From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756565AbZCDMBY (ORCPT ); Wed, 4 Mar 2009 07:01:24 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751922AbZCDMBG (ORCPT ); Wed, 4 Mar 2009 07:01:06 -0500 Received: from mail-bw0-f178.google.com ([209.85.218.178]:48884 "EHLO mail-bw0-f178.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752337AbZCDMA6 convert rfc822-to-8bit (ORCPT ); Wed, 4 Mar 2009 07:00:58 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; b=pavwZxCu3Ak7YDAavcGJ1yW0BcP/3C7WEYWhD4U2YKqxw0mQCbyXKO6wwWRDuupWuF vqnvmlwbpl/w4eV5h1BdvU7SY/HwmlPrVRkOQlH5nX3mR4rrPihzXf6sTBhtM/kfYSxt FqAQLRP3dG4aIKtNrZ8/BrI+J5haJluA5fBn0= MIME-Version: 1.0 In-Reply-To: <20090304114504.GB4916@elte.hu> References: <49AD342D.6030609@cn.fujitsu.com> <20090303140955.GD23822@elte.hu> <49AE484C.8020801@cn.fujitsu.com> <20090304114504.GB4916@elte.hu> Date: Wed, 4 Mar 2009 14:00:54 +0200 X-Google-Sender-Auth: a362c7f6b0ed5c8b Message-ID: <84144f020903040400m5a77fc4p2b09796e1111c3b9@mail.gmail.com> Subject: Re: [PATCH -mm 0/6] rcu: introduce kfree_rcu V2 From: Pekka Enberg To: Ingo Molnar Cc: Lai Jiangshan , Andrew Morton , Christoph Lameter , Nick Piggin , "Paul E. McKenney" , Manfred Spraul , Peter Zijlstra , linux-kernel@vger.kernel.org Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, Mar 4, 2009 at 1:45 PM, Ingo Molnar wrote: >> This is one of patches I test kfree_rcu(). >> And it could be an example conversions of this facility. >> >> --- >>  arch/ia64/sn/kernel/irq.c           |   14 +----------- >>  block/genhd.c                       |   10 -------- >>  ipc/sem.c                           |   10 +------- >>  kernel/audit_tree.c                 |    8 ------ >>  kernel/cgroup.c                     |    9 ------- >>  kernel/smp.c                        |   11 --------- >>  mm/vmalloc.c                        |   18 +-------------- >>  net/can/af_can.c                    |   14 +----------- >>  net/core/gen_estimator.c            |    9 ------- >>  net/core/net_namespace.c            |   10 -------- >>  net/ipv4/fib_trie.c                 |    7 ------ >>  net/ipv6/addrconf.c                 |   10 -------- >>  net/netfilter/nf_conntrack_extend.c |    8 ------ >>  net/netlabel/netlabel_unlabeled.c   |   42 +----------------------------------- >>  security/device_cgroup.c            |   10 -------- >>  security/keys/keyring.c             |   15 ------------ >>  security/keys/user_defined.c        |   18 +-------------- >>  security/selinux/netif.c            |   18 --------------- >>  security/selinux/netnode.c          |   20 +---------------- >>  security/selinux/netport.c          |   20 +---------------- >>  20 files changed, 28 insertions(+), 253 deletions(-) > > Looks convincing to me but Nick does not like the extra SLAB > field it uses :-/ FWIW, I'm fine with the patch series. One option for SLQB is to just remove slab coloring as I've suggested in the past (the performance benefit with current cpu caches is questionable). Pekka