DataTorrent RTS Delivers Greater Than 1 Billion Operations/Second With High Availability On Wide Set of Hadoop Distributions
SANTA CLARA, Calif. ' June 3, 2014 ' DataTorrent, creator of the world's first enterprise grade real-time stream processing platform on Hadoop, today announced the general availability of DataTorrent RTS. DataTorrent RTS enables enterprises to take action in real-time as a result of high-performance complex processing of data as it is created. Separately, DataTorrent announced a strategic go-to-market partnership with Trace3.
With today's release, DataTorrent RTS becomes the industry's first commercial offering to deliver real-time streaming analytic capabilities on Hadoop with performance greater than 1 billion data events per second — equivalent to processing 46 cumulative hours of streaming Twitter data in one second. Additionally, DataTorrent RTS' fault tolerant architecture ensures zero downtime and is certified to run on all major Hadoop and Cloud distributions.
"We are seeing increasing interest in stream-processing platforms for real-time analytics, as a complement to data warehouses and Apache Hadoop," said Jason Stamper, Research Analyst, 451 Group. "Enterprise adoption of stream-processing requires fast, in-memory processing of a large volume of events at scale" and in many cases a fault-tolerant architecture too."
By 2020, the number of smartphones, tablets, and personal computers in use will reach 7.3 billion units. Additionally, the number of Internet of Things (IoT) connected devices will grow to 26 billion units, a nearly 30-fold increase from 0.9 billion in 2009.i
As this massive amount of human and machine-generated data outpaces the capabilities of traditional databases, organizations are seeking ways to find scalable, predictable technology that enables reduced operational costs, increased revenue and increased customer satisfaction. Current Hadoop technology provides a scalable way to store and process data in a batch-oriented mode, but processing data in this way can take hours or even days.
DataTorrent RTS Streaming Analytics Platform
DataTorrent RTS allows organizations to harness the full potential of big data by enabling faster data ingestion, data processing, and more timely data insights. Key capabilities include:
- Streaming, scalable data ingestion & extraction from any source: DataTorrent RTS connects to thousands of systems simultaneously using pre-built operators and processes millions of incoming data events without delay.
- High performance data transformation and complex computation: In-memory processing on data and events as they happen provides near-zero latency. With the ability to scale to billions of data events per second, DataTorrent RTS delivers the needs of today's enterprises and future-proofs tomorrow's unexpected requirements.
- Real-time monitoring, alerting and action: DataTorrent RTS' architecture provides the ability to extend analytic capabilities beyond static queries. Custom business logic written in Java enables monitoring, alerting, analysis, and action all taken in real-time, saving organizations time and money while also increasing customer satisfaction.
- Compatibility with existing Big Data processes: DataTorrent RTS archives and loads results into any data store for archiving and query-based analytics. This ensures that an organization's existing processes work the same, just sooner — they no longer need to wait hours or days to do data analysis.
- Fault tolerant, highly available, dynamic system: DataTorrent RTS' streaming window implementation allows for in-line system checkpointing to ensure high availability and guarantees processing of every event. The fault tolerant implementation provides the flexibility to change business logic and insert or delete operators on a running system with no downtime.
"Hadoop has made big data analytics a reality; however, the true value of big data is unlocked when it can be acted upon in real-time," said Phu Hoang, co-founder and CEO, DataTorrent. "DataTorrent RTS is designed specifically to address this need for the enterprise. Through the advances provided by Hadoop 2.0, we are proud to raise the bar on real-time analytics to offer the industry's first true real-time data ingestion and analysis platform at scale."
Open Platform Support Provides Customer Choice
DataTorrent RTS is a Hadoop 2.0 (YARN) native application. One hundred percent Hadoop 2.0 compliance allows DataTorrent RTS and Hadoop Map Reduce to exist side-by-side. With more than 400 Apache 2.0 open source DataTorrent operators, creating and deploying real time streaming analytic application is now easier than ever.
DataTorrent's open approach is validated by certifications on the industry leading Hadoop distributions from Cloudera, Hortonworks and MapR Technologies as well as the leading cloud providers, Amazon Web Services and Google Compute Engine.
"The certification of DataTorrent RTS on Cloudera Enterprise 5, provides our joint customers the ability to ingest, analyze, and act on voluminous streams of data in real-time as data flows into an enterprise data hub" said Amr Awadallah, co-founder and chief technology officer, Cloudera. "This real-time capability allows joint customers to uncover real-time insights and enables them to realize the full value of Cloudera's industry leading platform for big data."
"We're pleased to certify DataTorrent RTS on Hortonworks Data Platform 2.1, the industry's only 100-percent open source Apache Hadoop distribution," said John Kreisa, vice president of strategic marketing at Hortonworks. "With partners like DataTorrent and their YARN Ready applications in the Hadoop ecosystem, we're able to provide enterprises with the ability to aggregate new types of data from sensors/machines, server logs, clickstreams, and other sources to a Data Lake, empowering a true modern data architecture that delivers business insights in real-time."
"Real-time data analysis at large scale with fault tolerance is a key customer requirement," said M.C. Srivas, CTO and Co-Founder of MapR Technologies. "DataTorrent RTS certification provides an enterprise-grade, real-time streaming application managed by YARN within the mission-critical, high-performance MapR Distribution for Apache Hadoop."
DataTorrent RTS for Hadoop is generally available today. For more information, or to download, click here.
- Visit the DataTorrent RTS Webpage
- Learn how DataTorrent handles over 1 billion data events per second
- Check out the DataTorrent blog
- Follow us on Twitter
DataTorrent RTS is the world's most powerful Big Data streaming platform built exclusively on Hadoop. With its massively scalable architecture, DataTorrent RTS allows enterprises to process, monitor, analyze and act on data instantaneously. Based in Santa Clara, California, DataTorrent is backed by leading investors including August Capital, Morado Ventures, and Yahoo co-founder Jerry Yang. For more information, visit our website or follow us on Twitter.