I/O

Virtualization emerged as an area of interest in IT earlier this decade and is now unarguably one of the hottest trends in IT at the moment.  Prior posts explored the technical details of how processor virtualization and I/O virtualization function.  But what are the uses of virtualization that are driving all this attention and interest from IT, vendors and the press? 

The most important use today for virtualization is server consolidation.  During the late 1990’s and early part of this decade, small rack-mounted x86 servers proliferated rapidly.  In part, this was due to the low cost of x86 servers using Linux or Windows, compared to their UNIX predecessors.  But this was also driven by the flakiness of the software stacks on those same servers.  The software and operating systems were not nearly as robust as they are today and it was problematic enough that a lot of IT staff considered isolating applications from one another a best practice – even if it lead to low utilization.  There were plenty of peculiar bugs that resulted from a combination of corner cases in the OS and different software packages and using a server dedicated to a specific application avoids that problem entirely.

The proliferation of small, underutilized servers was slowed down by the dot-com bust in 2001, but also by constraints on data center space, cooling and power.  Cooling and power were particularly sensitive, because while Moore’s Law means that you can get more computing power in a chip over time – it also means that the power density (whether it is W/cm² or W/cm³) increases substantially.  So a data center designed for 1995 servers is wholly inadequate for those in 2003.  Worse yet, data centers are incredibly expensive to build or redesign – for many companies there is a bit of pain as your data center approaches 80% capacity and the cooling or power system gets stretched.  But typically, building another data center is far too painful and expensive to be an acceptable solution. Read More »

In my earlier post, I discussed some of the main concepts, challenges and techniques that are essential for virtualizing a CPU or instruction set.  To a large degree, these concepts and techniques are not new – they are really just variations on a theme that has been around for a long time in computer science.  Virtualization is fundamentally about preserving the appearance of isolating resources, while actually sharing the resources harmoniously and efficiently.  Perhaps the most obvious example was virtual memory – I can still remember being excited about virtual memory when I upgraded to System 7 on an Apple Quadra!  Tricks with virtual memory would let you run applications without buying new RAM (although the loading performance was often horrible as a result…at least it ran).

 

One of the most difficult and complicated areas of a modern PC is the I/O architecture.  The I/O architecture governs how the processor and memory talk to the devices that make a computer interesting – keyboards, mice, network cards, GPUs and hard drives.  It’s essential to remember that I/O is really a first class priority of a computer, because as a CPU architect, I/O moves at a glacial speed. 

 

Modern CPUs operate at around 3GHz, so a single cycle is only 0.33ns.  In comparison, reading data from a disk takes around 5ms – or 15 million cycles!  The engineering maxim of ‘make the common case fast, and the uncommon case correct’ is sometimes erroneously simplified into ‘ignore the uncommon case’ – and when I/O only happens every 15 million cycles, it’s pretty uncommon. Read More »