Around the blogosphere, people are commenting on the definition of cloud computing. As we’ve noted, cloud computing is here to stay, and resistance is futile. And with $100 billion at stake (according to a Merrill Lynch research note), investors see the cloud as a promising business tool for the future. In fact, multiple analysis groups have devoted time to looking at the economics of the cloud, including Deutsche Bank, which released a report on SaaS and Cloud. Forrester Research analyst James Staten says that there are plenty of reasons to stick your head in the cloud.

So I’ve been reading my cloud feeds and have assembled some discussions on sharpening the edges on the fuzzy terminology of “cloud computing.”

Bob Plankers shared his friend Terry’s take on what cloud computing is:

To hell with cloud computing. Clouds are puffy crap that float lazily by. Is that what you want out of your service provider? Just floating by without a care in the world?

And John M. Willis asks if Guitar Hero is a cloud?

As the cloud-o-sphere tries to define this “cloud” thing, myself included, it seems like the list of who is a cloud just keeps getting longer and longer. I originally thought the Forrester 11 list was a little to long when it included SalesForce.com and Akamai as cloud providers. The general consensus seems to be, if you are a SaaS, PaaS, or a IaaS you are probably a cloud and this makes the list even longer.

Willis expounds on the aaS point with a bit of humor. He recently shared a discussion from an Awesome meeting, in which attendees asked “Does a cloud have to have an API to be a cloud?”.

If you’re stuck on what the difference is between a grid and cloud, Michael at Apistry provided useful definitions in an April post. Vontlin at cloudfunnel.com also provided a simple definition of SaaS and Cloud computing for newbies.
Michael Cote at RedMonk shared his experience at Cloud Conference week, including these two “anti-Cloud” definitions:

• “Cloud Computing means nothing and is, worse, fad-talk.” Indeed! As with all new technologies that come along, iterating through the journey to meaning is about 2/3 the point. Remember “blogs,” “Web 2.0″? We’re still chunking up on “Enterprise 2.0,” but we know it’s better than spending time thinking about “Enterprise 1.0.”
• “I knew grid computing, and you my friend are no grid computing.” There’s a Darwinian evolution of the exact definition of cloud computing running around. We’re about a country mile away from “knowing when I see it,” which is excellent progress. The cloud to everyone’s silver lining has enough material to write a 3-volume desktop reference at this point.

With all the hype and financial motivation, it’s not too surprising that vendor 3Tera is pushing toward a cloud computing standard. The company has received enough feedback that they’ve explained their thoughts on the usefulness of a standard, of course deemphasizing the profit motive that seemed obvious to a few.

What do you think? Still unclear or is it becoming more firm in your mind what this whole “cloud thing” means?

Photo credit: Benjamin Earwicker, “Storm Clouds 2″ posted at www.sxc.hu

I noticed a common theme at the string of computing conferences I’ve attended in the past couple of months: The future of the data center is going to be cloud computing, and resistance is futile.

I heard this from VMware Inc.’s President and Chief Executive Officer Diane Greene during her keynote at the JP Morgan Technology Conference in Boston in May, and the point was driven into the ground during the Enterprise 2.0 Conference there in June. I heard these predictions repeated during the annual Red Hat Summit and the USENIX 08 conferences, also held in Red Sox Nation last month.

Major league players in the data center space like VMware Inc. are putting their efforts into cloud computing because of predictions that it will eventually be the mainstream way information is handled and software vendors are starting to introduce products to manage cloud computing environments.

David Patterson, a professor of computer science at U.C. Berkeley, said during his keynote speech at USENIX that cloud computing is part of the data center evolution already under way.

“In addition to the processor evolution [from single-core to dual- and now quad-core processors], on a larger scale, there are a number of changes happening in the data center; flash memory is replacing mechanical disks, we have software as a service, and utility computing [a.k.a. cloud computing] is being used to outsource the data center,” Patterson said.

The advantages of cloud computing are clear, he said.

“With cloud computing, you put $0 down for your own data center, and pay as you go, and there is no penalty for scale up, which happens instantly. It allows fast scale up with no dead or idle CPUs, and no provisioning is required,” Patterson said.

This is especially appealing to data centers that have maxed out their power resources, but need to increase their infrastructure.

Though cloud computing is considered an immature technology, it really isn’t. The chief architect of the Xen project, Ian Pratt, said during his session at USENIX, called Xen and the Art if Virtualization, that the folks at Cambridge University who started the XenoServer project with him back in 1999 were architecting it under the cloud computing concept.

