Date: Wed, 20 Jun 2007 14:19:05 -0700 From: Julian Elischer <julian@elischer.org> To: Nicolas Cormier <n.cormier@gmail.com> Cc: freebsd-hackers@freebsd.org, John Polstra <jdp@polstra.com> Subject: Re: in-kernel tcp server Message-ID: <467999C9.9000402@elischer.org> In-Reply-To: <c4630b800706201350p176ddadcu6b4eb341751d94e7@mail.gmail.com> References: <c4630b800706180227x2f1f433dr4ef55e8623062bf1@mail.gmail.com> <467787EF.9060009@elischer.org> <46797825.10900@polstra.com> <c4630b800706201239jdf09685t1574e78493492029@mail.gmail.com> <46799032.5060009@polstra.com> <c4630b800706201350p176ddadcu6b4eb341751d94e7@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Nicolas Cormier wrote: > On 6/20/07, John Polstra <jdp@polstra.com> wrote: >> Using ng_ksocket is almost the same as using the so* functions, since >> the ksocket methods call the so* functions. But by using netgraph, you >> get a nice management interface, too. >> >> For my application, I found that going through the socket layer (the so* >> functions and/or ng_ksocket) hurt performance too much. That's why I >> ended up bypassing them. > > Thanks for this precision. I would actually like to address the performance issues. is there any chance the oldest version (4.x based) might be released, or at least it would be nice to get the code snippet that attaches to eh ng_ksocket and reads and writes the stream.. I could make a TCP ECHO node that way and use it for tracking down the bottlenecks I'm not too interested in the actual webserver itself.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?467999C9.9000402>