December 17, 2007
The customary thing to do in the last issue of the year is to take a look back, revisiting the top stories, analyzing how they shaped our remembrance of the year, and even ranking them in order of importance. I, however, will do none of those things, because if there is one thing I learned in 2007, it's that there is no looking back in the world of grid computing.
While grid computing still exists in its traditional sense, with grid middleware seeing regular improvement and adoption on the rise in organizations with heavy computational needs, it is the derivations of the grid architecture that really seem to be driving the industry into the future. For example, while anyone reading GRIDtoday on a regular basis likely was familiar with the emergence of grid-based application platforms, application fabrics and application virtualization heading into 2007, I feel like the vendors of the solutions (e.g., Appistry, GigaSpaces, DataSynapse, etc.) gained a lot of traction over the year and really made an impression in the overall IT market -- especially as it relates to heavy transaction-processing environments. Distributed caching, too, was establishing itself among forward-thinking users when Oracle snatched up Tangosol and took distributed data into the mainstream.
Taking it a step further, we even saw some start-ups and previously anonymous companies such as Evergrid and Cassatt offer their owns spins on the distributed architecture, viewing resources as virtualized pools and offering advanced power management capabilities for which most end-users aren't even prepared. And while all of this certainly is cutting-edge, these companies and their peers barely got to start spreading their messages when their technologies were swallowed up by the seemingly unstoppable wave that is being marketed as cloud computing. It all started when Google and IBM announced their project to take Web-scale computing to our universities, and has, in short order, been followed by a similar project from Yahoo, as well as the announcement of IBM's line of Blue Cloud solutions.
Which brings us to this week's issue and the realization that in our quest to keep looking forward, we might occasionally need to focus a few feet ahead of us rather than gazing steadily at the horizon. Cloud computing is a fascinating notion, no doubt, and when it is viable for run-of-the-mill organizations to be able to manage global sets of resources as a virtualized cloud, or fabric, we truly will have witnessed a computing revolution. The levels of flexibility and availability made possible by well-engineered cloud solutions could make current utility solutions look primordial by comparison. However, we're not there yet.
In speaking with IBM, I learned that its first Blue Cloud solution will be in the form of a virtualized BladeCenter, which will allow users to manage a cloud of resources, alright, but definitely not on the global scale with which all want to attach with cloud computing right now. Even optimistic analysts put this distributed vision several years out, and IBM is mum on when we can expect to see Blue Cloud realize its ultimate goal. So, as we head into 2008, hopefully we can look at cloud computing in a more realistic light -- at least until our attention is captured by the next "next big thing."
Of course, not all innovation is being done up in the stratosphere. Somewhere between "traditional" grid computing and cloud computing is gridGISTICS, a company that has merged grid, service virtualization and SOA into its flagship Aware Server solution. Designed to allow companies to tackle business problems previously thought untouchable, Aware Server, according to the gridGISTICS, simplifies the creation of highly distributed, highly scalable applications so organization can focus on their business needs rather than IT needs. We were able to speak with several members of the management team, who offer a variety of viewpoints on what they believe makes Aware Server so unique, so be sure to give this feature interview a read.
As usual, there also are quite a few big announcements this week, including: “Customers Modernize Legacy Environments w/ Oracle, HP”; “CERN Director General Reports on LHC Progress”; “DEISA, GridAustralia Interoperate for HIV Drug Simulations”; “xkoto Upgrades GRIDSCALE Data Virtualization Solution”; “SAP Supports VMware ESX for Production Environments”; “Microsoft Unveils Hyper-V Public Beta”; “VMware Improves Automation in Infrastructure 3 Update”; “3PAR 3cV a 'Blueprint for the Virtual Datacenter’”; “Yahoo! Becomes Apache Platinum Sponsor”; and “Virtualization, Automation Among Trends to Watch in 2008.”
In closing, I just want to wish all of our readers a safe and happy holiday season. We will resume publishing on Jan. 7 with a look at data virtualization provider Xkoto, and will look to continue improving our coverage of the on-demand, distributed ecosystem in the year to come.
Comments about GRIDtoday are welcomed and encouraged. Write to me, Derrick Harris, at firstname.lastname@example.org.
Posted by Derrick Harris - December 17, 2007 @ 11:02 AM, Pacific Standard Time
Derrick Harris is the Editor of On-Demand Enterprise
No Recent Blog Comments
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?