Announcement

Collapse
No announcement yet.

EXT4 File-System Looks To Do Well Against NTFS

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • 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...

    Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite

  • #2
    When you run filesystem tests, please specify if Windows Defender or any other antivirus software is running, it makes a huge difference.

    Comment


    • #3
      I assume it runs. Windows can't be considered safe without it.

      Comment


      • #4
        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.

        Comment


        • #5
          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.

          Comment


          • #6
            Interesting article. I winder how ext3 would perform against NTFS, since I still prefer it over ext4.

            Comment


            • #7
              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
              oVirt-HV1: Intel S2600C0, 2xE5-2658V2, 128GB, 8x2TB, 4x480GB SSD, GTX1080 (to-VM), Dell U3219Q, U2415, U2412M.
              oVirt-HV2: Intel S2400GP2, 2xE5-2448L, 120GB, 8x2TB, 4x480GB SSD, GTX730 (to-VM).
              oVirt-HV3: Gigabyte B85M-HD3, E3-1245V3, 32GB, 4x1TB, 2x480GB SSD, GTX980 (to-VM).
              Devel-2: Asus H110M-K, i5-6500, 16GB, 3x1TB + 128GB-SSD, F33.

              Comment


              • #8
                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].

                Comment


                • #9
                  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.

                  Comment


                  • #10
                    Originally posted by kraftman View Post
                    It wouldn't make sense if antivirus was running, so you can be nearly sure it wasn't.
                    This is Phoronix that is doing the benchmarking. I think we can assume it was running if it was not specified otherwise.

                    Comment

                    Working...
                    X