From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: RPS and forwarding Date: Mon, 26 Apr 2010 07:15:05 +0200 Message-ID: <1272258905.2069.971.camel@edumazet-laptop> References: <20100426022415.GA20323@gondor.apana.org.au> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Herbert Xu , "David S. Miller" , netdev@vger.kernel.org To: Tom Herbert Return-path: Received: from mail-bw0-f219.google.com ([209.85.218.219]:36909 "EHLO mail-bw0-f219.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751680Ab0DZFPJ (ORCPT ); Mon, 26 Apr 2010 01:15:09 -0400 Received: by bwz19 with SMTP id 19so127010bwz.21 for ; Sun, 25 Apr 2010 22:15:07 -0700 (PDT) In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: Le dimanche 25 avril 2010 =C3=A0 21:44 -0700, Tom Herbert a =C3=A9crit = : > > Apart from not using RPS on routers, I suppose people doing > > forwarding will simply have to maintain a constant RPS table, > > and forgo its local redirection capabilities. > > >=20 > I think you'd want RPS on router (steering packets using hash and CPU > mask). Most of your concerns are about RFS (steering by flows), whic= h > is probably more appropriate for a server. We could probably rename RFS parts to RFS to avoid confusion ?