From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755855Ab0EJRNB (ORCPT ); Mon, 10 May 2010 13:13:01 -0400 Received: from mga01.intel.com ([192.55.52.88]:38397 "EHLO mga01.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755664Ab0EJRM6 (ORCPT ); Mon, 10 May 2010 13:12:58 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.52,363,1270450800"; d="scan'208";a="797076157" From: "Sean Hefty" To: "'Jeff Squyres'" , "Eric B Munson" Cc: , , , , , , , , References: <1271943493-12120-1-git-send-email-ebmunson@us.ibm.com> <01C0A6AB-E4B6-4B56-AFAE-52952D152110@cisco.com> Subject: RE: [PATCH] ummunotify: Userspace support for MMU notifications V2 Date: Mon, 10 May 2010 10:12:56 -0700 Message-ID: <56643C62C30044F0A734365A5274C821@amr.corp.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Office Outlook 11 Thread-Index: Acrt3RQCVxEQbTOVRfOrwfFK2Z+gggChOphw In-Reply-To: <01C0A6AB-E4B6-4B56-AFAE-52952D152110@cisco.com> X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.5579 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org >> As discussed in >> and follow-up messages, libraries using RDMA would like to track >> precisely when application code changes memory mapping via free(), >> munmap(), etc. Current pure-userspace solutions using malloc hooks >> and other tricks are not robust, and the feeling among experts is that >> the issue is unfixable without kernel help. > >Sorry for not replying earlier -- just to throw in my $0.02 here: the MPI >community is *very interested* in having this stuff in upstream kernels. It >solves a fairly major problem for us. > >Open MPI (www.open-mpi.org) is ready to pretty much immediately take advantage >of these capabilities. The code to use ummunotify is in a Mercurial branch; >we're only waiting for ummunotify to go upstream before committing our support >for it to our main SVN development trunk. Intel's MPI team has examined this proposal as well and would also like to see this merged upstream. It is helpful implementing MPI over RDMA devices. - Sean