Re: [Xen-devel] cpuidle and un-eoid interrupts at the local apic

["Thimo E." <abc@xxxxxxxxxx>]

Hello Yang,

The problem that we are discussing here seems to come from the 
interaction of my raid controller (Areca, ARC-1212) and the hardware.
When I enable MSI on that controller the server crashes with the known 
error messages between 1 day and 7 days.  When I disable MSI I don't see 
these crashes anymore.
Andrew doesn't have this controller but he could also observe these type 
of crashes with another MSI enabled card, I think the networc card. But 
less often, I think 2 times in the last 4 months.
My cpuinfo nor dmesg show any microcode information, perhaps Xen hides 
that info ?!
Best regards
  Thimo

Am 17.09.2013 04:09, schrieb Zhang, Yang Z:
> Hi, Thimo,
>
> I cannot reproduce this issue in my box after running about two weeks:
> I started four guests (two PV guests and two HVM guests). And each guest runs a 
> simple workload (ping a remote machine). After two weeks, the machine still 
> works no crash and panic happen. Are there any special workload required to 
> reproduce this issue?
>
> Attached the cpuinfo and pci info in my box. Please compare it with yours to 
> see whether it is same. Especially, the microcode version.
>
> Best regards,
> Yang

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel