Crosswalk CEO Explains Storage Grid Solution

By Nicole Hemsoth

January 29, 2007

Crosswalk, Inc., a provider of intelligent storage grid systems that scale performance, access to data, capacity and resiliency, was recently voted the Most Innovative HPC Storage Technology or Product for 2006 by HPCwire readers. HPCwire asked storage industry pioneer Jack McDonnell, founder and CEO of Crosswalk, to provide his view on storage grids and their present and future impacts on HPC.

HPCwire: Why did you leave McDATA to start Crosswalk?

McDonnell: While still at McDATA, through experience and numerous conversations with end-users, industry experts and channel partners, one thing became very evident: a fundamental change must occur in storage systems and architectures. End-users have been demanding answers from their data to drive critical real-time business decisions and increase value in competitive markets. Yet technologies from today's vendors are not suited to deliver on this promise. End-users must choose among a hodgepodge of partial fixes and short-term “band-aids”.

These end-users are demanding storage systems that enable efficient sharing and consolidation of data and storage, compelling changes in the storage architecture and real business value. It became clear to me that the vendor that is able to meet these demands would be very successful.

HPCwire: Can you tell our readers what exactly Crosswalk does?

McDonnell: At Crosswalk, we approach technology and solution development from a unique standpoint. We believe that the ideal storage system solution does not require a forklift upgrade, or disruptive change, but does mandate new thinking about innovative grid-based architectures and intelligent networked storage technologies. We believe the industry and user expectations need to shift from “point-solutions” that only address the symptoms to simpler and more comprehensive solutions that efficiently fulfill fundamental business objectives.

In response to the needs of the end-user, we have developed the iGrid Intelligent Storage Grid System. This software-based solution is built from the ground up to meet the high-performance storage demands of computational grids and clusters in environments where productivity, results and time-to-completion are all being adversely impacted by inflexible, segmented storage architectures. Instead, iGrid is truly adaptable, enabling users to add storage capacity whenever it's needed, and to make each and every storage volume available to each and every application server and end-user. The bottom line here is that iGrid empowers collaborative project team members to focus on their work, not storage work-arounds.

HPCwire: How would you define a storage grid?

McDonnell: At a high level, a storage grid is an architecture that incorporates well-understood grid principles that enable organizations to leverage and share disparate storage resources.

As a long-time storage industry participant, I have seen the industry conquer many of the basic storage issues. But, the HPC community has presented a variety of unique challenges to the storage industry that have largely gone unanswered. This is due to the simple fact that today's storage architectures are static and inflexible, and therefore have proven themselves incapable of meeting these challenges. We at Crosswalk determined early on that in order to solve these problems, a radically new architecture was needed.  This new architecture must decouple the physical storage, and all of the physical storage challenges, from the applications to create a scalable shared infrastructure model that leverages economies of scale across the physical infrastructure. This is the premise upon which we built the iGrid Intelligent Storage Grid System.

HPCwire: Is there a difference between a storage grid and grid storage?

McDonnell: Some would argue that they are the same, just as they would argue that clustered storage is the same as grid storage. It may be just semantics, but we believe that there is a significant difference between a storage grid and grid storage. Definitions of grid storage typically involve “storage nodes”, where the node contains dedicated, self-contained storage. If this definition is taken literally, then the majority of clustered storage offerings could also be accurately defined as grid storage. In this case, if you need more storage, you add another “storage node”.

One of the key problems with that approach is that most potential customers already have a substantial investment in existing storage resources that are already not fully utilized. Furthermore, pricing of physical storage continues to decrease at a rate that suggests it should be treated as a commodity. We listened to the end-users, which led us to make a conscious decision to build an architecture that can leverage the customer's existing storage arrays. Not only does iGrid provide the customer with investment protection, it also provides storage grid services such as resource sharing and aggregation, policy-based load balancing, and automated failover and failback to create a storage grid that is linearly scalable in performance, access, capacity, and resiliency.

HPCwire: How and where are storage grids being utilized today?

McDonnell: At this point, I could argue that storage grids are not being utilized today, and this is the primary reason I founded Crosswalk.

