Fat, fatter, fattest: Microsoft's kings of bloat
Our tests show that Windows Vista and Office 2007 not only smash Redmond's previous records for weight gain, but given the same hardware diet, run at less than half the speed of generation XP
Let's start with the memory footprint. The average combined working set for Word, Excel, and PowerPoint 2007 when running the OfficeBench test script is 109MB. By contrast, Office 2000 consumed a paltry 9MB, which translates into a 12-fold increase in memory consumption (170 percent per year since 2000!). To be fair, previous builds of Office benefited from a peculiar behavior common to all pre-Office 12 versions: When minimized to the task bar, each Office application would release much of its noncritical working set memory. This resulted in a much smaller memory footprint, as measured by the Windows performance counters (which are employed by the DMS Clarity Tracker Agent used in my tests).
Microsoft has discontinued this practice with Office 2007, resulting in much higher average working set results. However, even factoring in this behavioral change, the working set for Office 2007 is truly massive. Combined with an average boot-time image of more than 500MB for even the minimal Windows Vista code base, it seems clear that any system configuration that specifies less than 1GB of RAM is a nonstarter with this version. And none of the above explains the significantly higher CPU demands of Office 2007, which are nearly double that of Office 2003 (peak utilization of 73 percent versus 39 percent). Likewise, the number of execution threads spawned by Office 2007 (32) is up, as is the total thread count for the entire software stack, which is nearly double the previous version (615 versus 370). View the overall test results. View more detailed test results at xpnet.com. Compare memory consumption.
Clearly, this latest generation of the Windows/Office desktop stack was designed with the next generation of hardware in mind. And in keeping with the TGMLC pattern, today's latest and greatest hardware is indeed up to the challenge. Dual cores, combined with 4MB or more of L2 cache, have helped to sop up the nearly doubled thread count, while 2GB standard RAM configurations are mitigating the nearly 1GB memory footprint of Vista and Office 2007.
The net result is that, surprise, Vista and Office 2007 on today’s state-of-the-art hardware delivers throughput that's still only 22 percent slower than Windows XP and Office 2003 on the previous generation of state-of-the-art hardware. In other words, the hardware gets faster, the code base gets fatter, and the user experience, as measured in terms of application response times and overall execution throughput, remains relatively intact. The Great Moore's Law Compensator is vindicated.
Give and take
The conventional wisdom regarding PC evolution, that Microsoft devours every Intel advance, continues to hold true right up through the current generation of Windows Vista and Office 2007. What's shocking, however, is the way that the IT community as a whole has grown to accept the status quo. There is a sense of inevitability attached to the concept of the Wintel duopoly, a feeling that the upgrade treadmill has become a part of the industry's DNA. Forces that challenge the status quo – such as Linux, Google, and Apple – are seen as working against the very fabric of the computing landscape.
But as Microsoft is learning, you can only push your customers so far before they push back. In the case of Windows Vista, the combination of heavy hardware requirements and few tangible benefits to IT has resulted in a mass rejection of Microsoft’s latest and greatest. Companies are finally saying enough is enough and stepping off the treadmill, at least for a while. Microsoft’s challenge will be to woo these customers back, and they can start by taking a hard look at their OS and application development practices. Instead of targeting the next generation of hardware, Microsoft engineers should try making sure that their new features and functions work well on the hardware of today, thus guaranteeing that they won’t overshoot their target and disrupt the fragile TGMLC balance. Maybe then customers will start looking forward to upgrading for a change.