Why is Project MegaGrid so MegaQuiet?

By By Peter Meade**

March 14, 2005

When Project MegaGrid was announced at OpenWorld late last year, it was executed with all the ingredients of an industry-shaking and -shaping blockbuster. Imagine Dell Inc., EMC Corp., Intel Corp. and Oracle Corp. entwining their individually monumental powers and products to, as was articulated at the time, “develop a standard approach to building and deploying an enterprise Grid computing infrastructure.”

Now, fast-forward about three months to today. Why hasn't there been a steady stream of progress reports made on MegaGrid detailing all that has been accomplished since Dell founder and chairman Michael Dell made his introductory speech that day in San Francisco? Perusing the Web sites of the four partners reveals an equally conspicuous absence of updated information on MegaGrid. So perhaps a reminder of the original intention is necessary.

Initially, MegaGrid was to be made up of Intel-powered dual Xeon and four-way Itanium processor-based Dell PowerEdge servers with network-attached storage and management software from EMC as well as Oracle's 10g technology. The goal: enlighten enterprises on how to take advantage of all the superlatives of next generation's distributed computing technology.

Most of EMC's product line was to be involved, most notably Clariion CX and Symmetrix DMX networked storage systems, Celerra NS Series/Gateway network attached storage systems as well as ControlCenter and Navisphere information management software. Aside from the servers, Dell was tossing in related I/O technology. In addition to hosting the Grid, Oracle supplied its 10g suite of software, application server, database, Real Application Clusters and Enterprise Manager. Additional technology was provided by Cramer, in the form of its application software, and F5 Networks Inc. with its Big-IP switches.

Where is this much-hailed project today? Has it accomplished its goal of showcasing how a Grid infrastructure can stand up to performance and price of traditional data centers? If so, it's been done mega-quietly. Phase one has been completed, according to Randy Hietter, director of product management for Oracle, and it seems with no fanfare.

“Oracle's contribution was [to provide] primary engineering support to plan, run and document the tests,” he explained. Aside from serving as provider of the physical hosting facility — the company's Global IT data center in Austin, Texas — Oracle also provided the database, infrastructure and management software. According to Hietter, the company supplied Oracle Database 10g, Oracle Real Application Clusters, Oracle Enterprise Manager 10g with Grid Control and Oracle Application Server 10g along with project management.

The first part of the project featured Dell and the others building a system that clustered up to 32 of the company's PowerEdge 1750 servers. At the same time, best practices guides were constructed detailing the design, deployment, testing and management of mega-clusters featuring technology from EMC, Intel and Oracle. While some of the specific details remain sketchy, one thing is sure: the companies did come through on their promise to offer white papers, cross-referenced Web site copy, how-tos and a demonstration or two. Unfortunately, real-world Grids require so much more.

According to Shawn Douglass, director of partner engineering for EMC, the events of phase one are documented in a series of three white papers. The first, on design considerations, maps out the standard operating system configuration and methodology. The second deals with capacity planning, including directions for scaling the configuration. The third lays out performance management, specifically detailing the myriad workload capabilities.

“What we have today is an operational methodology,” he explained. “Today you can't buy a Grid, you must build one. We have put the pieces in place, tested them and documented the results.” Yet despite this monumental task and the massive marketing muscle of the four partners, in uncharacteristically quiet fashion, the big four summarily moved onto phase two.

“Phase two entails further building out the Grid further and expanding the workload,” said Oracle's Hietter. “For now, the team is heads-down in doing work.” More details about what has and will transpire are on tap for early fall, he added.

This phase reportedly focuses on scaling the enterprise Grid to an excess of 100 servers running a mixed workload. “Grids don't run just one thing at a time,” said EMC's Douglass. “With this mixed workload we show how Grid lets enterprises allocate and reclaim resources as needed in a fully automated fashion.” The four partners expect to leverage a lot of what has taken place in Grid development in the academic world and translate it to a business situation, he added.

“We need to meet the changing needs of business while maintaining the expected quality of service levels,” said Douglass. From this exercise will come a document explaining resource provisioning and management, with emphasis on the operational procedures.

The second phase involves clusters of PowerEdge 1850 servers. While Oracle's Hietter categorized the progress as “on track,” he added “it was never sized at 128 servers,” as previously reported. Instead, he explained, “the Grid will grow in 2005 to at least 128 servers in phases subsequent to phase two.” Guidelines are expected to follow detailing best practices procedures for a variety of enterprise applications. The goal: deliver ways that enterprises can consolidate databases, applications, servers and storage onto a common Grid platform.

