The prospect of outsourcing servers and storage to the cloud has an irresistible lure of operational simplicity and cash efficiency for today’s application developers. Cloud computing vendors help operate social networking applications, micro-blogging sites, global gaming networks and a plethora of applications that we use everyday. Yet, as successful and economically desirable as clouds have been for many organizations, outsourcing servers and storage causes a serious emotional and operational dilemma for the hardened breed of systems administrators called server huggers.Everyone working in and around the Internet knows a server hugger. Server huggers relish spending time in air-conditioned data centers, sitting on raised floors under florescent lighting with a laptop connected to a console port of a server (or, if they are lucky, standing against a server rack using a dedicated terminal and a slide-out keyboard tray). They spend hours staring at command-line on a terminal and at notebooks of commands, passwords and IP addresses.

Server huggers like being near their servers -– they feel that the emotional well-being and efficient operation of their servers requires them to be physically close at all times. And while it may be easy to scoff at server huggers and their technical idiosyncrasies, it is this same breed of folks that keep the applications running on the Internet — we would all be grasping to master our social graph, unable to micro-blog to our abundant followers and forced to live in our real life without them.

But server huggers face an impending crisis — the data centers that host their servers in many large metropolitan areas such as Chicago, Los Angeles, New York and San Francisco are increasingly filled. It is unfulfilling to hug a server that sits in a cardboard box because there is no rack space left in a data center, so server huggers have been scrambling to put their servers in geographically desirable locations that do not require new construction or an exorbitant budget.

And that got me thinking: Does the data center of the future look like a mobile home park? A mobile home park provides a place for you to park a single-wide or double-wide home and some basic utilities — power, roads, mail, etc. Yet, unlike seemingly every person on the Jerry Springer Show, servers do not operate well in mobile homes. However, as Microsoft, HP, Verari and others have shown, high density blade servers can be packed with hundreds of terabytes of storage, cooled and operated efficiently inside standard shipping containers. Maybe instead of more metropolitan data centers for the server huggers, we need container parks.

A container park would be on a plot of land within a metropolitan area (or on the immediate outskirts) and provide basic services to host containers filled with servers. Container parks could be located in spare lots close to power generation facilities, or be set up along a high-bandwidth fiber routes or even adjacent to a telecommunications facilities.

Compared to building, a top-tier data center that can cost $1,000 per square foot, setting up a container park could be done relatively cheaply — all is needed is a plot of land with the appropriate physical security, a power distribution plant, backup generators and abundant Internet connectivity. These items are available in metropolitan locations where server huggers and their employers congregate. While the containers themselves are self-contained, there should be no reason that multiple organizations and their server huggers could not share servers in a single container. After all, server huggers already share cabinets and cage space in data centers today.

So, will container parks soon emerge as the next bastion of the server hugger? Given the choice of moving their beloved servers to the cloud or hugging them in a nearby cool container down the street, the choice seems somewhat obvious.

Image courtesy of Verari.

Want to know more about the rapidly changing Cloud Computing landscape? Preview our Cloud Computing Briefing or purchase the full version.

IBM wants to corner the market on cloud computing, from providing the physical servers that make up a cloud to offering services for those unwilling to build out their own. Today it announced plans to move further into the fog by creating a kind of Good Housekeeping Seal of Approval for cloud computing. IBM calls it the Resilient Cloud Validation program. Big Blue hopes to work with cloud providers to offer a program that reassures businesses that a cloud doesn’t go down often as well as helping answer other questions that keep businesses from trusting in the cloud model.

Coincidentally (yeah, right) companies hoping to gain that seal of approval will need to work with IBM’s cloud consulting practice. IBM is also announcing as part of that practice that it can help answer a question I’ve long bothered cloud providers with — When is it most cost effective to outsource your application to a cloud and when should you build your own, or at least buy your own, servers?

IBM has been pretty quiet about its cloud efforts. In part because it didn’t want to hack off large customers buying a ton of IBM servers by competing with them. The computing giant hasn’t been pushing its own cloud business until a half-hearted announcement at the end of July, about a month and half after a company exec had told me IBM didn’t really want to advertise its cloud services.

