News Stay informed about the latest enterprise technology news and product updates.

GreenBytes launches data deduplication for primary and secondary data storage

Startup GreenBytes builds file system based on Sun's ZFS to produce storage systems that deduplicate primary and secondary block and file data; supports iSCSI, CIFS and NFS.

GreenBytes Inc. today launched its first enterprise data storage system based on a modified version of ZFS file system that can deduplicate primary and secondary data.

There are a few differences in the GB-X Series from the system that GreenBytes previewed last year. While the systems are still based on Sun Microsystems Inc.'s open-source ZFS, GreenBytes has replaced Sun's SunFire X4540 storage server with whiteboxes from an unidentified OEM partner. GreenBytes now calls its proprietary file system GBFS instead of ZFS+.

GBFS enables inline data deduplication of block storage through iSCSI support as well as files through NFS and CIFS support.

The GB-X series includes two models with Intel Xeon 5520 processors and 2.5-inch Seagate Constellation drives with SAS interfaces. The GB-2000 is a 2U system with 24 drive bays and four internal SAS channels for 12 Gbps throughput. It scales from 12 TB to 60 TB with expansion shelves. The GB-4000 is a 4U system with 48 drive bays and eight internal SAS channels, and scales from 48 TB to 216 TB.

For connectivity, the GB-2000 has four Gigabit Ethernet ports with an optional 10 Gigabit Ethernet port. The GB-4000 ships standard with two 10 Gigabit Ethernet ports and four Gigabit Ethernet ports.

The systems support SAS or SATA disks or solid-state drives (SSDs). GB-X drives can also be placed into a lower power state to reduce power consumption.

Another change from the original product was to scrap a Web interface in favor of custom Microsoft Management Console (MMC) plug-ins. That makes it possible for Windows admins to manage the GB-X boxes through MMC, and provides snapshots and replication through Microsoft shadow copy.

GBFS natively deduplicates every block of data by default. GreenBytes CEO Bob Petrocelli said customers can turn off dedupe for specific data sets, but he maintains there is no advantage to doing that. Petrocelli claims GBFS can provide a 30% reduction in ordinary user files, a 10% to 20% reduction in data backup streams and 50% reduction in virtual desktop environments. GreenBytes claims a data ingest rate of 950 MBps for the GB-4000.

More on data deduplication and data backup

Data deduplication tutorial 

EMC completes acquisition of Data Domain 

Global deduplication can simplify administration of deduplication devices

"This is all homegrown, not anything from Sun," Petrocelli said. "We spent two years developing it. It took quite a while to refine and tune its performance. I'm not aware of anyone else who can do inline deduplication of iSCSI block storage. I envision others will try to do that, but it's hard to do."

Petrocelli said GreenBytes will let customers run GBFS on Sun X4540 servers if they want, but he said the uncertainty around Sun's future prompted him to switch to an unidentified supplier in Taiwan as his hardware partner.

"We thought it would be better if we had more control over the platform," he said.

Petrocelli said GreenBytes is seeking resellers specializing in either primary or secondary storage. GB-X devices will compete with dedupe vendors such as EMC's Data Domain and ExaGrid Systems, archiving dedupe vendors such as NEC Hydrastor and Permabit Technology Corp., and primary storage compression startups Ocarina Networks and Storwize. NetApp also deduplicates primary file data.

The list price for the GB-2000 with 12 TB is $65,000 and the GB-4000 with 24 TB will be just over $100,000, Petrocelli said. The systems will be available this month.

GreenBytes a good fit for secondary storage, SMBs

Taneja Group senior analyst Jeff Boles said he sees GreenBytes as a good fit as a secondary storage box for larger companies or a primary storage alternative for SMBs.

"Not too many deduplication vendors come to the game with a full file system as GreenBytes does," he said. "That's been an obstacle a lot of vendors have spent a fair amount of time working on. It's affordable capacity-optimized secondary storage for a disk-to-disk repository, and you can use that technology for archive and nearline storage.

"They have a value proposition for primary data, but the primary [enterprise] NAS market is a hard market to compete in. I think they will make inroads for primary storage in the Windows market, though. It's an attractive price option for the Windows file server customer who doesn't want to step up to a NetApp-type device yet."

Dig Deeper on Software-defined storage

Start the conversation

Send me notifications when other members comment.

Please create a username to comment.