[PVE-User] Patching current PVE kernel (was: soft lockup after live migration)

Tomasz Chmielewski mangoo at wpkg.org
Mon Oct 26 10:21:23 CET 2009


Hi,

What would be the best way to patch a current PVE kernel (so that I 
produce a .deb package out of it)?

I have some problems with live migration - guests are in soft lockup state.

See below for more info (I signalled it on kve mailing list a few days ago):


Marcelo Tosatti wrote:

> The screenshots seem to indicate a paravirt mmu problem.
> 
> Try to patch the x86.c file from kvm kernel module with:
> 
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 2bc9693..b2e196e 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -1238,8 +1238,8 @@ int kvm_dev_ioctl_check_extension(long ext)
>         case KVM_CAP_NR_MEMSLOTS:
>                 r = KVM_MEMORY_SLOTS;
>                 break;
> -       case KVM_CAP_PV_MMU:
> -               r = !tdp_enabled;
> +       case KVM_CAP_PV_MMU:    /* obsolete */
> +               r = 0;
>                 break;
>         case KVM_CAP_IOMMU:
>                 r = iommu_found();
> 
> You'll probaby have to do it manually (this disables pvmmu).
> 
> On Sat, Oct 24, 2009 at 02:40:20AM +0200, Tomasz Chmielewski wrote:
>> I have a "BUG: soft lockup" after live migrating guest from host_1 to host_2 (when I migrate the guest from host_2 to host_1, everything is good).
>>
>> The kernel still lives (the guest replies to pings, and the kernel prints "BUG: soft lockup" every minute, but that's all it can do when it happens).
>>
>>
>> I made some screenshots, available here:
>>
>> http://www1.wpkg.org/lockup1.png
>> http://www1.wpkg.org/lockup2.png
>>
>>
>> I tried adding "-cpu qemu64,-nx" to guest command line, but it didn't help.
>>
>> The guest is running Debian Lenny (2.6.26 kernel) with virtio.
>>
>> Is it a known issue? Is there a workaround to it?
>>
>> qemu-kvm is 0.11.0; kernel modules: 86.
>>
>>
>> Below, CPUs on both hosts:
>>
>> host_1 CPU:
>>
>> processor       : 0
>> vendor_id       : AuthenticAMD
>> cpu family      : 15
>> model           : 65
>> model name      : Dual-Core AMD Opteron(tm) Processor 2212
>> stepping        : 2
>> cpu MHz         : 1000.000
>> cache size      : 1024 KB
>> physical id     : 0
>> siblings        : 2
>> core id         : 0
>> cpu cores       : 2
>> fpu             : yes
>> fpu_exception   : yes
>> cpuid level     : 1
>> wp              : yes
>> flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt rdtscp lm 3dnowext 3dnow rep_good pni cx16 lahf_lm cmp_legacy svm extapic cr8_legacy
>> bogomips        : 1994.96
>> TLB size        : 1024 4K pages
>> clflush size    : 64
>> cache_alignment : 64
>> address sizes   : 40 bits physical, 48 bits virtual
>> power management: ts fid vid ttp tm stc
>>
>>
>>
>>
>> host_2 CPU:
>>
>> processor       : 0
>> vendor_id       : GenuineIntel
>> cpu family      : 6
>> model           : 15
>> model name      : Intel(R) Xeon(R) CPU            3050  @ 2.13GHz
>> stepping        : 6
>> cpu MHz         : 2133.407
>> cache size      : 2048 KB
>> physical id     : 0
>> siblings        : 2
>> core id         : 0
>> cpu cores       : 2
>> fpu             : yes
>> fpu_exception   : yes
>> cpuid level     : 10
>> wp              : yes
>> flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall lm constant_tsc arch_perfmon pebs bts rep_good pni monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr lahf_lm
>> bogomips        : 4270.04
>> clflush size    : 64
>> cache_alignment : 64
>> address sizes   : 36 bits physical, 48 bits virtual
>> power management:
>>
>>
>>
>> -- 
>> Tomasz Chmielewski
>> http://wpkg.org
>> --
>> To unsubscribe from this list: send the line "unsubscribe kvm" in
>> the body of a message to majordomo at vger.kernel.org
>> More majordomo info at  http://vger.kernel.org/majordomo-info.html




More information about the pve-user mailing list