Virtual Management, Virtual Mess

By By Kurt Westerfield, CTO, Managed Objects

March 10, 2008

Despite hand-wringing over the economy, budget forecasts for virtualization tools are on the rise. A recent UBS poll found that in 2008, a majority of CIOs plan to increase spending on virtualization by between 6 percent and 14 percent, which contrasts with overall IT budgets that respondents said would increase anywhere from zero percent and 5 percent. A CIO Insight survey recently went a step further and found that spending on virtualization for servers and storage is expected to grow more than 20 percent in 2008. What’s more, the data isn’t just limited to forecasts: at the Fall 2007 Gartner Symposium & ITXpo, an informal session poll with perhaps several hundred in the audience found that upward of 60 percent of IT organizations have virtualized servers in production.

What’s Driving Growth?

Server consolidation is often cited as one key driver for virtualization growth. Given IT budget woes, space issues, power consumption and green IT initiatives, consolidation sounds like a logical solution — and virtualization a means to achieve that end. Still, opportunities rarely come without costs and, in one sense, the idea that virtualization leads to consolidation might be misleading.

Forester analyst Galan Schrek pointed out in a research note last fall that virtual servers “act just like their physical counterparts, except that they exist only in software. Because they exist in software they can be created at the click of a button.” This is cause for concern because while it’s true that virtualization enables physical servers to be consolidated, the speed and ease in which new virtual machines can be created also means they could multiply — like water spilled on Gremlins. In fact, a social networking company indicated it already had 15,000 servers and was growing at 6 percent a week, which was partly attributable to virtualization.

Despite these concerns, there are many advantages that make virtualization attractive. A well-managed virtualization strategy will provide a high degree of flexibility to those managing the infrastructure in areas such as capacity management and disaster recovery. However, absent a service-based model of the enterprise, virtualization might also prove an IT management nightmare, growing components like weeds and buttressing the silos of data that IT operations endeavor to integrate.

Physical devices such as servers provide a natural and unavoidable system of checks and balances for restraining the growth of IT infrastructure: a budget. New hardware purchases must be justified, which might entail an inventory of existing assets, the manner in which those assets are deployed and the capacity at which they are utilized. In other words, the business case required to purchase physical infrastructure components may not apply in a virtual environment. As Forrester’s Schrek notes, virtualization enables IT “to build ever more complex systems and applications with a minimum of new effort.”

Virtual Mess

Virtualization might be compared to a desert mirage that has even got some experts confused. For example, one industry pundit stated that “the layers of abstraction virtualization enables” would help eliminate the “dense spiderwebs” of dependencies between IT components within the IT infrastructure. The analogy is accurate insofar as interdependencies are concerned, but the IT infrastructure is not comprised of multiple webs. Rather, it is comprised of multiple spiders spinning up simultaneous changes on a single — and perhaps modular and asymmetrical — web. It is the latter that presents the management challenge.

Why is this problematic? Because enterprises struggle with understanding how IT components map to corresponding applications and services, which makes problem diagnosis difficult and labor-intensive. For example, the company that finds it takes a 35-person conference call to resolve IT outages, or the IT operations staffer who sees his console filled with dozens of severity-1 alerts and can only guess which one should be addressed first. For most, the task is as painful as isolating the lone burned-out bulb on the string of old-fashioned Christmas tree lights. If it seems daunting to isolate the root cause of issues amid 5,000 physical servers, then 10,000 virtual machines (which virtualization can provide at the click of a mouse) might be insurmountable.

While virtualization will simplify some aspects of IT management, it may also add to the complexity. Therefore, it represents a double-edged sword. As Gartner analyst Milind Govekar said in a Financial Times article, “[I]f you virtualise [sic] a mess you’ll get a bigger mess. The overriding need is to cut complexity first.”

The Risk of Change

Complexity complicates change, so it is logical to see why an easier way to build more complex systems will inevitably lead to more complex changes. This is important because change is both a requirement and a risk IT organizations must reconcile; change is not optional. It’s a risk because as market researchers note, upward of 80 percent of downtime is caused by human error that stems from both planned and unplanned IT changes. Yet change is inevitable because software will need patches, servers will need upgrades and capacity will need to be re-allocated. The advent of virtualization in a distributed environment means these changes will be easier to make and, therefore, are likely to occur more frequently — which is all the more reason it is imperative that IT controls change.

Some virtualization tools come with management modules that incorporate limited management capability — ostensibly intended to help IT control change. However, such tools lack service context: an accurate end-to-end model of the IT enterprise and the relationships among its components, applications and services. The absence of a service-based model delineating service dependency on IT components means that IT is flying blind when it comes to making changes to the infrastructure. This has been the inherent problem with traditional component-based IT management tools for networks, systems and applications, and seems to have persisted in virtualization management. For example, when IT moves or retires a server — physical or virtual — IT generally does not truly have a good handle on the role each box plays in the IT infrastructure. What is the impact of making that change?

Consider the case of a virtual box sliced three ways, with two of those three virtual servers allocated to middleware and a Web application, respectively. It’s reasonable to say a database administrator has the capacity to move a database application from a physical server to that third slice in support of a server consolidation project. However, while the DBA might understand what is currently linked to the database, he or she is not likely have an understanding of the impact as a consequence of the move. The consequence of such a move may in fact be what keeps CIOs up at night, quite literally.

Service Perspective

The good news for advocates is that the virtualization market will not be alone in growth. AMR Research said in January that IT departments plan to spend upward of 9 percent more on performance improvement technology than in the previous year, which contrasts with plans for an overall IT spending increase of 5 percent. Though seemingly a contradiction, industry experts rationalize that “IT departments believe they can deliver almost twice as much bang this year for each new IT buck compared with their colleagues in the wider business.”

These conclusions correspond with market research firm Enterprise Management Associates’ (EMA) assessment that the business service management (BSM) market grew by 50 percent over the last two years and is poised for continued growth. One of the most important trends in aligning IT with business, BSM dynamically links IT components to applications that enable business process. This is a fundamental shift in both the thinking and the method for managing technology infrastructure. Instead of managing IT as individual components, such as routers, servers or applications, BSM views these components collectively according to the business service being delivered. In other words, BSM provides a platform — an end-to-end model — of information that illustrates the impact of IT with respect to the business.

What’s the connection with virtualization? Performance improvement tools, like BSM tools, which enable IT departments to manage IT infrastructure more effectively, are growing in tandem with tools that provide extraordinary flexibility and capacity. IT should plan for both at the same time — that is to say that IT should plan for virtualization in the context of a service perspective that BSM delivers. Virtual tools should be linked to services in order to understand the impact of change prior to implementing changes in a production environment.

Conclusion

The value proposition of virtualization provides an unprecedented flexibility for capacity, but this flexibility does not come without risk. As is the case with most cutting-edge technologies, both the risks and advantages have not been well defined, and perhaps have yet to be conceived. However, that risk can be mitigated so long as virtualization implementations are managed from a service perspective that incorporates an accurate end-to-end model of the IT infrastructure. Though this model, virtual components, like their physical counterparts, are linked to the services. In essence, BSM provides essential mapping and modeling capabilities to better understand IT and service relationships and dependencies needed to more effectively control change — especially in virtualized environments.

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!

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues 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 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…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion 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…

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