Ole, Thank you for quick reply. Reply inline.
> -----Original Message----- > From: vpp-dev@lists.fd.io [mailto:vpp-dev@lists.fd.io] On Behalf Of Ole Troan > Sent: Thursday, September 27, 2018 4:49 PM > To: Yang, Zhiyong <zhiyong.y...@intel.com> > Cc: vpp-dev@lists.fd.io; Kinsella, Ray <ray.kinse...@intel.com>; > hujie....@chinatelecom.cn; Liu, Frank M <frank.m....@intel.com> > Subject: Re: [vpp-dev] one question about IP fragment > > Zhiyong, > > >> The next steps for tunnels, to help avoid fragmentation is to add > >> some sort of tunnel path MTU discovery. > > > > It looks very interesting and helpful. And I'm looking forward to seeing it. > > > > However, we fail to send big packet greater than MTU now, for > > example, We have MTU = 1500, when 1500bytes packets are encapped by > > vxlan protocol, of course, the size of packets is bigger than MTU at > > the time , it looks that sending packets fails now. > > You are not master latest? > This is for IPv4 or IPv6 transport? > > Take a look at the packet trace and see how that looks like? > And note that IPv4 with DF=1 or not locally originated IPv6 is not fragmented. > > You can also do testing with https://gerrit.fd.io/r/#/c/14984/ included, which > fixes a problem with tracing after fragmentation. Hujie will check this testing. > > > BTW > > Is DPDK IP fragment/reassembly supported in VPP now? > > No. DPDK fragmentation uses indirect buffers which we don’t have in VPP. > Got it. Do you have plan to support this DPDK feature in VPP? Or always support VPP native implementation Only in future. > Best regards, > Ole Thanks Zhiyong
-=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#10685): https://lists.fd.io/g/vpp-dev/message/10685 Mute This Topic: https://lists.fd.io/mt/26229382/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-