Re: [PATCH 0/1] KVM: make get dirty log ioctl return the first dirty page's position

[Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>]

Avi Kivity wrote:
>>>
>>> Seems to confirm - not much can be skipped.
>>>
>>
>>
>> >> kvm_get_map(slot 1): r= 2044, slot.len= 535822336(2044)
>> Am I wrong? in this case, the return value is suggesting
>> we can skip every 2044(the value in the bracket) bitmap check, right?
> 
> Er, I was wrong, I thought the value in the brackets had the same units 
> as slots.len.  But it's in units of ulongs.
> 
> In this case, the entire bitmap can be skipped, so the saving would be 
> significant.  But this is for an idle load, where we'll converge quickly 
> anyway.  For a busy server, things will look different.
> 
> So I recommend you look at the double buffer approach.  This can 
> eliminate the kernel scan, the copying, and the userspace scan entirely, 
> as well as remove the vmalloc().
> 

OK, I want to try! Thanks for advice.

  Takuya