Follow Datanami:
October 29, 2013

RainStor Delivers Hadoop on EMC Isilon NAS

SAN FRANCISCO, Calif., Oct. 29 – RainStor, provider of the most efficient enterprise database for Big Data, has successfully completed product testing, resulting in validation of its database on EMC Corporation’s Isilon Scale-Out network-attached storage (NAS) running on the Hadoop Distributed File System (HDFS). RainStor is already in production with customers running on Isilon, and by adding native Hadoop capabilities, customers gain further benefits and flexible deployment options with Big Data initiatives.

As enterprise adoption of Hadoop increases, capabilities around ease-of-use, efficient scale and reliability become a high priority. To date, Hadoop has been deployed on low-cost commodity direct attached storage (DAS) environments but different architectures are now being deployed to optimize both compute and storage. As data volumes grow, the need to balance CPU and storage capacity is critical in order to achieve an optimal environment. With DAS deployments, compute and storage are rigid and cannot be separated which becomes challenging as requirements change over time.

RainStor enables enterprise customers to run Hadoop anywhere. With unique data compression yielding a 20-40X storage reduction, companies can scale their data with greater predictability and efficiency. The RainStor highly-compressed file format is virtualized from the underlying storage layer and therefore behaves the same whether running on DAS or NAS. With the ability to co-exist Hadoop data running on both DAS and NAS, you can now separate the compute layer from the storage layer and gain both scale efficiencies and query performance.

“Isilon running on RainStor provides high-impact use cases, including a compliance data archive for years of history reaching petabyte scale,” said Sam Grocott, Vice President, Marketing and Product Management, EMC Isilon Storage Division. “The one-two punch of RainStor and Hadoop on Isilon gives customers both performance and efficient scale with the added bonus of being easy to deploy and maintain. Case in point: a RainStor and Isilon customer saw a 32X compression rate enabling efficient, predictable scale.”

Running Hadoop on Isilon with RainStor, you achieve:

  • Flexible New Architecture Running Hadoop on NAS and DAS together: Companies leverage DAS local storage for hot data where performance is critical and use Isilon for mass data storage. With RainStor’s compression, you efficiently move more data across the network, essentially creating an I/O multiplier.
  • Built-in Security and Reliability: Data is securely stored with built-in encryption, and data masking in addition to user authentication and authorization. Carrying very little overhead, you benefit from Isilon FlexProtect, which provides a reliable, highly available Big Data environment.
  • Query Speed-up: Data is queried using a variety of tools including standard SQL, BI tools Hive, Pig and MapReduce. With built-in filtering, queries speed-up by a factor of 2-10X compared to Hive on HDFS/DAS.
  • Compliant WORM Solution: For absolute retention and protection of business critical data — including stringent SEC 17a-4 requirements you leverage Isilon’s SmartLock in addition to RainStor’s built-in immutable data retention capabilities.

“RainStor has allowed AdaptiveMobile to support a large telecommunications customer for a number of years managing over two petabytes of communications data loading around 1 billion records daily,” said Gareth MacLachlan, chief operating officer, AdaptiveMobile, a long-time RainStor partner. “We believe RainStor on scale-out Isilon NAS is a highly efficient way to manage petabyte volume, with excellent performant load and query capabilities,” added MacLachlan.

“With RainStor’s compression and efficiency, we enable new Big Data architectures that were simply not possible before,” says John Bantleman, CEO of RainStor. “EMC’s Isilon scale-out NAS is ideal for enterprises that have skills in-house that know how to manage these environments. Our customers are looking for new architectures where they can combine a one-petabyte Hadoop cluster with a multi-petabyte NAS store for mass storage, no compromise for query and the lowest TCO.”