Slashdot Mirror

← Back to Stories (view on slashdot.org)

Virtualized Linux Faster Than Native?

Posted by ryuzaki0 on from the too-specialized-to-count dept.

^switch writes "Aussies at NICTA have developed a para-virtualized Linux called Wombat that they claim outperforms native Linux. From the article: 'The L4 Microkernel works with its own open source operating system Iguana, which is specifically designed as a base for use in embedded systems.'" Specific performance results are also available from the NICTA website.

24 of 153 comments (clear)

  1. Curious warning on the website by LiquidCoooled · · Score: 5, Funny

    Warning

    Running a virtual Iguana OS from within a virtualised Linux environment is dangerous.
    ETROS and NICTA will not be held responsible for any resulting time paradoxes.


    hmmmm

    --
    liqbase :: faster than paper
    1. Re:Curious warning on the website by Rorian · · Score: 5, Funny

      Well thats the answer to the better-than-native performance then. It simply creates a hole in the space-time continuum, off-loads all processing work to the infinite monkies with infinite abacuses, and reports 0.0 cpu load to the benchmark program.

      Obvious really.

      --
      Will program for karma.
  2. Bad Second Link by Ctrl+Alt+De1337 · · Score: 4, Informative

    Ignore the second link. The actual performance results are here.

  3. This makes me wonder... by DaHat · · Score: 5, Interesting

    Just how fast would a virtualized Linux instance running inside of a virtualized Linux instance running on hardware be?

    --
    Help Brendan pay off his student loans
    1. Re:This makes me wonder... by bazorg · · Score: 5, Funny

      Do you think that's air you're breathing now?

    2. Re:This makes me wonder... by Hitch · · Score: 4, Funny

      so...it's actually *penguins* all the way down?

      --
      You see, without that little doohicky, the universe stops.
      http://propheteer.org
  4. ARM v4 or v5 processors only by XoXus · · Score: 5, Informative

    The summary is misleading a bit - it's only faster on ARM v4 or v5 processors.

    From TFA:

    Wombat, NICTA's architecture-independent para-virtualised Linux for L4-embedded, can be faster than native Linux on the same hardware. Specifically on popular ARM v4 or v5 processors, such as ARM9 cores or the XScale, Wombat benefits from the fast address-space switch (FASS) technology implemented in L4-embedded, while this is not supported in native Linux distributions.

  5. Twice the buffering by jellomizer · · Score: 3, Interesting

    It is possible. First you have drive access. Normally the data is buffered in memory then is paged out to the drive when the OS sees fit. When it is on the memory it can be accessed faster. So now you are virtualizing the hardware so when the OS says write to the Hard Drive it goes to the Host OS who then buffers it in memory and writes to the drive when it seems fit, so the files are buffered in memory for twice as long, allowing twice the time that it can access the faster data. Usually that is the largest slowdown on the system is drive access, also because when the host OS is writing to the drive the Virtualized Linux kernel is free to do what it wants. I am sure if the application requires a lot of interrupt calls or a lot of displaying to the screen it will slowdown (Unless the virtualized video drivers are much more optimized then the normal ones)
    So it is possible, just as long as you have a system powerful enough to run both OSs well and with a lot of RAM.

    --
    If something is so important that you feel the need to post it on the internet... It probably isn't that important.
    1. Re:Twice the buffering by tomstdenis · · Score: 3, Informative

      This is OT.

      The speedup comes from TLB caching between processes. Not from "double caching".

      In Linux when you switch processes the TLB is flushed [e.g. reloading CR3 on x86-*]. This is a safe [but slow] way to ensure your virtual memory for a given process is mapped correctly. I'm guessing [didn't fully read the linked research papers] that they share a virtual memory base between processes but map processes to different regions or something. Unless they have segment limits this will cause problems with process isolation.

      For those not in the know, a TLB cache holds the translation of a virtual address into a physical one. Parsing a typical 32-bit address requires several layers [with 4KB pages it's four I think] of table lookup which is slow if you had to do it for every memory access. For example, take your 32-bit address, the lower 12 bits is the byte in a 4KB page, the next 10 bits points selects one 4KB page, the next 10 bits selects one 1024-entry array of pointers to 4KB pages. [iirc]. It's even worse in x86-64 mode as we are parsing a 48-bit virtual address.

      So the processor will cache TLB lookups. When you switch processes you have to flush it because the translations don't map to your processes physicals memory.

      Tom

      --
      Someday, I'll have a real sig.
  6. Hm by FidelCatsro · · Score: 4, Informative

    Could it be because linux for ARM is not that well optimised . I can't imagine such massive performance gains otherwise , bar a massive bug in the kernel.

    Fast Address-Space Switching for ARM Linux Kernels

    The Fast Address-Space Switching (FASS) project aims to utilise some of the features of the Memory Management Unit in the ARM architecture to improve the performance of context switches under the L4 kernel and ARM Linux.

