Recently in data server Category

Racks of Cisco Unified Computing Systems gear supporting 23 different labs at VMworld. Source: Cisco Systems

In previous blog postings, I've attempted to pique your interest in the rapid technological changes that are transforming the data centers that we all rely on. Very soon these changes will revolutionize how folks around the world will use the Internet and what they will be able to do with it.

You don't have to just take my word for it, though. Tomorrow (Wednesday, 9/29) Cisco Systems will host a live Internet TV broadcast and Q&A session to discuss its vision for Data Center 3.0 and how the company's core technologies and new solutions are mapping to its overall corporate business strategy. Best of all, you don't have to be anyone special to attend. The session will be distributed free to all. No registration required. Just visit the event URL at 10:00 a.m. PDT and select "Play" to launch the live presentation.

Presenters will include:

Rajiv Ramaswami, vice president and general manager of the Data Center Switching Technology Group, will discuss how storage networking technology is evolving, including a glimpse at Cisco's future technology for storage networking innovation.

Ed Chapman, vice president of product management, Server Access and Virtualization Group, Cisco, will discuss how IT organizations are evolving their data centers with new protocols such as Fibre Channel over Ethernet (FCoE) to reduce operating costs and simplify management. The presentation will include a glimpse at new technology being developed for unifying SAN and LAN networks in the data center.

Derek Masseth, Senior Director for Infrastructure Services at the University of Arizona, will describe how the university recently united its data center networks using Fibre Channel over Ethernet to create a unified fabric. Masseth will explain the reasons for choosing this technology and the upgrade process, as well as benefits and cost reductions achieved.

The event will air Tuesday, September 29, 2009, from 10:00 to 11:00 a.m. PDT. Attendees who experience difficulties connecting can contact support at (866) 614-0208 or (617) 778-9652. Phone support is available 30 minutes prior to and after the event, as well as during the videocast. Attendees may also submit an Online Support Request to CiscoTV_help@external.cisco.com or ciscotv_help@btci.com if necessary.

I've just spent some time debating with my book publisher at Whitehorse Press about what we should put into a new chapter to be included in the third edition of my book How to Set Up Your Motorcycle Workshop. The reason there's any debate is because we're in the middle of a change in computer architecture that's bigger than the introduction of the PC. (See my July 8 blog entry "Why a Thin Layer of Chrome Will be the New Thick.")

First of all, I need to specify what I mean by "PC." Some folks want to reserve the term for stand-alone desktop machines running a Windows operating system (OS). I, on the other hand, am old school. To me "PC" is just shorthand for "personal computer," and that means a computer made for personal use by, well, a person. It includes all the offerings of such machines from Acer to Zenith . Main PC OSs include Mac OS, certain distributions of Linux, and, of course, the various versions of Windows. It also includes laptops, tablets, etc. that are just modified packages for computers meant to be used in exactly the same way that the desktop systems are used.

Closely allied are workstations, which are intended for use in an intensive work environment. They are generally connected to an enterprise intranet, rather than directly to the Internet. They usually have enhanced processors and memories, and data-storage capabilities. They generally run larger and more involved programs appropriate to meeting enterprise-level needs.

Also similar to PCs are netbooks, which are essentially stripped-down models intended for thin-client applications, such as surfing the net. They have far less memory storage space, and may even lack hard drives. What distinguishes netbooks from what I call PCs is their intended use as thin-client terminals at the expense of making them practically useless for anything else.

Just as PCs' performance is sandwiched between that of workstations and netbooks, their price range is as well. Workstations are generally more expensive (often several times more expensive) than PCs, while netbooks typically cost far less.

In the past, any introduction to computer use would have to start with choosing an operating system. That's no longer the case, however. The choice of operating system has become pretty much moot, as there's application software available for every popular OS to do pretty much anything, and non-PC architectures are becoming increasingly important.

Advanced networking technologies, such as virtualization and cloud computing, are driving this shift by making it possible to serve up most applications, from email to computational fluid dynamics (CFD) as Web applications. With this technology, the user's computer becomes a thin client - little more than a terminal to display the system's user interface. Since Web applications are OS agnostic, choice of OS to run on your personal computing station (PC, netbook, mobile platform, or whatever) is immaterial.

These are not future technologies. As a technology journalist, I get to see these things develop years before mainstream media. I've been watching these technologies - and using them - for about five years. They are quite ready for prime time, and in regular use by mainstream computer users today.

All major ISPs use virtualization and cloud computing technology to run their operations. Most e-commerce sites are built on MySQL databases. This generation of PCs are capable of virtualization using software downloadable from Xen. Every bank website is a thin-client Web app.

Dell's already seeing PC sales crash. Microsoft's scrambling to react. Apple's already made the transition, as have Google and leading chip makers like Intel.

In the end, PCs as such will be squeezed practically out of existence. Very soon PCs will be dinosaurs. Ordinary folks won't have or want to have them. It'll all be netbooks and mobile computing. Even Kindle may be obsolete before it really gets started! It'll just be an application on next years' iPods and Blackberrys.

What will count will be the application you run, and not the OS.

The trend is moving much faster than I thought it would. I figured we'd still have another 2-3 years for it to roll out. Now it looks more like a matter of months.

The PC, as such, is already dead, the general public just doesn't know it, yet. PC sales will not recover significantly from the present slump. "Computer" sales growth has already moved to other platforms, such as products from Apple, RIM, and Palm.

The media is painting it as a wrestling match between giants: Google vs. Microsoft. Operating system king Microsoft recently introduced a new Bing! browser, followed last night by search engine titan Google's announcement that it's working on an operating system for netbooks.

As usual, the mass media have somewhat missed the mark. What's actually happening is the whole landscape of computing is changing, and a race is on to see who's going to plant their flag on the new territory first.

The change in computing is the steady migration of computer technology from a thick client model to a thin client model for most routine computing needs. If you haven't yet heard about this, yet, let me explain:

Thick Clients are powerful stand-alone computers with network access. To do something useful, you download the file you want to do it to from a server; do it; then upload the file to the server again, keeping (or not) a copy of the updated file on your local computer.

Thin Clients are computers with powerful communications and display capabilities, but which are otherwise pretty anemic by conventional computer-performance standards. To do something useful, you visit an extremely powerful server, which is actually a supercomputer based on cloud-computing architecture (see "Computing With Your Head in the Clouds"). This server creates a virtual computer (See "Virtualization flies under the mass-media radar") with enough resources to run an application program (which it preloads onto the virtual computer) to do whatever it is you want to do with the file (which is stored somewhere in the computing cloud). When you're done doing your thing, the server updates the file and dissolves the virtual computer into - nothing.

Thin clients have been around for a long time. The old time-shared computer terminals we used in the 1970s to access minicomputers were very much like today's thin clients, which you know as netbooks.

The term was coined in the early 1990s by Tim Negris, VP of Server Marketing at Oracle Corp. The technology has been growing in popularity and usefulness ever since. Expect in the future (probably less than 5 years) that this style of computing will be almost universal, with everything from mobile devices to home entertainment centers architected as thin clients allowing users to interface over the Internet with service providers, such as banks, online stores, news providers, and entertainment content providers. I'm already writing this blog entry using exactly this technology!

Don't invest in companies that make personal computers.

So, how does the Google vs. Microsoft struggle fit into this landscape? They both see it coming and want to provide you with the means to partake of its bounties. The problem is that they have competition. All the makers of mobile devices, household appliances, TV set-top-boxes, telecommunications suppliers, and virtually anyone who makes anything with even the potential for Internet connectivity sees it coming, too. Especially, all the Internet service providers building all the computer clouds see it coming. Google and Microsoft are really just struggling to avoid being left behind!

Google does have one advantage, at least relative to Microsoft. Google is wisely basing its Chrome OS on Linux, which is the Open Source leader. To develop application software in a Linux-based thin-client environment, a company can hire a few pimply-faced ex-hackers who learned to roll their own Linux distribution before they reached puberty. Software engineers with expertise in the latest of the never-ending stream of Windows versions are harder to come by.

Basically, the days when anybody cares what operating system or browser your Internet-connected device uses are gone. In the thin-client/cloud-computing world of the future, like in the post-Civil-War land of Gone With the Wind, frankly, my dear, nobody is going to give a damn.

As with so many terms bandied about in mass media, "Smart Grid" is a cutesy umbrella term that allows politicians, analysts, and newscasters to vaguely refer to a collection of technologies that neither they nor their audiences fully comprehend, with advantages that are easily stated, and of uncertain measurability.

While that sounds pretty negative, let me point out that nothing in the above paragraph says anything against the technologies themselves, or their value, but merely pans vague marketspeak terms in general, and the folks who rely on them for ... anything.

Smart grids are part of a general technology trend toward incorporating embedded microcontrollers and data-communication capabilities into all sorts of previously existing devices. For those unfamiliar with them, a "microcontroller" is an integrated circuit that includes a microprocessor and peripheral circuits that allow the microprocessor to sense conditions and events in the external world (data acquisition) and put out signals to drive actuators in the external world (control).

