Aster Data Announces Version 4.0,
An Industry First that Brings Applications Inside an MPP Database for Ultra-Fast Analysis of Big Data

Enquisite, Full Tilt Poker, and Telefonica I+D Validate the Analytics Power of Running Applications-Within™ a Database

San Carlos, Calif. – November 2, 2009 - Aster Data, a proven leader dedicated to providing the best data processing and management platform for ‘Big Data’ applications, today announced Aster Data Version 4.0, the industry’s first ‘Massively Parallel Data-Application Server.’ Aster Data 4.0 allows companies to embed applications inside Aster Data’s massively scalable MPP data warehouse, so businesses can now store, analyze and dramatically speed processing of terabytes to petabytes of data. The ability to push applications down into the MPP database also opens a new opportunity for companies to deliver new interactive, big data applications.

Traditional data warehouses, DBMS and analytics solutions of the last two decades have separated data from applications, resulting in large data movement, high latency and restricted data analysis. With today’s massive amounts of data, moving an enormous boulder of data to an application is not a viable option. The 20-year old architecture simply fails in today’s big data, analytics-intensive environments. Aster Data 4.0 delivers a fundamental breakthrough that brings together data and application processing in one system, fully parallelizing both, to enable ultra-fast, sophisticated analysis on massive data scales. Companies such as Full Tilt Poker, Enquisite, Telefonica I+D and others recognize the power of Version 4.0 for big data.

Today’s big data needs span a wide range of applications. Example applications include near real-time fraud detection, customer behavior modeling, granular pattern analysis, micro-targeting, merchandising optimization, affinity marketing, trending and simulations, and trading surveillance. Such analytics-intensive applications are unique in that they need the flexibility of processing data programmatically and entail algorithms that are not expressible in SQL. Further, such analytics-intensive applications use memory data-structures that entail data-structures that are hard to map to relational tables. The massive data scales and analytics sophistication involved in these new types of applications demand a new approach to data management.

"We see the Internet, both fixed and mobile, becoming increasingly important for telecommunication operators, generating more and more data. In order to take advantage of this, real-time analysis is becoming a key element for making online decisions," said Richard Benjamins, Director of User Modeling at Telefonica I+D. "We have done an analysis of what is currently available in the market concerning modern large-scale data analytics solutions, and Aster Data had the most complete product that met our requirements for rich analytics, scale, speed and overall cost of ownership."

Aster Data's Massively Parallel Data-Application Server 4.0 allows companies to embed application logic within Aster's MPP database, allowing dramatically faster, deep analysis on massive data scales. What’s unique about Aster's Massively Parallel Data-Application Server architecture is that within the system, data management lives independently from application processing, but critical to the architecture is that both data and applications exist as first class citizens and each have their respective data and application management services to deliver the highest performance and availability.

The Data-Application Server is responsible for the management and coordination of activities and sharing of resources in the cluster. It additionally acts as a host for the application processing and data that is managed inside the cluster. In its role as a data host, it manages incremental scaling, fault tolerance and heterogeneous hardware; for application processing it manages workloads via Aster Data's new Dynamic Workload Management (WLM) capability, security, fault isolation; and for data management it manages data storage, transactional correctness, online backups and Information Lifecycle Management (ILM). This architecture and suite of services makes it possible to effectively manage data and application processes inside the cluster.

The separation of data management and application processing also provides maximum application portability so a wide range of applications can be pushed down into the system. This data analysis architecture also highly distinguishes Aster's solution from lightweight implementations of MapReduce, including what some vendors refer to as 'In-Database MapReduce.'

Aster Data’s Massively Parallel Data-Application Server 4.0 - Feature Highlights

  • Application Push-down: The ability to push an application down into Aster’s MPP database, so applications execute inside the database in a massively parallel manner for ultra-fast data processing on massive data scales. Applications are automatically fully parallelized for high performance and massive scalability.
  • Application Portability: Companies can take their existing Java, C, C++, C#, .NET, Perl and Python applications, MapReduce-enable them and push them down into the data.
  • Application Process management: Parallelized applications can utilize terabytes of memory and thousands of CPU cores.
  • State-of-the-art Dynamic Workload Management (WLM): Supports hundreds of concurrent mixed workloads that can span interactive and batch data queries, as well as application execution. Includes granular rule-based prioritization of workloads and dynamic allocation and re-allocation of resources. This feature is also the first-ever Dynamic Workload Management capability available on a MPP system that runs on commodity hardware.
  • Trickle feeds: Trickle feeds for granular data loading and interactive queries with millisecond response times.
  • Infinite scaling through Online Partition Splitting: New online partition splitting capabilities adds to Aster Data’s leading incremental scaling architecture to allow infinite cost-effective scaling.
  • Dual-stage query optimizer: Ensures peak performance across hundreds to thousands of CPU cores.
  • Connectors: Integrations with leading BI tools and Hadoop.

"Using Aster’s MPP database in our search platform is a huge benefit for us and our customers. We have a worldwide network capturing search click activity 24x7x365 for some of the largest sites on the Internet. One of the reasons we chose Aster Data is because of their deep MapReduce implementation that speeds data processing and helps give our customers even faster performance and more granular information so they can drive more traffic and transactions through organic search," said Richard Zwicky, Founder and President of Enquisite, a leading provider of search optimization software and solutions. "With Aster Data, response times for large queries has dropped from 5 minutes to 5-10 seconds, and queries that previously were not possible now can be executed in 20-30 seconds," Zwicky added.

"Aster Data’s Massively Parallel Data-Application Server is a breakthrough in data management and processing. For the first time it brings applications to the data, which is the only way to handle today’s big data. Fundamentally, we are bringing to an end the stranglehold of the traditional data pipeline – where large data sets were summarized, sampled and reduced to small data sets upon which basic analytics were performed – a process in itself that took days to weeks at best," said Mayank Bawa, Aster Data CEO and Co-founder. "With a Massively Parallel Data-Application Server, we believe we will radically transform big data management and open a new opportunity for interactive, analytics-intensive big data applications."

About Aster Data
Aster Data is a proven leader in big data management and big data analysis for data-driven applications.  Aster Data’s nCluster is the first MPP data warehouse architecture that allows applications to be fully embedded within the database engine to enable ultra-fast, deep analysis of massive data sets. Aster Data's unique “applications-within™” approach allows application logic to exist and execute with the data itself. Termed a “Massively Parallel Data-Application Server,” Aster Data’s solution effectively utilizes Aster’s patent-pending SQL-MapReduce together with parallelized data processing and applications to address the big data challenge. Companies using Aster Data include Coremetrics, MySpace, Akamai, Full Tilt Poker, and ShareThis. Aster Data is headquartered in San Carlos, California and is backed by Sequoia Capital, JAFCO Ventures, IVP, and Cambrian Ventures, as well as industry visionaries including David Cheriton, Ron Conway, and Rajeev Motwani. For more information please visit http://www.asterdata.com, or call 1.888.Aster.Data.

Aster Data, Aster Data nCluster, the Aster logo and Applications-Within™ are registered trademarks of Aster Data. All other brands and trademarks referenced herein are acknowledged to be trademarks or registered trademarks of their respective holders.

Press Contact:
Marlena Fernandez Berkowitz
ZAG Communications for Aster Data Systems

The Best Insights Possible
Whitepaper: A New Approach for Large-Scale Data Management and Data Analysis
Whitepaper: Deriving Deep Insights from Large Datasets
Research Report: MapReduce and the Data Scientist