July 12, 2012
The Uptime Institute has released its second annual datacenter survey. While more than 2,000 industry professionals including vendors, consultants and users took part, the analysis was based on a pool of 1,100 owners and operators. The data provide insight regarding infrastructure deployment and practices, and while a number of long-held observations regarding cloud computing still apply, there were also a few surprises.
On the positive end, despite economic woes, 55 percent of datacenter operators claimed a budget increase over last year. This continues a trend of annually growing funds for datacenters. The biggest boon was reported in Asia, where 55 percent of respondents claimed budgets increasing more than 10 percent for the upcoming year.
Unfortunately, the added resources have struggled to keep pace with demand. 80 percent of those surveyed have built or upgraded a datacenter within the past five years. While that growth has expanded capacity, 30 percent of respondents still expect to run out of power, cooling, space or network bandwidth by the end of this year. In Asia, 86 percent of professionals surveyed have recently built a new datacenter, but 35 percent are experiencing capacity limitations.
This seemingly untenable situation has led some operators to question the strategy of relying solely on datacenter expansions to address capacity woes. 10 percent fewer respondents plan to build a new datacenter compared with last year's report. And while the authors hesitated to suggest a direct correlation, 10 percent more operators plan to migrate workloads to cloud services.
Cloud technologies have become an attractive alternative to ever-growing private datacenter infrastructures, receiving far more attention recently. This year, 25 percent of those surveyed use public cloud services, up from 16 percent the previous year. While 49 percent are deploying private clouds, up from 35 percent last year.
The survey results match up with similar findings by ChangeWave Research. In 2010, the firm counted 11 percent public cloud adoption in 2010 compared with 30 percent in 2012.
There are a few interesting takeaways regarding the shift to cloud services. Geographically, Asia claims the highest public cloud adoption, but lags behind in private cloud deployments. Also, the size of a company seems to have an effect on cloud strategies. Large companies appeared more open to migrate workloads to cloud infrastructures.
The picture isn't all rosy, though, when tech providers were removed from the data, traditional enterprises still seemed rather timid regarding cloud services. The survey authors write:
This provides a reality check of sorts – apart from technology companies who are arguably eating their own dog food, the survey indicates that the broader market is less sanguine about cloud and modular data center technologies.
A number of common reservations were confirmed when respondents were asked about barriers to adoption. Security, compliance and reliability were among concerns mentioned. The survey authors explained that while the potential of saving capital by moving to the cloud is an attractive option, ultimately IT professionals may be responsible for malfunctions outside of their control. For example, if a company was running virtualized desktops via Amazon's elastic cloud, downtime in their availability zone could lead to a loss of productivity.
As cloud services continue to mature, these sticking points will most likely be addressed, leading to further adoption of the technology.
The report is available for download (with registration) at http://uptimeinstitute.com/2012-survey-results.
The ever-growing complexity of scientific and engineering problems continues to pose new computational challenges. Thus, we present a novel federation model that enables end-users with the ability to aggregate heterogeneous resource scale problems. The feasibility of this federation model has been proven, in the context of the UberCloud HPC Experiment, by gathering the most comprehensive information to date on the effects of pillars on microfluid channel flow.
Large-scale, worldwide scientific initiatives rely on some cloud-based system to both coordinate efforts and manage computational efforts at peak times that cannot be contained within the combined in-house HPC resources. Last week at Google I/O, Brookhaven National Lab’s Sergey Panitkin discussed the role of the Google Compute Engine in providing computational support to ATLAS, a detector of high-energy particles at the Large Hadron Collider (LHC).
Frank Ding, engineering analysis & technical computing manager at Simpson Strong-Tie, discussed the advantages of utilizing the cloud for occasional scientific computing, identified the obstacles to doing so, and proposed workarounds to some of those obstacles.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.