Perhaps the first "smart" devices were automobile engines, which came under microprocessor control during the late 1970s, long before the term "smart xxx" became current. Such engine control modules (ECMs) sensed such variables as outside air temperature and throttle position, and used that information to control such parameters as fuel/air ratio and spark timing. Later, ECMs gained the ability to communicate with additional embedded microcontrollers managing such functions as anti-lock braking systems (ABS) and alarm systems. Modern automobiles now contain dozens of networked microcontrollers operating nearly all functions.

Today, most significant appliances operate under guidance of microcontrollers. Microwave ovens, dishwashers, clothes dryers, televisions, and home thermostats are familiar examples. The extent to which manufacturing operations rely on "smart" technology is even more profound.

Electricity generation and distribution networks, however, are far behind other industries in incorporating smart technology. That is the impetus behind all of the noise and fury about "Smart Grids" in the media.

To be fair, there are significant barriers to incorporating smart technology into electric-power infrastructure. Most significantly, it is imperative to keep the system operating reliably while applying new technology to it. Second, the cost of upgrading existing equipment that was never intended to be part of a computer-integrated system is, shall we say, large. There are many additional issues to be considered when making the move to smart utility grids.

The motivation to incorporate computer control and networking technology into the electric power system is not just to make it more "modern." The concept avoids Scheiber's Rule (Just because you can doesn't mean you should.) by solving a number of present and future problems arising from electric-utility development trends.

The first issue is the fact that the present distribution grid developed from early systems where a single generating plant distributed power to an isolated netword of loads. That placed the responsibility for maintaining voltage, frequency, and phase of the provided electricity squarely on one generating facility. Such installations are amenable to simple closed-loop control.

Later, but still quite some time ago, outputs from multiple generating plants were combined to supply power to the user network. That created the issue of coordinating the output levels and phases of the sources. At least, the sources on a given network were controlled by a common authority capable of centrally guiding the generators via more complex closed-loop control.

Problems became serious when power-distribution networks were interconnected to allow power sharing between sources operated by separate authorities. This makes simple reactive closed-loop control problematic. When you have multiple agents independently providing control inputs in response to observed conditions, the system becomes chaotic. This is not a slam on the engineers who designed and operated the system. It's a fact of life dictated by mathematics. Voltage variations, unpredictable frequency and phase shifts, and seemingly random catastrophic failures ensue.

Happily, all the folks on the supply side of the system were highly intelligent professionals who realized that the only solution was to co-operate their power-generation controls. We'll call it meta-control, where individual operators don't blindly react to every movement of the controlled system, which is what drives the system into chaotic behavior. Instead, when they observe a departure from nominal status, they first communicate among themselves, and devise a coordinated response that brings the entire system back toward nominal.

You can do that when there are relatively few operators. As the number of operators grows, the time needed to communicate and devise a coordinated strategy becomes longer, while the frequency and severity of divergences become more severe.

In the past, the economics of power-generation have favored large generating stations because they can be made more efficient. Costs for fossil fuels and nuclear power scale more slowly than generating plants' output. Emerging energy sources, such as photoelectric and wind power, have been billed as "free energy sources," although they are nothing of the kind, so power-plant efficiency figures less in the installation decision. Thus, we expect to see many more smaller plants. With more small plants, the number of sources that need to be coordinated will rise dramatically, and system-control cost and difficulty will increase.

The assumption is that increased deployment of smart-grid technology will make it possible to maintain system control in the face of increased chaos. High-speed data sharing is to improve coordination while expanded computer automation improves the speed and quality of meta-control decision making.

According to Wikipedia, support for smart grids became federal policy with passage of the Energy Independence and Security Act of 2007. The law, Title13, set out $100 million per fiscal year in funding for fiscal years 2008-2012, established a matching program for states, utilities and consumers to build smart grid capabilities, and created a Grid Modernization Commission to assess the benefits of demand response, and recommend protocol standards.

The Act directs the National Institute of Standards and Technology (NIST) to coordinate the development of smart grid standards, which the Federal Energy Regulatory Commission (FERC) would then promulgate through official rulemakings. Smart grids received further support with the passage of the American Recovery and Reinvestment Act of 2009, which set aside $11 billion for the creation of a smart grid.

