June 25, 2007
New virtualization technologies allow companies to deploy a few highly scalable, highly reliable, enterprise-class servers to do the same work that used to require a roomful of servers, each running an individual application and sitting idle whenever the application wasn't at work. With this capability, virtualization technologies promise less hardware to buy, provision and maintain -- contributing to enterprise cost savings, improved efficiency and an enhanced "green" factor.
But virtualization doesn't stop with server consolidation. Today's virtualization technologies enable a wide range of usage scenarios and benefits and can help distributed datacenters improve efficiency while cutting costs. However, as virtualization adoption grows, questions still remain. In fact, datacenter managers and CIOs are finding that virtualization makes it more difficult to confidently manage day-to-day tasks in the distributed datacenter, such as scheduling jobs, automating load balancing and accurately tracking where work is done.
To make the most of virtualization, organizations must employ the next breed of systems management tools that include desktop-to-datacenter management automation. Deploying datacenter management products with virtualization technology is the only way to save money and increase datacenter efficiency. These solutions deliver automated, policy-based management for physical and virtual distributed datacenter environments, giving organizations the tools they need to manage the complexity of their IT infrastructure.
An Old Idea Made Better -- A Lot Better
Virtualization is not a new concept. Techniques were commonly used throughout the 1960s and 1970s to boost performance for shared mainframe systems. However, as microprocessors became ever more powerful and affordable in the 1980s and 1990s, PC servers replaced mainframe and minicomputer systems. Moreover, as x86-based servers became more affordable and ubiquitous, departments and workgroups became accustomed to "owning" their own servers, and datacenters were distributed to bring the data closer to the people who needed it. The result, for many companies, has been an alarming increase in sprawl, causing many enterprise servers to be utilized at an appallingly low rate -- as little as 15 percent capacity -- even while datacenters are stuffed to the rafters with power-hungry servers.
As the costs continue to rise for housing, powering, cooling and maintaining all these servers, especially in distributed environments, many enterprises today are looking to transition to a usage-oriented computing model -- that is, an environment where computing resources can be dynamically reassigned to accommodate changing demands.
Virtualization is the keystone in this service-oriented dynamic computing model. Unlike the performance gains of first-generation virtualization technologies on mainframes that were confined to one “box," today's existing and emerging server virtualization technologies promise to bring unprecedented flexibility to the distributed enterprise datacenter, enabling new levels of cost efficiency and responsiveness across heterogeneous unique environments. In short, what many have only hoped for and imagined -- adaptive and responsive virtualization -- is here today.
From Lower Costs to Green Technology: The Promise of Virtualization
Few can deny the promises and benefits that virtualization brings to the datacenter. At a high level, virtualization provides flexibility and cost efficiency. For datacenter managers, business continuity is key. Virtualization can make their jobs easier by providing:
Virtualization also lessens the burden corporations place on the environment. Analyst firm IDC estimates that the total power and cooling bill for servers in the United States costs a whopping $14 billion per year, and if the current trends persist, the bill is going to rise to $50 billion by the end of the decade. The energy needed to cool and fuel datacenters is enormous. Virtualization requires less space in the datacenter, and thus less electricity and cooling, which is better for the environment.
New virtualization technologies are rapidly emerging, giving rise to new industry organizations, like The Green Grid, which are committed to improving energy efficiency in the datacenter. Clean virtualization strategies, backed by technology consortiums, create new usage models that can transform the entire IT enterprise. Or, to put it more appropriately, virtualize the entire enterprise.
Virtualization is Half the Story: Datacenter Automation is the Missing Link
Virtualization is here and the benefits are already proving to be fruitful. However, if organizations are excited by virtualization's promises (and it's hard not to be), decision-makers might find it difficult to see an additional, larger need: datacenter automation tools.
Imagine assembling the world's best orchestra -- you scour every continent for the best violinists and trumpet players, the most skilled drummers and harpists -- but you fail to hire a conductor, let alone an experienced, advanced conductor. All the musicians gather to play what is expected to be the best Handel's "Messiah" ever played. However, without a conductor, everyone is playing at once, the tempo is off and no one knows when to begin the next movement -- hardly worth the time and effort to develop the orchestra.
Without datacenter automation tools, the same holds true for virtualization. It brings a new set of management challenges that must be considered. According to Yankee Group analyst George Hamilton, "You can very quickly deploy virtual machines into an environment, and it's very easy to get virtual-machine sprawl. You can end up with capacity issues and resource allocation issues, so a lot of the initial challenges are around how to optimize the physical infrastructure for all the virtual machines."
A second challenge is that once multiple virtual machines have been deployed to a physical server, multiple applications and business systems are critically affected in the event of a server failure. It is no longer enough to just replace a downed server and suffer a short application outage. Should a physical server fail, there must be an automatic, rapid deployment of services in order to achieve business continuity.
A lack of management tools is just bad business. Today, organizations have to define "blackout" periods, the windows of time that IT "owns" in order to patch or update systems to better secure them or to support new application features. These blackout periods mean that some -- or all -- of the business must come to a halt, which could cost a company millions in revenue. The business needs a way to assign priority between the update and the needs of the business. The ability to dynamically allocate resources through preemption, or "starving," can offer the business the best case for maintaining the balance between business process and systems maintenance.
To combat these challenges, a single automated solution can be used to manage virtual machines, identities, storage and systems in a coordinated and intelligent way according to workload requirements, hardware health and business policies.
Taking it a step further, it is crucial to have cross-platform solutions that: are based on policies that the company sets; are interoperable with the systems already in the IT environment; and allow the manager to orchestrate the management of both virtual and physical environments. Policy-driven solutions ensure security and compliance, eliminate administrator effort and enable total control over the IT environment from remote locations or on-site administrators.
To turn virtualization into a powerful, flexible platform, the industry will need to create tools for tying management of physical and virtual machines together. New, open virtualization formats will make it easier to migrate workloads across virtual machines, including Xen, with minimal modification. Other technology advances make it possible to repurpose virtual machines and migrate workloads on the fly, as well as in an integrated management model for both physical and virtual machines. The objective is to create an agile, policy-based environment -- one that automates and orchestrates management of identities, systems, storage and virtual machines in a distributed environment.
Virtualization and its benefits are possible, but they cannot be attained without effective management in place. With orchestrated management tools that automate critical datacenter processes, like dynamic load balancing and workload scheduling, organizations with distributed datacenters are able to boost their environmental policies while making the virtualization dream a reality.
About Joe Wagner
Joe Wagner serves as the general manager of the Systems and Resource Management business unit at Novell. He is responsible for the development of comprehensive information technology management solutions across the technology stack including Novell's ZENworks suite of solutions. Wagner holds a B.S. in chemical engineering from Carnegie Mellon University and an M.B.A. from Boston University.
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.
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.
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.
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.