As we discussed previously, only a new, innovative storage architecture is capable of meeting not only the demands of the HPC community, but also those of the “traditional” enterprise customer. While we continue to see widespread use of grid principles and architectures in research applications for markets like oil and gas exploration, pharmaceuticals, and manufacturing, we are also seeing an increase in the adoption of grid architectures in transaction-intensive markets such as financial services, particularly investment banks and insurers. Additionally, we are seeing increased interest from the telco market, especially with respect to billing systems and resource brokering, such as storage utility services.

HPCwire: How would an end-user purchase and implement iGrid?

McDonnell: The system is sold as a bundled system, meaning the hardware and software are priced together and not separated. Crosswalk has made a conscious decision to provide a simple pricing model in the early stages of the product, charging by the node rather than a complex charge on terabytes supported and/or by the number of servers or users supported.

Crosswalk's competitive advantage and value-add comes from the iGridOS software, which is installed on a purpose-built, commodity server. We call this an iGrid node. The hardware platform used for iGrid takes advantage of industry-standard hardware, which allows Crosswalk to leverage processor and physical interface advancements without having to perform any hardware development.

iGrid nodes are installed between application servers using industry-standard Gigabit Ethernet or InfiniBand and Fibre Channel storage using either 2 or 4 Gbps Fibre Channel interfaces. Once installed, the iGrid nodes logically consolidate all attached physical storage devices into a single, scalable shared storage resource that allows each iGrid node to simultaneously access any file system, any file, and any volume within the shared storage pool. Clients mount file systems using industry-standard NFS and CIFS protocols.

The user has a great deal of flexibility in the selection of storage for the system. Disk storage can be provided by the customer or Crosswalk can provide it as part of the system. If they wish to provide their own storage with existing hardware or if they have a preferred provider with whom they do business, iGrid doesn't require specific or proprietary disk storage. If it is more convenient for Crosswalk to provide the storage as part of the system, Fibre Channel or SATA II disk technology is made available to the customer at a competitive price.

HPCwire: Who do you see as Crosswalk's main competitors?

McDonnell: Current static and inflexible storage architectures that limit scalability and are complex to manage. While “new” offerings, such as clustered NAS, parallel file systems, and clustered storage address specific requirements well, they still rely on legacy storage architectures and principles that restrict access and sharing, create data segmentation, and do not improve storage utilization.

HPCwire: What is the company's market strategy?

McDonnell: Crosswalk's initial strategy is to focus on the high performance computing market for a number of reasons. First, most HPC users continue to struggle with how to manage large compute environments that have massive storage and input/output requirements. The creation of clustered computing and/or compute grids has made major steps forward in increasing compute power at lower costs than the previous generations of supercomputers; however, little if any progress has been made with how to effectively provide high-performing mass storage for these systems. As a result, HPC users continually look for new solutions and are much more receptive to new companies that provide unique solutions.

Service providers have also been an interesting target market because of their requirements for rapid non-disruptive storage configuration changes to meet new customer demands.
 
Data mining is another area of interest because the applications tend to be I/O intensive and can benefit from the scalability, shared storage and caching capabilities of iGrid.

HPCwire: How confident are you that Crosswalk will succeed?

McDonnell: We are looking forward to an exciting 2007 that we believe will represent a fundamental and exciting re-shaping of our industry and the value it drives for end-users and their organizations.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

Harvard/Google Use AI to Help Produce Astonishing 3D Map of Brain Tissue

May 10, 2024

Although LLMs are getting all the notice lately, AI techniques of many varieties are being infused throughout science. For example, Harvard researchers, Google, and colleagues published a 3D map in Science this week that Read more…

ISC Preview: Focus Will Be on Top500 and HPC Diversity 

May 9, 2024

Last year's Supercomputing 2023 in November had record attendance, but the direction of high-performance computing was a hot topic on the floor. Expect more of that at the upcoming ISC High Performance 2024, which is hap Read more…

Processor Security: Taking the Wong Path

May 9, 2024

More research at UC San Diego revealed yet another side-channel attack on x86_64 processors. The research identified a new vulnerability that allows precise control of conditional branch prediction in modern processors.� Read more…