While I may have doubted if IBM really “got” cloud computing in the past, a project it detailed in a press release today about a research project in China has me convinced that IBM knows exactly what the cloud is, and plans to capitalize on its name and experience to compete with Amazon for enterprise business. Check it out:

IBM’s China Research Lab is piloting a newly developed cloud computing platform, codenamed Project Yun which is Chinese for “cloud,” for companies to access business services, designed to make the selection and implementation of new cloud services as easy as selecting an item from a drop-down menu. With no need for back-end provisioning, the IBM platform stands to cut the time required to deliver new services dramatically. The Yun platform allocates storage, server and network resources for the customer application with zero human input, achieving top performance, availability and power utilization.

Instant provisioning with no human intervention. Right now it sounds like vaporware, but if IBM pulls it off, its cloud offerings will move from so much vapor to a competitive business.

Want to know more about the rapidly changing Cloud Computing landscape? Preview our Cloud Computing Briefing or purchase the full version.

At the SC 08 show that ends today in Austin, I was struck by how much the lines between supercomputing and corporate computing have blurred. The show even had a panel on high-performance computing and cloud computing! But after visiting with vendors of all types and sizes, I realized that since supercomputers can be built with commodity chips and networking gear, high-performance computing isn’t really about the hardware like it was back in the days of Cray. Today it’s all about the software.

Heck, IBM’s Roadrunner, currently the fastest supercomputer in the world, runs on AMD x86 chips and the Cell processor found in millions of PlayStation 3 gaming consoles. But it’s the software that integrates those two types of chips together that make the computer interesting. And software is what will enable HPC systems to keep moving out of the scientific niche into corporate offices and even into workstations for traders and researchers.

Reza Rooholamini, director of engineering at Dell, reinforced his boss’s keynote, in which Dell talked about the fourth wave of supercomputing. He pointed out that the next generation of supercomputers would rely most on manageability and other software features to attract customers. That will enable Dell to drive high-performance computing to the level of workstations and smaller professional nodes. “Our strategy from the inception…was how can we take this high-end expensive technology and make it available,” Rooholamini says. “This fourth wave is a focus on manageability, scalability, high availability and tools automation.”

This sentiment was echoed by John Lee, V-P of the Advanced Technology Solutions Group with Appro, a company that builds and delivers custom-high performance computers to customers ranging from Renault to Lawrence Livermore National Lab. Lee said the HPC market is attracting new customers who don’t have the experience or inclination to build and customize their own machines. When it comes to programming and operating HPC systems those corporate customers also lack the free labor provided by students who work at labs or universities, meaning the software and services piece of the equation is more important.

“Instead of a government lab where they understand the bleeding edge, now we’re talking to financial institutions and gas and oil guys who know they are behind the curve and so they rely on the vendors to make sure it will run fine,” Lee says.

So while there will always be niche players such as SiCortex, which is building custom semiconductors for the HPC set, it’s far more likely that the key to growing the market for these systems will be software — a fact underscored by Microsoft’s entry into the space in 2005 and bolstered by the software giant’s push into a desktop supercomputer offered by Cray. “Thirty-three years ago people asked Bill Gates ‘Why are you getting into computers?’” said Jeff Weirer, a senior product manager at Microsoft. “At that time Bill Gates had a vision of a PC on every desk and this is really just the evolution of that vision.”

As HPC moves downstream, plenty of vendors are lining up to make supercomputing look pretty much like personal or corporate computing. Since few people could really define a supercomputer outside of the types of jobs it does, those vendors appear to be succeeding.

The folks in charge of the SC 08 conference being held in Austin, Texas, this week have trumpeted the phenomenal growth of the supercomputing show, with attendance up by almost 10 percent from the previous year, but I’m beginning to doubt that high-performance computing is driving this growth as much as the broad changes in the data center world. As Ori Aruj, CEO a GM of switch chipmaker Dune Networks, told me when I asked why he was at the show, “This is no longer about high-performance computing and research. This is now a data center conference.”

I’m inclined to agree with him, as there are a lot of networking and storage vendors here with really large and visible booths that seem outsized compared with the HPC market opportunity. There are also attendees here from companies that have little or no business in supercomputing, such as Dune Networks, Isilon or Rackable Systems. Some of the 219 industry exhibitors (as opposed to the 118 research exhibitors) can’t possibly make enough in the HPC market to justify such a large presence at the show, although a product manager at Ciena, which makes networking gear,  pointed out that HPC installations can act as an effective advertisement for other business.

