Hello,

Michael Beecher, le jeu. 08 oct. 2026 05:12:40 +0000, a ecrit:
> Patch attached. I found this while getting networking usable on hurd-amd64 on
> my Dell E6420 (82579LM). I noticed TCP was very slow and saw that bursts of
> packets got dropped consistently.

Michael Beecher, le jeu. 08 oct. 2026 15:33:24 +0000, a ecrit:
> Anyways, a single read with BPF could return several packets packed
> back-to-back, each preceded by a struct bpf_hdr.  The rump kernel pads each
> record to BPF_ALIGNMENT, which NetBSD's <net/bpf.h> defines as sizeof (long). 
>  rumpnet/net-rump.c advances with its own BPF_WORDALIGN, uses Mach's <device/
> bpf.h>, where that is sizeof (int).

Uh, and then everything gets all wrong from there on.

Nice spot :)

I have rather fixed mach's bpf.h, there is no real reason to stay stuck
with a bogus value there.

Thanks!
Samuel

Reply via email to