Date: Thu, 25 May 2017 18:21:14 +0200 From: Vincenzo Maffione <v.maffione@gmail.com> To: Harry Schmalzbauer <freebsd@omnilan.de> Cc: freebsd-net <freebsd-net@freebsd.org> Subject: Re: [panic] netmap(4) and if_lagg(4) Message-ID: <CA%2B_eA9i6wG3iPv4modNhSU5DmThKyhnw6YM_Xwt3ai3Kfz7cJQ@mail.gmail.com> In-Reply-To: <592701D6.7030301@omnilan.de> References: <58CBCD7A.8060301@omnilan.de> <CA%2B_eA9iCT7evWUcZMA_ViKfrZnSHp3OpBTS5c4iJ9=ZjO-Pfgw@mail.gmail.com> <58CC23F5.7060507@omnilan.de> <CA%2B_eA9iajZOUFsnWKdodN7zMvst8wn0xViM4xxEx%2B41jw_0B3g@mail.gmail.com> <58CFA394.8070901@omnilan.de> <CA%2B_eA9jf_VjcYUZynu5CXx-ps5z7PSxOky=QLpR-miqtxmMU5w@mail.gmail.com> <5926EE96.1010000@omnilan.de> <CA%2B_eA9gcMD1QyG35p5UY8kz6n1kF%2B56Arz3q1T8HVBfMv3XN0w@mail.gmail.com> <5926F9F9.4040706@omnilan.de> <CA%2B_eA9hripEStmfJhj_Q93OF5jFf2nfQXeuA2DnuSjBmJi6j4g@mail.gmail.com> <592701D6.7030301@omnilan.de>
next in thread | previous in thread | raw e-mail | index | archive | help
2017-05-25 18:09 GMT+02:00 Harry Schmalzbauer <freebsd@omnilan.de>: > Bez=C3=BCglich Vincenzo Maffione's Nachricht vom 25.05.2017 17:56 (localt= ime): > > I see the bug is in FreeBSD 11. I attached the simple patch to fix it. > > Can someone commit the patch to 11/stable? > > > > Harry: You should be able to workaround the bug by setting > > > > # sysctl dev.netmap.generic_rings=3D1 > > I'll recompile with your patch, thanks a lot! > > > And yes, if_lagg(4) doesn't have native netmap support, like all the > > meta-drivers (e.g. vlan, tunnels, etc.). > > Point is that you should implement link aggregation in your application > (in > > user-space). > > Thanks for confirmation. > My problem is that I can't pass frames to guests without vlan filtering > first :-( > Then you need an ad-hoc userspace netmap application that does this job, reading the tagged frames from the NIC, strip the tag and dispatch to the proper VM. > > Focus is not on inter-VM-connection, but most efficient port usage _and_ > vm-interconnection. The more I learn the less I know what to do ;-) > If I only had VF-capable hardware (actually VF-"supported" hardware, > 82576 was SR-IOV enabled, but at the advent of 10GbE, SR-IOV support for > older chips was removed - where initially implemented - and of course > not implemented anywhere else). > > -harry > > --=20 Vincenzo Maffione
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CA%2B_eA9i6wG3iPv4modNhSU5DmThKyhnw6YM_Xwt3ai3Kfz7cJQ>