So here among the 10,764 attendees at the show one might be forgiven for occasionally forgetting that Microsoft, Intel, Nvidia and a host of other consumer brands aren’t here to talk about basic computing — but supercomputing.

I’m intrigued by the idea of personal supercomputers such as the Cray CX1, which was unveiled earlier this year, as well as the Dell Workstation that was given a teraflop boost using an Nvidia Telsa card. So I jumped at the chance to chat with SiCortex, a maker of high-performance computing systems that in March announced a 72-core workstation that runs at 300 watts. The company just closed a $37 million round of funding in September and also has a larger HPC system as well. For more, check out the video.

Michael Dell, chairman and CEO of Dell Inc., in a speech at the SC08 Conference in Austin, Texas, today highlighted the democratization of supercomputing thanks to the use of standards and off-the-shelf parts. That democratization, he noted, blurs the line between high-performance computing and corporate computing, which powers services such as Facebook and Microsoft’s cloud computing service (both of which are built on Dell hardware, of course).

It also means high-performance computers will be found everywhere — even on your desktop. In his speech Dell gave a boost to Nvidia and its use of GPUs in supercomputers by announcing that Dell would add 1 teraflop to its personal HPC workstations through a Nvidia Telsa card. The idea of a supercomputer on your desktop is a big theme at the show this year, with vendors ranging from Cray to SiCortex highlighting their high-performance workstations, and vendors such as Microsoft pushing new HPC software.

Moving far beyond the desktop, Dell also announced the creation of a 96-teraflop supercomputing test bed called Project Hyperion in partnership with Lawrence Livermore Laboratories and several other vendors. A teraflop is a measure of how many floating point operations per second a computer can handle. The fastest computer today is running at more than 1 petaflop, a thousand times the power of a teraflop. The goal of the Hyperion testbed is to figure out file systems, cluster management software and networking technology in a peta-scale environment. That environment is getting closer as more power can now be crammed onto fewer machines than ever before.

As an example of the increasing power, Dell pointed to server density improvements thanks to the use of blade servers and the ability to place as many multicore processors on them as possible. He gave the example of a Dell cluster built in 2003 that used x86 processors on 1,250 servers to create a 9.8-teraflop computer. In 2008 it took 155 servers to build a 10.7-teraflop computer.

As compute power has become democratized and cheaper — Dell also noted that five years ago $1 million could buy someone 2 teraflops of computing vs. 25 teraflops today — the world is finding more uses for it. That means that in addition to the traditional scientific uses such as climate change research and gene sequencing, companies use HPC to create animated films and to virtually build products before they are ever manufactured. It also means HPC is a bright spot amid a tumbling economy.

Today Amazon Web Services launched the beta version of its content delivery network service called CloudFront. As Om mentioned in September when the service was announced, this is a good move for Amazon, and something that may put the hurt on fellow CDNs such as Limelight and Akamai. Amazon will charge a usage-based fee, rather than a long-term contract, bringing CDN prices even lower for smaller web players who don’t have the scale to negotiate lower prices. Here’s how it works from the release:

The service caches copies of content close to end users for low latency delivery, while also providing fast, sustained data transfer rates needed to deliver popular objects to end users at scale. CloudFront works seamlessly with Amazon S3, where users store the original versions of objects delivered through the service. Customers need only put their objects into an Amazon S3 bucket and then register that bucket with the new service using a simple API call, which then returns a domain name used to access content through the network of edge locations.

Werner Vogels, CTO of Amazon, explains all about CloudFront on his blog.

A content delivery service that would extend Amazon S3 has been something that is very high on the wish list of our customers. They were already successfully using Amazon S3 for some of their content distribution needs, but many wanted the choice to do so with even lower latency and with higher data transfer rates to any place in the world.

He goes on to explain:

Using Amazon CloudFront is dead simple. Many of our private beta customers have reported that it only took them 10-15 minutes from the moment that they first signed up for the service to the moment that Amazon CloudFront was distributing their content.

