[dpdk-dev] [RFC PATCH] virtio: virtio ring layout optimization and vectorization rx

Stephen Hemminger stephen at networkplumber.org
Wed Sep 23 00:55:23 CEST 2015


On Tue, 22 Sep 2015 15:37:13 +0200
Thomas Monjalon <thomas.monjalon at 6wind.com> wrote:

> 2015-09-22 09:29, Xie, Huawei:
> > On 9/22/2015 4:38 PM, Thomas Monjalon wrote:
> > > I thought it was clear we must avoid #ifdef for configuration.
> > > Please check how to add a runtime flag.
> > > Or better: keep only one path which works everywhere and well optimized.
> > 
> > Thomas, i have this in mind when i am developing this feature and i plan
> > to discuss this with you. In theory, the best solution would be using
> > run time flag and the result would be normally we always choose the
> > optimized path.
> > The situation in real world is, in my mind, this feature isn't mature
> > enough(Of course this doesn't mean it has known issues). One good
> > solution in kernel community is experimental features.
> > Could we also have experimental/development tag? I would like to put
> > this as experimental/development feature temporarily, turn it off by
> > default and continue to improve it.
> 
> I think it is a rework, not an experimental feature.
> 
> > The advantage is we have it in tree and every developers could pull it
> > and help improve it. Also, it is the base for continuous vhost
> > optimization. We should have a performance optimized driver for the
> > device side optimization.
> 
> If there are some acceptance problem, it can be solved on the list.
> If there are some bugs after integration, it can be fixed before the release,
> as there are some validation and non-regression tests.
> 
> If the new Rx/Tx code can replace the old one, please replace it.
> If the use cases are different, please use a runtime flag.
> It it is not ready, please do more tests and re-submit later.
> 
> By the way, thanks for your work.

Agree with Thomas.
Any feature should be always on, and negotiated by existing virtio
feature bits.


More information about the dev mailing list