Advanced Computing in the Age of AI | Thursday, April 25, 2024

Caringo FileFly Cuts Storage TCO, Simplifies Data Access 

A consistent, growing challenge enterprises face in the big data age revolves around decreasing the total cost of ownership for storage while simultaneously providing ready access to petabytes of data for the expanding number of employees involved in analytics. Caringo intends FileFly for Swarm, released today, to address both these concerns.

While FileFly installs on a Windows server or virtual machine, it helps organizations that have high performance computing or immense storage repositories because of its integration with Caringo Swarm, which can scale to hundred of petabytes of data and beyond via a mix of commodity hardware, according to the vendor.

"We're bridging what is done today in HPC and bringing it into the cloud world," said Adrian Herrera, vice president of marketing at the software-defined object storage vendor, in an interview.

FileFly reduces TCO more than 400 percent, moves less frequently accessed files to Swarm, streamlines backup and recovery, and consolidates an organization's file servers on Swarm storage, Caringo said. Post-consolidation, files are secure, searchable, and accessible, the developer said.

"In the HPC space you have very fresh data you want to analyze and digest. Once that data is analyzed and digested, where do you put it? You might want to run those tests every month, every two months, every three months – without that secondary storage you'll have to keep building up that primary data," Tony Barbagallo, vice president of products, told EnterpriseTech. "In this scenario, after you've done analysis and a few months have gone by, [FileFly] moves it and if you have to do analysis again, it will move seamlessly back. That's what we hear a lot, not only from storage administrators for home directories bursting at seams, but also in high performance scenarios. People doing analysis want to store everything and that primary storage keeps growing and growing – and it's expensive."

Every day, we create approximately 2.5 quintillion bytes of data; 90 percent of data in the world was created in the past two years. Yet many experts expound that only 20 percent of this almost unfathomable amount of data – ranging from texts, social media posts, and word processing documents to maps, traffic signals, and medical images – is useful.

To get the most out of their portion of this data, meet regulatory or industry requirements, and bolster their competitive edge, enterprises want to leverage the most appropriate forms of storage technologies depending on the use case, type, and format of stored data, yet ensure even older data is accessible if needed. Caringo ties together organizations' legacy systems with a searchable solution, said Scott Sinclair, analyst at Enterprise Strategy Group.

"With FileFly, an organization's investment in their primary storage assets is preserved and optimized while creating a transparent bridge to the benefits of object storage," he said. "Caringo is addressing the primary issues to adoption for object storage, while at the same time addressing the storage silo and cost issues inherent with the use of filers."

Organizations can install FileFly on either a Windows server or VM and administrators can set file- and directory-level policies to automatically relocate data to Caringo Swarm from NetApp or Windows file servers. Administrators then set policies based on any file attribute that can run at any time, and files can be copied or tiered to Swarm. In addition, administrators can opt to archive off primary storage, according to Caringo.

The solution includes AES-256 bit data encryption in flight and at rest within Swarm and SSL encryption during transit between FileFly and Swarm, plus flexible access over HTTP via Swarm API, Amazon S3 API, standard protocols, or Caringo partner applications. FileFly also provides an array of search capabilities such as source file name, folder path, and MIME type, as well as the ability to write files to administrator-defined buckets.

"You have devices in your datacenter and a lot of times you're using them just to keep up. Inevitably, those devices become data junk drawers," said Herrera. "That's just misusing your primary storage. That leads to wasted budget. Scale-up storage is more expensive than software-defined storage. Once you have information stored on a scale-up device it's very difficult or limited to find reuse for it."

Typically used by organizations with 1 petabyte or 2 petabytes of data and billions of files, FileFly is available now, according to Caringo. Under the company's Quick Start program, FileFly costs $34,995 for 100 terabytes, the developer said.

About the author: Alison Diana

Managing editor of Enterprise Technology. I've been covering tech and business for many years, for publications such as InformationWeek, Baseline Magazine, and Florida Today. A native Brit and longtime Yankees fan, I live with my husband, daughter, and two cats on the Space Coast in Florida.

EnterpriseAI