Date: Tue, 5 Aug 2003 22:19:38 +0300 From: "Petri Helenius" <pete@he.iki.fi> To: <net@freebsd.org>, "John Polstra" <jdp@polstra.com> Cc: edwin@freebsd.org Subject: Re: bpf, ipfw and before-and-after Message-ID: <01ca01c35b86$83c75590$812a40c1@PETEX31> References: <20030805133922.GA7713@k7.mavetju> <200308051817.h75IH7jb006622@strings.polstra.com>
next in thread | previous in thread | raw e-mail | index | archive | help
> > This would add additional delays to the code path for both ingress > and egress. In a world where gigabit ethernet is becoming the norm, > every nanosecond counts. I don't think the benefits of your proposal > would justify the performance loss. At the very least, I'd want the > extra calls to bpf_mtap to be present in the code only if enabled by > an option in the kernel config file. > bpf is slow by design because the design mandates a packet copy. It´s not a justification to make it slower but gigabit performance out of bpf is just not there until memory speeds increase a lot or the copying goes away. Pete
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?01ca01c35b86$83c75590$812a40c1>