Progress has been swift, as it needs to be. Federal Energy Regulatory Commission (FERC) issued a proposed policy statement and action plan on 19 March 2009 for standards governing the development of a smart grid. However, FERC noted that the electric industry started moving ahead with smart grid technologies prior to these government initiatives. The Commission is proposing to establish some general principles that the smart grid standards should follow.

We have known for some years that the trend was toward more numerous smaller power plants. The handwriting has been on the wall since the introduction of a feed-in tariff (FIT) system in 1978. A feed-in tariff is an incentive structure to encourage the adoption of renewable energy through government legislation. The regional or national electricity utilities are obligated to buy renewable electricity (electricity generated from renewable sources, such as solar photovoltaics, wind power, biomass, hydropower and geothermal power) at above-market rates set by the government. The higher price helps overcome the cost disadvantages of renewable energy sources. The rate may differ among various forms of power generation.

FIT means that any Tom, Dick, and Harriett with access to enough cash can set up a generating station, then sell the power to utilities, which are obliged to buy it. This model works well for facilities, such as hospitals and certain manufacturing operations, that need to maintain back-up power generation plants in the event of power failure. Most of the time these generators stand idle. FIT allows their owners to defray some of their cost by running them during peak periods, when demand may exceed fixed-power plant capacity and electricity costs (and FIT repayments) are largest.

The unintended consequence, of course, was a more chaotic electricity environment. Specifically, since a hallmark of chaotic systems is scale invariance, departures from nominal expanded to higher spectral frequencies with smaller amplitude signals (amplitude varies inversely with frequency. While these departures are smaller, their higher frequency translates into the need for faster response. Utilities began experimenting with smart-grid technology in hope of reigning in chaos over a much larger bandwidth.

ADDITIONAL RESOURCES:

U.S. Department of Energy Smart Grid

IBM Smart Grid

American Superconductor Smart Grid: It's More than you Think

This entry is about a survey of IT executives conducted by Symantec Corp. in which respondents indicated that Green IT budgets are rising and they are willing to pay more up front for energy efficient solutions. Before I get into that topic, however, I want to invoke the blogger's prerogative to interject personal ramblings only peripherally related to the subject.

It's been about two years now since I got really, really tired of hearing people talk about "Green" as if it were not only the most important thing in human history, but that it actually meant one thing and everyone knew what that was. It's the name of a color for pity's sake! Spectroscopically speaking, it's pretty mundane, lying dead bang in the middle of the visible spectrum. Yellow is more visible to human eyes. Red is much more exciting. Blue is about the coolest color you can see.

Green with a capital "G," however, is a broad, marketing-speak-like term intended to encompass anything and everything "environmentally friendly" (whatever that means). If most such vague terms are referred to as "buckets," Green is a bathtub. No, it's a swimming pool. It's like what Texans refer to as a "tank," which is an artificial pond containing enough water to get a whole herd of cattle through the dry season. We're talking ambiguous to an astronomical degree here!

Clearly, an underpowered electric car with bad styling and no leg room has no excuse for existing except to be Green. But, does a natural-gas-fired electric power plant, which generates the power to charge that electric car's battery, qualify as Green? It's certainly Greener than a coal-fired generating station built in the 1950s and never updated, but not as Green as a photovoltaic solar array.

I'm just asking.

Anyway, admitting the word Green (through tightly clenched teeth) to the modern English lexicon as meaning looking for ways to get the same work done (energy being defined in the professional physics game as "the ability to do work") while littering the landscape with less noxious byproducts and using up less of any limited resources, it certainly points to a noble calling. It's right up there with motherhood and apple pie on the list of things that should be encouraged by any and all means available.

So, what's the debate?

The debate is that it's hard. Ultimately, according to the Second Law of Thermodynamics, it's a losing battle. You reach the point of diminishing returns where ekeing out that next few percent of efficiency takes more time, effort, money, etc. than all the gains made since Neandertals noticed that they got more warmth by building fires inside the cave than outside.

The point of diminishing returns is, of course, a fallacy. There is no point of diminishing returns. Returns always diminish! It's that pesky Second Law of Thermodynamics, again. The only trigger point is where the cost of the energy saved relative to the cost of saving the energy becomes greater than unity. And, both costs are moving targets.

What has changed is that the realization that the cost of energy to be saved has gone up, while the cost of saving the energy has gone down due to application of some clever computerized measurement and control technology. Now, we can actually measure, in real time, the power bleeding off into the Great Outdoors with finer granularity than ever before. The control part of the technology simultaneously gives us more effective means of doing something about it.

