From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754976Ab1ELIzY (ORCPT ); Thu, 12 May 2011 04:55:24 -0400 Received: from mga11.intel.com ([192.55.52.93]:37589 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754280Ab1ELIzX (ORCPT ); Thu, 12 May 2011 04:55:23 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.64,357,1301900400"; d="scan'208";a="702692" Subject: Re: [patch v2 0/5] percpu_counter: bug fix and enhancement From: Shaohua Li To: Tejun Heo Cc: "linux-kernel@vger.kernel.org" , "akpm@linux-foundation.org" , "eric.dumazet@gmail.com" , "cl@linux.com" , "npiggin@kernel.dk" In-Reply-To: <20110512082159.GB1030@htj.dyndns.org> References: <20110511081012.903869567@sli10-conroe.sh.intel.com> <20110511092848.GE1661@htj.dyndns.org> <1305168493.2373.15.camel@sli10-conroe> <20110512082159.GB1030@htj.dyndns.org> Content-Type: text/plain; charset="UTF-8" Date: Thu, 12 May 2011 16:55:20 +0800 Message-ID: <1305190520.2373.18.camel@sli10-conroe> Mime-Version: 1.0 X-Mailer: Evolution 2.30.3 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi, On Thu, 2011-05-12 at 16:21 +0800, Tejun Heo wrote: > On Thu, May 12, 2011 at 10:48:13AM +0800, Shaohua Li wrote: > > And the atomic64 approach not just improved the performance (which is > > always welcomed), but it also fixes a bug for 32-bit system. The usage > > of lglock is actually quite straightforward and is standard usage of > > lglock (the comments of lglock.h declare such usage), just lglock > > doesn't work for dynamatically allocated structure currently, which > > needs a convert. > > lglock doesn't seem like the right solution for the problem at hand. > It's way too heavy handed and used to close a very small race window. > It doesn't seem right. Eric's idea seemed much better to me and I > don't see why that can't be improved and used instead. Would you be > interested in looking that direction? sure, but it's quite difficult to determine a @maxfuzzy in his proposal I thought (and could confuse user), did I miss anything? Thanks, Shaohua