On 07/18/2012 07:46 AM, Orion Poplawski wrote:
> On 07/17/2012 04:17 PM, zxq9 wrote:
>> On 07/18/2012 06:55 AM, Orion Poplawski wrote:
>>> While staring at top on my kvm server waiting for it to crash, I noticed
>>> that my idle Fedora kvm guests appear to be consuming between 8-12% cpu
>>> while my idle SL6 guests appear to be consuming between 0.3-2% cpu as
>>> shown in the qemu-kvm processes in top.
>>>
>>> Does anyone have any insight as to why this would be the case?
>>
>> That depends heavily on what version of Fedora they are (particularly
>> Rawhide
>> instances), and what services they are running.
>
> Well, I have a Fedora 17 instance running now with nothing but kernel
> processes and the qemu-kvm process still shows using 7-8% cpu.

There's pretty much no such thing as a F17 instance with nothing but the 
kernel running. Can you log in to one of the instances and check what 
top says is running (like the top 10 or so processes by CPU use)?

The odds that kvm itself is spinning more just to keep F17 alive over 
anything else is remote, but the odds that something in F17 defaults to 
wasteful behavior is quite high (particularly if you are hosting X with 
Gnome Shell -- there are any number of things that waste cycles in there).

That said, you may be affected by the Fedora version of the July 1st 
leap second bug where processes like qpidd eat 1 core (or equivalent) 
entirely while stuck in an infinite loop (this behavior can survive a 
reboot). If you see a single process in top eating a significant 
percentage of its allocated resources try:

date; date $(date +"%m%d%H%M%C%y.%S"); date

on the misbehaving Fedora instance and see if things change.