InfoWorld: WinXP much slower than Win2K

— 5:40 PM on November 1, 2001

InfoWorld has taken a long look at Microsoft's XP (both the OS and Office), from a business standpoint. (Thanks to missense for the tip.) They asked, "How fast is the new software compared to the previous generation?" and paid particular attention to multitasking. And they made graphs.

They didn't like what they found. WinXP ran much slower than Windows 2000, even when they turned off much of the eye candy on both (the default XP interface is a bit processor-hungry all by itself, and even W2K's will chew through some cycles):

Our tests of the multitasking capabilities of Windows XP and Windows 2000 demonstrated that under the same heavy load on identical hardware, Windows 2000 significantly outperformed Windows XP. In the most extreme scenario, our Windows XP system took nearly twice as long to complete a workload as did the Windows 2000 client...

Except for a few instances, Windows XP increasingly ate the dust of Windows 2000 as load ramped up, regardless of machine specs or Office version...

Overall we are quite disappointed with Windows XP's ability to pull serious weight when compared to Windows 2000.

They paired Office in both generations with the OSes and it got even worse:
Finally, our cross-generational testing, which measured the performance of Windows XP and Office XP directly against that of Windows 2000 and Office 2000, found that once again, newer means slower. In every one of our scenarios the combination of Windows XP and Office XP took noticeably longer—from 35 percent to 68 percent longer—to complete the script than Windows 2000 and Office 2000.
Then comes the interesting part: they recommend SMP machines for XP!
Our testing also suggests that companies determined to deploy Windows XP should consider ordering desktop systems with dual CPUs to get the most out of the new OS...

Our tests on a dual-CPU system indicate that both Windows XP and Windows 2000 run better on an SMP (symmetric multiprocessing) configuration with relatively slow CPUs than on a single-CPU system with a screamingly fast processor. As we added more and more load, the benefits of a dual-processor configuration became more apparent. Both OSes (using Office 2000 and optimized UIs) handled the heaviest workload (scenario 3) nearly 40 percent faster on the SMP client machine [a dual 1GHz PIII] than on the [1.5GHz] single-CPU Pentium 4.

This actually doesn't surprise me. I've been an SMP advocate for a long time, for exactly the reasons they've given. But SMP in the office is not at all common, and it's an indication of how big a performance hit XP actually delivers that they suggest it at all.

Microsoft claims they can't reproduce the InfoWorld results, but InfoWorld's standing by their tests until and unless Microsoft can supply a better explanation or identify major flaws in their tests. They end up their review by saying...

until 2GHz desktop PCs become commonplace, we have a hard time recommending widespread adoption of Windows XP at all. Granted, it appears that for light-duty service on the newest hardware, Windows XP with Office XP is an acceptable choice—if an 11 percent performance hit, or 53 minutes added to an 8-hour day, is acceptable. But beware of this combination in more demanding environments, whether the workload is greater or the equipment is older.

Shops lured by XP features should weigh their options carefully. In many cases, these features may not be compelling enough to justify saddling your end-users with a slower OS. Although differences between Windows XP and Windows 2000 can be measured in seconds, what business can afford to put a 20 percent or greater bite on worker productivity?

It's a pretty damning indictment: I know from my years in corporate management that much smaller inefficiencies have halted upgrades. And that's without considering Microsoft's new licensing arrangements. Has Microsoft finally gone too far?
Tip: You can use the A/Z keys to walk threads.
View options

This discussion is now closed.