File/Networking Performance

Finally we have file and networking performance. As Ubuntu uses a different file system (ext3 versus Windows’ NTFS) there’s the potential for some significant differences here.

Starting with file performance, we will be using a collection of roughly 1500 files, totaling 380MB.

Even after SP1, file performance has long been a thron in the side of Vista. Here it manages an embarrassing loss to Ubuntu, taking over 50% longer to make a copy of the same folder.

Looking at ZIP compression times, it’s an even larger gap. Vista needs 75% longer to compress the same folder. While compression can be CPU bound, looking at our data this specific test is largely I/O bound. We’ve already established at Windows’ built-in ZIP abilities are pretty bad, but we’ve never figured out why this is.

Decompression is even worse for Windows. It takes nearly 4 times as long to decompress the same archive. It’s not even a contest – Ubuntu wins, if only because it’s the only competent operating system out of the two.

Meanwhile in our network copy tests, we are copying that folder to a server running Windows Server 2003. This gives Windows an advantage since we’re using SMB, but since SMB is the predominant protocol for consumer file server gear, it’s a fair test of such use.

Here it’s nearly a dead heat. Both Ubuntu and Vista need just as long to copy our file collection to the server, meanwhile Windows needs a bit less time to copy that same folder off of the server.

Switching gears, using a 2.6GB ISO we see a clear performance difference. In both copying to and from the server, Ubuntu needs at least 50% longer. Since this test isn’t using a lot of CPU time, our best guess is that Windows is doing some buffering that Ubuntu doesn’t get to do. The transfer rates for Linux are below what the hard drives on either end can manage.

Ultimately for users with lots of local storage, Ubuntu appears to outshine Vista. But for users with lots of remote storage (e.g. a NAS), Vista outshines Ubuntu.

Finally we have the amount of time it takes to start up each operating system, another disk-bound test. Vista is not something I would consider particularly speedy, so I’m a bit surprised that Ubuntu did not manage to outperform it here. The 2 second difference is measurable, but small enough that it won’t make any real impact.

Browser & Video Benchmarks First Thoughts
Comments Locked

195 Comments

View All Comments

  • Guspaz - Wednesday, August 26, 2009 - link

    "Not that it would necessarily be of much use, the last time I saw any statistics for instant messaging network usage, the vast majority of North American users were on AOL’s AIM network."

    IM use is highly regionalized. As such, AIM is clearly the dominant IM in the USA. However, Canada is dominated by MSN Messenger, and has been for many years (most of us migrated from ICQ to MSN around the release of Windows XP, I believe, due to the bundling of then Windows Messenger).

    So, if Canada is dominated by MSN, while I can't speak for Mexico, it's misleading to claim that "the vast majority of North American users". As a Canadian, I can't think of anybody I know in person that uses AIM. They all use MSN or Google Talk without exception.
  • Aclough - Wednesday, August 26, 2009 - link

    For myself, the thing that most bugs me when I have to go back to Windows is all the missing features from the window manager. I've come to rely on having multiple workspaces on my desktop, but I can adjust to having just one fairly easily when I'm not working on a lot of different stuff at once. What really bugs me, though, is how much more effort it takes to move or resize windows in Windows. On Linux I can press ALT and then click anywhere on the window, but with Windows I have to carefully click the title bar or the very edge of the window and that takes a noticeably longer time once you're used to doing things differently.

    Oh, and I find that the Linux scheduler seems to be noticeably better than the Windows one in preserving responsiveness when the system is under load.
  • fumacapena - Wednesday, August 26, 2009 - link

    Great article!

    How about some benchmarks of "minimal" distros (like Puppy, Tine Core, ...)??
    I like the idea of "ressurect" an old PC, but I would like to see benchmarks in Quad Cores, i7 too!

    Anandtech is great, Bench(beta) is awesome!!
    (sorry by bad english)

    Thanks
  • InGraphite - Wednesday, August 26, 2009 - link

    A few months ago most major trackers unbanned Transmission, but it still doesn't seem to be universally accepted on private trackers.

    I remember offhand (I could be wrong) that the main gripe was due to the fact it made excessive queries and thus flooded trackers with requests, or had the ability to.
  • chomlee - Wednesday, August 26, 2009 - link

    I think you really need to mention the big picture here.

    I myself just tried Ubuntu for the first time 2 months ago and although I will admit that I have spent up to 8 hours trying to figure out how to install a specific program (before I found out there was a way to get the package manager to find the install), and I wanted to smash my computer at times. Now that I have learned quite a bit more, I realized that the few things I have installed worked great and flawlessly.

    Anyhow back to the big picture. I can understand some of your concerns with how the OS will work with specific programs but what I have found is that most people I know use their computers for 2 things email and web browsing. Most of these people are constantly having problems with the system running too slow and cant seem to get rid of hidden viruses/malware. So I think that those people could easily be much happier with a simple OS like Ubuntu just for email and web browsing (And I would get a heck of alot of less calls from my dad asking my why his computer is running too slow). Lets also not forget that everything is moving to be browser compatible (like you mentioned).

    Also, for people like myself, I use my Ubuntu system for a file server as well as a media center (XBMC is Awesome).

    So, yes, for burning DVDs/CDs/Playing Games/Microsoft Office, I see no reason why you wouldn't use windows, but I think 95% of the users would be perfectly fine with ubuntu which is something that Mr Bill would not be very happy about when the public realizes this.
  • Keno - Thursday, August 27, 2009 - link

    I think you have missed one small but important part.
    I am Ubuntu user since 8.04. I came to Linux because of the constant treat of viruses.
    Last month I have installed 7 and it is very user friendly and I think it is very user frinedly but after Avira Antivir got crashed by virus I installed Kaspersky INternet security 2010. then it took almost twice as long to boot. Then I gladly returned to Ubuntu 9.04. Because MIcrosoft can not exist without Antivirus I think you should do some real benchmarking and test windows WITH Antivirus.
    On Ubuntu I have ClamWin just in case i get some files from Windows users:)
    Thanks
  • ioannis - Wednesday, August 26, 2009 - link

    just wanted to point out that you can install software under the LiveCD. Of course it does not install on the hard drive. It remains on a ram-drive, so when you reboot, it's gone. It's still useful, if you wish to test out some package or perform some task with a tool not installed by default on the LiveCD
  • strikeback03 - Wednesday, August 26, 2009 - link

    Even more useful (and not mentioned) is that Ubuntu can easily run off a flash drive, and more recent versions even include a GUI tool for installing it to one. Then all installs and other changes are saved from session to session, and everything runs much more quickly than the LiveCD.
  • Mr Pearce - Wednesday, August 26, 2009 - link

    It would be great if you could do more articles on compiler and especially driver performance differences. That was the most interesting part of this article.
  • Ryan Smith - Wednesday, August 26, 2009 - link

    This is what Part 2 will look at. I can compile some stuff by hand to see if it closes the Windows/Ubuntu gap, and I have plenty of video cards on hand to test what I can when it comes to graphics.

Log in

Don't have an account? Sign up now