Another take on Vista vs. XP benchmarks

Another take on Vista vs. XP benchmarks

Summary: When I read my colleague Adrian Kingsley-Hughes’ epic account of his benchmark tests of Windows Vista SP1 versus Windows XP SP2, the first thing that struck me was how far apart his numbers were from those I was seeing. In fact, I went back and redid all my tests to confirm that I hadn’t missed anything along the way. They checked out completely. On my test bed, with only one exception, Vista SP1 was consistently as fast as or faster than XP SP2. Why the difference? I have a few theories.


As anyone who’s ever worked in a PC performance lab knows, the #1 rule of benchmarking is: Your mileage may vary.

I remembered that rule when I read my colleague Adrian Kingsley-Hughes’ epic account of his benchmark tests of Windows Vista SP1 versus Windows XP SP2 (Part 1 and Part 2). The first thing that struck me was how far apart his numbers were from those I was getting. In fact, I went back and redid all my tests to confirm that I hadn’t missed anything along the way. They checked out completely. On my test bed, with only one exception, Vista SP1 was consistently as fast as or faster than XP SP2, a result markedly at odds with Adrian’s findings.

I have no doubt that Adrian's tests and timings were accurate, just as mine were. So what’s the difference?

For starters, our test beds were very different:

  • Adrian chose a desktop system with a first-generation Intel dual-core processor, the 3.4 GHz Pentium 950D. I chose a Dell Inspiron 6400 notebook with an Intel T2050 1.6 GHz Core 2 Duo processor. (I bought this system in December 2006, a few weeks after Vista was released to business customers. It originally came with XP SP2 installed on it, and I upgraded the system to Vista almost immediately.)
  • I chose to use a dual-boot configuration, designing my tests carefully so that file copy operations with each OS were done between the same source and destination volumes to minimize the effects of disk geometry on performance. Adrian used separate hard drives for each OS and each file copy operation.
  • I used a wireless 802.11g network connection. Adrian used wired Gigabit Ethernet connections.
  • Neither of us performed any special optimizations to either configuration except to ensure that drives were defragmented.

For my test files, I chose the same two groups of files I had used in previous rounds of performance testing last year. The first consisted of two large ISO files, each containing the contents of a ready-to-burn DVD, with a total size of 4.2 GB. The second group is a collection of music files, just over 1 GB in size, consisting of 272 MP3 files in 16 folders.

As it turns out, the test bed I chose is one that matches nicely with a lot of real world business-class systems. Notebooks represent the majority of the PC market these days, and the 802.11g connection in this one is by far the most popular networking option on portable PCs. From a performance standpoint, it's neither a speed demon nor a slug. More importantly, this system's specs match those that Microsoft's engineers had in mind when they reengineered the file copy engine with Vista RTM and then with SP1. As Mark Russinovich notes in his detailed description of these changes, copies over high-latency networks such as WLANs are especially likely to benefit from the changes in Vista.

I ran each test multiple times and took the average of at least three tests. The graphs shown here are normalized, with Windows XP SP2 set to 100 and the results for Vista SP1 and Vista RTM charted proportionally.

Next -->

As you can see, several file operations were essentially identical between Vista SP1 and XP SP2 (other scenarios I tested but didn't chart, such as a copy from a local hard disk to an external USB drive, showed the same identical results). My numbers matched up with Adrian's only on the Zip test, which measured how long it took to stuff 1 GB of files into a compressed archive. Vista is slower at this task than XP.

Copy two large files between volumes on a single hard disk

Copy a folder full of many smaller files across two volumes

Download a group of files from Windows Home Server

Upload a group of files to Windows Home Server

Zip a folder full of files into a compressed archive

Next -->

So, why did my results vary from those that Adrian reported?

One thing I noticed early on is that it’s easy to overlook the background tasks that Windows Vista performs immediately after the SP1 upgrade. These tasks are the same as those that occur after a clean install. When I first performed the small file copy test, for instance, I got wildly inconsistent results. Looking in Task Manager, which shows the amount of CPU usage associated with each running process, I didn’t see any active tasks. But as it turned out, the system was busy. I was able to explain the differences by looking at the Disk section in Vista’s Reliability and Performance Monitor, where I found that Vista’s Search Indexer, SuperFetch, and ReadyBoost were all using small but measurable amounts of disk resources as background tasks. The green lines indicate CPU and disk activity in the side-by-side graphs. Note that CPU usage is practically nonexistent, but each task was using a polite but measurable amount of disk resources; the collective impact was enough to steal as much as 10 MB/sec of disk performance.

Disk activity in background after installation of Vista SP1

When I re-ran the tests after making sure that these tasks were no longer running in the background, I got the consistent results shown here.

I agreed completely with a remark Adrian tossed off almost as an aside in the middle of Part 2 of his report:

[O]ddly enough, Vista SP1 felt more responsive [than XP SP2] to user inputs such as opening applications and saving files while the tasks were being performed (we tried this out on separate runs). Problem is that it’s darn hard to measure this end responsiveness without relying more on synthetic benchmarks.

