From owner-freebsd-hackers Fri Oct 22 13:15:40 1999 Delivered-To: freebsd-hackers@freebsd.org Received: from dingo.cdrom.com (dingo.cdrom.com [204.216.28.145]) by hub.freebsd.org (Postfix) with ESMTP id 9C6E214BD3 for ; Fri, 22 Oct 1999 13:15:37 -0700 (PDT) (envelope-from mike@dingo.cdrom.com) Received: from dingo.cdrom.com (localhost [127.0.0.1]) by dingo.cdrom.com (8.9.3/8.8.8) with ESMTP id BAA00435; Fri, 22 Oct 1999 01:54:15 -0700 (PDT) (envelope-from mike@dingo.cdrom.com) Message-Id: <199910220854.BAA00435@dingo.cdrom.com> X-Mailer: exmh version 2.0.2 2/24/98 To: "Ronald G. Minnich" Cc: hackers@freebsd.org Subject: Re: profile of tcp In-reply-to: Your message of "Thu, 21 Oct 1999 14:54:06 MDT." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Fri, 22 Oct 1999 01:54:15 -0700 From: Mike Smith Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG > I'm wondering if anyone in this group has done or knows of a good profile > of a tcp send going from user mode to bits on the wire. Reason I'm asking > is the old "put TCP/IP on the NIC" is once again rearing its head, and I'm > hoping there are numbers I can point to (ones that aren't old, that is) > about why this may not be the best idea in the world. FreeBSD seems a good > choice since it has a pretty reasonable implementation. I'd start with "the NIC will require insane amounts of memory to deal with links with large bandwidth/delay products". And when people tell you that the NIC can just use system memory, you should slap them around the head. The thought of a piece of hardware screwing with the kernel memory allocator gives me the creeps. 8) -- \\ Give a man a fish, and you feed him for a day. \\ Mike Smith \\ Tell him he should learn how to fish himself, \\ msmith@freebsd.org \\ and he'll hate you for a lifetime. \\ msmith@cdrom.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message