Though their ideas about what the cloud would look like differ from what we see today, the concept was similar: Develop a public infrastructure for wide-area distributed computing that can be used by people across the world.

“We originally thought there would be data centers all over the world, and clients would be able to choose a location, perhaps close to another IP address they wanted to interact with,” Pratt said. “The other difference is, we thought the machines would be owned by many different merchants, and there would be a broker acting as a third party recommending the different vendors, and those brokers would take a fee.”

Instead, we have companies like Amazon.com, Google and Salesforce.com offering the complete cloud computing environments , but Pratt expects this to change.

“I think we will see cloud computing move in the direction where it will become more open instead of all of the hardware, software and networking being located at and owned by a Google or Amazon.”

Today, most cloud computing providers host x86-compatible applications on virtualized servers, and most support only the Linux OS, according to Cambridge, Mass.-based Forrester Research Inc. To keep costs low, many cloud providers use a Xen-based hypervisor. Charges for usage are usually based on CPU hours, gigabits consumed and gigabits per second transferred rather than on a monthly service fee.

Specifically, Amazon charges 10 cents per compute hour used and 15 cents per gigabyte of storage. According to Forrester, that translates into about $70 to $150 per month for a fully utilized Amazon server, versus the average $400 a month that it costs an enterprise to run a server.

The benefits aside, IT pros are apprehensive about taking their mission critical apps out of their secure data centers and putting them into something as translucent sounding as cloud computing. This fear was quite evident during the Enterprise 2.0 conference event called “An Evening in the Clouds.” A panel of IT pros sat and listed to Google, Amazon and Salesforce as they fluffed cloud computing, and then they voiced their many concerns.

Is it secure? Is it reliable? Does it perform better than my existing data center?

The answer from all the cloud computing providers was, of course, a resounding “yes.”

But not all applications are available in the cloud, so it isn’t for every company. The cloud computing environment also lacks government standards, which makes some users nervous.

“I wouldn’t suggest moving all of your apps over to the cloud today, but hopefully one day all will be right in the world,” said Jeff Keltner, the business development manager at Google Apps.

I awoke this morning to a story that combined two of my main interests: IT and chocolate.

IBM’s Blue Gene is being use study the genetic code of the cocoa bean to help safeguard this precious resource. The cocoa industry has suffered a series of fungal diseases that have harmed the crop to the tune of $700 million annually. By sequencing the genome of the cacao trees, scientists at the Agricultural Research Service (ARS) Subtropical Horticultural Research Station (SHRS) in Miami, Fla., can develop productive cacao (Theobroma cacao) trees resistant to these diseases. Genetic sequencing used to be a slow and ponderous process, but harnessing the power of supercomputing, the thousands of small gene sequences can be assembled into a large genetic code that can then be analyzed for gene function — similar to the Human Genome Project.

While high performance computing (HPC) on the scale of IBM’s Blue Gene is unlikely to be the charge of most data center managers, smaller HPC projects are being conducted by life sciences companies around the globe, harnessing the same technology on a smaller scale. More and more, HPC is being used by companies that previously would have shied away because of cost. But the off-the-shelf functionality offered by today’s HPC systems and the lower cost is making the advantages to harnessing the technology more attractive to companies in many different industries. The HPC market is expected to grow, and companies are responding as we have seen in recent announcements from AMD and HP among others.

While your company may not be focused on something as important as the improvement of chocolate, you may be using HPC in other areas. So, we want to know: Have you recently installed an HPC system? Why? Were there any big challenges?

We want to hear from you.

Photo by Leah Rosin. Chocolate alter made by Theo Chocolate in Seattle, Wa.

Microsoft Corp. announced today that a Windows HPC Server 2008 beta-based system now ranks among the top 25 supercomputers in the world, and the company also announced the release candidate version will be available for download in the last week of June.

To date there have been about 560 downloads of the beta version of HPC Server 2008 so far, said Ryan Waite, Microsoft’s group program manager. The final version of HPC Server 2008 will be available by the end of the year.

Microsoft also announced that the Beta 2 version of HPC Server 2008 was used for clusters by the National Center for Supercomputing Applications (NCSA) which ranked 23 on the Top 500 Supercomputers list, which is published twice a year by the International Supercomputing Conference.

The NCSA achieved 68.5 teraflops and 77.7% efficiency on 9,472 cores, making this one of the most powerful supercomputing systems in the world. This also marks the first time a Microsoft cluster made it into the top 25, Waite said.