So, now we have a circular mechanism where clarity of observation makes it possible to know, for the first time, exactly what's going on. The picture that's emerging gives business managers apoplectic fits. That motivates facilities engineers to employ shiny new technology (always popular among engineers of every stripe) to stop up the energy leaks.

Symantec Corp. undertook the effort to measure this phenomenon by surveying senior-level IT executives about their companies' interest in Green IT strategies and solutions. Most of us techno-geeks know Symantec as a purveyor of anti-malware software applications. A closer look reveals that it does a lot more. It is, after all, descended from the old Norton Utilities company that helped us out of stupidity-induced computer jams long before anybody figured out how to surreptitiously introduce code into other people's operating systems in order to induce mayhem on purpose. It provides all sorts of tools that operate in the background to help computer users get the most out of their applications.

Ninety-seven percent of respondents, according to the Symantec announcement, state they are at least discussing a Green IT strategy, while 45% have already implemented green IT initiatives. Respondents cited key drivers as reducing electricity consumption (90%), reducing cooling costs (87%), and corporate pressure to be "green" (86%). Furthermore, 83% of respondents are now responsible or cross-charged for the electricity consumed in the data center, which brings visibility and accountability for one of IT's biggest costs to the enterprise. The typical respondent reported spending up to $27 million on data center electricity.

IT professionals are regularly deploying several key initiatives for green IT purposes. Replacing old equipment was the most popular strategy, with 95% reporting new energy efficient equipment as part of their strategy, followed by equipment for monitoring power consumption (94%), server virtualization (94%), and server consolidation (93%). Additionally, more than half (57%) of respondents see software-as-a-service offerings as Green solutions.

Significantly, respondents report a willingness to pay a premium for energy efficient products. Two-thirds of respondents said they would pay at least 10% more, while 41% are willing to pay at least 20% more. Additionally, 89% of respondents said product efficiency is either important or very important in their purchase decisions.

Company managements are supporting this practice with a significant increase in Green IT budgets. Some 73% of respondents expect some increase in Green IT budgets over the next 12 months, with 19% expecting increases of more than 10%.

It has been clear for at least a couple of years that reducing energy costs is good business. Years of political efforts to motivate Green behavior through education, moral arguments, and yammering about climate change have done practically nothing. Simple cost-benefit analysis of funds flowing through individual businesses, however, has made a huge difference.

Before I get into this posting, I want to apologize for going "silent" for a few weeks. I spent a week clearing a bunch of on-deadline projects off my desk so I could spend a vacation week obsessing about my "new" boat.

At 25 years old, most folks would not call my boat "new." Welcome to my life, in which Charlie spends inordinate amounts of time hunting the greater Chicago area looking for a fixer-upper that will provide an excuse for endless hours of puttering around in the workshop.

Anyway, I finally got the thing:
1. Legally titled and registered;
2. Tested to the point where I could believe it would both float and take me where I want to go;
3. Moved from the far side of Lake Michigan up the Illinois river to its berth at the (name suppressed on account of paranoia) marina, stopping for a week along the way to haul the thing out to check for damage after hitting a massive object drifting just under the surface in the middle of the channel;
4. Moved again to another (and far more expensive) berth to satisfy my wife's insistence on being in the Ritzy-cratic part of town; and
5. Finally getting in a one-day fun cruise.

Now that I list it all out, it does seem like an awful lot to have accomplished in less than a month!

Now to business: before wandering off to play boats, I'd started covering developments at (mostly) Cisco Systems surrounding virtualization technology. Mainstream media, including business media, haven't said much of anything about this development, despite 2-3 press releases coming over the wire per day. I know 'cause I've watched.

Apparently, virtualization, which is going to end up being built into every operating system for nearly every computer on the planet and will change the way we use computers forever, is too sophisticated for the liberal-arts majors running mass media. So, as usual, they're ignoring it.

In previous posts, I've explained what virtualization is and a little of what it brings to the party. Today, I want to give you a link to a series of seminars sponsored by Schneider Electric's APC unit that can help you learn a little more about it and other landscape-changing developments. To learn more about the seminars, visit the company's APC Learning page, and look for events with NetApp Alliance in the title. The series kicks off on 2 June with a seminar located in Chicago.

Entitled the "Go Green and Stop the Red" event series. The half-day seminars, co-hosted by APC, Microsoft and NetApp, at their technology demonstration centers across the United States, will examine how to leverage advances in data center applications and architecture to yield a more positive impact on the environment and the company's bottom line. One of those advances, as I've subtly intimated, is virtualization.

