueryHash().theme || 'solarized-dark',
|
||
|
||
// default/cube/page/concave/zoom/linear/fade/none
|
||
transition: Reveal.getQueryHash().transition || 'linear',
|
||
|
||
// Optional libraries used to extend on reveal.js
|
||
dependencies: [
|
||
{ src: '..//.reveal.js-3.2.0/lib/js/classList.js', condition: function() { return !document.body.classList; } },
|
||
{ src: '..//.reveal.js-3.2.0/plugin/markdown/showdown.js', condition: function() { return !!document.querySelector( '[data-markdown]' ); } },
|
||
{ src: '..//.reveal.js-3.2.0/plugin/markdown/markdown.js', condition: function() { return !!document.querySelector( '[data-markdown]' ); } },
|
||
{ src: '..//.reveal.js-3.2.0/plugin/highlight/highlight.js', async: true, callback: function() { hljs.initHighlightingOnLoad(); } },
|
||
{ src: '..//.reveal.js-3.2.0/plugin/zoom-js/zoom.js', async: true, condition: function() { return !!document.body.classList; } },
|
||
{ src: '..//.reveal.js-3.2.0/plugin/notes/notes.js', async: true, condition: function() { return !!document.body.classList; } }
|
||
]
|
||
});
|
||
|
||
</script>
|
||
|
||
</body>
|
||
</html>
|