From owner-svn-src-head@FreeBSD.ORG Fri Feb 4 22:07:52 2011 Return-Path: Delivered-To: svn-src-head@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id A9C631065670; Fri, 4 Feb 2011 22:07:52 +0000 (UTC) (envelope-from tuexen@fh-muenster.de) Received: from mail-n.franken.de (drew.ipv6.franken.de [IPv6:2001:638:a02:a001:20e:cff:fe4a:feaa]) by mx1.freebsd.org (Postfix) with ESMTP id 09DB68FC08; Fri, 4 Feb 2011 22:07:52 +0000 (UTC) Received: from [192.168.1.113] (p508FA367.dip.t-dialin.net [80.143.163.103]) (Authenticated sender: macmic) by mail-n.franken.de (Postfix) with ESMTP id D059F1C0C0BD8; Fri, 4 Feb 2011 23:07:50 +0100 (CET) Mime-Version: 1.0 (Apple Message framework v1082) Content-Type: text/plain; charset=us-ascii From: Michael Tuexen In-Reply-To: <1F9E5E6D-ADCA-4F43-B04D-54CCBD5AC2A8@freebsd.org> Date: Fri, 4 Feb 2011 23:07:49 +0100 Content-Transfer-Encoding: quoted-printable Message-Id: <37716196-EE55-4D94-82BB-4DE19AAF34F2@fh-muenster.de> References: <201102031005.p13A5Vwi040803@svn.freebsd.org> <1F9E5E6D-ADCA-4F43-B04D-54CCBD5AC2A8@freebsd.org> To: "Robert N. M. Watson" X-Mailer: Apple Mail (2.1082) Cc: svn-src-head@freebsd.org, Randall Stewart , svn-src-all@freebsd.org, src-committers@freebsd.org Subject: Re: svn commit: r218211 - in head/sys: conf netinet X-BeenThere: svn-src-head@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SVN commit messages for the src tree for head/-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Feb 2011 22:07:52 -0000 On Feb 4, 2011, at 11:00 PM, Robert N. M. Watson wrote: >=20 > On 4 Feb 2011, at 13:30, Michael Tuexen wrote: >=20 >>> Hmm. It might be better to add a new NETISR_SCTP and use netisr's = support for multithreading? >> That sounds really good. >>=20 >> Is it possible that different network cards put packets in the same = queue? >> That would be helpful in the case of SCTP. >>>=20 >>> (I'm preparing a patch for review that enhances that a bit so that = protocols can be a bit more expressive in terms of specifying dispatch = policy, etc, currently). >> Great! >=20 > You get a spectrum of possibilities -- protocols can request source = ordering (i.e., ifnet), flow ordering (in which they expose ordering = information but not CPU affinity), or a full CPU affinity. How work is = distributed and what queue it ends up in depends on the model, but yes, = you can request that interfaces distribute packets to various queues, = and that multiple interfaces use consistent distribution models. I = implement this for RSS, where there's a global RSS setup that is = propagated to supporting device drivers so that they can align their = distribution with the network stack's affinity model for connection = groups. That sounds great. Let us know when the code is ready for testing... Best regards Michael >=20 > Robert >=20 >=20