From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1030310AbXDKTxT (ORCPT ); Wed, 11 Apr 2007 15:53:19 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1030314AbXDKTxT (ORCPT ); Wed, 11 Apr 2007 15:53:19 -0400 Received: from agminet01.oracle.com ([141.146.126.228]:59085 "EHLO agminet01.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1030310AbXDKTxS (ORCPT ); Wed, 11 Apr 2007 15:53:18 -0400 Date: Wed, 11 Apr 2007 12:52:56 -0700 From: Zach Brown To: Benjamin LaHaise Cc: Ken Chen , akpm@linux-foundation.org, linux-aio@kvack.org, linux-kernel@vger.kernel.org Subject: Re: [patch] convert aio event reap to use atomic-op instead of spin_lock Message-ID: <20070411195256.GD9602@mami.zabbo.net> References: <20070410235353.325A7346F64@localhost> <20070411180038.GN28322@mami.zabbo.net> <20070411194504.GM13621@kvack.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20070411194504.GM13621@kvack.org> User-Agent: Mutt/1.4.2.1i X-Brightmail-Tracker: AAAAAQAAAAI= X-Whitelist: TRUE Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org > > I kept on getting requests from application developers who want that > > feature. My initial patch was dated back May 2004. > > The right way to do it involves synchronization between the kernel side > io_getevents() and the userspace code pulling events out of the ring. > Alan Cox suggested embedding a futex in the shared memory region, but I > don't think anyone ever implemented that. Yeah, I like the idea of futexes. I'm worried that virtual aliasing spells doom for the current home-brewed serialization that fs/aio.c is doing with the shared ring head/tail accesses. Am I worrying about nothing here? > > I will look into this aside from this patch. > > That's probably the case. Also, any changes in this area *must* correctly > update the compat/incompat feature flags in the ring buffer header. That > has been missed in the past... Do you know of anyone using the current ring info ABI? The *only* user I know of is the check of ctx->magic in libaio. - z