Membase-Cloudera Integration Joins Leading Hadoop Distribution and Real-Time NoSQL Database

Oct/12/2010

Bi-directional Connection Between Membase and Cloudera’s Distribution for Hadoop Is Revolutionizing Ad, Offer and Content Targeting at AOL Advertising and ShareThis

New York – October 12, 2010 – Hadoop World – Membase, Inc. (formerly NorthScale) and Cloudera today announced they have executed a partnership agreement and completed an integration of Membase Server with Cloudera’s Distribution for Hadoop (CDH). At Hadoop World today, AOL Advertising and ShareThis will deliver a presentation outlining how this integration has accelerated and increased the effectiveness of their ad targeting and serving platforms.

• Membase Server is a simple, fast, elastic, distributed NoSQL database management system, optimized for low-latency, high-volume data access by web applications.
• CDH is the most comprehensive platform available for accelerating the deployment of Apache-Hadoop.
• Ad (and other content) targeting systems must make complex decisions in a very small window of time – typically between 40-100 milliseconds.
• In consumer-facing web systems, many of these decisions are made in parallel.
• Minimizing input data load time leaves more time on the clock to make intelligent targeting decisions; with enough time, even complex real-time customization of ad content is possible.
• User, or cookie, profiles are standard input data to targeting systems

“The integration of Membase Server and the Cloudera’s Distribution for Hadoop dramatically increases the performance and effectiveness of ad targeting platforms like those in use at AOL and ShareThis, where sub-millisecond random access to a very large data set can lead to measurable increases in advertising effectiveness,” said James Phillips, co-founder and SVP of Products at Membase. “No other database system can maintain the low latency and high throughput characteristics of Membase. For a 2KB user profile, Membase can sustain mean random read and write latency of 300 microseconds with 99th percentile latency under 800 microseconds; and it can do it while scaling from a single node to a multi-hundred node cluster.”

CDH and Membase together provide the technology underpinnings to support ad, offer, and content targeting scenarios:
• User profiles are generated using CDH.
• A stream of events associated with a given cookie or user is fed to CDH from Membase and other sources.
• Scheduled MapReduce jobs are used to process and transform these event streams into user profiles, which are fed in to Membase.
• Membase speeds delivery of the user profile data to the targeting logic, maximizing the amount of time the ad serving platform has for decision making and ad customization.

“AOL serves billions of impressions per day from our ad serving platforms, and any incremental improvement in processing time translates to huge benefits in our ability to more effectively serve the ads to needed meet our contractual commitments,” said Pero Subasic, Chief Architect, AOL. “Traditional databases lack the scalability required to support our goal of five milliseconds per read/write. Creating user profiles with Hadoop, then serving them from Membase, reduces profile read and write access to under a millisecond, leaving the bulk of the processing time budget for improved targeting and customization.”

“Integrating with Membase Server with Cloudera’s Distribution for Hadoop adds complementary functionality that customers are interested in,” said Mike Olson, Cloudera CEO. “The result is a highly optimized data delivery system with virtually no lag time. This real-time processing capability is essential for any solution on which split decisions must be made, including ad targeting and social gaming.”

AOL Chief Architect Pero Subasic and ShareThis Architect Manu Mukerji will join Membase co-founder James Phillips at Hadoop World later today to present “Better ad, offer and content targeting using Membase with Hadoop.” The session will be held at 1:45pm in Sutton South at the Hilton New York.

Online Resources
• Membase blog on the integration
• Download Membase Server today
• Download Cloudera’s Distribution for Hadoop

About Membase

Membase, Inc., (formerly NorthScale) is the company behind Membase, the simple, fast, elastic NoSQL database technology. The company provides products and services that enable customers to dramatically lower costs while simultaneously improving the scalability and performance of their interactive web applications. Membase is behind some of the world’s busiest web applications: it is the primary database for the popular FarmVille and Café World applications at Zynga; and it provides a shared data management platform for NHN, Korea’s largest web application operator with nearly 70 million unique users. Membase is also available through cloud service providers such as Heroku and RightScale, supporting thousands of applications of all sizes. Founded in 2009 and headquartered in Mountain View, Calif., Membase is a privately held company funded by Accel Partners, Mayfield Fund and North Bridge Venture Partners. www.membase.com

About Cloudera

Cloudera, the leader in Apache Hadoop-based software and services, enables data driven enterprises to easily derive business value from all their structured and unstructured data. Cloudera's Distribution including Apache Hadoop (CDH), available to download for free at www.cloudera.com/downloads, is the most comprehensive, tested, stable and widely deployed distribution of Hadoop in commercial and non-commercial environments. For the fastest path to reliably using this completely open source technology in production for Big Data analytics and answering previously un-addressable big questions, organizations can subscribe to Cloudera Enterprise, comprised of Cloudera Manager software and Cloudera Support. Cloudera also offers training and certification on Apache technologies, as well as consulting services. As the top contributor to the Apache open source community and with tens of thousands of nodes under management across customers in financial services, government, telecommunications, media, web, advertising, retail, energy, bioinformatics, pharma/healthcare, university research, oil and gas and gaming, Cloudera's depth of experience and commitment to sharing expertise are unrivaled. www.cloudera.com

Connect with Cloudera

Read the blog: http://www.cloudera.com/blog/
Follow on Twitter: http://twitter.com/cloudera
Visit on Facebook: http://www.facebook.com/cloudera