From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932191AbYEOLMr (ORCPT ); Thu, 15 May 2008 07:12:47 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754854AbYEOLMi (ORCPT ); Thu, 15 May 2008 07:12:38 -0400 Received: from bzq-179-150-194.static.bezeqint.net ([212.179.150.194]:49085 "EHLO il.qumranet.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752396AbYEOLMi (ORCPT ); Thu, 15 May 2008 07:12:38 -0400 Message-ID: <482C1AA2.20307@qumranet.com> Date: Thu, 15 May 2008 14:12:34 +0300 From: Avi Kivity User-Agent: Thunderbird 2.0.0.14 (X11/20080501) MIME-Version: 1.0 To: Robin Holt CC: Nick Piggin , Nick Piggin , Linus Torvalds , Andrea Arcangeli , Andrew Morton , Christoph Lameter , Jack Steiner , Peter Zijlstra , kvm-devel@lists.sourceforge.net, Kanoj Sarcar , Roland Dreier , Steve Wise , linux-kernel@vger.kernel.org, linux-mm@kvack.org, general@lists.openfabrics.org, Hugh Dickins , Rusty Russell , Anthony Liguori , Chris Wright , Marcelo Tosatti , Eric Dumazet , "Paul E. McKenney" Subject: Re: [PATCH 08 of 11] anon-vma-rwsem References: <6b384bb988786aa78ef0.1210170958@duo.random> <20080508003838.GA9878@sgi.com> <200805132206.47655.nickpiggin@yahoo.com.au> <20080513153238.GL19717@sgi.com> <20080514041122.GE24516@wotan.suse.de> <20080514112625.GY9878@sgi.com> <20080515075747.GA7177@wotan.suse.de> <20080515110147.GD10126@sgi.com> In-Reply-To: <20080515110147.GD10126@sgi.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Robin Holt wrote: > Then we need to deposit the information needed to do the invalidate. > > Lastly, we would need to interrupt. Unfortunately, here we have a > thundering herd. There could be up to 16256 processors interrupting the > same processor. That will be a lot of work. It will need to look up the > mm (without grabbing any sleeping locks in either xpmem or the kernel) > and do the tlb invalidates. > > You don't need to interrupt every time. Place your data in a queue (you do support rmw operations, right?) and interrupt. Invalidates from other processors will see that the queue hasn't been processed yet and skip the interrupt. -- error compiling committee.c: too many arguments to function From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: [ofa-general] Re: [PATCH 08 of 11] anon-vma-rwsem Date: Thu, 15 May 2008 14:12:34 +0300 Message-ID: <482C1AA2.20307@qumranet.com> References: <6b384bb988786aa78ef0.1210170958@duo.random> <20080508003838.GA9878@sgi.com> <200805132206.47655.nickpiggin@yahoo.com.au> <20080513153238.GL19717@sgi.com> <20080514041122.GE24516@wotan.suse.de> <20080514112625.GY9878@sgi.com> <20080515075747.GA7177@wotan.suse.de> <20080515110147.GD10126@sgi.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: linux-mm@kvack.org, Hugh Dickins , Nick Piggin , kvm-devel@lists.sourceforge.net, Roland Dreier , Eric Dumazet , general@lists.openfabrics.org, Christoph Lameter , Nick Piggin , Jack Steiner , Andrea Arcangeli , Peter Zijlstra , Rusty Russell , Chris Wright , Anthony Liguori , Marcelo Tosatti , Kanoj Sarcar , linux-kernel@vger.kernel.org, "Paul E. McKenney" , Andrew Morton , Linus Torvalds To: Robin Holt Return-path: In-Reply-To: <20080515110147.GD10126@sgi.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: general-bounces@lists.openfabrics.org Errors-To: general-bounces@lists.openfabrics.org List-Id: kvm.vger.kernel.org Robin Holt wrote: > Then we need to deposit the information needed to do the invalidate. > > Lastly, we would need to interrupt. Unfortunately, here we have a > thundering herd. There could be up to 16256 processors interrupting the > same processor. That will be a lot of work. It will need to look up the > mm (without grabbing any sleeping locks in either xpmem or the kernel) > and do the tlb invalidates. > > You don't need to interrupt every time. Place your data in a queue (you do support rmw operations, right?) and interrupt. Invalidates from other processors will see that the queue hasn't been processed yet and skip the interrupt. -- error compiling committee.c: too many arguments to function From mboxrd@z Thu Jan 1 00:00:00 1970 Message-ID: <482C1AA2.20307@qumranet.com> Date: Thu, 15 May 2008 14:12:34 +0300 From: Avi Kivity MIME-Version: 1.0 Subject: Re: [PATCH 08 of 11] anon-vma-rwsem References: <6b384bb988786aa78ef0.1210170958@duo.random> <20080508003838.GA9878@sgi.com> <200805132206.47655.nickpiggin@yahoo.com.au> <20080513153238.GL19717@sgi.com> <20080514041122.GE24516@wotan.suse.de> <20080514112625.GY9878@sgi.com> <20080515075747.GA7177@wotan.suse.de> <20080515110147.GD10126@sgi.com> In-Reply-To: <20080515110147.GD10126@sgi.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: owner-linux-mm@kvack.org Return-Path: To: Robin Holt Cc: Nick Piggin , Nick Piggin , Linus Torvalds , Andrea Arcangeli , Andrew Morton , Christoph Lameter , Jack Steiner , Peter Zijlstra , kvm-devel@lists.sourceforge.net, Kanoj Sarcar , Roland Dreier , Steve Wise , linux-kernel@vger.kernel.org, linux-mm@kvack.org, general@lists.openfabrics.org, Hugh Dickins , Rusty Russell , Anthony Liguori , Chris Wright , Marcelo Tosatti , Eric Dumazet , "Paul E. McKenney" List-ID: Robin Holt wrote: > Then we need to deposit the information needed to do the invalidate. > > Lastly, we would need to interrupt. Unfortunately, here we have a > thundering herd. There could be up to 16256 processors interrupting the > same processor. That will be a lot of work. It will need to look up the > mm (without grabbing any sleeping locks in either xpmem or the kernel) > and do the tlb invalidates. > > You don't need to interrupt every time. Place your data in a queue (you do support rmw operations, right?) and interrupt. Invalidates from other processors will see that the queue hasn't been processed yet and skip the interrupt. -- error compiling committee.c: too many arguments to function -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org