On Wed, Nov 2, 2016 at 3:57 PM, Thomas Graf <tg...@suug.ch> wrote: > On 1 November 2016 at 17:07, Tom Herbert <t...@herbertland.com> wrote: >> On the other hand, I'm not really sure how to implement for this level >> of performance this in LWT+BPF either. It seems like one way to do >> that would be to create a program each destination and set it each >> host. As you point out would create a million different programs which >> doesn't seem manageable. I don't think the BPF map works either since >> that implies we need a lookup (?). It seems like what we need is one >> program but allow it to be parameterized with per destination >> information saved in the route (LWT structure). > > Attaching different BPF programs to millions of unique dsts doesn't > make any sense. That will obivously will never scale and it's not > supposed to scale. This is meant to be used for prefixes which > represent a series of endpoints, f.e. all local containers, all > non-internal traffic, all vpn traffic, etc. I'm also not sure why we > are talking about ILA here, you have written a native implementation, > why would you want to solve it with BPF again? > We are talking about ILA because you specifically mentioned that in overview log as a use case: "ILA like uses cases where L3 addresses are resolved and then routed".
Tom > If you want to run a single program for all dsts, feel free to run the > same BPF program for each dst. Nobody is forcing you to attach > individual programs.