The second Amazon Web Services principle that sets Amazon CloudFront apart is that no upfront commitments are necessary and you only pay for what you have used. There are no upfront fees or high volume requirements and no negotiations are necessary because we have published low prices from the start.

The second point is the more disruptive one. When Amazon announced its CDN in September we wrote,

Akamai is less likely to be impacted in the near term, but it further commoditizes the CDN business and forces a big shakeout in the industry, taking down the small and the weak. Akamai has been focusing on value-add services, as a way to stay ahead of the commoditization of the basic CDN services.

With prices ranging from 17 cents per gigabyte for the first 10 terabytes sent out a month, to 9 cents per GB for everything over 150 TB, the service seems to undercut the pricing offered by other CDNs for small to medium sized customers. It might be a good thing that Akamai’s looking at diversifying into online advertising.

Want to know more about the rapidly changing Cloud Computing landscape? Preview our Cloud Computing Briefing or purchase the full version.

For the first time ever, a supercomputer using Nvidia chips has achieved a spot on the Top 500 list of the world’s fastest supercomputers. The Nvidia-containing machine is ranked No. 29 on the list that was released late Friday; it’s a cluster built by NEC and Sun Microsystems that uses chips from Nvidia, Intel and AMD. As Nvidia and AMD, which bought graphics chipmaker ATI in 2005, push graphics processors for scientific computing, this is a big milestone. The rest of the list was pretty anticlimactic, with IBM’s Roadrunner computer narrowly beating Cray’s Jaguar computer to stay on top of the twice-annual Top 500 list. Both machines are petaflop computers, meaning they can achieve a quadrillion floating point operations a second — a record that was broken by Roadrunner back in June.

Sun Microsystems today announced that it is going to cut between 15 and 18 percent of its work force. That’s somewhere between 5,000 and 6,000 jobs. The company plans to cut its annual costs by between $600 million and $800 million. It blamed the cuts on the global economic downturn. But I think that like many other companies, Sun is using the downturn as an excuse for what were pre-existing problems, foretold by its stock price, which seems to be in an unending swoon. The cuts also come with the rearrangement of executive responsibilities, prompting Larry Dignan to write: “Sun is a company mired in what seems like a never-ending transition.”

Here are some of the changes:

* Anil Gadre, currently Chief Marketing Officer, will now head up the Application Platform Software business, which would include Java, MySQL and other such stuff.
* John Fowler will now lead Systems Platforms, which includes some of its new storage and analytics products.
* Dave Douglas will head up company’s Cloud Computing & Developer Platforms units, including the Network.com efforts.

Will these help? I am sure they can’t hurt. Or as someone recently said — leaky oil tankers take a long time to sink, so there is enough time to patch stuff up.

After his keynote at NewTeeVee Live today in San Francisco, Jason Kilar, CEO of Hulu, took some time to talk with Om about infrastructure issues for the network-supported online video distribution platform.

(See the embedded video here)

Maybe Larry Ellison was right — maybe cloud computing has been so overhyped that the term now applies to pretty much anything. A perfect example: Salesforce.com’s Dreamforce event. After riding the SasS wave to a market capitalization of $3.7 billion, it seems co-founder and CEO Marc Benioff and his minions have jumped on the cloud computing bandwagon. Salesforce.com is now calling itself a cloud computing company. And you shouldn’t expect any less from Benioff, the master marketer. On Monday, attendees of the event currently in progress at the Moscone Center in San Francisco were greeted with giant cloud-shaped balloons. During Benioff’s keynote, the hall was filled with mist. In fact, Benioff said the word “cloud” so many times that at one point I had to check if I was still on terra firma.

Joking aside, the fact remains that Benioff has created something of a movement with Salesforce.com’s software and more recently, its platform. Don’t get me wrong, Dreamforce is no OracleWorld just yet. But it will be.

The proof could be found away from Benioff’s blustery speech, in the Expo hall, where dozens of companies were showing off wares based on Salesforce’s Force.com platform. I ran into Jeff Bonforte and Matt Brezina of Xobni at the show, which makes me wonder if they’re developing something new for the Force.com environment, too.

By specifically targeting the enterprise, Salesforce.com is leveraging its billing relationships with some million-odd subscribers and opening up that opportunity to tiny startups, as co-founder Parker Harris explained at our Structure conference earlier this year. (Read more in the company’s press release.)

