Juli Mallett

I'd just amend that to note that even with a promiscuous listen, you still have to have L2 and L3 connectivity towards the host running the application, which means all...

Those sound like both good long-term goals and a good set of reasonable next-steps. I've always felt that a packet processor alongside `libuinet` is the only reasonable configuration, and I...

Please include the command you ran, the directory within libuinet you ran it in, and the output you got.

@ratliffstan, what @weliu is saying is that removing the net/vnet.h include from uinet_internal.h and then adding, I believe, a forward declaration in its place of `struct vnet;` or similar. It...

@weliu, some of that sounds suspicious to me. It seems likely that the files in question should be using the libuinet copies of headers, not the ones in /usr/include. Right,...

@ratliffstan, that is a reasonable concern, but honestly I'm not sure libuinet is the place to fix it. Honestly, in that sort of situation what you want is to use...

Abdul Alim, Thanks for submitting this bug; it sounds like you've done some of the initial checks needed. I'm sure @pkelsey has noticed your bug as have I, and so...

I can't speak for Pat, but I wonder if you could say more about what the value of sendfile(2) would be for you in this case. That is, if you...

See issue #11 for information on `libuinet`'s current inability to make use of checksum offloading due to deficiencies of `netmap`. And yes, if running in a VM or on hardware...

I don't think `netmap` has any way to indicate that a packet has a hardware checksum yet; presumably the `flags` field in `struct netmap_slot` would need to track this, as...