From owner-freebsd-net Tue May 29 2: 8:31 2001 Delivered-To: freebsd-net@freebsd.org Received: from mail.chem.msu.ru (mail.chem.msu.ru [195.208.208.19]) by hub.freebsd.org (Postfix) with ESMTP id AD56B37B424 for ; Tue, 29 May 2001 02:08:27 -0700 (PDT) (envelope-from yar@comp.chem.msu.su) Received: from comp.chem.msu.su ([158.250.32.97]) by mail.chem.msu.ru with SMTP (Microsoft Exchange Internet Mail Service Version 5.5.2650.21) id LR567R5H; Tue, 29 May 2001 12:46:10 +0400 Received: (from yar@localhost) by comp.chem.msu.su (8.11.1/8.11.1) id f4T8n5l97267; Tue, 29 May 2001 12:49:05 +0400 (MSD) (envelope-from yar) Date: Tue, 29 May 2001 12:49:04 +0400 From: Yar Tikhiy To: Jonathan Graehl Cc: freebsd-net@FreeBSD.ORG Subject: Re: Ipfilter nat vs ipfw divert + natd performance Message-ID: <20010529124904.A94542@comp.chem.msu.su> References: <000001c0e7e6$6fb1ee00$6dfeac40@straylight.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5i In-Reply-To: <000001c0e7e6$6fb1ee00$6dfeac40@straylight.com>; from jonathan@graehl.org on Mon, May 28, 2001 at 07:24:05PM -0700 Sender: owner-freebsd-net@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hi Jonathan, On Mon, May 28, 2001 at 07:24:05PM -0700, Jonathan Graehl wrote: > I've set up an old Pentium to NAT my little brother's cablemodem using > ipfw/natd. Would I see much better performance from ipfilter? (I > assume that in-kernel NAT would be faster and have more consistent > latency than a user process which might not be scheduled for a while?) > The family does play a game of Tribes now and then, so unpredictable > 10ms delays would not be fun for them. I'd suggest you measure the performance parameters (packet delay, CPU time spent in interrupts etc) for the two cases, and send a small report here ;-) -- Yar To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message