From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751979Ab3KFWdP (ORCPT ); Wed, 6 Nov 2013 17:33:15 -0500 Received: from mail.linuxfoundation.org ([140.211.169.12]:39734 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750729Ab3KFWdO (ORCPT ); Wed, 6 Nov 2013 17:33:14 -0500 Date: Wed, 6 Nov 2013 14:33:13 -0800 From: Andrew Morton To: Jerome Marchand Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, dave hansen Subject: Re: [PATCH v4 2/2] mm: allow to set overcommit ratio more precisely Message-Id: <20131106143313.1a368250df917fba0faf56fe@linux-foundation.org> In-Reply-To: <1450211196.19341043.1383727340985.JavaMail.root@redhat.com> References: <1382101019-23563-1-git-send-email-jmarchan@redhat.com> <1382101019-23563-2-git-send-email-jmarchan@redhat.com> <20131105155319.732dcbefb162c2ee4716ef9d@linux-foundation.org> <1450211196.19341043.1383727340985.JavaMail.root@redhat.com> X-Mailer: Sylpheed 3.2.0beta5 (GTK+ 2.24.10; x86_64-pc-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 6 Nov 2013 03:42:20 -0500 (EST) Jerome Marchand wrote: > > > ----- Original Message ----- > > From: "Andrew Morton" > > To: "Jerome Marchand" > > Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, "dave hansen" > > Sent: Wednesday, November 6, 2013 12:53:19 AM > > Subject: Re: [PATCH v4 2/2] mm: allow to set overcommit ratio more precisely > > > > On Fri, 18 Oct 2013 14:56:59 +0200 Jerome Marchand > > wrote: > > > > > Some applications that run on HPC clusters are designed around the > > > availability of RAM and the overcommit ratio is fine tuned to get the > > > maximum usage of memory without swapping. With growing memory, the 1% > > > of all RAM grain provided by overcommit_ratio has become too coarse > > > for these workload (on a 2TB machine it represents no less than > > > 20GB). > > > > > > This patch adds the new overcommit_ratio_ppm sysctl variable that > > > allow to set overcommit ratio with a part per million precision. > > > The old overcommit_ratio variable can still be used to set and read > > > the ratio with a 1% precision. That way, overcommit_ratio interface > > > isn't broken in any way that I can imagine. > > > > The way we've permanently squished this mistake in the past is to > > switch to "bytes". See /proc/sys/vm/*bytes. > > > > Would that approach work in this case? > > > > That was my first version of this patch (actually "kbytes" to avoid > overflow). > Dave raised the issue that it silently breaks the user interface: > overcommit_ratio is zero while the system behaves differently. I don't understand that at all. We keep overcommit_ratio as-is, with the same default values and add a different way of altering it. That should be back-compatible?