From mboxrd@z Thu Jan 1 00:00:00 1970 From: Matthew Wilcox Subject: Re: [RFC] Remove BKL from fs/locks.c Date: Sun, 30 Dec 2007 07:42:42 -0700 Message-ID: <20071230144241.GT11638@parisc-linux.org> References: <20071230061615.GS11638@parisc-linux.org> <20071230203644.00675d5a.sfr@canb.auug.org.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: linux-fsdevel@vger.kernel.org To: Stephen Rothwell Return-path: Received: from palinux.external.hp.com ([192.25.206.14]:47056 "EHLO mail.parisc-linux.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752911AbXL3Omn (ORCPT ); Sun, 30 Dec 2007 09:42:43 -0500 Content-Disposition: inline In-Reply-To: <20071230203644.00675d5a.sfr@canb.auug.org.au> Sender: linux-fsdevel-owner@vger.kernel.org List-ID: On Sun, Dec 30, 2007 at 08:36:44PM +1100, Stephen Rothwell wrote: > We should probably do some performance testing on this because the last > time we tried the impact was quite noticeable. You should ping Tridge as > he has some good lock testing setups. And he cares if we slow him down :-) Last time I did this, I switched to a semaphore instead of a spinlock. That was what slowed us down. I doubt we can see a performance loss with this patch since it's a 1-1 substitution of the BKL spinlock with a private spinlock. Good idea about asking tridge for an evaluation of the patch though. -- Intel are signing my paycheques ... these opinions are still mine "Bill, look, we understand that you're interested in selling us this operating system, but compare it to ours. We can't possibly take such a retrograde step."