The Ultimate 2024 Winter Class Round-Up

May 8, 2024

To make navigating easier, we have compiled a collection of all the 2024 Winter Classic News in this single page round-up. Meet The Teams   Introducing Team Lobo This is the other team from University of New Mex Read more…

How the Chip Industry is Helping a Battery Company

May 8, 2024

Chip companies, once seen as engineering pure plays, are now at the center of geopolitical intrigue. Chip manufacturing firms, especially TSMC and Intel, have become the backbone of devices with an on/off switch. Thes Read more…

Illinois Considers $20 Billion Quantum Manhattan Project Says Report

May 7, 2024

There are multiple reports that Illinois governor Jay Robert Pritzker is considering a $20 billion Quantum Manhattan-like project for the Chicago area. According to the reports, photonics quantum computer developer PsiQu Read more…

ISC Preview: Focus Will Be on Top500 and HPC Diversity 

May 9, 2024

Last year's Supercomputing 2023 in November had record attendance, but the direction of high-performance computing was a hot topic on the floor. Expect more of Read more…

Illinois Considers $20 Billion Quantum Manhattan Project Says Report

May 7, 2024

There are multiple reports that Illinois governor Jay Robert Pritzker is considering a $20 billion Quantum Manhattan-like project for the Chicago area. Accordin Read more…

The NASA Black Hole Plunge

May 7, 2024

We have all thought about it. No one has done it, but now, thanks to HPC, we see what it looks like. Hold on to your feet because NASA has released videos of wh Read more…

How Nvidia Could Use $700M Run.ai Acquisition for AI Consumption

May 6, 2024

Nvidia is touching $2 trillion in market cap purely on the brute force of its GPU sales, and there's room for the company to grow with software. The company hop Read more…

Hyperion To Provide a Peek at Storage, File System Usage with Global Site Survey

May 3, 2024

Curious how the market for distributed file systems, interconnects, and high-end storage is playing out in 2024? Then you might be interested in the market anal Read more…

Qubit Watch: Intel Process, IBM’s Heron, APS March Meeting, PsiQuantum Platform, QED-C on Logistics, FS Comparison

May 1, 2024

Intel has long argued that leveraging its semiconductor manufacturing prowess and use of quantum dot qubits will help Intel emerge as a leader in the race to de Read more…

Stanford HAI AI Index Report: Science and Medicine

April 29, 2024

While AI tools are incredibly useful in a variety of industries, they truly shine when applied to solving problems in scientific and medical discovery. Research Read more…

IBM Delivers Qiskit 1.0 and Best Practices for Transitioning to It

April 29, 2024

After spending much of its December Quantum Summit discussing forthcoming quantum software development kit Qiskit 1.0 — the first full version — IBM quietly Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Leading Solution Providers

Contributors

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

Eyes on the Quantum Prize – D-Wave Says its Time is Now

January 30, 2024

Early quantum computing pioneer D-Wave again asserted – that at least for D-Wave – the commercial quantum era has begun. Speaking at its first in-person Ana Read more…

The GenAI Datacenter Squeeze Is Here

February 1, 2024

The immediate effect of the GenAI GPU Squeeze was to reduce availability, either direct purchase or cloud access, increase cost, and push demand through the roof. A secondary issue has been developing over the last several years. Even though your organization secured several racks... Read more…

The NASA Black Hole Plunge

May 7, 2024

We have all thought about it. No one has done it, but now, thanks to HPC, we see what it looks like. Hold on to your feet because NASA has released videos of wh Read more…

Intel Plans Falcon Shores 2 GPU Supercomputing Chip for 2026  

August 8, 2023

Intel is planning to onboard a new version of the Falcon Shores chip in 2026, which is code-named Falcon Shores 2. The new product was announced by CEO Pat Gel Read more…

GenAI Having Major Impact on Data Culture, Survey Says

February 21, 2024

While 2023 was the year of GenAI, the adoption rates for GenAI did not match expectations. Most organizations are continuing to invest in GenAI but are yet to Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

A Big Memory Nvidia GH200 Next to Your Desk: Closer Than You Think

February 22, 2024

Students of the microprocessor may recall that the original 8086/8088 processors did not have floating point units. The motherboard often had an extra socket fo Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire