From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: [PATCH v6] net: batch skb dequeueing from softnet input_pkt_queue Date: Sun, 2 May 2010 23:54:50 +0200 Message-ID: <20100502215450.GC2673@gargoyle.fritz.box> References: <20100429214144.GA10663@gargoyle.fritz.box> <20100430.163857.180417789.davem@davemloft.net> <20100501110000.GB9434@gargoyle.fritz.box> <1272783366.2173.13.camel@edumazet-laptop> <20100502092020.GA9655@gargoyle.fritz.box> <1272797690.2173.26.camel@edumazet-laptop> <20100502154649.GA18063@gargoyle.fritz.box> <1272818131.2173.127.camel@edumazet-laptop> <20100502212550.GA2673@gargoyle.fritz.box> <1272836755.2173.153.camel@edumazet-laptop> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: David Miller , hadi@cyberus.ca, xiaosuo@gmail.com, therbert@google.com, shemminger@vyatta.com, netdev@vger.kernel.org, lenb@kernel.org, arjan@infradead.org To: Eric Dumazet Return-path: Received: from one.firstfloor.org ([213.235.205.2]:54627 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755008Ab0EBVwT (ORCPT ); Sun, 2 May 2010 17:52:19 -0400 Content-Disposition: inline In-Reply-To: <1272836755.2173.153.camel@edumazet-laptop> Sender: netdev-owner@vger.kernel.org List-ID: On Sun, May 02, 2010 at 11:45:55PM +0200, Eric Dumazet wrote: > Le dimanche 02 mai 2010 =E0 23:25 +0200, Andi Kleen a =E9crit : >=20 > > It's pointless to send an IPI to your thread sibling for this.=20 > > Everything it could do you can do yourself too with the same perfor= mance. > >=20 > > -Andi >=20 > Amen That is in terms of cache locality. >=20 > Tests just prove the reverse. What do you mean?=20 >=20 > I have some collegues that disable HyperThreading for exact same > reasons. I wonder why Intel designed HT. Should be marketing I guess. HT (especially Nehalem HT) is useful for a wide range of workloads. Just handling network interrupts for its thread sibling is not one of t= hem. -Andi