"Businesses are continually faced with the challenge of how to maximize efficiency and savings, while minimizing space and waste," said Alistair Pim, APC's vice president of global strategic alliances. "This event series features presentations from experts that look at how adopting sustainable IT practices, such as virtualization, can be cost effective solutions for long-term business growth."

"Deploy virtualization projects to save assets, support and energy costs. Such projects can produce a reduction of more than 80% in energy consumption," stated Rakesh Kumar, Gartner's research vice president, in the May 7, 2009 report "How to Cut Your Data Center Costs.

Seminars will feature industry experts who will demonstrate how to:
* Connect virtual and physical infrastructures to achieve a holistic view of your data center energy consumption.
* Accelerate business breakthroughs and achieve cost efficiencies by
implementing data management solutions.
* Build pay-as-you-grow data center architecture to reduce operating expenses today and plan more effectively for tomorrow.

A few weeks ago, the CEO of a large, very competent computer services company made me feel much better by publicly admitting that he didn't know what people were talking about when they mentioned cloud computing. I, too, had been made to feel inadequate by the term.

Like "fuzzy logic," the term "cloud computing" sounds like its meaning should be obvious, but it isn't when you actually think about it. If you ask the average technophile what cloud computing is, you're likely to get a response like: "Cloud computing is ... unh ... I'm not sure what it is!"

So, I did a little digging to start coralling a meaning for this slippery term. Here's what I've been able to piece together:

Cloud computing seems to be a way to monetize unused capacity of large data storage and analysis facilities by "renting out" the extra capacity on a more-or-less short term basis. Statistics are available that indicate that large distributed computer systems (such as the server farms maintained by Internet service providers) typically run at 10% of capacity most of the time. They need the extra capacity for peak loading, but peak loads appear only occasionally.

This is, of course, similar to the issue that led to the rise of multi-tasking computer operating systems during the 1970s. The solution is similar: provide systems that allow multiple users to time share the unused computing resources at off-peak times.

The difference is a matter of scale. Multitasking operating systems allow multiple users to independently access single-processor computing hardware. Cloud computing systems allow multiple users to independently access large multi-server installations. The effect is the same: as long as the computing resources do not become overloaded, users gain low-cost access to computing resources they never could afford to install themselves.

Users access the resources on an as-needed basis via the Internet. So, a scientist or engineer with a large compute-intensive problem, such as simulating how a protein folds, might rent out unused capacity from, say Yahoo, or Google, or another provider that has a large server farm. Servers are, after all, just high-speed computers with really, really big hard drives, whose sole raison d' etre is to download web pages to every Tom, Dick, and Harriet who makes a request via the network. For big server farms, "the network" is usually the Internet, but it could be a corporate intranet.

The provider's cloud-computing system would create a virtual machine (VM), which appears to the user like a supercomputer dedicated to his or her problem, while looking like just another application program running in the background on the provider's massive multiprocessor system. During peak loads (which appear more-or-less randomly for relatively short periods), the server farm drops the scientist's problem and handles the load for its owner. When the load peak passes, it again activates the VM, which picks up the protein-folding problem where it left off. Since any problem big enough to make cloud computing worthwhile would take a very long time on a desktop machine, the user doesn't even notice the hiccup as the virtual supercomputer runs off to take care of its file-serving duties during the load peak.

After solving the scientist's protein-folding problem, the VM downloads the results (perhaps by emailing them to the user, or by storing them in a file for later download by the user) and disappears. The scientist pays only for the computing time actually used. The cloud-computing provider earns extra income from spare capacity that would otherwise be wasted. Everybody wins.

We like that!

Goooood technology. Nice technology. Now, roll over like a good puppy and I'll scratch your tummy.

Our friends at virtual infrastructure developer Virtual Instruments, and IT technology research firm Taneja Group plan to host an interactive and educational webinar on April 29 titled "Virtual Infrastructure Optimization: What You Can't See Can Hurt You." This live session will feature Dave Bartoletti and Jeff Byrne, both senior analysts and consultants at the Taneja Group, and Mark Urdahl, CEO of Virtual Instruments.

Our March 18 blog entry "Cisco, HP, and the forgotten factor of virtualization" introduced the concept of software virtualization in the context of data servers. These systems should be on the minds of everyone interested in infrastructure expansion and modification while the U.S. economy shifts from contraction to expansion later in 2009. While most folks who think of "infrastructure" as bridges, highways, and buildings, the real infrastructure of the technology-driven U.S. economy, as well as the economies of the fastest growing nations globally, is information technology (IT).

