Comment by iscoelho
15 hours ago
You're correct, kernel isn't faster by default. With that said, the following is true:
1) the WireGuard kernel implementation, despite not even being zero-copy, exceeds the performance of the userspace implementation
2) implementations utilizing the userspace network stack have a maximum potential performance (context switch + memcpy is very slow, and that affects UDP disproportionately). It's the wrong approach for meaningful improvement.
Io_uring doesn’t have context switching and may not have memcpy. The trickier thing I suspect to get with wireguard is the encryption and GSO offload
That is not true unfortunately. io_uring only avoids the userspace copy/switch. There are many other copies in the Linux userspace network stack.
What do you mean by “userspace network stack” when we’re talking about io_uring? That’s a contradiction. Unless you mean extra memcpy’s within the kernel network stack, but when talking about the buffer you supply I don’t believe that’s true - your data generally gets directly DMA’ed into the device because the buffer you supplied is pinned and can’t be released until the second CQE is delivered. It would be helpful if you clarified.