My experience is the same. In fact, it appears that Vista’s designers have made a conscious choice to favor smooth, consistent performance over raw speed. The latter makes for more satisfying benchmarks, but it can also result in annoying performance glitches in day-to-day use.

So, was that the right design decision? Is file copying really a critical performance benchmark? If it takes me 10 seconds more or less to copy a group of files, I truly don't care. For mainstream business use, there's no practical difference between a job that takes 5:52 and one that takes 6:18, especially when the copy operation takes place in the background while I busy myself with other work.

Ultimately, the act of benchmarking file copy operations is distinctly unnatural. Both Adrian and I sat for hours clicking a stopwatch and staring at Windows Explorer windows as we waited for progress dialog boxes to close. We're both a little obsessive like that. Your mileage may vary.

Topics: Windows, CXO, Hardware, Microsoft, Operating Systems, Software, IT Employment

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.


Log in or register to join the discussion
  • benchmarks

    well, i do agree with you about the difference in times to copy a file. i've never really had issues with vista performance. i've used either dual core or quad core cpu's during the beta.

    what i have problems with are the ui changes in vista and a few bugs that ms refuses to fix.

    sometime i'd like get your take on what i think is wrong with vista's ui.
    • I have some gripes with Windows Explorer

      Although there are some brilliant features in Vista's updated Windows Explorer, there are also some bonehead design decisions. I have this on my list of upcoming topics and might move it up.

      What do you dislike about the UI?
      Ed Bott
      • here they are


        thanks for the reply. these are in no specific order and some are minor and only hpeen once, but here they are:

        1. forced to wait for performance test on first boot
        2. forced to defrag all drives, unless command line used; No GUI (a little better in sp1, still no gui)
        3. cannot drag custom toolbar from taskbar to desktop
        4. cannot put menu bar on same line as toolbar in windows mail or internet explorer (only with reg hack)
        5. when autohide is selected, cannot drag shortcut to taskbar without dragging it over start button area
        6. takes more clicks to change date/time (3 instead of 1 double click)
        7. takes more clicks to update time (5 instead of 2, 1 double click)
        8. can?t right click on network icon to get properties
        9. No network repair option, only diagnose and repair(whatever that does)
        10. can?t change attachment/watched column widths in windows mail
        11. mail column dividers are only 1 pixel wide, hard to drag
        12. windows mail watched messages doesn?t work (they know and won?t fix).i use this a lot and it's the worst one for me.
        13. entire row has focus when view files in explorer details view.
        14. can?t right click on a folder to search, it has to be opened first..
        15. no manual compact option in windows mail.
        16. starting defrag recreates the deleted scheduled tasks without warning. (after i've intentionally deleted them)
        17. windows mail autocomplete holds 29 addresses, instead of autocomplete from all contacts
        18. folder views aren?t remembered.(they know and won?t fix)
        19. folder layout flawed. To add menu, details, Preview and navigation, you have to go through the menu system 4 times. Click organize, then layout then the option you want. This has to be repeated 3 more times instead of being able to select any combination in one operation.
        20. more clicks to check the network adapter status, connected time (5 instead of 2)
        21. when opening a folder in explorer, you can no loner see the size in the status bar without selecting all of the file manually.
        • I'll add...

          ...the way Explorer forgets your view settings on a periodic basis. Similarly sidebar occasionally mixes up the order of the gadgets.

          On the plus side, the file info bar at the bottom of explorer windows, which originally annoyed the hell out of me, I now find much more useful, especially now I am more au fait with tagging and rating files.

          I'll add my voice to complaints about the networking interface as well. Bring back the XP wireless centre - much more intuitive!
          • Networking in Vista

            I'd like to add my voice to the complaints about the networking interface as well!

            But I CAN right click a folder and search it.
          • Vista and XP networking

            This is a odd one, been networking windows forever but I cannot get these two to play with each other. Using a simple "home" as the workgroup name, It appears that they are connected but they're JUST not there. on the XP side I can see all my PCs, Linux, and Macs WITH The exception of Vista. On the Mac side I see the XPs, Linux, and Macs but not the Vistas. On the Linux side I get the XPs, Macs, and Linux, but not the Vistas. On the Vista side I see ONLY the Vista machine. I have full internet connectivity on all systems, BUT I should be able to see all my boxes on ALL Windows/Macs networks. I'm running SP3 V3264 on the XP box and I have tried that netsetup.exe fix, but it's telling me that I cannot load it, that a newer version already exists on the XP box. Any suggestions? you can contact me at
          • Check you subnet masks

            Sound like you might have your Vista PC in a different subnet than the others. Ping sometimes works over mis configured subnets but some applications aren't as forgiving.
          • Vista and XP networking

            I would be very interested in thr responce to;s question. I have similar problem. I have a vista machine and a xp machine. I do not user a static ip address The vista machine can access the xp machine's drives but the xp machine can not access the vista drives except the public directory. I was told to try putting a user logon account on the vista machine on the Xp machine and a user login on the Xp machine on the vista machine, but this did not help. Can you tell me what else to try. You can respond to me at
          • Use a NAS drive

            You need to use another piece of hardware to make them play nice. I would recommend a Linksys Storage system. It can take 2 SATA drives and store 1 terabyte mirrored or 2 terabytes with one logical volume on two drives.

