Re: Google Summer of Code

[Mohit Dhingra <mohitdhingras@xxxxxxxxx>]

--90e6ba614d0623a4f004d86a4ad9
Content-Type: text/plain; charset=ISO-8859-1

*Hi Venkatesh,*

Thanks for clarifications and support. I have been looking around for the
problem of VM exits. I think the following project also shares the same
motivation of bringing down the no. of VM exits


*
----------------------------
Thanks & Regards
Mohit Dhingra
+919611190435*


On 21 March 2013 03:00, Venkatesh Srinivas <vsrinivas@ops101.org> wrote:

> On Tue, Mar 05, 2013 at 03:15:12PM +0530, Mohit Dhingra wrote:
>
>> *Hi Venkatesh,*
>>
>>
>> Thanks a lot for a nice explanatory mail!
>>
>> I found the second project quite interesting, just to repeat  --
>> ** virtio-blk currently 'kicks' the host VMM directly from its
>>   strategy() routine; it may make sense to defer this to a taskqueue. This
>>   is a tiny change, but understanding the performance implications may
>>   take a bit longer.
>>
>> As per my understanding, the notification to host through kick() involves
>> the exit of the guest (as per attached paper). Hence, the aim for this
>> project would also be to minimize the exits, or rather instantaneous
>> exits.
>> Deferring it to the task queue should definitely help. Other things that
>> can be done in this project is batching of the buffers before kick() and
>> dynamically deciding how many buffers can be batched together.
>>
>> Also, not all of the times deferring the 'kick' to taskqueue might not be
>> a
>> good idea. Finding those scenarios would be interesting where it helps,
>> and
>> where it is merely an overhead.
>>
>
> Yep, your understanding is correct.
> QEMU and friends generally try to handle batches of requests per-VMexit,
> so sometimes (often) there are wins to deferred 'kicks'.
> On Mon, Mar 11, 2013 at 09:42:08PM +0530, Mohit Dhingra wrote:
>
>>   Hi Venkatesh,
>>   Will you be able to mentor this project? I actually wanted to get
>>   some
>>   more info and hands on before applying for GSoC project. Please also
>>   check
>>   the previous mail and my proposal.
>>
>
> I'd be happy to mentor a project to work on performance of DFly under
> virtualization (KVM or w/e), but this alone would be too small for a
> full GSoC project, I think. Working on a few of the aspects I mentioned
> earlier (or anything you come up with! very strongly encouraged!) would
> be a better fit for a full project.
>  Take care,
> -- vs;
>

--90e6ba614d0623a4f004d86a4ad9
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr"><b>Hi Venkatesh,</b><div><br></div><div>Thanks for clarifi=
cations and support. I have been looking around for the problem of VM exits=
. I think the following project also shares the same motivation of bringing=
 down the no. of VM exits=A0</div>

<div><br><div class=3D"gmail_extra"><br clear=3D"all"><div><b><div><b>-----=
----------------------- <br></b></div>Thanks &amp; Regards<br><font color=
=3D"#888888">Mohit Dhingra=A0<br>+919611190435</font></b></div>
<br><br><div class=3D"gmail_quote">On 21 March 2013 03:00, Venkatesh Sriniv=
as <span dir=3D"ltr">&lt;<a href=3D"mailto:vsrinivas@ops101.org"; target=3D"=
_blank">vsrinivas@ops101.org</a>&gt;</span> wrote:<br><blockquote class=3D"=
gmail_quote" style=3D"margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-=
left:1ex">

On Tue, Mar 05, 2013 at 03:15:12PM +0530, Mohit Dhingra wrote:<br>
<blockquote class=3D"gmail_quote" style=3D"margin:0 0 0 .8ex;border-left:1p=
x #ccc solid;padding-left:1ex">
*Hi Venkatesh,*<div class=3D"im"><br>
<br>
Thanks a lot for a nice explanatory mail!<br>
<br>
I found the second project quite interesting, just to repeat =A0--<br>
** virtio-blk currently &#39;kicks&#39; the host VMM directly from its<br>
=A0 strategy() routine; it may make sense to defer this to a taskqueue. Thi=
s<br>
=A0 is a tiny change, but understanding the performance implications may<br=
>
=A0 take a bit longer.<br>
<br>
As per my understanding, the notification to host through kick() involves<b=
r>
the exit of the guest (as per attached paper). Hence, the aim for this<br>
project would also be to minimize the exits, or rather instantaneous exits.=
<br>
Deferring it to the task queue should definitely help. Other things that<br=
>
can be done in this project is batching of the buffers before kick() and<br=
>
dynamically deciding how many buffers can be batched together.<br>
<br>
Also, not all of the times deferring the &#39;kick&#39; to taskqueue might =
not be a<br>
good idea. Finding those scenarios would be interesting where it helps, and=
<br>
where it is merely an overhead.<br>
</div></blockquote>
<br>
Yep, your understanding is correct. <br>
QEMU and friends generally try to handle batches of requests per-VMexit, so=
 sometimes (often) there are wins to deferred &#39;kicks&#39;. <br><div cla=
ss=3D"im">
On Mon, Mar 11, 2013 at 09:42:08PM +0530, Mohit Dhingra wrote:<br>
<blockquote class=3D"gmail_quote" style=3D"margin:0 0 0 .8ex;border-left:1p=
x #ccc solid;padding-left:1ex">
=A0 Hi Venkatesh,<br>
=A0 Will you be able to mentor this project? I actually wanted to get<br>
=A0 some<br>
=A0 more info and hands on before applying for GSoC project. Please also<br=
>
=A0 check<br>
=A0 the previous mail and my proposal.<br>
</blockquote>
<br></div>
I&#39;d be happy to mentor a project to work on performance of DFly under<b=
r>
virtualization (KVM or w/e), but this alone would be too small for a<br>
full GSoC project, I think. Working on a few of the aspects I mentioned<br>
earlier (or anything you come up with! very strongly encouraged!) would<br>
be a better fit for a full project.<br>
=A0Take care,<br>
-- vs;<br>
</blockquote></div><br></div></div></div>

--90e6ba614d0623a4f004d86a4ad9--