Re: [PATCH RFC v2 5/6] KVM: moving dirty bitmaps to user space

Avi Kivity <[email protected]> Fri, 23 Apr 2010 11:45:37 +0000
Newsgroups org.kernel.vger.kvm-ia64,org.kernel.vger.kvm,org.kernel.vger.kvm-ppc
Message-ID <[email protected]>
On 04/23/2010 02:14 PM, Takuya Yoshikawa wrote:
>
>> Do you have performance numbers? I'm interested in both measurements of
>> KVM_SWITCH_DIRTY_LOG under various conditions and macro benchmarks (for
>> example, total guest throughput improvement under Kemari).
>>
>
> Currently, I'm just checking the performance visually.
>   - on laptops, we can feel the speed directly: my favorite is installing
>     ubuntu or debian by alternate installers
>
>   - live migration with heavy work load
>
> Now that I've got the overall design, I want to measure the 
> performance by numbers.
>
>
> About performance under Kemari: we(oss.ntt.co.jp staffs: me and 
> Fernando) are
> now concentrating on improving the basic live-migration 
> infrastructures and
> they(lab.ntt.co.jp staffs) are working hard for building Kemari itself.
>
>   - We are also interested in using live-migration with HA software 
> and this needs
>     light, stable live-migration: same as Kemari!
>

General live migration improvements are also interesting, I just the 
improvement would be more pronounced under Kemari.  Looking forward to 
seeing the results.

-- 
Do not meddle in the internals of kernels, for they are subtle and quick to panic.