Grid computing. Cloud computing. Are there any IT paradigms that have garnered more hype and more skepticism without most people even knowing what they mean? Probably not, but maybe that is because the terms themselves have no real meanings to most IT consumers, just connotations.
And connotations can be scary. Burned to some degree by the existing confusion surrounding grid computing, many grid vendors have drastically cut the term from their marketing strategies. Learning from what might be perceived as mistakes, these vendors are not so quick to latch onto cloud computing. However, many of their new directions could easily fall under the cloud umbrella, and those in the know readily acknowledge that grid technologies underlie the cloud.
So, what’s a middleware vendor to do?
Within the Data Center Business Division at Univa UD, messaging around grid computing has been all but eliminated as the division attempts to build traction for its Reliance datacenter orchestration product (from which the company also has nixed the Grid MP middleware component). What division general manager Alex Brown calls the “traffic cop or brains of the operation,” Reliance combines application awareness, closed-loop orchestration and SLA automation to deliver optimal application performance, and Univa UD customers and prospects view it as a key part of their cloud or utility infrastructures.
Although no one is talking about grid computing, Univa UD’s Gordon Jackson says the company’s experiences with grid and large-scale distributing processing management feed directly into its success with Reliance, especially as it relates to resource management and distribution. Jackson is the technical director of the Data Center Business Division former virtualization evangelist at DataSynapse.
Brown agrees that a real cloud-like solution requires a significant understanding of grid concepts. “However, because people thought of grid as so specialized, it got a lot of baggage,” he explains. “So while a lot of the core technology is very relevant, a lot of the terminology and a lot of the old processes are not. In fact, they hinder the adoption of the technology for cloud.”
Ivan Casanova, vice president of product marketing at the aforementioned DataSynapse sees a connection, too, calling grid computing the starting point for cloud computing — “a proof point for shared and dynamic infrastructure.” A big part of cloud computing is the ability to scale based on demand, and grid computing middleware is a great method for doing so, he says. (Casanova also notes that SOA is the architectural model for cloud computing, and DataSynapse has customers deploying SOAs and using the company’s GridServer product to scale those services.)
On the data grid front, Oracle’s Cameron Purdy, vice president of Fusion Middleware, says, “Data grid technology … is almost essential in any transactional processing or other data-intensive system that would be deployed into a cloud environment. I can’t imagine how you would run a data-intensive application across any number of servers in that type of environment without the ability to share and coordinate access to and operate and react to changes and events occurring to that information.”
According to Platform Computing Chairman and CEO Songnian Zhou, his customers definitely see the grid-cloud connection as they move from HPC-focused enterprise grids to general-purpose, often virtualized, shared-services platforms. “They may not call it cloud, they may not call it on-demand datacenter, but they clearly are doing it,” he says.
The transition from grid to cloud, at least internally, Zhou says, is really a matter of evolution: the architectures and goals are the same, but the scope is different. As users move from HPC workloads to more generic workloads, they add components like J2EE middleware and hypervisors to enable more dynamic applications and increase mobility. “The tools and containers need to be brought to the plate, but [in terms of] fundamental architecture and approach, I don’t see much of a difference between grid and the cloud or on-demand or dynamic datacenter,” he says. “It’s a continuous evolution and expansion … away from the siloed client servers.”
Univa UD’s Jackson also sees this move happening. Even in HPC, he believes, grid is ripe to become a platform for serving multiple applications and classes of users. “[A]s soon as you start applying the intelligence to differentiate between the platinum customer and the bronze customer, or the applications … and services I need to execute on behalf of those customers, then I think you’ve taken your grid and you’ve turned it into a utility infrastructure,” he says. Moving discrete grids into one big, intelligent resource pool means the most bang for the buck for the corporation, he added.
Paul Strong, distinguished engineer at eBay Research Labs and active Open Grid Forum participant, isn’t even sure we should draw the distinction between so-called internal clouds and service-oriented grids. In either case, users are leveraging shared infrastructures and virtualization to achieve high utilization and application flexibility based on changes in workloads and business needs. Essentially, Strong says, users are solving the same problems with the same core technologies.
This is true even for eBay’s infrastructure, which Strong has explained as a grid for years. There are many “cloudy” aspects to eBay’s infrastructure, he says, including a heavily virtualized database architecture to allow for massive scalability, and global service delivery backed up by SLAs, continuous availability and security. “By some definition of the word,” he acknowledges, “I would say we’ve been doing aspects of cloud computing for a while.”
There are, however, differences between the grid and the cloud, especially, but not exclusively, where external cloud services are involved. Univa UD’s Brown makes a marked distinction between the two paradigms. For him, grid computing (on the enterprise front, at least) takes place inside the firewall. Apparently, Univa UD also notices grid computing’s HPC connotation, as the company has moved its Grid MP middleware to its HPC division, leaving (as noted above) the datacenter division to focus on Reliance and its automation capabilities.
A similar mindset seems to be present at Platform. Although not formally in place, Zhou says the company is moving toward two distinct foci — HPC and the datacenter. Regardless of the technological similarities, customers see grid computing being part of the former and cloud computing (to whatever degree the term arises) being part of the latter. As the datacenter division takes shape, Zhou says, “We will not emphasize grid much because for datacenters, I think, grid is foreign. It has too much connotation, it is tainted from the HPC or research and government space, and it’s too complex.”
At DataSynapse, the difference is very application-focused. Casanova believes grid addresses a specific class of applications, which have been successfully optimized using the company’s GridServer product. When customers wanted to run a more general class of applications on a shared, dynamic infrastructure, the result was DataSynapse’s FabricServer product. Going forward, both are part of the company’s greater application-focused cloud-like strategy.
“I don’t think people started out envisioning grid computing to be this seamless model where all these enterprise services or different types of applications were running in a cloud, they were universally accessible, they were technology-agnostic,” says Casanova. “I think they started that conversation around ‘I really need to scale up this application from a performance perspective, and I want to leverage commodity hardware and systems I already own to help me [experience] an order of magnitude improvement [in how] this important application executes.'” The cloud movement inside organizations, he adds, really has been driven by what they see Internet companies like Amazon doing with their infrastructures.
Further illustrating the fundamental differences between the paradigms, Casanova cites capabilities that must be added to grid solutions if they are to be repackaged and sold as cloud solutions: automated provisioning, horizontal scalability and visibility into utilization. For corporate users, he says, utilization insight helps them define policies to further automate and maximize resource usage. For cloud service providers, he says, usage data becomes the foundation for their chargeback models.
eBay’s Strong views grids and external clouds “less in terms of technology and more in terms of the way we think differently about business.” With cloud computing, he says, all a company needs to do is codify its one differentiating idea. The company can obtain everything else — infrastructure, non-critical business services, etc. — from the cloud.
Grid computing, Strong explains, was about building and optimizing infrastructure to run certain types of workloads. Cloud computing complements and advances that notion, but also helps companies move away from the “nitty-gritty” aspects, he says. It’s more about flexibly delivering services within an organization (internal cloud) or flexibly receiving commodity services (external cloud). “I think clouds take us to that next conceptual step of moving beyond … the weeds, where a lot of the grid work was, to [asking] ‘How do we move this closer to the business and deliver the right value for the business?'” Strong says. “The set of underlying technologies are, in essence, the same, but the discussion has changed.”
Up next: The second half of our look at the nexus of grid computing and cloud computing will focus on the future dynamic datacenter-oriented strategies of these old-guard grid computing vendors. We’ll look at how, if at all, they plan to leverage cloud computing hype as a marketing term, and how the idea of cloud computing actually relates to what they’re doing.