From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [PATCH v3] net: batch skb dequeueing from softnet input_pkt_queue Date: Thu, 22 Apr 2010 09:13:22 +0200 Message-ID: <1271920402.7895.4732.camel@edumazet-laptop> References: <1271238738-8386-1-git-send-email-xiaosuo@gmail.com> <1271891149.7895.3751.camel@edumazet-laptop> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: "David S. Miller" , netdev@vger.kernel.org, Tom Herbert , jamal To: Changli Gao Return-path: Received: from mail-bw0-f225.google.com ([209.85.218.225]:55935 "EHLO mail-bw0-f225.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751240Ab0DVHNc (ORCPT ); Thu, 22 Apr 2010 03:13:32 -0400 Received: by bwz25 with SMTP id 25so9162301bwz.28 for ; Thu, 22 Apr 2010 00:13:31 -0700 (PDT) In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: Le jeudi 22 avril 2010 =C3=A0 14:33 +0800, Changli Gao a =C3=A9crit : > On Thu, Apr 22, 2010 at 7:05 AM, Eric Dumazet wrote: > > Le mercredi 14 avril 2010 =C3=A0 17:52 +0800, Changli Gao a =C3=A9c= rit : > >> batch skb dequeueing from softnet input_pkt_queue > >> > >> batch skb dequeueing from softnet input_pkt_queue to reduce potent= ial lock > >> contention and irq disabling/enabling. > >> > >> Signed-off-by: Changli Gao > >> ---- > > > > lock contention _is_ a problem, Jamal tests can show it. > > > > irq disabling/enabling is not, and force to use stop_machine() kill= er. > > >=20 > Although irq_disabling/enabling is not, we should do our best to make > fast path as quickly as possible, and because stop_machine() is used > in slow patch, I think we can afford its weight. >=20 >=20 No thanks, this is out of the question. Talk to ixiacom guys, some people settle/dismantle dozens of network device per second, on production machines.