[dpdk-dev] [PATCH] doc: introduce PVP reference benchmark

Maxime Coquelin maxime.coquelin at redhat.com
Tue Nov 29 11:29:58 CET 2016


Hi Yuanhan,

On 11/29/2016 11:16 AM, Yuanhan Liu wrote:
> On Thu, Nov 24, 2016 at 08:35:51AM +0100, Maxime Coquelin wrote:
>>
>>
>> On 11/24/2016 06:07 AM, Yuanhan Liu wrote:
>>> First of all, thanks for the doc! It's a great one.
>> Thanks.
>> I would be interested to know if you have other tuning I don't mention
>> in this doc.
>
> I was thinking we may need doc some performance impacts by some features,
> say we observed that indirect desc may be good for some cases, while may
> be bad for others. Also, the non mergeable Rx path outweighs the mergeable
> Rx path. If user cares about the perfomance and ascertains all packets
> fits into a typical MTU, he may likely want to disable the mergeable
> feature, which is enabled by default.
>
> Maybe we could start a new doc, or maybe we could add a new section here?

I agree that we should documents impact of Virtio features on traffic
profile.
My opinion is that it deserves a dedicated document.

For this PVP doc, I suggest we add a section stating that one could try
with different Virtio features, and in Kevin's result template
proposal, we add a line for Virtio features enabled/disabled.

Thanks,
Maxime
>
> 	--yliu
>


More information about the dev mailing list