Caringo touts clustered storage capabilities

By Kevin Komiega

—Caringo has announced a new version of its CAStor content-addressed storage (CAS) platform with an eye toward making its software an attractive, low-cost option for users interested in clustered storage.

CAStor 2.2 is the latest release of the company's flagship archiving software, with performance improvements over previous versions of the product that the company claims accelerate volume recovery and deliver the performance, scalability, and reliability needed to implement a clustered storage infrastructure.

"We have been put into that niche area of being archive storage, but we see customers using CAStor for clustered storage for online data access as well as for archiving," says Derek Gascon, Caringo vice president of marketing. "We can build an online cloud of storage that serves as the infrastructure for customers who are actively serving rich media content."

Gascon says CAStor 2.2 creates a scalable, flat address space suited for storing and serving massive volumes of digital content and file-based data. CAStor presents one single-tier storage pool for digital content by virtualizing storage across a cluster of standard servers.

A CAStor cluster scales without the need to provision or configure new capacity: Simply plug a CAStor USB drive into a piece of hardware and you're off.

"A lot of the other clustered storage vendors are really offering clustered NAS solutions," says Gascon. "Our architecture, which is based on CAS, gives us an infinitely scalable cluster, and the commodity hardware the software runs on gives users flexibility in how they upgrade and scale the clusters."

CAStor 2.2 has been given a speed boost in the area of Fast Volume Recovery. Caringo tweaked the feature so that if a node within a CAStor cluster were to fail, it could quickly be rebuilt on other nodes, enabling improved data availability and recovery from failures.

Gascon admits some customers may have some concerns about whether CAStor can deliver adequate performance when compared to other clustered storage systems, but without citing specific speeds he claims that CAStor's "performance is very good for small files, while other products are best equipped for serving large files. But we've also tested our system on large files and our read/write performance is very strong."

This article was originally published on May 14, 2008