Forgot your password?
typodupeerror
Linux Software

LinuxWorld: Stronger I/O & VM Coming Soon to Linux 37

Posted by timothy
from the what-does-this-guy-know-anyhow dept.
Mark Brunelli, News Editor writes "Tim Witham, CTO of Open Source Development Labs and a featured speaker at LinuxWorld, says the next Linux kernel will feature improved input/output and virtualization capabilities. Said Witham: 'Enabling virtualization is a big win [for Linux 2.6] as it allows IT shops to start their development cycles for a technology they will be looking at deploying within the next year or so. There has been lots of good work done with regard to system scalability, memory management, disk I/O, process and thread scalability. Also, work done for availability, like a greatly improved multi-path I/O [were victories].'"
This discussion has been archived. No new comments can be posted.

LinuxWorld: Stronger I/O & VM Coming Soon to Linux

Comments Filter:
  • Content-free (Score:5, Informative)

    by interiot (50685) on Monday August 08, 2005 @03:20PM (#13272287) Homepage
    Since the linked article seems to no more information that what the summary says, here's another link [serverwatch.com] that discusses virtualization+kernel a little more. It looks like it's the Xen work that's going into the kernel (the project that IBM and AMD and others have been putting money and developers into to get working [paperlined.org]).
  • 'VM', in the context of the Linux kernel, refers to its virtual memory manager, not virtual machines. It's incredibly misleading to read about 'stronger VM' like this.

    Wasn't usermode Linux integrated into the 2.6 kernel anyway? What improvements in virtualisation is TFA referring to? It seemed remarkably short on details.

    • VM refers to both, just depending on the context. While I agree with you I generally think of VM as Virtual Memory, not as Virtual Machine, it's just one of those things. For the first six months they talked about UML and getting it integrated into the kernel, I thought they were talking about "Unified Modelling Language". Just get over the title. Your initial assumptions and intuition misled you. Shocking.

      User Mode Linux is in 2.6, however, I believe they are referring to "Xen" which is a separate "

    • Re:Terrible title (Score:3, Informative)

      by jd (1658)
      I believe they're referring to Xen, which can virtualize (in theory) any OS - not just Linux - and is (reputedly) considerably faster than UML.
      • Re:Terrible title (Score:2, Insightful)

        by stevey (64018)

        No Xen cannot virtualize/host any OS.

        Instead the OS must be modified to support it. If you look at the Xen homepage [cam.ac.uk] you'll see more details.

        Whilst this doesn't diminish the usefulness of the project it does mean you cannot host an XP installation - like you can with Qemu [bellard.free.fr] , or the commerical software VMWare.

        I have used Qemu extensively in the past to host installations of Windows upon my Debian machine [debian-adm...ration.org] - whilst it is not as fast as Xen promises to be it is the best around at the moment (short of spendin

        • by jd (1658)
          ...once CPUs are capable of supporting virtualization directly (the next generation of Intel and AMD should do this), host OS modifications will not be required.


          So, whilst you are correct it cannot virtualize any OS on current processors, that is not quite the same as saying it can't virtualize any OS in the future, which is what I was referring to. Apologies on my part if I wasn't clear on that - I'm not always as clear as I could be.

  • by Anonymous Coward
    What does this mean to a typical home user?
    • Some thoughts (Score:3, Interesting)

      by jd (1658)
      Once virtualization is introduced into microprocessors, you will be able to run a real copy of Windows in parallel to Linux, using Xen.


      Improved I/O means home networks should run closer to the capabilities of the wire, plus multimedia on the computer is less likely to stall when playing. It may also make Linux more attractive to games writers, as a lot of games these days are heavy on multimedia.

  • by bill_mcgonigle (4333) * on Monday August 08, 2005 @04:00PM (#13272702) Homepage Journal
    What's the deal with disk I/O killing the responsiveness of the system anyway? When you have to move monstrous amounts of data, a Linux system can get practically unusable, no matter which user is initiating the load.

    I used to think this would go away with faster machines, or the interrupts would be freed by using SCSI HBA's, but the symptoms still persist today, even on a modern 'fast' machine.

    I never experienced anything like it on, say, Sun hardware, in the pre-Linux days.
    • I agree it's annoying, even using a pre-emptive kernel doesn't seem to help much anymore, although I swear it used to.
    • And I've just spent the last 6 months trying to find out what's hanging on to that IRQ and blocking everything else..

      DMA should stop this from happening (I wonder if it happens outside X86)
    • Yeah, I don't want to start a holy war here, but what is the deal with you Linux fanatics? I've been sitting here at my freelance gig in front of a Linux box (a PIII/750 w/64 Megs of RAM) for about 20 minutes now while it attempts to copy a 17 Meg file from one folder on the hard drive to another folder. 20 minutes. At home, on my PowerMac 8600/300 running OS9, which by all standards should be a lot slower than this linux box, the same operation would take about 2 minutes. If that.

      (This post is a joke, inci [wikipedia.org]
    • I noticed this when I switched from 2.4.x to 2.6.x kernel (Now running 2.6.8-24).

      When I cp a 2+gig file to a different partion (ext3 to fat32) the system acts sluggish and I can't play games or compile with any responsiveness. It could be the filesystem layer, but I don't buy it.

      When I burn a CD iso (XCDRoast), I have no responsiveness problems playing Cube/Privateer or anything else. Go figure.

      Its still better I/O than Windows though. Install Open Office from a windows share, install an another application
      • You got something wrong in your Windows. I'm copying ~10 gig Virtual PC file to another drive and writing this message, playing MP3 from same drive I'm copying (with MWP), using SSH-client and even compiling C#.NET application at the same time. No responsiveness problems, no locking-up or anything. I don't have floppy drive attached so I can't try what it would do, but copying from DVD doesn't cause any problems. Maybe your hardware is broken?
        • Or, indeed, maybe hardware driver is broken...
        • You got something wrong in your Windows.
          Why would you say that? My Windows (2000) is lean and clean. My hardware is also different from yours.

          I'm copying ~10 gig Virtual PC file to another drive and writing this message, playing MP3 from same drive I'm copying (with MWP), using SSH-client and even compiling C#.NET application at the same time. No responsiveness problems, no locking-up or anything.

          Im also running a PIII with 256 Meg of RAM. Are you? I didn't buy this computer with the intention of runn
          • Okay, your hardware is little old and you're using W2K. That explains a lot. I have AMD 2600+, 1.5 GB RAM and Windows XP. I'm not running Anti-Virus or Ad-Aware programs. Well, I've checked my computer couple of times for viruses and found absolutely nothing.

            My program works on Linux, FreeBSD and Windows without ... reassembling it (is that the correct word?). I don't know if assemblies are portable across different processor architectures, but I guess it runs on StrongARM also (Windows CE). I've never used
    • by Anonymous Coward
      The simple answer is Linux uses write-back caching, and will let a process write data faster than it can actually be sent to the disk, thus filling up all the available memory pages and blocking other I/O.
      • Shouldn't the kernel tell the task to slow up when you're getting toward 2/3 (or 50%, 75%, 80% etc.) of the available memory pages? Would boot-up tests that store data-rate metrics for the available storage allow the system to slow down tasks likely to fill the memory pages before the disks can catch up which would allow the system to retain 'teh snappy'?
  • An added bit of usability and stability to an already stable and usable system can't hurt in the war on microsoft.
    • Not sure if that was a real post or meant to be humor, but mucking with the VM is not the way to be more stable. There were major stability issues in the early 2.4 kernels due to the new VM that was swapped in. My company is still dealing with bugs in what can be seen as a VM issue - the 4Gb user/4Gb kernel split in RedHat advanced server, and this is in the new U5 update.
  • The article doesn't say which next version exactly that we can expect these improvements in. When I think "next Linux kernel" I think the next point release in the current version (in this case, 2.6.13), but these sort of sweeping changes seem awfully ambitious for such a short period of time, thus we should expect these changes in 2.8.0? But what happened to 2.8.0 not coming any time soon?

    Anybody know what they're talking about when they refer to "next Linux kernel"?

    • Xen support won't be in 2.6.13 but could be in 2.6.14. Basically the hold up is in restructuring to fit with emerging kernel policies on x86-like architectures (i.e. fit them into the i386 directory, instead of forking a separate arch tree as x86_64 did). Once this restructuring is done, the Xen patches should get merged.
  • Last time volume managers and raidtabs came out for linux, the market quickly flooded with too many mediocre flavors. I expect multipathing software to do the exact same.

    • I'm hoping for better, as it's the only flavour of Multipathing that RedHat will support! Where I work we use QLogic's 2300 series HBAs - single adapters with dual paths for test, dual adapters with dual paths for production. They are very VERY sweet, and once you start playing with SANSurfer, you discover the power of SAN disk configuration that users of "big iron" would typically take for granted. The catch is, you need to install the vendor's HBA drivers (remember to fix RedHat's broken qla2300_conf m

"The pyramid is opening!" "Which one?" "The one with the ever-widening hole in it!" -- The Firesign Theatre

Working...