While brick-and-mortar infrastructure is certainly important, and woefully in need of attention, most of the effect of the Federal government's stimulus efforts will be to boost IT infrastructure. That is, it will drive expansion of public and private sector organizations' abilities to store and communicate mountains of data. We will be modernizing, building, and expanding data servers and the networks that interconnect them.

Virtualization will surely be an important core technology built into most, if not all, of this expanded IT infrastructure. As pointed out in the 3/18 blog entry, virtualization provides critical capabilities to data server operators, whether they are in government, financial, healthcare, or other sectors. Anyone involved in any of these sectors needs to understand what virtualization is, what benefits it provides, and how it provides them.

Attending the 4/29 seminar on optimizing virtualized data servers is a good way to bone up on the critical information everyone involved in activities enabled by data-server technology needs to know. To attend, visit the webinar's free registration website. the webinar will be held live on April 29, 2009 at 8:30 a.m. PT (4:30 p.m. GMT)

According to Virtual Instruments, the webinar will introduce new research on the topic of virtual Infrastructure optimization (VIO) - the market category of solutions designed to significantly improve the performance of virtualized applications and to help optimize the utilization of both storage and server resources. The hosts will highlight how IT managers and administrators can:

* Tackle challenges associated with deploying virtualization for performance sensitive, business-critical applications, including visibility into and managing the internal cloud.

* Proactively avoid over-provisioning and under-provisioning of server and storage assets

* Track system interdependencies to accelerate identification of performance choke points

* Select monitoring and analysis tools with the instrumentation needed to address today's scale and complexity

* Gain clear visibility into real-time virtual SAN performance

* Confidently deploy virtualization in business-critical environments

Speakers and audience participants - who will be able to ask questions during the event - will discuss how new solutions enable administrators to peer into multiple dimensions of the infrastructure in real-time and obtain the integrated monitoring and analytics required to optimize and troubleshoot virtual infrastructure performance holistically across every element of the system - from the application to the spindle.

Technophiles who happen to be wandering around northern California (actually, it's really central California, but Californians seem to consider anything north of, say, Bakersfield to be "northern California.") with time on their hands could do a lot worse than to drop in at the Embedded Systems Conference going on this week at the San Jose McEnery Convention Center -- surprisingly actually located in San Jose. It's a compendium of all the computer and computer-related technology at the forefront of what makes our society go.

Not many decades ago, the only computers available were giant clunky things of little value to anyone but scientists, insurance companies, and corporate accountants. The overwhelming majority of Americans had never seen a computer outside of the occasional Hollywood movie.

Not no more! Most of us now either spend much of our working days tapping at a desktop or laptop computer, or know somebody who does. Nearly everyone has access to and is comfortable using such machines. That, most people think, is what makes our society computer-bound.

The vast majority of computers we encounter today, however, don't look like computers at all. They're what are called "embedded systems." To find the nearest embedded system, all you have to do is pull your cellphone, Ipod, PDA, or whatever you like to call your mobile communications device, out of your pocket. It's nothing but a glorified wireless networking computer.

Want more? Go heat up a cup of coffee in a microwave oven. The few non-computer-controlled microwaves still in existence are pretty much dinosaurs. The same goes for your clothes washer. If your television isn't just a big computer terminal set up to display streaming video, its days are numbered. By this summer, it'll need a computer called a "set-top-box" to receive digital TV signals and convert them to the analog signals such ancient non-computerized TVs need.

As I've often said, just about every piece of equipment more complicated than a lead pencil is now computer controlled. That may be a bit of an exaggeration, but not by much.

All those computerized gadgets, from the thermostat on your wall to the radio in your car are embedded systems.Such microprocessor-based control systems are called "microcontrollers."

Indeed, virtually all of the cars on the road today are run by multiple interconnected embedded computers, each running one of the vehicles subsystems. New vehicles, for example, are all required to have tire-pressure monitoring systems consisting of a module in each tire with a sensor feeding pressure data to a tiny microcontroller, which then passes the information via a tiny radio to a receiver in the wheel well, which then feeds it to a microcontroller that runs your electronic dashboard. If the tire pressure starts to sag, all those separate microcontrollers send up an alarm that culminates in a light blinking on your dashboard to warn you about it.

By now you should be convinced that embedded computers are all around you, like little gnomes hiding in the woodwork watching and reacting to your every move. Put that way, it seems kinda creepy. In fact, though, embedded systems are more like little invisible servants waiting at your beck and call. They only show up when you want or need something that they can provide. If you don't think about it, you'll never even notice them.

