Received: (from majordomo@localhost) by oss.sgi.com (8.11.2/8.11.3) id f6GManc02206 for netdev-outgoing; Mon, 16 Jul 2001 15:36:49 -0700 Received: from pizda.ninka.net (IDENT:root@pizda.ninka.net [216.101.162.242]) by oss.sgi.com (8.11.2/8.11.3) with SMTP id f6GMamV02203 for ; Mon, 16 Jul 2001 15:36:48 -0700 Received: (from davem@localhost) by pizda.ninka.net (8.9.3/8.9.3) id PAA16263; Mon, 16 Jul 2001 15:36:46 -0700 From: "David S. Miller" MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <15187.27774.725094.688515@pizda.ninka.net> Date: Mon, 16 Jul 2001 15:36:46 -0700 (PDT) To: Ben LaHaise Cc: Subject: Re: [PATCH] skb_{over,under}_panic optimizations In-Reply-To: References: X-Mailer: VM 6.75 under 21.1 (patch 13) "Crater Lake" XEmacs Lucid Sender: owner-netdev@oss.sgi.com Precedence: bulk Content-Length: 802 Lines: 24 Ben LaHaise writes: > Below is a patch that moves the skb_{over,under}_panic function calls in > skb_put and skb_push out of line on i386 and hopefully improves register > allocation. If this turns out to be useful, there are bunch of other > places we can move these kinds useful debugging assertions out of line. > Comments? I can't see how this can make all that much of a difference, as Andi has stated already. Especially on x86. I mean, GCC is going to generate a branch around the "call skb_foo_panic" code block, and that code block will likely sit in (at least mostly) it's own cache line. x86 code is so dense anyways, so this change can hardly make a difference. I'm willing to, and would happily be, proven wrong. Show me some numbers. Later, David S. Miller davem@redhat.com