Another Microsoft HPC Server 2008 cluster also popped up on the list. Computer scientists at Umea University in northern Sweden used beta version of Windows HPC Server 2008 on their supercluster and achieved 46 teraflops and 85.5% efficiency on 5,376 cores, making their system the second-largest Windows cluster ever deployed and the fastest academic cluster in Sweden, Microsoft reported.

Umea University will run the new supercomputer at its facility known as HPC2N. The university’s cluster is made up of 672 IBM blade servers, and also marks the first time that Windows HPC Server 2008 has been run publicly on IBM hardware.

“We are making serious engineering investments in HPC Server 2008 to make sure it works well with these types of workloads, and I think that shows here,” said Waite.

Microsoft would not disclose the amount invested in the development of HPC Server 2008.

The operating system is based on a Windows Server 2008 foundation, but can scale to thousands of cores because of features like a new high-speed NetworkDirect RDMA, Microsoft’s new remote direct memory access interface, cluster management tools, a service-oriented architecture (SOA) job scheduler, and cluster interoperability through standards such as the High Performance Computing Basic Profile (HPCBP) specification produced by the Open Grid Forum (OGF).

Microsoft announced the release of Windows HPC Server 2008 Beta 2 today.
Windows HPC Server 2008 is used for cluster based supercomputing based on x64 versions of Windows Server 2008. Windows HPC Server can be used for massively parallel programs (computational fluid dynamics, reservoir simulation) as well as embarrassingly parallel programs (BLAST, Monte Carlo simulations), according to Microsoft.

The Windows HPC Server is a cluster of servers that includes a single head node, and one or more compute nodes. The head node controls and mediates all access to the cluster resources and is the single point of management, deployment and job scheduling for the compute cluster. It uses an existing Active Directory infrastructure for security and account management.

This offering lets users design their applications to work with Windows HPC Server 2008 so that users can submit and monitor jobs from within familiar applications without having to learn new interfaces.

The Evaluation copy of Windows HPC Server 2008 Beta 2 is now available on Microsoft’s Beta site.

I was at TheServerSide.com’s Java Symposium last week and got a fascinating perspective on where high-end Java apps are headed, and the infrastructure that will be needed to support them.

Hedge funds and more traditional financial service firms all are deep into creating what they call grids (they’re not talking about time sharing across occasionally idle computers) for doing performance intensive stuff like programmed trading. Imagine hundreds of motherboards ripped out of servers and velcroed into racks, all running stripped down Linux cores and highly tuned Java Virtual Machines (JVMs) on top.

Kirk Pepperdine, veteran Java performance tuning consultant, discussed the growing reliance on non-volatile memory over disk (you’ll have to register to download the talk, but it’s pretty easy) to reduce latency in these applications. NVRAM can mean high-memory footprint motherboards, as we are now in the hundreds of gigabytes for some systems. But it can also mean solid state disk, which maybe undergoing one of its periodic surges. Not only are people trying to put entire programs in memory, but as much data as they can, too.

Typical databases of, say, 1990, would easily fit into today’s NVRAM. But not necessarily the databases of today, which have grown into millions and millions of rows. But objects and services give developers an option they are starting to explore: stuffing the data into the objects themselves and stuffing the objects into solid state caches, whether that’s onboard or outboard.

One thing that is making this possible is using the grid. Some shops are using what is effectively distributed memory, as Iona Technology’s technical director, John Davies, pointed out. Products like GiagSpaces, Oracle’s Coherence and GemFire create and manage a memory space across many machines.

Another take comes from Azul Compute Appliance, your classic black box.The company has attacked a specific and troublesome problem with Java apps – garbage collection. The JVM can pause for as long as 30 seconds every few minutes to do its thing. Even if garbage collection isn’t that extreme, brief pauses are not acceptable for high-performance trading apps. So Azul designed its own chips that use a proprietary instruction set to make garbage collection non-disruptive. They stuff up to 768 of them in a box, with up to 768GB RAM. Software on the hosts redirects calls to the JVM to the Azul box, where it runs as if it was on the host.

Azul’s boxes run in the tens and hundreds of thousands of dollars, but they can run many JVMs at once. According to benchmark’s run by Pepperdine, they definitely turn up the heat on Java apps.

Server managers in the big Wall Street firms are already dealing with these new concepts, and you can expect them to migrate outward in coming years. Just as storage and networking have been disaggregated from the computer, some amount of memory and processing, at least for specialized purposes, may also migrate on to the network (probably 10GigE or InfiniBand). One of the big reasons pointed out by Pepperdine: with multicore processors, clock speeds are not increasing. Therefore, app developers must seek other ways to increase performance.

