In my previous article, I introduced the idea of data locality in HCI. I also explored some basic math that illustrates the impact of scaling an HCI cluster. I compared a cluster without data locality to a cluster that does have locality. Today, I want to look at what happens when we need more than two copies of data, as well as to examine the impact of IO size on the storage network. My third article in this series will discuss the causes and effects of incomplete data locality, and it will also present a special case of data locality.
End User Computing
End User Computing (EUC) is the emperor’s new clothes. It is the new nomenclature for what used to be termed “VDI” (virtual desktop infrastructure). It is, however, much more, encompassing all aspects of desktop and endpoint management: (Read More)
- Application Virtualization: The art of abstracting the application and its presence from the desktop, making it truly mobile across locations and devices
- Personalization Virtualization: The art of abstracting the user and their presence from the desktop
- Presentation Virtualization: An application delivery method that delivers desktops or applications from a shared server
- Desktop Virtualization: The art of delivering a full desktop experience remotely
- Endpoint Management: The art of managing and securing access to data
- Application Layering: “on-demand” application delivery from a single image
End User Computing is an important overarching paradigm for companies that wish to ensure that users get a consistent experience and consistent access to information across multiple devices—for example, desktop computers, laptops, notebooks, tablets, and phones—and across disparate operating systems like Windows, Linux, iOS, and Android.
Major areas of focus include barriers to adoption, progress on the part of End User Computing vendors in alleviating those barriers, and management of the transition from a static desktop to the mobile martini world of “anyplace, anytime, anywhere, on any device.”
When VDI and DaaS were first introduced, many claims were made for their superiority over distributed desktops. They were cheaper, faster, more secure, easier to manage, etc. At the time, with few exceptions, these claims were no more than fantasy. Over the last few years, though, sufficient improvements in the core platforms and underlying infrastructure have brought some truth to most of these claims. Management tools have improved beyond measure. High-performance converged infrastructure appliances can deliver performance as good as or better than even that of the fastest desktops, and they do so at a cost that is less than that of a managed, enterprise-class desktop PC.
Thursday marked the closing of the 20th BriForum conference in Boston, Massachusetts, and the end of an era. As the largest independent virtualization industry conference, it’s a place where geeks explain how products really work (or don’t) and where unfiltered side-by-side comparisons are the norm.
One of the trends in virtual desktops is Desktop as a Service (DaaS). The premise here is that a cloud provider can run a massive multi-tenant VDI environment well, better than most medium organizations can run their VDI on-premises. The medium or smaller organizations just rent the desktops they need. The assumption here is that desktops are a commodity and any desktop anywhere is just fine. The problem comes with those DaaS desktops accessing data—in particular, desktops at a cloud provider accessing data inside the client’s network. The desktop may run just fine, but if every application accessing corporate data slows to a crawl, there won’t be many happy users.