Univa HPC Job Bank
HPC in the Cloud


Dedicated to covering high-end cloud computing
in science, industry and the datacenter

Language Flags

Marvell Unveils DragonFly Cache Accelerator


SANTA CLARA, Calif., Jan. 3 – Marvell today announced the availability of the Marvell DragonFly NVDRIVE, a turnkey enterprise-class PCIe SSD caching solution with built-in SSD modules that extends the company's award-winning DragonFly NVCACHE and NVRAM adapter product offerings first announced last August. Targeted for large-scale Internet and cloud computing datacenters, the DragonFly NVDRIVE dramatically scales both bare metal and virtualized server applications, including Web servers, OLTP and analytic databases, as well as NoSQL and big data distributed applications.

"The NVDRIVE is a game-changing extension of the popular DragonFly NVRAM and NVCACHE family. It delivers the same unprecedented application acceleration as the existing NVCACHE solution, but now seamlessly integrates with onboard SSD modules for plug-and-play ease of use," said Alan Armstrong , vice president of marketing of Marvell Semiconductor's Storage Business Group. "The innovative application of non-volatile DDR memory, highly optimized caching algorithms, and entry enterprise SSD modules creates a converged solution that is ideally suited for mixed-workload cloud data centers. The NVDRIVE raises the bar on affordability and performance, and its unique cache automation and consistent write latency capabilities will be sought after by both OEM and cloud computing customers who require predictable performance at reasonable costs."

The DragonFly NVDRIVE is powered by Marvell's world-class storage SoC technology and seamlessly merges large capacity non-volatile DRAM with onboard SSD modules to enable up to 100 times higher performance for random read- and write-heavy application workloads as compared to traditional disk-based solutions. Additionally, automated caching removes the guesswork, maintenance and high capital costs required by manual data tiering approaches. Unique to the industry, DragonFly writeback caching is fully powered by ARM-based storage processors and enables storage administrators to configure granular cache policies at either a file or block level.

Data protection and reliability are ensured via intelligent RAID software and peer-to-peer synchronous mirroring to prevent data loss against any failure – server, adapter, SSD module or NAND components. An ultra-thin filter driver residing in Linux or Xen is transparent to applications and supports caching across all storage protocols, including SCSI (local DAS), NFS, iSCSI, FCoE and FCP.

Marvell's partners and OEMs are already expressing strong enthusiasm for the DragonFly NVDRIVE. "The SanDisk X100 mSATA SSDs provide small form factor, low-latency, high-performance and cost-effective non-volatile storage for the Marvell DragonFly NVDRIVE," said Kevin Conley , senior vice president and general manager, Client Storage Solutions at SanDisk. "Optimized for entry level enterprise workloads, the Marvell NVDRIVE based on the X100 SSDs provides an ideal solution for customers seeking performance demanding business-critical data center applications."

"As organizations increasingly adopt both virtualization and cloud storage solutions, their demand for powerful and intelligent plug-and-play acceleration of their IO and applications will only increase," said Mark Peters , senior analyst at Enterprise Strategy Group. "And, of course, this enhanced performance should ideally be delivered with a simultaneous TCO reduction to help IT professionals juggle demands where the only certainty is growth. Solutions such as Marvell's DragonFly NVDRIVE possess the ability to deliver this desired combination, and reflect an entire industry that's focused on delivering a storage model - whether on premise or in the cloud - that is effective, efficient and sustainable."

Feature highlights of the Dragonfly NVDRIVE include:

  • Up to 1.5 TB of useable SSD capacity with the industry's largest integrated non-volatile DRAM cache.
  • Highly predictable performance across mixed write/read workloads. Cache mode sustained performance exceeds 200,000 4K random IOPS, 3GBps throughput and sub-10us average latency.
  • Enterprise-class embedded write-back cache software. Simple, smart and fully automated.
  • Robust data protection, including RAID and HA peer-to-peer synchronous mirroring software.
  • Rich command line interface (CLI) and cache policies for granular file/block object level configurations.
  • Application-transparent OS filter driver supports all major protocols – SCSI, iSCSI, NFS, FCoE and FCP.
  • Hypervisor integration enables virtual machine migration, HA, snapshots, clones and more.
  • Fully integrated DragonFly Manager for GUI-based administration and performance monitoring.

Pricing and Availability

The Marvell DragonFly NVDRIVE will be sampling later in Q1 with OEM and cloud computing customers. DragonFly NVDRIVE is offered at 750GB and 1.5TB capacity points. Pricing starts at a manufacturer's suggested retail price (MSRP) of $2,995 USD.

About Marvell

Marvell is a world leader in the development of storage, communications and consumer silicon solutions. Marvell's diverse product portfolio includes switching, transceiver, communications controller, wireless and storage solutions that power the entire communications infrastructure, including enterprise, metro, home and storage networking. As used in this release, the term "Marvell" refers to Marvell Technology Group Ltd. and its subsidiaries.

-----

Source: Marvell

Most Read Blogs

Aspen

Feature Articles

CometCloud: Using a Federated HPC-Cloud to Understand Fluid Flow in Microchannels

The ever-growing complexity of scientific and engineering problems continues to pose new computational challenges. Thus, we present a novel federation model that enables end-users with the ability to aggregate heterogeneous resource scale problems. The feasibility of this federation model has been proven, in the context of the UberCloud HPC Experiment, by gathering the most comprehensive information to date on the effects of pillars on microfluid channel flow.
Read more...

CERN, Google, and the Future of Global Science Initiatives

Large-scale, worldwide scientific initiatives rely on some cloud-based system to both coordinate efforts and manage computational efforts at peak times that cannot be contained within the combined in-house HPC resources. Last week at Google I/O, Brookhaven National Lab’s Sergey Panitkin discussed the role of the Google Compute Engine in providing computational support to ATLAS, a detector of high-energy particles at the Large Hadron Collider (LHC).
Read more...

Avoiding Scientific Computing Bottlenecks in the Cloud

Frank Ding, engineering analysis & technical computing manager at Simpson Strong-Tie, discussed the advantages of utilizing the cloud for occasional scientific computing, identified the obstacles to doing so, and proposed workarounds to some of those obstacles.
Read more...

Short Takes

NASA Builds 'Climate in a Box'

May 23, 2013 | The study of climate change is one of those scientific problems where it is almost essential to model the entire Earth to attain accurate results and make worthwhile predictions. In an attempt to make climate science more accessible to smaller research facilities, NASA introduced what they call ‘Climate in a Box,’ a system they note acts as a desktop supercomputer.
Read more...

Running Computational Fluid Dynamics in the Cloud

May 16, 2013 | When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
Read more...

Sponsored Whitepapers

Best Practices in Big Data Storage

05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.

Exploring the Potential of Heterogeneous Computing

04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.

Sponsored Multimedias

Newsletters

Stay informed! Subscribe to HPC in the Cloud email Newsletters.

HPC in the Cloud Update
HPCwire Weekly Update
Digital Manufacturing Report
Datanami
HPCwire Conferences & Events
Job Bank
HPCwire Product Showcases



HPC Job Bank


Featured Events



  • June 16, 2013 - June 20, 2013
    ISC'13
    Leipzig,
    Germany

  • June 17, 2013 - June 18, 2013
    Forecast 2013
    San Francisco, CA
    United States




HPC in the Cloud Conferences & Events