From mboxrd@z Thu Jan 1 00:00:00 1970 From: Changli Gao Subject: Re: [PATCH 3/3] ifb: move tq from ifb_private Date: Sun, 5 Dec 2010 23:22:27 +0800 Message-ID: References: <1291442121-3302-1-git-send-email-xiaosuo@gmail.com> <1291442121-3302-3-git-send-email-xiaosuo@gmail.com> <4CFA3F01.20109@gmail.com> <1291472889.2159.18.camel@mojatatu> <1291474127.2159.35.camel@mojatatu> <20101204154007.GA1981@del.dom.local> <1291478881.2159.70.camel@mojatatu> <20101204165609.GB1981@del.dom.local> <1291559402.2159.687.camel@mojatatu> <1291562028.2159.692.camel@mojatatu> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Jarek Poplawski , netdev@vger.kernel.org To: hadi@cyberus.ca Return-path: Received: from mail-fx0-f46.google.com ([209.85.161.46]:55661 "EHLO mail-fx0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755878Ab0LEPWt convert rfc822-to-8bit (ORCPT ); Sun, 5 Dec 2010 10:22:49 -0500 Received: by fxm20 with SMTP id 20so3545347fxm.19 for ; Sun, 05 Dec 2010 07:22:48 -0800 (PST) In-Reply-To: <1291562028.2159.692.camel@mojatatu> Sender: netdev-owner@vger.kernel.org List-ID: On Sun, Dec 5, 2010 at 11:13 PM, jamal wrote: > On Sun, 2010-12-05 at 22:40 +0800, Changli Gao wrote: >> On Sun, Dec 5, 2010 at 10:30 PM, jamal wrote: > >> > - we use tasklets. When we =A0reschedule we can end up on a differ= rent >> > cpu. >> >> The tasklets always been scheduled to the current CPU unless it has >> been schedule already on the other CPU. > > I dont think this can be guaranteed - So the potential of packet > reordering exists. > The current implementation can guarantee it. However, I can't find documentation about this 'feature', but I think this behavior should not be changed in future since maybe some call sites relay on it. --=20 Regards, Changli Gao(xiaosuo@gmail.com)