The Embedded Systems Conference now going on in San Jose is the annual West Coast gathering for all the software and hardware engineers that make embedded systems possible. There are two such gatherings, of which ESC West is the largest. The smaller gathering (ESC East) happens in the Fall in Boston, Mass. At these gatherings, embedded-system developers share information about the latest bits and pieces available to go into their creations, and the latest ideas about how to put them together.

For example, Lantronix, Inc., which specializes in secure, remote device networking and data center management technologies, is announcing support for Linux on their wired embedded device server product, MatchPort AR. The company says its Linux software development kit (SDK) significantly simplifies and accelerates the process of developing Linux-based embedded platforms. Developers can integrate their applications using predefined configuration profiles and software assembly tools. Sample applications are provided within the SDK, allowing developers to jump-start their application development.

The company says its SDK helps users take advantage of the well-established Linux development community, allowing engineers to create new applications with greater flexibility and improving time to market. "The Linux development community is one of the fastest growing today," says Daryl Miller, vice president of engineering of Lantronix. "Working with our partner Nissin Systems, we were able to take this first leap in penetrating the Linux space, and will continue to establish Linux as the base platform for our product development moving forward."

Another company, Virtium Technology Inc., which is a provider of memory and solid state storage solutions for mission-critical applications, introduced a new family of DDR3 dual-function semiconductor memory modules combining a DRAM module and SATA compact Flash or SSD modules into a single space-saving form-factor. The company says its new module family is an innovative way to fit more memory and storage into space-constrained embedded systems. The modules are said to implement new DDR3 technology to offer higher data bandwidths up to 12.8 Gigabytes per second and at lower power consumption to reduce heat dissipation and improve reliability by minimizing or eliminating single bit ECC errors.

The company is making the memory modules available in commercial grade and industrial grade, and can provide ruggedized units for adverse environments. Virtium engineers are available to show ESC attendees techniques for saving space in embedded applications for industrial automation, motion control, mobile systems, military and defense systems, medical equipment, and other systems.

These are just two examples from the hundreds of technological developments that attendees are learning about at the Embedded Systems Conference. Most of the major providers of embedded components are represented, as well as a large cross section of Silicon Valley engineers combining these elements into the next generation of computer-controlled devices that will provide the infrastructure we will rely on for services from highway transportation to entertainment from now into the foreseeable future.

Improving patient care and reducing overall healthcare costs through smart technology systems is a key priority of The American Recovery and Reinvestment Act of 2009. Allocated economic recovery funding includes $19 billion for grants and incentives that utilize health IT in order to save lives by reducing waste and decreasing medical errors.

One of the few trends in health care technology that promises to actually reduce costs while improving patient care is the move toward seamless networking of electronic patient records. The ultimate goal is to move all working records, from detailed test results to clinical history files for every individual, to electronic database form, and to make such records shareable between healthcare professionals on an as-needed basis. Likely, this will include wearable personal monitoring devices, such as for EKG and blood pressure, wirelessly linked into the database.

Development of this trend is proceeding as a number of parallel threads we expect to eventually converge. One of those threads is seamless sharing of medical records between institutions.

On Friday (3/20/09), a collaborative effort involving computer-system developer IBM, healthcare information technology developer MedVirginia, and the U.S. Social Security Administration (SSA) announced a first-of-a-kind electronic records exchange system to help speed the process of granting disability benefits for millions of Americans. Through the use of new software and services, the SSA claims to have shaved time needed to evaluate disability benefits from months to minutes.

The project, part of the U.S. Department of Health and Human Services' Nationwide Health Information Network (NHIN) Cooperative, represents the first health information exchange between a regional health information organization and a U.S. federal agency. The new system, which uses IBM's Health Information Provider (HSP) solution, is said to not only reduce processing times, but improve claims accuracy and reduce costs.

Spokespersons for the project explain that SSA uses individual medical records to determine almost 3 million disability claims each year. To make those decisions, the agency relies on doctors, hospitals, and other health professionals to provide medical information about patients. Through the migration from paper to electronic transmissions based on the patient's authorization, the agency is able to significantly reduce the time spent waiting for medical records and improve the service for those it serves. NHIN's goal is to enable secure access to such healthcare data and real time information sharing and exchange of healthcare data among physicians, patients, hospitals, laboratories and pharmacies, and other stakeholders, regardless of the location or application.

Providing such information-sharing infrastructure is, of course, key to achieving the ultimate goal of seamless integration of the healthcare IT system.