From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: [patch 00/52] vfs scalability patches updated Date: Thu, 01 Jul 2010 19:36:45 +0200 Message-ID: <87lj9vyuhe.fsf@basil.nowhere.org> References: <20100624030212.676457061@suse.de> <20100630113054.GL24712@dastard> <20100630124049.GH21358@laptop> <20100701035657.GU24712@dastard> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Nick Piggin , linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, John Stultz , Frank Mayhar To: Dave Chinner Return-path: Received: from one.firstfloor.org ([213.235.205.2]:55271 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752916Ab0GARgr (ORCPT ); Thu, 1 Jul 2010 13:36:47 -0400 In-Reply-To: <20100701035657.GU24712@dastard> (Dave Chinner's message of "Thu, 1 Jul 2010 13:56:57 +1000") Sender: linux-fsdevel-owner@vger.kernel.org List-ID: Dave Chinner writes: > > I'm not denying it that we need to do work here - I'm questioning > the "change everything at once" approach this patch set takes. > You've started from the assumption that everything the dcache_lock > and inode_lock protect are a problem and goes from there. Global code locks in a core subsystem are definitely a problem. In many ways they're as bad a a BKL. There will be always workloads where they hurt. They are bad coding style. They just have to go. I don't understand how anyone can even defend them. Especially bad are code locks that protect lots of different things. Those are not only bad for scalability, but also bad for maintainability, because few people can really understand them even. With smaller well defined locks that's usually easier. -Andi -- ak@linux.intel.com -- Speaking for myself only.