Page 1 of 4 123 ... LastLast
Results 1 to 10 of 36

Thread: EXT4 File-System Looks To Do Well Against NTFS

  1. #1
    Join Date
    Jan 2007
    Posts
    15,378

    Default EXT4 File-System Looks To Do Well Against NTFS

    Phoronix: EXT4 File-System Looks To Do Well Against NTFS

    We began this week by providing the first extensive Windows 7 vs. Ubuntu 10.04 benchmarks to see whether Microsoft's operating system is faster than the most popular Linux distribution. In that first article we began by providing the OpenGL graphics benchmarks and the numbers were certainly interesting. Subsequently we delivered power consumption tests between Ubuntu Linux and Microsoft Windows on a netbook and a notebook. Now we are still preparing for the next set of tests, but until then, here are two disk tests looking at the file-system performance on Windows 7 with NTFS versus Ubuntu 10.04 LTS with EXT4...

    http://www.phoronix.com/vr.php?view=ODIxNw

  2. #2
    Join Date
    May 2010
    Posts
    15

    Default

    When you run filesystem tests, please specify if Windows Defender or any other antivirus software is running, it makes a huge difference.

  3. #3
    Join Date
    Sep 2008
    Posts
    270

    Default

    I assume it runs. Windows can't be considered safe without it.

  4. #4
    Join Date
    May 2010
    Posts
    15

    Default

    Quote Originally Posted by MaestroMaus View Post
    I assume it runs. Windows can't be considered safe without it.
    When you need performance and you are using Windows 7 on a workstation, it doesn't make any sense to have real time antivirus running.
    If you are just a home user, you should always run real time antivirus, but in that case the perfomence hit doesn't make any difference.

  5. #5
    Join Date
    Nov 2008
    Location
    Germany
    Posts
    5,411

    Default

    *Trumps UP*

    Michael your windows7 vs linux tests are the best articles to read over years!

    Its really important to know what is bad on Linux to fix that for the future

    Real benchmarks only hurts microsoft!

    GOGOGOGOGO!!!!!! hero of the truth

  6. #6
    Join Date
    Feb 2008
    Location
    127.0.0.1
    Posts
    89

    Default

    This is third test that compares Windows 7 with Ubuntu 10.04.
    It is important to understand that it is Windows vs Ubuntu and not Windows with Linux.
    The tests like power consumption is almost useless as it compares power consumption of mobile computers which connected to wall !!!
    I follow Phoronix for some time and I feel kind of disappointment from PTS. the results are pointless in terms of telling you what ca and what cannot be done with your computer. The best example is HD video playback.

  7. #7
    Join Date
    Feb 2009
    Location
    Belgium
    Posts
    115

    Default

    Interesting article. I winder how ext3 would perform against NTFS, since I still prefer it over ext4.

  8. #8
    Join Date
    Oct 2006
    Location
    Israel
    Posts
    621

    Default

    Actually these results are -very- favorable to Windows 7.
    In one of my previous projects we developed a high-performance network storage server that was forced to handle a constant stream of literally billions of extremely small files (average size was under 2KB).

    As Windows 2K8's CreateFile is notoriously slow (we developed a fully cross platform code), no matter how many optimization we added to the code, and no matter how many registry keys we flipped (E.g. disable 8.3 support) we simply couldn't get NTFS anywhere close to ext3 and ext4.

    As I recall, ext3 (out-of-the-box) was somewhat faster than a optimized ext4 (write barrier disabled, we were using a huge FC storage).
    And both were ~12-20x faster then 2K8 NTFS.

    Naturally I used the benchmark to throw yet another Windows server out of our system.

    - Gilboa
    DEV: Intel S2600C0, 2xE52658V2, 32GB, 4x2TB, GTX780, F20/x86_64, Dell U2711.
    SRV: Intel S5520SC, 2xX5680, 36GB, 4x2TB, GTX550, F20/x86_64, Dell U2412..
    BACK: Tyan Tempest i5400XT, 2xE5335, 8GB, 3x1.5TB, 9800GTX, F20/x86-64.
    LAP: ASUS N56VJ, i7-3630QM, 16GB, 1TB, 635M, F20/x86_64.

  9. #9
    Join Date
    May 2010
    Posts
    36

    Default

    I have the same impression as gilboa has with windows and filesystem performance.

    Its piss poor.

    I don't know what the graphs in the article are showing, but it seems to benchmark on block or single file basis?

    Try many files, like a simple "make clean" on a bigger project or extracting an archive with tons of files. On Windows/NTFS, it takes _at least_ 10x the time compared to Linux/ext[234].

  10. #10

    Default

    Quote Originally Posted by Enrox View Post
    When you need performance and you are using Windows 7 on a workstation, it doesn't make any sense to have real time antivirus running.
    If you are just a home user, you should always run real time antivirus, but in that case the perfomence hit doesn't make any difference.
    It wouldn't make sense if antivirus was running, so you can be nearly sure it wasn't.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •