Announcement

Collapse
No announcement yet.

BFS Scheduler Benchmarks

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

  • L33F3R
    replied
    Originally posted by Ant P. View Post
    This is a problem to who, exactly? Only proprietary software parasites like nVidia, Creative, Adaptec who are too lazy to maintain their junk blobs.
    You have a problem with nvidia blobs? I dont. Im quite impressed at how nvidia maintains them. Creative is too lazy to even make a decent driver, period. I dont know anything about adaptec unfortunately..

    Leave a comment:


  • nanonyme
    replied
    Originally posted by Ant P. View Post
    This is a problem to who, exactly? Only proprietary software parasites like nVidia, Creative, Adaptec who are too lazy to maintain their junk blobs.
    Not entirely true. It hurt DRM git repo so bad that it was eventually abandoned. :3 Unstatic ABI means distros have the responsibility of backporting features from newer kernels to older kernels instead of just being able to compile drivers against a different kernel tree and we all know they're oh so competent...
    Last edited by nanonyme; 25 September 2009, 05:36 AM.

    Leave a comment:


  • kebabbert
    replied
    Zetbo,
    Let me ask you: "Who is the troll? He who always had stated that Linux is bloated and suffers from unstable ABIs, or the ones who falsely accuse him of being Troll?"

    I can not see that I am a Troll when I say that Linux is bloated? It is TRUE, as even Linus T confirms it.

    What is a Troll? Someone who says true things?? Is he a Troll? Do you mean that all the links and interviews with Linux kernel developers such as Andrew Morton, Linus T, Con Kolivas etc I have shown is lies and Trolling?

    I always back my claims up. That is not lying. I am not making things up. No phantasies. Lots of guru programmers think this about Linux, I only link to them gurus. If there were no guru programmers that said so about Linux, I couldnt link and I would have nothing to say. I am not making things up, I always link. Actually I am not stating my own opinions about Linux, I always write what others think about Linux. If everyone would think that Linux is good, it would be impossible for me to show bad links, and I would be quiet.



    I would say that you are a troll, because you accuse me (who always links to kernel devs and dont lie) of being a Troll.

    Who is the Troll, he who says things that kernel devs say, or the ones who falsely accuse others of Trolling (when they in fact are telling the true?)




    Ant.P
    Solaris runs on several arcitechtures and it is not half as bloated. ZFS doesnt need raids and lots of GB of Ram. The point of ZFS is that it protects against Silent Corruption, against bit rot. Your data is being eaten away, without even telling you. That is serious. With ZFS you dont have that problem. No file system solves this Silent Corruption except ZFS. Silent Corruption is the ONLY reason to use ZFS. Not speed, nor snapshots, etc. If you didnt knew about bit rot and Silent Corruption you should just study it for a few minutes. It is critical to know.

    ZFS requires one disc and 512MB RAM to protect against Silent Corruption. You dont need to use ZFS either, if you dont wish too.

    "All the unstable ABIs is a problem to who?". Are you kidding? I have posted people forced to roll back to earlier kernel versions. I have posted that twice. There are many complaints about that. New linux breaks existing functionality. It is not a problem only for nvidia. Read my post again and you will see.



    BlackStar
    It is not about one bench going faster for your personal setup. Intel has done several benches and shown that Linux drops more than 10% performance. On average. It is not about one bench.

    If you think that ext4 is fast and therefore better than ZFS, good for you. Speed is totally unimportant if your data is subject to Silent Corruption. What do you prefer? 300MB/sec and 0.0001% risc that your data gets corrupted for each read, or 50MB/sec and your data is safe? Ergo, ext4 is not hot. It may be fast, but speed is totally unimportant. Your data being safe is important. For large loads ZFS does some impressive things so I doubt ext4 is faster than ZFS actually.

    And Linux just copies. BTRFS is a ZFS wannabee. Systemtap is a DTrace wannabee. etc. Tell me of something that Linux has invented that is really hot as ZFS or DTrace, or Zones? Prove me wrong. Tell me some Linux tech that everyone drools over.

    I agree that OpenSolaris uses Gnome and therefore is a copy of Ubuntu. GUI wise. They are very similar. That is true and no one can deny that. I am not calling you a troll for telling true things.



    RealNC,
    You haven read my link? Linus T says Linux is "far from the slim and hyper efficient Kernel he envisioned". It has a scaringly huge IO footprint. It is bloated. You know, the more code, the more bugs. Is this lies from me? Am I lying about this? Am I trolling? Did Linus T not say those things? Did not Intel's benches showed that Linux dropped more than 10% performance on average recently? Are there no kernel devs complaining about the Linux code quality? I have shown links to all this. Am I lying? Have I produced the links myself? Am I trolling?



    Zetbo:
    Look: if someone tells the truth, he is NOT trolling. If I only write down here what Linux kernel devs says, I am not lying nor Trolling.

    Show me a lie, that I have produced. Show me. If you can not, YOU are the Troll because you accuse others for things not true. I can always back my claims up. You can not. Hence it is you that is the Troll, bacuse you are lying about me. You claim I lie, but can not prove me lying. Then it must be that lies and Trolls.

    Leave a comment:


  • RealNC
    replied
    Funny argument. Linux is not bloated in the usual sense, it's only bloated if you look at all the stuff you can enable in the kernel.

    During runtime, it's not bloated. But since the kernel is a big, big place where everything is put into, it is bloated from a development and maintenance point of view. It would be much simpler to not have even a single filesystem in the kernel, and not a single driver, but have everything split off elsewhere.