    --
    The only things certain in war are Propaganda and Death. You can never be sure which is which though
  7. Only? by Anonymous Coward · · Score: 4, Interesting

    I'm not sure if you realize the market penetration of ARM-based processors. They're basically everywhere. One popular use is in routers. Many printers also have ARM chips. They're also very widely used in cell phones and other mobile technology.

    It benefits us all of more performance can be extracted from such chips, just because they're so widely used. Being able to get a greater degree of performance out of a device already in use can lead to lower-cost systems. To suggest that this is of limited use is naive, just because of how prevalent these processors are.

    1. Re:Only? by JanneM · · Score: 5, Informative

      It benefits us all of more performance can be extracted from such chips, just because they're so widely used.

      The reaction is not against the performance but the disingenious presentation. A cursory reading makes it seem as if the performance gain was somehow tied to it being a microkernel, or that the virtualization step somehow magically speeded things up. It wasn't - their kernel is using some platform specific optimizations that Linux doesn't, that's all.

      --
      Trust the Computer. The Computer is your friend.
  8. Re:defend his position that microkernels are crap? by AKAImBatman · · Score: 3, Informative

    Whenever a free microkernel design comes remotely close to the mindshare of Linux, there may be a basis for discussion.

    QNX

    'Nuff said.

    --
    Javascript + Nintendo DSi = DSiCade
  9. KLAATU... VERATA... by dsginter · · Score: 4, Funny

    NICTA... necktie...

    Definitely an n-word.

    --
    More
  10. As somebody familiar with the project by agent+dero · · Score: 4, Informative

    I've been researching more and more into NICTA's microkernel and virtualization (for my L4::BSD idea) and one thing that is important to understand is that NICTA's development is mainly on ARM, the Kenge toolset, as well as the Iguana OS are both much further along on ARM as opposed to i386

    Considering the work that NICTA does with companies that produce embedded hardware like Qualcomm, this isn't surprising, but don't go crazy about this.

    Linux development is much more fine tuned on x86, and Kenge/Iguana development is much more fine tuned on ARM; no need to start holy wars here ;)

    That said, nice work benno, chuck, and gernot (and whomever else I'm forgetting)

    --
    Error 407 - No creative sig found
  11. A new form of energy by waif69 · · Score: 3, Funny

    If one were to use 33 levels of virtualization on the ARM processor, the efficiency is so great that power may be removed and the system runs on its own efficiency. Yeah! We don't need oil anymore.

  12. Time to cue up some U2 by pmbuko · · Score: 3, Funny

    Even better than the real thing....

    1. Re:Time to cue up some U2 by datafr0g · · Score: 3, Funny

      This virtualized Linux moves in mysterious ways, but I still haven't found what I'm looking for.

      --
      "Who says nothing is impossible? Some people do it every day!" - Alfred E. Neuman
  13. Re:This makes me wonder... ?? by electr01nik · · Score: 3, Funny
    Yes it does make me wonder..... Running virtualized Linux on virtualized Linux hosted by Linux.... Now that seems to be just a bit overkill does it not....

    Yeah but...imagine a Beowulf cluster of them!

  14. The more microkernels the better? by mikael · · Score: 3, Funny

    ^switch writes "Aussies at NICTA have developed a para-virtualized Linux called Wombat that they claim outperforms native Linux.

    So if a para-virtualised microkernel runs a para-virtualised microkernel running Linux, then there should be an even greater speedup?

    --
    Vintage computer adverts: http://www.vintageadbrowser.com/computers-and-software-ads
  15. Strange by Sgt+Pinback · · Score: 3, Insightful

    So, what are they trying to show? "Because we've implemented support for a certain MMU feature and native Linux hasn't, we've demonstrated that virtualizing Linux on L4 is a good idea"? Doesn't sound perfectly logical to me. Apples and oranges come to mind.

    --

    --

    I do not like the men on this space ship!
  16. Welcome by Anonymous Coward · · Score: 3, Funny

    I for one welcome our new Fast Address-Space Switching overlords!

  17. Re:Ignite the flames of the microkernel debate aga by hey! · · Score: 3, Interesting

    Last time I read Linus talking about microkernels, it was a lot more nuanced than "Microkernels are crap". It was more along the lines that microkernel architectures end up with greater complexity and more comunication overhead at higher levels. It certainly leaves open the possiblity that a particular microkernel could be fast at a particular set of operations.

    What's interesting about a what we're apparently talking here is a virtualized linux running on top of a microkernel. I'm reasonably certain that they didn't do a complete reengineering of Linux as a microkernel, they just got it to run on top of a microkernel. So, we're still talking about a monolithic kernel with all kinds of tight coupling, but the virutalized hardware can make certain hardware related tasks faster. In particular they talk about context switches being much faster; since the microkernel is specifically designed for single architecture (ARM), it may not be so surprising that they can take better advantage of certain architectural features.

    --
    Post may contain irony: discontinue use if experiencing mood swings, nausea or elevated blood pressure.
  18. Re:Informative? Only to those w/o senses of humor. by Ryan+Amos · · Score: 3, Funny

    Please.

    A low slashdot id just means you've been heaping shit on the pile longer than anyone else.