Think of this as platform specialization – or as Benioff would like you to believe – cloud specialization. Either way, I think they are taking the right approach. Force.com is being integrated with Amazon Web Services and Facebook’s social networking platform. And of course, we all know how tight Salesforce.com’s relationship is with Google.

Here is how a theoretical web application could tap into these various services:

• Amazon Web Services: Host (or the computer, in traditional desktop terms).
• Force.com: Subscriber relationships and a payment/billing system, programming environment (the operating system, in traditional desktop terms).
• Facebook: Another authentication system (Facebook Connect).
• Google/Facebook: Sources of data and application environments where our theoretical application can interface with end users.

We outline our way of thinking about the cloud in our Cloud Computing Briefing. I have included an image from that briefing to help illustrate the cloud stack more clearly.

While these seem like great moves for Force.com, there are questions as to how it would all translate into dollar and cents. In other words, if Salesforce.com is looking to use this to move its shares higher in the short term, then it could be sorely disappointed. But in the long term, this is the right move for the company.

Image courtesy of Mountjoy via Flickr.

Want to know more about the rapidly changing Cloud Computing landscape? Preview our Cloud Computing Briefing or purchase the full version.

UPDATED: Joyent, a Sausalito, Calif.-based cloud storage infrastructure startup, says the economic downturn is bringing on the good times. Since August its annualized revenue is up more than 25 percent. Is Joyent’s good fortune a sign utility computing will get a boost from the glum economy?

The 19-employee company provides scalable cloud storage that started out as web hosting provider has diversified into providing cloud services, becoming a default infrastructure provider to many social applications, notably the Facebook platform. Joyent got a start with a seed round four years ago and is cash-flow positive, according to Joyent VP Rod Boothby.

A very informal survey of developers at Microsoft’s Professional Developers Conference earlier this week suggested there’s still broad anxiety around the security and reliability of cloud services, including storage. But companies feeling the pinch of the credit crisis may have to forgo new, large data centers — or even just a handful of servers — and instead look to cloud-based services storage is and find them to look a lot more appealing. Cloud storage infrastructure contracts don’t present the immediate or longer-term capital or staffing commitments that new server farms demand.

Economies of scale presented by cloud vendors could trump immediate concerns about reliability, but such concerns are likely to persist, and vendors will be differentiated by how they handle data security integrity.

Want to know more about the rapidly changing Cloud Computing landscape? Preview our Cloud Computing Briefing or purchase the full version.

A quick and very unscientific poll of developers at the Microsoft Professional Developers conference in Los Angeles this week suggests that even the Microsoft brand might not bring enterprises rushing headlong into the cloud.

There was broad but cautious enthusiasm about the company having stepped up its push into collaborative services and software — after all “the cloud” isn’t going away, most people said, and Microsoft is making the right move by using its global heft and broad product and services reach to try and seamlessly link PCs, phones and web services for consumers and enterprise customers and developers.

I spoke with several attendees who work with companies and government agencies that handle very sensitive data, and all of them said their clients would balk at cloud storage until they get a closer look at the security and reliability of the architecture. In the U.S. there are, at the very least, regulatory hurdles around storing sensitive data remotely, said one developer who works with insurance companies. A Norwegian developer said he would run into similar roadblocks with his banking and government health services customers. That said, cloud services could also be a real boon for backend testing and development, another developer said.

More than a few attendees said there were no real big bangs at the conference, but given that the PDC is about broad ideas rather than rolling out finished products, that’s also probably no surprise. Biggest kudos — after the curiosity around Windows Azure — went to developments in the Windows Live platform’s Mesh services and the increasing openness of Microsoft’s platforms more generally.

Want to know more about the rapidly changing Cloud Computing landscape? Preview our Cloud Computing Briefing or purchase the full version.

With a flurry of announcements in recent weeks, Amazon has extended its cloud computing lead. The beta label’s gone. It can run Windows applications. By investing in firms like Elastra, it’s tackling enterprise deployment. And there’s a 99.95 percent uptime guarantee.

Much of this is a pre-emptive strike at Microsoft’s upcoming cloud offering. Microsoft has a huge advantage: It owns the stack from OS and virtual machine through to application. Amazon wants to compete on reliability and performance, rather than software suites and licensing. But there are still some things missing before enterprises will really embrace it.

