Big Data Without Big Database: Extreme In-Memory Caching

Location: E144 Level: Intermediate
Average rating: *****
(5.00, 2 ratings)

These days it is not uncommon to have 100s of gigabytes of data that needs to be sliced and diced then delivered fast and rendered quickly. Typically solutions involve lots of caching and expensive hardware with lots of memory. And while those solutions certainly can work, they aren’t always cost effective, or feasible in certain environments (like in the cloud). This talk seeks to cover some strategies for caching large data sets without tons of expensive hardware, but through software and data design.

It’s common wisdom that serving your data from memory dramatically improves application performance and is a key to scaling. However, caching large datasets brings its own challenges: distribution, consistency, dealing with memory limits, and optimizing data loading just to name a few. Leveraging common characteristics of non-transactional datasets (such as centrally updated product/service/offer catalogs, or other “reference” data) can greatly simplify dealing with these challenges, and opens up some interesting opportunities to leverage data in new ways.

This talk will cover how to make your non-transactional data shine in the cache, including:

  • How to store millions of complex entries on a modestly sized JVM heap without sacrificing expressiveness
  • Keeping caches consistent with continuously updated multiple and dependent datasets
  • Slicing and dicing your in-memory data with SQL-like queries, fast!
  • How to leverage cache partitioning to scale this to the moon

The audience will come away armed with a number of practical techniques for organizing and building caches for non-transactional datasets that can be applied to scale existing systems, or design new systems to access lots of data in new and different ways.

Photo of Leon Stein

Leon Stein


Leon Stein is currently Chief Architect at Decide, where he is helping build world’s smartest online shopping site. Prior to Decide, he helped architect and build Farecast — online travel startup which was acquired by Microsoft in 2008 and now is a part of Bing search. Prior to that Leon worked at other leading technology companies like Amazon and AT&T Wireless, and was doing software consulting.

Leon has extensive experience in building large scale distributed web systems, working with big data and cloud platforms. He holds Masters degree in Theoretical Nuclear Physics from Moscow Engineering Physics Institute, Russia (currently National Research Nuclear University) and MBA from University of Indianapolis.


For information on exhibition and sponsorship opportunities at the conference, contact Sharon Cordesse at (707) 827-7065 or

View a complete list of OSCON contacts