Given that parallelism is still only minimally doable for all but the rocket scientists, techniques like greater use of caching are bound to gain popularity, so it’s probably worth your while to start investigating this whole technology area. At the architecture level, there’s plenty to understand: should you virtualize and cluster at the app level, or go the route of Virtual Iron or ScaleMP, which allow you to concatenate multiple physical machines into a single large VM?

Never a dull moment.

The twice-yearly TOP500 list of the world’s fastest supercomputers released November 12 is dominated by IBM in number of systems and performance.

The TOP500 list was released at SC07, the international conference on high performance computing, networking, storage and analysis, in Reno, Nevada.

The top spot is held by reigning world champion Blue Gene/L System. Pictured below, the system is a joint development of IBM and the Department of Energy’s (DOE) National Nuclear Security Administration (NNSA) and is installed at DOE’s Lawrence Livermore National Laboratory in Livermore, Calif. The system was upgraded recently and now achieves a Linpack benchmark performance of now 478.2 teraflops (TFlop/s) — or trillions of calculations per second.

Coming in at No. 2 is a brand-new installation of the same type of IBM system, albeit a newer version. It is a Blue Gene/P system installed in Germany at the Forschungszentrum Juelich (FZJ) and it achieved performance of 167.3 TFlop/s.

It’s not before No. 3 in the TOP500 list that you find a non-IBM system. That honor is reserved for the New Mexico Computing Applications Center (NMCAC), which has a Silicon Graphics Inc. (SGI) system built on the Altix ICE 8200 model that posted a speed of 126.9 TFlop/s.

In the latest list, IBM regained a solid lead in the total number of systems with 232 (46.4%) over Hewlett-Packard (HP) with 166 systems (33.2%).

Amazon Elastic Compute Cloud(EC2), a web service that provides resizable compute capacity in the “cloud,” went down Saturday and a bunch of customers lost their application data. We saw this info in Data Center Knowledge and thought it was interesting enough to post here.

Amazon EC2 is basically a virtual data center that allows developers to increase or decrease capacity — from one to even thousands of server instances simultaneously — within moments.

Using Xen Virtualization, each virtual machine is the “equivalent of a system with a 1.7Ghz x86 processor, 1.75GB of RAM, 160GB of local disk, and 250Mb/s of network bandwidth.”

The incident understandably ticked off EC2 users who lost their data, but it doesn’t look like they have much recourse, since this service is still considered beta and lacks service level agreements.

The outage signals a serious need for backup.

One user, Reuven, posted a comment saying, “To be blunt, this scares the hell out of me. What kind of redundancy does the current EC2 API have to avoid this from happening again? Does EC2 practice what it preaches and use SQS or some other queue service?”
This incident is considered by Amazon as growing pains of EC2 service, which is about a year old now.

Not too long ago I wrote a blog about Sun’s CIO saying the days corporate owned and operated data centers will be a thing of the past by 2015.

But virtualization/ cloud computing issues like this do nothing to win the confidence of conservative data center managers who likely sigh a collective “I told you so” from the safety of their brick and mortar facilities full of physical machines and back up.

Windows introduced its first operating system for high performance computing clusters last year, and its already achieved two spots on the Top 500 Supercomputers List.

Windows Compute Cluster Server 2003 appeared on the computing industry’s semiannual top 500 list of the world’s most powerful supercomputers this week.

The operating system served on a new HPC cluster at Mitsubishi UFJ Securities of  Japan, which placed at 193 on the list

The top 500 benchmark was run on a 448-node IBM BladeCenter HS21 cluster with 1,760 processors. The benchmark result was 6.52 trillion computations per second (teraflops).

Windows also served as operating system for a new HPC cluster at Microsoft’s datacenter in Tukwila, Wash., which ranked 106 in the top 500. This system achieved 8.99 teraflops on 256 compute nodes and 2,048 processing cores of 64-bit Intel Xeon 5300 quad-core processors, powering Dell blade servers.  

I spoke with Microsoft this week for a story on their emergence into the high performance computing market, and they were pretty psyched about making this list.

Look out Linux.

IBM announced today the availability of Windows Compute Cluster Server 2003 for the IBM System Cluster 1350, giving mid-market and enterprise clients a familiar operating system to work with in additional to Linux.

IBM also announced today expanded server, storage and networking options for clusters.

High performance computing clusters can range from a few up to thousands of servers woven together to deliver high-speed performance.

The clustered system is also designed to leverage Novell SUSE Linux Enterprise Server (SLES), and now supports the SLES10 operating system.

To read more, go to IBM’s press room.