[dpdk-dev] [PATCH v5 3/4] vhost: using EVENTFD_COPY2

[Pavel Boldin]

Huawei, Thomas,

Please find an updated patchset in the appropriate mail thread.

With best regards,
Pavel

On Mon, Oct 26, 2015 at 3:45 AM, Xie, Huawei <huawei.xie at intel.com> wrote:

> On 10/21/2015 8:16 PM, Pavel Boldin wrote:
> > Xie,
> >
> > Please find my comments intermixed below.
> >
> > On Tue, Oct 20, 2015 at 12:52 PM, Xie, Huawei <huawei.xie at intel.com
> > <mailto:huawei.xie at intel.com>> wrote:
> >
> >     Thanks Pavel for this work.
> >     This is what we think is the better implementation for eventfd
> >     proxy, in
> >     our last review.
> >     Could you add an additional patch to remove the old implementation?
> >
> > I'm not really sure if we should do it -- imagine upgrading from one
> > version of DPDK to another.
> > Given the current implementation there is a backward compatibility.
> I couldn't image the case any one would run old dpdk app with the new
> dpdk module. However I am ok you leave it here, :), we could remove this
> in next release.
> Could you finish rebasing the patch before end of next week, otherwise
> it will lose chance of being merged.
> >
> >
> >
> >     Again, please run checkpatch.pl <http://checkpatch.pl> against
> >     your patch.
> >
> > Oops. Thanks for pointing out.
> >
> >
> >     On 8/29/2015 2:51 AM, Pavel Boldin wrote:
> >
> >     [...]
> >     > +
> >     > +int
> >     > +eventfd_init(void)
> >     > +{
> >     > +     if (eventfd_link > 0)
> >     0 could be valid fd. Change it to:
> >
> > Got it. Thanks.
> >
> >
> >         if (eventfd_link >= 0)
> >     Change elsewhere if i miss it.
> >     > +int
> >     > +eventfd_free(void)
> >     > +{
> >     > +     if (eventfd_link > 0)
> >     same as above:
> >         if (eventfd_link >= 0)
> >
> >     [...]
> >
> >
> > --
> > Sincerely,
> >  Pavel
>
>