From owner-freebsd-hackers Sun Mar 8 00:04:34 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id AAA24232 for freebsd-hackers-outgoing; Sun, 8 Mar 1998 00:04:34 -0800 (PST) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from dingo.cdrom.com (dingo.cdrom.com [204.216.28.145]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id AAA24221 for ; Sun, 8 Mar 1998 00:04:31 -0800 (PST) (envelope-from mike@dingo.cdrom.com) Received: from dingo.cdrom.com (localhost [127.0.0.1]) by dingo.cdrom.com (8.8.8/8.8.5) with ESMTP id AAA09131; Sun, 8 Mar 1998 00:02:09 -0800 (PST) Message-Id: <199803080802.AAA09131@dingo.cdrom.com> X-Mailer: exmh version 2.0zeta 7/24/97 To: Marc Slemko cc: Mike Smith , hackers@FreeBSD.ORG Subject: Re: kernel wishlist for web server performance In-reply-to: Your message of "Sat, 07 Mar 1998 23:26:55 MST." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sun, 08 Mar 1998 00:02:07 -0800 From: Mike Smith Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG > On Sat, 7 Mar 1998, Mike Smith wrote: > > > this regard (ie. have specific HTTP-transmit-file system calls > > everywhere)? > > Now, if you want to talk about HTTP-transmit-file calls and things being > specialized for just one protocol, I was actually joking about that > earlier today. > > HTTP-NG, which is currently under very initial development, will > almost certainly allow for multiplexed transfers. ie. multiple > documents multiplexed over a single TCP connection. Ugh. Why multiplex over an already-multiplexing protocol? This sounds like yet another attempt at trying to get around a problem with a new solution rather than fixing the original one. > Now, consider how to efficiently implement sending small fragments > (in SMUX, a fragment is a contiguous bit of data from one of the > multiplexed streams in the TCP connection) on the server. With > the obvious ways, all these efficiency gains go out the window. > So, to get around that, I was joking that an Apache LKM to implement > MUX would probably help. No, I'm not really serious because > it is such a lame thing to do and has horrible portability. But... > this problem is probably going to come up in the future, and I'm > still trying to see about efficient ways of doing it. Sigh. Heh. What you want is to always stuff your datagrams out, either with more data (hang back a bit) or with junk. Call it "synchronous TCP". 8) -- \\ Sometimes you're ahead, \\ Mike Smith \\ sometimes you're behind. \\ mike@smith.net.au \\ The race is long, and in the \\ msmith@freebsd.org \\ end it's only with yourself. \\ msmith@cdrom.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message