From owner-freebsd-net Sat Jun 3 19:44:55 2000 Delivered-To: freebsd-net@freebsd.org Received: from bubba.whistle.com (bubba.whistle.com [207.76.205.7]) by hub.freebsd.org (Postfix) with ESMTP id 77C6537B8F8 for ; Sat, 3 Jun 2000 19:44:53 -0700 (PDT) (envelope-from archie@whistle.com) Received: (from archie@localhost) by bubba.whistle.com (8.9.3/8.9.2) id TAA72017; Sat, 3 Jun 2000 19:44:14 -0700 (PDT) From: Archie Cobbs Message-Id: <200006040244.TAA72017@bubba.whistle.com> Subject: Re: Patch review request (ng_ether(4)) In-Reply-To: from Bruce Evans at "Jun 3, 2000 06:01:56 pm" To: bde@zeta.org.au (Bruce Evans) Date: Sat, 3 Jun 2000 19:44:14 -0700 (PDT) Cc: julian@elischer.org, freebsd-net@freebsd.org X-Mailer: ELM [version 2.4ME+ PL54 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-net@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Bruce Evans writes: > > I think the impact will be small, pretty much one pointer != NULL > > test per packet. The fact that ether_input() has been split into > > ether_input() and ether_input2() should not matter because gcc will > > optimize away the function call to ether_input2(), because it comes > > at the very tail end of ether_input(). > > gcc is only documented to do tail call optimizations on Intel 960's, > only with the option -mtail-call. For i386's, -mtail-call doesn't > exist, and I've never seen gcc do tail-call optimizations. Hmm.. I was under the impression that tail-call optimization was a "normal" optimization.. maybe not. -Archie ___________________________________________________________________________ Archie Cobbs * Whistle Communications, Inc. * http://www.whistle.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message