Marvell DragonFly Virtual Storage Accelerator

Marvell Technology Group Ltd. launched the Marvell DragonFly Virtual Storage Accelerator (VSA) powered by HyperScale embedded processor technology.

 
In what is a first for Marvell, the new DragonFly VSA, which plugs directly into all commercially available servers, combines Marvell’s chip technology with its newly designed circuit boards. The result is a systems solution that is designed to achieve 10x server I/O performance, while reducing power, space and storage capital costs in the datacenter. What’s more, the DragonFly VSA is suited for virtualized server applications.
 
The DragonFly VSA represents new architecture  achieving the benefits of virtualization scaling and enterprise NAS/SAN/DAS storage cost reduction via turn-key hardware rather than software.
 
"The Marvell DragonFly VSA is a revolutionary product for enterprise-class cloud computing, offering powerful host server I/O cache acceleration to solve worsening storage I/O bottlenecks," said Pantas Sutardja, Chief Technology Officer at Marvell. "The HyperScale caching technology embedded in the DragonFly VSA is the product of leveraging our leadership in HDD, SSD storage technologies, and extending our advanced-integration capabilities. The DragonFly VSA presents itself as a powerful tool for data center architects in optimizing the costs of the server/storage infrastructure. We look forward to collaborating with visionary Cloud storage architects to achieve a leapfrog improvement in virtualization scalability."
 
About DragonFly VSA
The DragonFly VSA is a purpose-built, turn-key solution that is designed to provide benefits to enterprise data centers (private clouds) and hosted service providers (public clouds). Powered by HyperScale embedded technology, the Marvell DragonFly VSA enables cloud computing deployments to break through the storage I/O barrier by enabling 10x virtual server IOPS while lowering NAS/SAN/DAS storage costs by 50 percent or more. The Dragonfly VSA enables the creation of a next-generation cloud-optimized data center architecture where data is automatically cached in a low-latency, high-bandwidth ‘host I/O cache’ in application servers on its way to/from higher-latency, higher-capacity storage. The Dragonfly VSA is designed to create a host I/O write and read cache that is agnostic to storage protocols and can be configured to serve as a data cache for DAS, SAN or NAS storage arrays.
 
The Dragonfly VSA’s distributed host I/O cache employs a two-level cache for low-latency and high burst throughput. The two levels are composed of a level-1 non-volatile DRAM (NVRAM) cache and a level-2 cache created from off-the-shelf commodity SSD drives. The two-level cache enables consistent, high-level performance to applications running on the host server.
 
As an industry standard PCIe adaptor, the DragonFly VSA offers a turn-key ‘appliance-on-a-card’ that fits into all commercially available rack-mount servers and is operating system independent. By offering an add-on card to commodity servers, the DragonFly VSA enables a cost-effective distributed cache that incrementally scales IOPS and NVRAM/SSD capacity as your application servers grow over time.
 
Powered by embedded HyperScale technology, Marvell DragonFly VSA is designed to offer the following high-value features for cloud computing storage deployments:

• 10x write performance-flash-aware write buffering & re-ordered coalescing
• 10x read performance-intelligent block/file read caching algorithms
• HA synchronous mirroring for SPOF protection
• Zero-warm up cache upon power loss
• Multi-protocol storage caching (NFS, iSCSI, FC, FCoE, SCSI DAS)

Availability
Marvell DragonFly VSA will be on display at the Storage Networking World conference on April 5-6 at the Santa Clara Convention Center. Beta trial sampling is expected in CQ3 2011.