From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: bnx2/5709: Strange interrupts spread Date: Mon, 19 Jul 2010 21:47:55 +0200 Message-ID: <1279568875.2458.0.camel@edumazet-laptop> References: <1279565231.20559.14.camel@HP1> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Christophe Ngo Van Duc , "netdev@vger.kernel.org" To: Michael Chan Return-path: Received: from mail-ww0-f44.google.com ([74.125.82.44]:61290 "EHLO mail-ww0-f44.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S966448Ab0GSTsC (ORCPT ); Mon, 19 Jul 2010 15:48:02 -0400 Received: by wwb39 with SMTP id 39so542822wwb.1 for ; Mon, 19 Jul 2010 12:48:01 -0700 (PDT) In-Reply-To: <1279565231.20559.14.camel@HP1> Sender: netdev-owner@vger.kernel.org List-ID: Le lundi 19 juillet 2010 =C3=A0 11:47 -0700, Michael Chan a =C3=A9crit = : > On Mon, 2010-07-19 at 08:55 -0700, Christophe Ngo Van Duc wrote: > > So i've been able to do some test today: > > If I put the 2 interface in a bridge with no IP adress, the interru= pts > > are on 1 CPU > > If I put the 2 interface in a bridge with IP adress, the interrupts > > are still on 1 CPU > > If I put the 2 interface outside the bridge with IP address, > > everything works fine the interrupts get spread on the CPU > >=20 > > So the conclusion seems to be that when the bnx2 is put into > > promiscuous mode by the bridge, the RSS hash stop to work even if > > traffic is IP in nature. >=20 > I did a quick test with bridging and saw no problem with RSS. I did = see > this though: >=20 > br0 received packet on queue 4, but number of RX queues is 1 >=20 > Looks like it is a warning message from RPS. >=20 Christophe uses an old kernel, not RPS enabled ;)