FalconStor Software on Tuesday unveiled a new deduplication technology which allows elimination of duplicate copies of files sent to either a NAS appliance, a virtual tape library, or both.
Deduplication, also called "dedupe," removes duplicate information as data is backed up or archived. It can be done at the file level, where duplicate files are replaced with a marker pointing to one copy of the file, and/or at the sub-file or byte level, where duplicate bytes of data are removed and replaced by pointers, resulting in a significant decrease in storage capacity requirements.
Virtual tape libraries, or VTLs, are disk arrays configured to look to the host server and the backup software as if they are physical tape libraries. Data is streamed to and recovered from the VTL as if it were tape, so no changes are needed to the backup process. However, because they use hard drives, the backup and recover speed is much higher than when using tape drives. Data backed up to a VTL can also be backed up to a physical tape for archiving or off-site storage.
FalconStor's new file-interface deduplication system technology enables both SAN-based and NAS-based deduplication during the backup process, said Fadi Albatal, director of marketing for the Melville, N.Y.-based vendor.
As a result, when archiving and backing up the same file, only one copy of that file is actually stored in order to cut the amount of storage capacity required, Albatal said.
"This allows us to scale up the dedupe repository," he said. "Other vendors create multiple island-like repositories based on their appliances. We're trying to avoid that by providing a single, scalable dedupe repository across the enterprise."
FalconStor's file-interface deduplication system is a revolutionary technology and will help solution providers compete against Data Domain, the company best-known for dedupe, said Greg Knieriemen, vice president of marketing at Chi Corp., a Cleveland-based solution provider which until last year also worked with Data Domain.
While Chi has not yet had a chance to try the new technology, Knieriemen said, it looks to bring new options for dedupe. "And when you consider replication with such deduplication in one package, it is a slick solution," he said.
Data Domain created awareness of deduplication, and talks with customers about the technology nearly always drift include that vendor, said Rob Kinney, lead systems engineer at Chi.
However, Kinney said, Data Domain requires additional hardware to scale dedupe repositories over a certain size, while FalconStor does not. "FalconStor will bring single-instance storage with their dedupe and replication technologies, and attach to any storage your customers want to use," he said. "They don't need to buy additional intelligence in the form of new hardware every time they need to increase capacity."
The new technology is high-availability-enabled for clustered storage, Albatal said. It currently works in a two-node, active-passive configuration, but next year will be available for active-active configuration in a multinode cluster when it will be able to share a dedupe repository with a virtual tape library, he said.
FalconStor's file-interface deduplication system is expected to be available during the first quarter of 2009 in two versions. Pricing for the software that can be downloaded onto a physical server is expected to be $10,000 for the software plus $3,000 per managed terabyte of data. A virtual appliance version is also planned with a price of $3,000 for the software plus $2,000.
FalconStor also unveiled VTL 5.1 software for building virtual tape libraries. This latest version of the software, in addition to supporting 10-Gbit Ethernet and 8-Gbit Fibre Channel connectivity, also combines tape cashing on the front end and deduplication on the back end for improved backup streaming performance, Albatal said.
It also now supports new tape library and tape drive emulations, including the Sun StorageTek T100000B drive, giving customers potentially huge savings by cutting the number of tape drives they need, he said.
"These are $32,000 drives," he said. "We can aggregate multiple drive streams through the VTL, and then use only two physical tape drives to send data to tape."