From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: netif_tx_disable and lockless TX Date: Tue, 30 May 2006 21:13:22 -0700 (PDT) Message-ID: <20060530.211322.51700292.davem@davemloft.net> References: <20060531040307.GA6447@gondor.apana.org.au> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: mchan@broadcom.com, jgarzik@pobox.com, netdev@vger.kernel.org Return-path: Received: from dsl027-180-168.sfo1.dsl.speakeasy.net ([216.27.180.168]:10369 "EHLO sunset.sfo1.dsl.speakeasy.net") by vger.kernel.org with ESMTP id S1751664AbWEaEMz (ORCPT ); Wed, 31 May 2006 00:12:55 -0400 To: herbert@gondor.apana.org.au In-Reply-To: <20060531040307.GA6447@gondor.apana.org.au> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org From: Herbert Xu Date: Wed, 31 May 2006 14:03:07 +1000 > I must say though that I'm becoming less and less impressed by the > lockless feature based on the number of problems that it has caused. > Does anyone have any hard figures as to its effectiveness (excluding > any stats relating to the loopback interface which can be easily > separated from normal NIC drivers). There were numbers posted for real drivers at one point, I do remember that, and the gains were non-trivial. At least enough to justify the feature. As per the bug, I always keep thinking about changing how we do the lockless stuff by simply making xmit_lock a pointer. Drivers like tg3 can make it point to their local driver lock. This leaves still the cases like loopback which do no locking whatsoever. I don't know how to fit it into the above idea.