From owner-freebsd-net@FreeBSD.ORG Fri Jan 16 16:35:05 2004 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D2D9C16A4CE; Fri, 16 Jan 2004 16:35:05 -0800 (PST) Received: from phantom.cris.net (phantom.cris.net [212.110.130.74]) by mx1.FreeBSD.org (Postfix) with ESMTP id E2A5343D3F; Fri, 16 Jan 2004 16:35:00 -0800 (PST) (envelope-from ru@FreeBSD.org.ua) Received: from phantom.cris.net (ru@localhost [127.0.0.1]) by phantom.cris.net (8.12.10/8.12.10) with ESMTP id i0H0Zfjm010122; Sat, 17 Jan 2004 02:35:41 +0200 (EET) (envelope-from ru@FreeBSD.org.ua) Received: (from ru@localhost) by phantom.cris.net (8.12.10/8.12.10/Submit) id i0H0Zfme010117; Sat, 17 Jan 2004 02:35:41 +0200 (EET) (envelope-from ru) Date: Sat, 17 Jan 2004 02:35:41 +0200 From: Ruslan Ermilov To: Sten Daniel S?rsdal Message-ID: <20040117003541.GE9410@FreeBSD.org.ua> References: <0AF1BBDF1218F14E9B4CCE414744E70F5D97FF@exchange.wanglobal.net> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="vmttodhTwj0NAgWp" Content-Disposition: inline In-Reply-To: <0AF1BBDF1218F14E9B4CCE414744E70F5D97FF@exchange.wanglobal.net> User-Agent: Mutt/1.5.5.1i cc: freebsd-hackers@freebsd.org cc: freebsd-net@freebsd.org Subject: Re: ip_input - chksum - why is it done so early in ip_input? X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 17 Jan 2004 00:35:06 -0000 --vmttodhTwj0NAgWp Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Sat, Jan 17, 2004 at 12:50:04AM +0100, Sten Daniel S?rsdal wrote: >=20 > Apologies for the cross-post, i wasnt sure if this was hackers or net mat= erial. >=20 > I've often wondered why ip checksumming is done on every incoming=20 > packet and not only on the packets that need to be delivered locally. > It looks like a very expensive way of doing it, especially on high > PPS. Basically all hosts do checksumming so why not just pass the bad > packet on, making the forward process alot cheaper (cpu wise)? >=20 > I ran some tests (unable to disclose results) by removing it completely > and it seems to make a noticable impact on the performance. > Especially on for example gaming services where there is a high PPS versus > actual data. >=20 > Besides that i'd like to add that FreeBSD has the fastest forwarding engi= ne > i've seen on any free OS. It's in my opinion a very suitable OS for=20 > routing/forwarding. >=20 Have you tried ``sysctl net.inet.ip.fastforwarding=3D1''? It's documented in the inet(4) manpage. Cheers, --=20 Ruslan Ermilov FreeBSD committer ru@FreeBSD.org --vmttodhTwj0NAgWp Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.4 (FreeBSD) iD8DBQFACINdUkv4P6juNwoRAhHyAJ0ZfQo7YSJ/xababxfCHJWvHxh1MQCdHG5N V+1gNTE7l1R0Q5nCVNAKUB0= =7MK9 -----END PGP SIGNATURE----- --vmttodhTwj0NAgWp--