From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: RPS and forwarding Date: Mon, 26 Apr 2010 09:38:54 +0200 Message-ID: <1272267534.2346.7.camel@edumazet-laptop> References: <20100426045316.GA21810@gondor.apana.org.au> <20100425.232857.145290769.davem@davemloft.net> <20100426063136.GA22401@gondor.apana.org.au> <1272266716.2346.5.camel@edumazet-laptop> <20100426073017.GA22803@gondor.apana.org.au> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: David Miller , therbert@google.com, netdev@vger.kernel.org To: Herbert Xu Return-path: Received: from mail-bw0-f219.google.com ([209.85.218.219]:54360 "EHLO mail-bw0-f219.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753717Ab0DZHjA (ORCPT ); Mon, 26 Apr 2010 03:39:00 -0400 Received: by bwz19 with SMTP id 19so192137bwz.21 for ; Mon, 26 Apr 2010 00:38:57 -0700 (PDT) In-Reply-To: <20100426073017.GA22803@gondor.apana.org.au> Sender: netdev-owner@vger.kernel.org List-ID: Le lundi 26 avril 2010 =C3=A0 15:30 +0800, Herbert Xu a =C3=A9crit : > On Mon, Apr 26, 2010 at 09:25:16AM +0200, Eric Dumazet wrote: > > > > RFS is already working like that, if RPS is not used in conjonction= =2E > >=20 > > Forwarded traffic will see a non tagged rfs flow entry, so this skb= will > > be processed by this cpu, not a remote one. > >=20 > > Currently, only an application can set a RFS flow entry. >=20 > I was referring to the case when a forwarded flow gets hashed to > the same index as a local flow. Ah OK, with same rxhash I guess ? (we could store rxhash next to cpu in struct rps_dev_flow, or 16bit par= t of it in the existing padding)