[dpdk-dev] [PATCH v4 0/5] lib/librte_vhost: user space vhost cuse driver library

[Xie, Huawei]

I turned off CONFIG_RTE_IXGBE_INC_VEC, everything works fine. 

> -----Original Message-----
> From: Xie, Huawei
> Sent: Thursday, September 25, 2014 10:27 PM
> To: Xie, Huawei; Thomas Monjalon
> Cc: dev at dpdk.org
> Subject: RE: [dpdk-dev] [PATCH v4 0/5] lib/librte_vhost: user space vhost cuse
> driver library
> 
> I am preparing v5 patch for vhost lib and vhost example, merging the merge-
> able
> feature. The weird thing is merge-able feature ever works smoothly in my old
> code base which is based on
> 1.7.1, while after I merge with latest repo, mergeable could cause mbuf
> allocation failure.
> I did code comparison of vhost example and lib, the only change is the mbuf
> change.
> Debugging the issue.
> 
> 
> 
> > -----Original Message-----
> > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Xie, Huawei
> > Sent: Thursday, September 25, 2014 11:10 AM
> > To: Thomas Monjalon
> > Cc: dev at dpdk.org
> > Subject: Re: [dpdk-dev] [PATCH v4 0/5] lib/librte_vhost: user space vhost cuse
> > driver library
> >
> >
> >
> > > -----Original Message-----
> > > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > > Sent: Thursday, September 25, 2014 12:22 AM
> > > To: Xie, Huawei
> > > Cc: dev at dpdk.org; Ouyang, Changchun
> > > Subject: Re: [dpdk-dev] [PATCH v4 0/5] lib/librte_vhost: user space vhost
> cuse
> > > driver library
> > >
> > > Hi,
> > >
> > > 2014-09-24 14:32, Ouyang, Changchun:
> > > > This v4 patch remove the jumbo frame related codes
> > > > and Huawei will add it back in a separate patch,
> > >
> > > I'd prefer a v5 which includes these changes.
> > > I know this patchset is pending and reworked many times,
> > > so I'll try to integrate v5 with top priority.
> > >
> > > Other comments:
> > > - examples/vhost/Makefile should not be copied (and removed just after)
> > > - coding style fixes are aligning things but antislashes are not well aligned
> >
> > "Anti-slashes alignment" issues are inherited from old code.
> > There are also hundreds of other serious coding style issues inherited.
> > I would send a separate patch to fix all those coding style issues after the final
> > patch. Otherwise if i have to rework the patch, I have to redo the hundreds of
> > style
> > fixes line by line, which would take too much time, which is very inefficient.
> >
> >
> > > - fuse-devel and kernel-modules-extra packages are not available in
> > >   this form in all distributions, it's better to describe what is behind
> > >   these package names (especially for kernel-modules-extra)
> > >
> > > I won't have time to properly review the big refactoring. But I'm sure
> > > we'll better check it when using it once integrated.
> > > The essential is to be able to view the changes in the git history.
> > > Thanks for this effort.
> > >
> > > --
> > > Thomas