From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932273AbYAaJxw (ORCPT ); Thu, 31 Jan 2008 04:53:52 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755654AbYAaJxo (ORCPT ); Thu, 31 Jan 2008 04:53:44 -0500 Received: from bombadil.infradead.org ([18.85.46.34]:53446 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754682AbYAaJxn (ORCPT ); Thu, 31 Jan 2008 04:53:43 -0500 Subject: Re: [PATCH] mm: MADV_WILLNEED implementation for anonymous memory From: Peter Zijlstra To: Andrew Morton Cc: hugh@veritas.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org, npiggin@suse.de, riel@redhat.com, mztabzr@0pointer.de, mpm@selenic.com In-Reply-To: <20080131014702.705f1040.akpm@linux-foundation.org> References: <1201714139.28547.237.camel@lappy> <20080130144049.73596898.akpm@linux-foundation.org> <1201769040.28547.245.camel@lappy> <20080131011227.257b9437.akpm@linux-foundation.org> <1201772118.28547.254.camel@lappy> <20080131014702.705f1040.akpm@linux-foundation.org> Content-Type: text/plain Date: Thu, 31 Jan 2008 10:53:26 +0100 Message-Id: <1201773206.28547.259.camel@lappy> Mime-Version: 1.0 X-Mailer: Evolution 2.21.5 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, 2008-01-31 at 01:47 -0800, Andrew Morton wrote: > On Thu, 31 Jan 2008 10:35:18 +0100 Peter Zijlstra wrote: > > > > > On Thu, 2008-01-31 at 01:12 -0800, Andrew Morton wrote: > > > > > Implementation-wise: make_pages_present() _can_ be converted to do this. > > > But it's a lot of patching, and the result will be a cleaner, faster and > > > smaller core MM. Whereas your approach is easy, but adds more code and > > > leaves the old stuff slow-and-dirty. > > > > > > Guess which approach is preferred? ;) > > > > Ok, I'll look at using make_pages_present(). > > Am still curious to know what inspired this change. What are the use > cases? Performance testing results, etc? Ah, that is Lennarts Pulse Audio thing, he has samples in memory which might not have been used for a while, and he wants to be able to pre-fetch those when he suspects they might need to be played. So that once the audio thread comes along and stuffs them down /dev/dsp its all nice in memory. Since its all soft real-time at best he feels its better to do a best effort at not hitting swap than it is to strain the system with mlock usage.