Am Montag, 1. Oktober 2018, 21:04:33 CEST schrieb Ido Schimmel: > On Mon, Oct 01, 2018 at 08:54:08PM +0200, Richard Weinberger wrote: > > So the only option is having a bridge and transport STP via tc-mirred > > or patching the bridge code (what we do right now). > > And I vote for the first option. I understand it involves more typing,
hehe, it is not about typing. The setup is done by a script. And we both know that getting a patch upstream is much more work than typing a few lines of hacky bash scripts. Since I want a decent solution and feedback I'm bringing this up here. I could also just go with my in-house patch and don't tell anyone... > but I see no reason to push more complexity into the kernel - and break > standards - when you can relatively easily accomplish the same thing in > other ways. If having a bridge plus u32+mirred for STP bypass is the preferred solution, I'm fine with it. So far we use the kernel patch and didn't test the mirred-bypass a lot. My fear was that mirred rules from eth0 to eth1 and back might cause a loop or confuse the bridge... > Adding Nik and Roopa who now maintain the bridge code and should > eventually decide about this. Thanks, //richard
