Announcement

Collapse
No announcement yet.

New Tests due to the Kernel-Memory-Problem of Intel?

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

  • New Tests due to the Kernel-Memory-Problem of Intel?

    Will you provide new performance tests due to the kernel-problem described here: https://www.theregister.co.uk/2018/0...u_design_flaw/
    (Sorry I don't not yet how urls are pasted here).
    It seems that some cpu can loose up to 37% of their performance due to the fix coming next week!

  • #2
    Likely we'll have a look at it. I don't think anyone has got access to the patch as yet to test it. So for the moment we'll just have to wait.

    From what I read most of the impact is going to be on Kernel calls. Meaning pure CPU load from an application might not be impacted much. But things that require the O/S (like disk access, network I/O, display graphics, etc.. ) might be effected.

    Comment


    • #3
      Update: I saw some benchmarks. Impact seems to be exaggerated. Numbers like 0% slow down to 10% in rare cases are more likely.

      Comment


      • #4
        May be these links can help you:

        https://amp.thehackernews.com/thn/20...mpression=true

        Google said:
        The Executive Summary

        One. There are two attacks, Meltdown and Spectre.
        2. Meltdown only affects Intel, KPTI helps against it.
        Spectre concerns everyone, it's still unclear what helps.
        4. research is far from over.
        5. so far Intel, especially Haswell, has been the focus.
        For successful attacks you have to find out details of the hardware's functionality.

        Meltdown is Intel-specific.

        It is the "simple" attack, and only against that KAISER/KPTI helps. AMD is not affected by this. But every Intel CPU since Pentium Pro, with the exception of the first In-Order atoms.

        Spectre also affects ARM and AMD and potentially even more (POWER was mentioned). As already suspected, it is based on https://cyber.wtf/2017/07/28/negativ...rom-user-mode/

        KPTI does not help against this. You can access any memory of other processes or the kernel. It is a universal "Heartbleed", and even works with Javascript.
        A combination of microcode updates and new compiler options is under discussion. Yes, you have to recompile everything, so a lot of software will be affected until you have new CPUs.

        So far only ARM speaks plain text (although "The majority of arm processors are not impacted" is nonsense from the end user's point of view - almost all Android devices should be affected):
        https://developer.arm.com/support/security-update

        Edit: some links...
        https://googleprojectzero.blogspot.d...with-side.html
        https://spectreattack.com/spectre.pdf



        Intel:https://newsroom.intel.com/news/inte...arch-findings/
        Recent reports that these exploits are caused by a “bug” or a “flaw” and are unique to Intel products are incorrect. Based on the analysis to date, many types of computing devices — with many different vendors’ processors and operating systems — are susceptible to these exploits.
        Intel is committed to product and customer security and is working closely with many other technology companies, including AMD, ARM Holdings and several operating system vendors, to develop an industry-wide approach to resolve this issue promptly and constructively.

        The name of the patches:
        Win7:
        https://www.catalog.update.microsoft...px?q=KB4056897
        Win8.1:
        https://www.catalog.update.microsoft...px?q=KB4056898
        Win10(is already distributed):
        https://www.catalog.update.microsoft...px?q=KB4056892
        Win7 and 8 will get the patch only next Tuesday.

        Comment


        • #5
          Will you provide a PerformanceTest that checks the local existence of the a.m. patches as some will try to avoid installing the patches?
          Last edited by Gooly; Jan-04-2018, 10:48 AM.

          Comment


          • #6

            We should have better figures in the next few days as the patch is rolled out. If it really is a 30% impact, then we'll need to do something. If it near 0% difference for CPU performance (which we suspect it might be) then there isn't much reason to do anything.

            Comment


            • #7
              It depends very much what PerformanceTest measures!
              Here (a German Linux magazine) you can read:
              Initial experience with the loss of speed due to workarounds has been gained from "near-0" to "system call overhead", extending from 100 to 350 ns "(Dragonfly BSD) to doubled CPU load for cloud providers.
              And Epic-Games shows a drastic cpu utilization:
              Click image for larger version

Name:	cpu_util.png
Views:	234
Size:	41.6 KB
ID:	41287

              Comment


              • #8
                This link from Microsoft includes a nice summary of the situation
                https://cloudblogs.microsoft.com/mic...ndows-systems/

                Seems performance impact will depend on the age of the CPU, the type of CPU, the version of Windows in use & if BIOS firmware microcode patches have been applied.
                Based on past experience it might be months before all the motherboard vendors release new firmware with updated CPU microcode. So it is going to drag on for a while.

                Comment

                Working...
                X