There are public clouds like Amazon’s EC2, and private clouds run by many large institutions that exist behind firewalls, but some networking and storage experts believe that the big opportunity for infrastructure companies and service providers in the future will be in finding ways of blending the private and public, or creating bridges between the two. As Michael Crandell, CEO of RightScale, told the GigaOM Structure conference, there are already hybrids in existence, to the extent that some companies have some of their operations in clouds outside the corporate firewall, but others that are in private clouds within the enterprise. What needs to be further developed now, he said, are ways of helping those two things work together so that companies can take advantage of both.

EMC vice-president Tom Roloff said that a lot of large companies have started to see the benefits of cloud computing, and so are experimenting with private clouds internally, but will likely expand beyond those to use public clouds as well once they get comfortable with them. “It’s a multiyear journey in some cases,” he said. “I think we have a ways to go.” Roloff said that in the future he expects there will be hundreds of public clouds, but also tens of thousands of private clouds.

What’s happening in many cases, said Terremark’s manager of cloud services, Randy Rowland, is that a lot of Fortune 1,000 companies are using cloud services of some kind “but it didn’t come in through IT.” Instead, it started with a business unit or application developers, and then the IT department had to take over and decide to shut it down or find a way to manage it. “I think that’s where a lot of the growth for cloud computing is going to come from,” he said, when companies decide to manage the cloud services they find parts of their business using, and start to see the benefits.

Marten Mickos, CEO of Eucalyptus Systems, said he hopes that the industry will begin to develop common APIs that work across both public and private clouds and allow applications developers to make use of both seamlessly, and that he believes Amazon’s API could become the basis of such a standard, in the same way that IBM’s personal computer became the standard that allowed the PC industry to grow. “We think Amazon is an absolutely dominant player,” he said. Other panelists disagreed, however, saying they hoped there would be competing providers rather than a single standard.

http://cdn.livestream.com/grid/LSPlayer.swf?channel=gigaomtv&clip=pla_7a8babfe-7b50-472e-bbb8-1619d153ada4&autoPlay=false&mute=false

The growth in bandwidth and cloud computing makes it easier to handle the massive amounts of data that the world is producing every day, but latency — the lag in transferring that information across large networks — is still an issue, networking experts told attendees at the GigaOM Structure conference today. The best way to deal with that latency problem was the subject of some debate on a panel on the topic, which was made up of representatives from Cisco and several other networking technology companies.

Mark Day, chief scientist at Riverbed Technology, said that as cloud computing becomes more widespread, companies and application developers have to think about the implications of no longer having a physical box that they use on their premises, but instead have software that interacts with the network, or virtual appliances somewhere in the cloud. All of this can add complexity for companies when trying to develop applications or services.

Optimization of the network to deal with the latency this introduces is something that will simply be expected, said Baruch Deutsch, director of product marketing for Cisco. There are various ways of handling that, through caching, compression and so on, but the networking equipment company’s view is that the best way is to “integrate that service as tightly as possible into devices that exist already,” such as the router, he said. Kenneth Duda, a vice-president at Arista Networks, agreed that virtualization provides the ability to get beyond hardware appliances when it comes to network optimization.

Michelle Munson, co-founder and president of Aspera, said that the biggest networking issue — particularly in the life sciences field and research areas such as genomics — is the enormous amounts of data that are produced, and how to move those massive amounts of data around efficiently. She said the best solution is to “build it directly into the applications themselves,” which is what Aspera does. But Deutsch argued that app developers shouldn’t have to worry about dealing with latency. “The ability to handle that optimization should be something the underlying network should provide as a service to you,” he said.

The bottom line, the Cisco executive said, is: “Latency is not going away until someone proves the theory of relativity incorrect.”

http://cdn.livestream.com/grid/LSPlayer.swf?channel=gigaomtv&clip=pla_09678794-0af3-432d-956f-c07cc625d0ce&autoPlay=false&mute=false

Supercomputer experts, including the chief information officer of NASA’s Ames Research Center and a computer strategist for the U.S. Army’s research and development center, said at the GigaOM Network’s Structure conference today that scientists are still working towards developing an “exascale” computer — that is, one that can do a million trillion calculations per second — to try and keep up with the flood of data that the world is producing every day, which continues to increase at exponential rates.

Chris Kemp, the chief information officer at Ames, said that the space program is also facing a storage issue that he called “the exabyte problem” when it comes to storing and processing the massive amounts of data it produces every day. “From Mars, we have Google Earth-resolution images coming down, and there are telescopes that generate an exabyte of data a day,” he said. “It gets to the point where you are forced to throw away data because you literally can’t store it all.”

But it’s not just NASA: Jason Hoffman, the chief technology officer of Joyent, noted that Apple recently announced it has sold 3 million iPads, “which means that they have basically shipped 100 petabytes of distributed storage in a matter of months.” When it comes to developing computers that can handle the processing of those kinds of data, however, science is running up against energy and cost issues, said John West, special assistant for computation strategy with the U.S. Army Engineer Research and Development Center.

The No. 1 supercomputing system today, he said, is the “Jaguar” system being used by the Oakridge National Laboratory of the Department of Energy to do climate modeling and other research. It can do 1.8 petaflops in terms of calculation ability, but it also sucks up about 7 megawatts of power to run, he said, and “these are $500-$100 million computers.” The Army scientist said that if you tried to get to exascale-level computing just by adding more processors, “you would be looking at 4 gigawatts of power and 125 million cores. We really can’t do this today.”

Chris Kemp also noted that having this much computing power has other impacts on storage and memory and other parts of a computer as well. “When you’re talking about that number of processors writing to memory, or writing to cache or writing to disk, it’s like the difference between driving across the street to Starbucks vs. going to the moon or going to Pluto in terms of the time it takes.”

http://cdn.livestream.com/grid/LSPlayer.swf?channel=gigaomtv&clip=pla_e91cb54d-d725-4a09-9cbb-7fa4a7cbc51a&autoPlay=false&mute=false