Originally hailed as “an open-ended venture,” MegaGrid was expected to embrace other players as members. Yet the reality is there has been a curious lack of announcements, which cannot bode well for wider-spread acceptance of the project. Perhaps the project needs more than the two existing levels of participation — full partners such as Oracle, Dell, EMC and Intel, the founding four — and technology contributors, such as F5 Networks Inc. and Cramer Systems.

While not utilized much in the first phase, F5 expects to make a more pivotal contribution in phase two. According to Bill Evidon, senior business development manager for F5, the company's switch will become “the broker for a lot of resources,” helping the MegaGrid handle huge traffic loads. “F5 brings hardened, high-performance network development to MegaGrid,” he explained. “Big-IP's intelligent traffic handling ability and Web services API let the other vendors make pro-active network adjustments.”

According to Jeff Browning, F5 product manager, a crucial part of phase two is expanding network nodes with more workloads and applications. F5 will pay particular focus to the management of service level agreements and automation. The Big-IP switch really shines in these aspects, he added, with its dynamic workload balancing, which keys on the applications or services being loaded while monitoring areas of excess capacity. Perhaps focusing on the lesser-name players, such as F5 and Cramer, will provide MegaGrid with some diversity until the big four can cajole some new comrades.

“We are always evaluating possible new partners,” said Hietter. “Right now we are in the midst of speaking with some other potential members. We aren't in a position to disclose any further details on those discussions at this time.” While phase two originally was ticketed for the inclusion of operating systems from Microsoft Corp. and Novell Inc., no word has emerged from either camp about becoming any level of MegaGrid member.

However, there remains hope of turning the MegaGrid quartet into a quintet or more. Don't be surprised if “a strong network player” is added in time to be announced at this year's Oracle OpenWorld, which is scheduled for September, said EMC's Douglass.

“There has been a groundswell of interest,” added Douglass, who just returned from Asia, where she said he met with several interested parties.  “We need to figure out how to best plug them in.”

Granted, it's no simple task to combine the complex core technologies and massive technical resources of this foursome. But the incentive is huge. Let's face it, the quartet of some of the computing industry's biggest names are not banding together just for the goodness of providing cost-effective Grid computing solutions. More succinctly, it's because they are feeling the collective pain from selling vs. the pricey, hulking Unix boxes hawked by Hewlett-Packard Co., IBM and Sun Microsystems Inc., as well as the foes' complete Grid solutions.

The aforementioned trio individually already has customers with large Grid installations, so the MegaGrid foursome must do a better job of tooting their horn on the progress being made. So far, the only MegaGrid solutions that have been trumpeted are online store Overstock.com and BT, where an online transaction processing application comprised of 10 Dell servers (cost: $69,000) replaced a $2.9 million Sun Solaris setup. This is an impressive cost saving, so rear back and blow.

According to F5's Browning, his company already has a great comfortable level with MegaGrid partner Oracle. The Big-IP switch has been used internally at the software giant for many mission-critical applications. Even so, he added F5 welcomes the challenges ahead in phase two. “We have done a lot of horizontal scaling of databases,” he explained. “But traditionally, it's been with big, proprietary Unix boxes.” F5 is looking forward to showing its process in this high-profile Grid configuration.

While no new product introductions are expected from Project MegaGrid, the process of working as a team should give the partners excellent usage data for designing and configuring various combinations of Grid hardware and software. As MegaGrid further addresses specific business needs, there may emerge bundled product packages that are “MegaGrid tested” for use outside the project.

It's clear that Dell, EMC and Oracle all can achieve raised status in the Grid market, if they want it badly enough. The picture remains unclear, however, whether this high-profile project will succeed to where businesses will consider the MegaGrid partners to deliver the framework for new Grid implementations.  Regarding Intel, as in almost every market it has entered, the “inside” giant is entrenched in a “no lose” situation. Do any of the other MegaGrid members see that Intel wins in Grid as long as businesses select anyone other than Sun? That said, it's more constructive to make sure Intel remains true to its MegaGrid commitments. Then, if the project has something great to announce, well, go on and say it.

“Four big players, all together, have agreed, build, documented and tested,” said EMC's Douglass of MegaGrid's achievements so far. “Most such projects of this magnitude don't ever get out of the gate.”

** Peter Meade is editor of DSstar, a sister publication of GRIDtoday that covers the enterprise storage market. He is a frequent contributor to this publication.

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!

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 power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

Nvidia Appoints Andy Grant as EMEA Director of Supercomputing, Higher Education, and AI

March 22, 2024

Nvidia recently appointed Andy Grant as Director, Supercomputing, Higher Education, and AI for Europe, the Middle East, and Africa (EMEA). With over 25 years of high-performance computing (HPC) experience, Grant brings a 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…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen 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…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the fi Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. 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…

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…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a 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…

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…

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…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

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…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t 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…

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…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire