Slashdot Mirror

← Back to Stories (view on slashdot.org)

Microsoft Advice Against Nehalem Xeons Snuffed Out

Posted by Soulskill on from the keep-that-under-your-hat dept.

Eukariote writes "In an article outlining hidden strife in the processor world, Andreas Stiller has reported the scoop that Microsoft advised against the use of Intel Nehalem Xeon (Core i7/i5) processors under Windows Server 2008 R2, but was pressured by Intel to refrain from publishing this advisory. The issue concerns a bug causing spurious interrupts that locks up the Hypervisor of Server 2008. Though there is a hotfix, it is unattractive as it disables power savings and turbo boost states. (The original German-language version of the article is also available.)"

2 of 154 comments (clear)

  1. First Rev of New Architecture by bill_mcgonigle · · Score: 4, Interesting

    Many of the benchmarking sites have also posted some poor results - I was thinking this might be a generation to skip, but now I wonder if a flaw has been discovered that could be fixed with a microcode upload. Might help the benchmarks too if it was a hidden variable.

    --
    My God, it's Full of Source!
    OUTSIDE_IP=$(dig +short my.ip @outsideip.net)
  2. Re:Isn't it really a bug in Windows Server? by AcidPenguin9873 · · Score: 4, Interesting
    I don't think so. Here's the text from the Intel erratum:

    During a complex set of conditions, if the APIC timer is being used to generate interrupts, unexpected interrupts not related to the APIC timer may be signaled when a core exits the C6 power state. The APIC timer stops counting in C6 and as such isn't typically used to generate interrupts when the C6 core power state is enabled. Implication: Unexpected interrupt vectors could be sent from the APIC to a logical processor.

    Interrupts not related to the APIC timer being caused by the APIC timer is not a software problem, it's a hardware problem. I could understand your argument if the APIC timer was generating too many interrupts upon C6 exit, or something else related to messed-up APIC timekeeping near power management events, but this is unrelated interrupts being generated.

    I don't know the details, but I would assume Microsoft is using the APIC timer in its hypervisor for a reason. Maybe it's because the hypervisor is required to virtualize all the other timekeeping mechanisms for the guest.