            For the Windows part, I would recommend using filezilla. Windows XP may have problems seeing it if you just run the utility. Vista and 2003 server have no problem using the Linksys driver and utility CD.

            Filezilla is also available with Linux as well. Using filezilla as a standard for all operating systems makes the user's experience much more straight forward.

            You can download it here.


            Modern computers have permissions and security features that may not be compatible when different operating systems are used.

            A NAS drive such as the Linksys costs about $200 if you factor in the cost of a SATA drive as well.
          • Check your settings in the .....

            ... Network and Sharing Window in Vista. Make sure Network Discovery is turned on. Also make sure you have the proper share settings set.
          • Help

            There's a file, which I'm not sure is included with XP SP3 or not, but you need to install it before XP will see Vista. There's also making sure the workgroup name is the same, network discovery is on, disable the firewall while testing... there are lots of things to try.
          • I had a similar problem

            My network runs the gamet with windows. (Win 3.11, Win95b, 2ea Win98SE, Win XP Home). I purchased a new notebook that came with Vista Home Premium. I got Vista on the internet pretty quickly, too bad it couldn't even see my SHARED printer on XP Home. I can print from all the machines except Vista. Once I installed XP Pro on the Vista machine, I had no more issues.
          • You forgot...

            And it finds and connects to the internet faster!
          • Do you mean Vista?

            I'd agree with that, but even if it is connected, it takes a good 30 seconds for the wireless icon in the system tray to show network activity as opposed to no connectivity. I can be browsing and on IM before that icon catches up! ;)
          • Sometimes too fast!

            While trying to set up the encryption keys on my wireless network I had a terrible time with it connecting to the neighbors unsecured network before I could make the changes. It kept making the neighbors network the default.
          • Network UI

            I also have weird problems with the network systray icon. Sometimes it displays the "not connected" icon, even though the network connection works fine, and shows up under the control panel as fine.
          • XP sp2 has the same bug...

            the sys tray icon will often stay in the connecting mode and mouse over says theres an issue connecting to the wireless network but i'm accessing the network without issue anyway. i think it's an MS thing. after all, everyone knows if you want it to work flawlessly use linux or mac
          • Vista/XP networking problem

            OK this is even got weirder. I start the pinging(example) It pings once, then it changes the address to the machine that's requested the ping (example for this case which keeps timeing out. The subnet mask is fine all the way around, just the standard, and double checked to verify "" and the subnet is on ALL Windows/Macs/Linux boxes.

            Microsoft Windows [Version 6.0.6000]
            Copyright (c) 2006 Microsoft Corporation. All rights reserved.

            C:\Users\Mike>cd ..

            C:\Users>cd ..

            C:\>ping MechTech
            Ping request could not find host MechTech. Please check the name and try again.

            'ip' is not recognized as an internal or external command,
            operable program or batch file.


            Pinging with 32 bytes of data:

            Reply from Destination host unreachable.
            Reply from Destination host unreachable.
            Reply from Destination host unreachable.
            Reply from Destination host unreachable.

            Ping statistics for
            Packets: Sent = 4, Received = 4, Lost = 0 (0% loss),


            Pinging with 32 bytes of data:

            Reply from Destination host unreachable.
            Reply from Destination host unreachable.
            Reply from Destination host unreachable.
            Reply from Destination host unreachable.

            Ping statistics for
            Packets: Sent = 4, Received = 4, Lost = 0 (0% loss),


            Windows IP Configuration

            Ethernet adapter mshome:

            Connection-specific DNS Suffix . :
            Link-local IPv6 Address . . . . . : fe80::fcc0:f3a1:8bb5:2f8c%8
            IPv4 Address. . . . . . . . . . . :
            Subnet Mask . . . . . . . . . . . :
            Default Gateway . . . . . . . . . :

            ***Below are the results***


            Pinging with 32 bytes of data:

            Reply from Destination host unreachable.
            Reply from Destination host unreachable.
            Reply from Destination host unreachable.
            Reply from Destination host unreachable.

            Ping statistics for
            Packets: Sent = 4, Received = 4, Lost = 0 (0% loss),


            Note: The destination host is the actual maching I'm using now, and has done the ping (This PC has Vista as it's O/S. Also to note It is saying there is no lost packets as well.
          • It's a feature ONLY found in Vista!

        • Get some exercise.

          So ignoring the ones that are down to being lazy, there's about... 4 or 5 in that list...