Back in May, most of the people we asked were more likely to trust Amazon than Microsoft with their enterprise applications. But while enterprise customers are using Amazon already, in many cases that use is limited to a department or a short-term project. If Amazon wants to capture entire IT departments, it needs to prove it’s as good or better than in-house infrastructure. And that means delivering responsive, highly available applications, not just an SLA.

To accomplish this, Amazon needs to tackle performance and availability at an architectural level. When companies build their own applications, they rely on building blocks like load-balancing, WAN acceleration, managed DNS and redundant data centers. Fortunately, this is where much of Amazon’s roadmap leads.

• Network performance: Amazon’s CDN will get static content closer to users. With availability zones, Amazon can also get computation near the edge. All of this reduces the time it takes to deliver bits to users. But it can be faster still: Modern enterprises squeeze every millisecond out of the network. Amazon should also add route optimization, HTTP and TCP optimization to really address network delay.


Amazon's plans for integrated scaling, monitoring, and load balancing in EC2

• Processing performance: Internet architects improve server performance with load-balancing. First send the request to the fastest data center, then send it to the fastest machine in that data center. If there aren’t any fast machines, the newly announced dynamic scaling will make new ones. All that’s missing (though hinted at) is the ability to measure user experience so EC2 knows when to add new servers. Amazon needs a complete load balancing/monitoring/scaling strategy — with proper controls so IT staff can manage it — to make elastic computing a reality. While they’re at it, a performance SLA would be great, too.
• Network availability: Those same load balancing technologies improve uptime, using DNS or BGP to bypass unreachable data centers. Amazon needs to launch a SimpleDNS service, tied to availability zones and performance, that gives operators more control. It’s going to have to deal with DNS when it launches its CDN anyway. This looks less like managed DNS (Amazon uses UltraDNS already) and more like products from F5, Citrix or others. Amazon also needs to open up about its carriers and peering arrangements for enterprises to feel comfortable.
• Processing availability: Big Internet sites don’t achieve high uptime with machines that always work. Instead, they monitor for failure and then have the load balancers take out bad servers. That way, overall availability can be high, even when individual components are broken. Amazon should add load testing and profiling capabilities – particularly since EC2 doesn’t give users deep visibility into the platform — to ensure that applications work worldwide under stress.

As Amazon CTO Werner Vogels pointed out, enterprises like cloud computing for its economics, its elastic capacity and its ability to deliver high reliability. With this roadmap, Amazon goes after Microsoft’s weak spots. But it’s not there yet.

Want to know more about the rapidly changing Cloud Computing landscape? Preview our Cloud Computing Briefing or purchase the full version.

Yahoo said today it plans to invest $100 million to build a data center and service center in two Nebraskan cities — a few days after is said it would cut expenses and lay off 1,500 people. The Internet portal company qualified for millions in tax breaks there, according to a Lincoln, Neb., paper, but the report didn’t say how much, or what the incentives entailed.

But Yahoo must invest at least $100 million in the state and create a 100 jobs with a minimum average salary of $68,700 to keep its economic development cash. The La Vista Sun, which covers the town where the data center will be, says the data center should employ about 50 people.

What puzzles me about the announcement is why a government would offer incentives for a data center to be located in their state. A customer service center with its many, mid-level jobs — that I get. But data centers don’t employ all that many people and can be huge drain on power resources. They’re not glamorous and don’t offer a community a lot of visibility with which to attract other knowledge workers. They don’t consume a lot of local goods and send money back into the local economy. What am I missing here?

Wow, that was fast. Amazon Web Services, which said three weeks ago it would begin offering Windows on its Elastic Compute Cloud in closed beta, has opened the beta service up for all. Even bigger news is the beta tag has been removed from the rest of the EC2 service, and users now have a 99.95 percent up-time service level agreement. Yesterday, Rackspace ran hard to keep up with Amazon’s cloud offerings — acquiring two startups — but, with a full production computing cloud out of beta, it looks like Amazon is still in the lead.

Want to know more about the rapidly changing Cloud Computing landscape? Preview our Cloud Computing Briefing or purchase the full version.