    The user in the end of course will still need to pull the stuff he needs from this "elsewhere". It doesn't matter whether that stuff currently is provided directly by the kernel or not; the user is going to use it anyway. Therefore, there's no point in saying it's bloated; the user uses what he needs regardless of how much stuff is available.

    The developer however, has 11 million lines, all thrown together, to deal with. And all that stuff has nothing to do with the kernel itself, in the end. A filesystem for example is not a kernel thing; the filesystem should *use* the kernel (in kernel space or user space doesn't matter). Same for drivers. But this isn't the case. It's all thrown together. I believe that's the "bloat" Linus is referring to, and from the end-user's point of view, it's pretty much of no consequence.
    Last edited by RealNC; 24 September 2009, 06:11 PM.

    Leave a comment:


  • BlackStar
    replied
    Originally posted by kebabbert View Post
    1. Slowing performance:
    12% lower performance is a significant number.
    2.6.31 boots 15% fasrter than 2.6.28 for me.

    See? I can pull numbers out of thin air, too. Saying "an Intel benchmark" without qualifying the what and the how is completely useless.

    4. ext4 not hot
    True. ZFS is hot. And BTRFS is hot (because it is a copy of something hot: ZFS)
    You've got to be kidding. Have you ever *used* EXT4? It is so much faster than EXT3 that it's not funny.

    If there's one kernel changed that has improved my day-to-day experience, this is EXT4. It's improved my compile times to the point they are almost indistinguishable from a ramdisk. Applications like Firefox and Evolution start up significantly faster. Boot times and fsck times are much, *much* shorter.

    ZFS may be "hot" but it's certainly no speed demon.

    5. Linux just copies and never invents new smoking hot tech.
    Now you are just plain trolling.

    Please remind us, why are you even using Linux on the first place?

    Leave a comment:


  • Ant P.
    replied
    Originally posted by kebabbert View Post
    2. More bloat
    Same link. Linus T says Linux gets more bloated.
    Having better hardware support than every other OS doesn't come for free. Does Windows 7 run on a 486? Does Solaris work on a router with 4MB of storage?

    Originally posted by kebabbert View Post
    3. Unstable ABI
    Everyone knows this.
    This is a problem to who, exactly? Only proprietary software parasites like nVidia, Creative, Adaptec who are too lazy to maintain their junk blobs.

    Originally posted by kebabbert View Post
    BTRFS is a ZFS wannabe.
    ZFS is a prime example of bloat. What's OpenSolaris a wannabe of? Ubuntu 4.10? Who runs a desktop OS with a filesystem that only works well with gigantic RAID arrays and gigs of RAM, especially when it doesn't have drivers for most desktop hardware?

    At least Linux gives you a choice to not use BTRFS.

    Leave a comment:


  • Zetbo
    replied
    Great! Kebabbert troll is here. You can read his trolling on OSNews in every article that involves Linux.http://www.osnews.com/story/22207/Li...rocess_Working So please do not feed the troll. He has his head stuck so badly in Jonathan Schwartzs ass so he can't stop.

    Leave a comment:


  • kebabbert
    replied
    "On-hand: slowing performance, more bloat, unstable ABIs, etc. How hot is Ext4 for instance? Not really. Why not invent some new smoking hot tech instead of just copying other OSes?"
    Originally posted by Ant P. View Post
    Show us the facts and figures behind this assertion. Meaningful ones please, not ".31 IZ 0.0023 SECONDS SLOWER THAN .11 OMG!!2".
    I claim five things here. Slowing performance. More bloat. Unstable ABI. Ext4 is not hot. And that Linux just copies from other OSes, for instance from Solaris, and never invents new smoking hot tech

    1. Slowing performance:
    12% lower performance is a significant number.

    "Citing an internal Intel study that tracked kernel releases, Bottomley said Linux performance had dropped about two per centage points at every release, for a cumulative drop of about 12 per cent over the last ten releases."


    2. More bloat
    Same link. Linus T says Linux gets more bloated.


    3. Unstable ABI
    Everyone knows this.


    4. ext4 not hot
    True. ZFS is hot. And BTRFS is hot (because it is a copy of something hot: ZFS)


    5. Linux just copies and never invents new smoking hot tech.
    BTRFS is a ZFS wannabe. Systemtap is a DTrace wannabe. All I see is wannabes. I havent heard of some new hot Linux tech that excites people.





    VESA,
    Yes you are true. Sorry for this off topic. I will stop this off topic now. (Too bad people will not believe that Linux has it's flaws until Linus T says so. And even then, people will not believe it. They continue to accuse others of being Troll, even when Linus T confirms. They never think themselves. As someone said:

    "It never fails to amaze me how fanboyism can kill rational thought in otherwise intelligent human beings.")



    On topic, this BFS scheduler seems really nice I think! I always liked Con Kolivas and his ideas. Come on, who can learn to kernel hack from themselves? It is mighty impressive, as he is trained as a doctor and not a programmer. I am impressed by him. Too bad others are not.

    Leave a comment:


  • vesa
    replied
    Any chances you guys go and benchmark BFS to get some more content to this thread?

    Leave a comment:


  • Ant P.
    replied
    Originally posted by kebabbert View Post
    On-hand: slowing performance, more bloat, unstable ABIs, etc. How hot is Ext4 for instance? Not really. Why not invent some new smoking hot tech instead of just copying other OSes?
    Show us the facts and figures behind this assertion. Meaningful ones please, not ".31 IZ 0.0023 SECONDS SLOWER THAN .11 OMG!!2".

    Leave a comment:

Working...
X