From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756538Ab0KRKnR (ORCPT ); Thu, 18 Nov 2010 05:43:17 -0500 Received: from DMZ-MAILSEC-SCANNER-1.MIT.EDU ([18.9.25.12]:53599 "EHLO dmz-mailsec-scanner-1.mit.edu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755832Ab0KRKnP convert rfc822-to-8bit (ORCPT ); Thu, 18 Nov 2010 05:43:15 -0500 X-AuditID: 1209190c-b7ba9ae0000009f8-3e-4ce5034294ba Subject: Re: [PATCH 3/3] mlock: avoid dirtying pages and triggering writeback Mime-Version: 1.0 (Apple Message framework v1082) Content-Type: text/plain; charset=us-ascii From: Theodore Tso In-Reply-To: <20101118054629.GA3339@amd> Date: Thu, 18 Nov 2010 05:43:06 -0500 Cc: Peter Zijlstra , Michel Lespinasse , linux-mm@kvack.org, linux-kernel@vger.kernel.org, Andrew Morton , Hugh Dickins , Rik van Riel , Kosaki Motohiro , Theodore Tso , Michael Rubin , Suleiman Souhlal Content-Transfer-Encoding: 8BIT Message-Id: <2ADBEB7E-0EC8-4536-B556-0453A8E1D5FA@mit.edu> References: <1289996638-21439-1-git-send-email-walken@google.com> <1289996638-21439-4-git-send-email-walken@google.com> <20101117125756.GA5576@amd> <1290007734.2109.941.camel@laptop> <20101118054629.GA3339@amd> To: Nick Piggin X-Mailer: Apple Mail (2.1082) X-Brightmail-Tracker: AAAAAA== Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Nov 18, 2010, at 12:46 AM, Nick Piggin wrote: > The right way to fix this would not be to introduce the new regression > but either/both: a specific syscall to mlock-for-read which does not do > any reservations, fix filesystem hook to allow reservation without > implying dirtying. A simple flag to page_mkwrite will be enough (plus > the logic to call it from VM). Why is it at all important that mlock() force block allocation for sparse blocks? It's not at all specified in the mlock() API definition that it does that. Are there really programs that assume that mlock() == fallocate()?!? -- Ted From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail190.messagelabs.com (mail190.messagelabs.com [216.82.249.51]) by kanga.kvack.org (Postfix) with SMTP id B07B56B0089 for ; Thu, 18 Nov 2010 05:43:16 -0500 (EST) Subject: Re: [PATCH 3/3] mlock: avoid dirtying pages and triggering writeback Mime-Version: 1.0 (Apple Message framework v1082) Content-Type: text/plain; charset=us-ascii From: Theodore Tso In-Reply-To: <20101118054629.GA3339@amd> Date: Thu, 18 Nov 2010 05:43:06 -0500 Content-Transfer-Encoding: quoted-printable Message-Id: <2ADBEB7E-0EC8-4536-B556-0453A8E1D5FA@mit.edu> References: <1289996638-21439-1-git-send-email-walken@google.com> <1289996638-21439-4-git-send-email-walken@google.com> <20101117125756.GA5576@amd> <1290007734.2109.941.camel@laptop> <20101118054629.GA3339@amd> Sender: owner-linux-mm@kvack.org To: Nick Piggin Cc: Peter Zijlstra , Michel Lespinasse , linux-mm@kvack.org, linux-kernel@vger.kernel.org, Andrew Morton , Hugh Dickins , Rik van Riel , Kosaki Motohiro , Theodore Tso , Michael Rubin , Suleiman Souhlal List-ID: On Nov 18, 2010, at 12:46 AM, Nick Piggin wrote: > The right way to fix this would not be to introduce the new regression > but either/both: a specific syscall to mlock-for-read which does not = do > any reservations, fix filesystem hook to allow reservation without > implying dirtying. A simple flag to page_mkwrite will be enough (plus > the logic to call it from VM). Why is it at all important that mlock() force block allocation for = sparse blocks? It's not at all specified in the mlock() API = definition that it does that. Are there really programs that assume that mlock() =3D=3D fallocate()?!? -- Ted -- 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/ . Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/ Don't email: email@kvack.org