From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932175Ab3KFIm4 (ORCPT ); Wed, 6 Nov 2013 03:42:56 -0500 Received: from mx4-phx2.redhat.com ([209.132.183.25]:38783 "EHLO mx4-phx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932088Ab3KFImz (ORCPT ); Wed, 6 Nov 2013 03:42:55 -0500 Date: Wed, 6 Nov 2013 03:42:20 -0500 (EST) From: Jerome Marchand To: Andrew Morton Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, dave hansen Message-ID: <1450211196.19341043.1383727340985.JavaMail.root@redhat.com> In-Reply-To: <20131105155319.732dcbefb162c2ee4716ef9d@linux-foundation.org> References: <1382101019-23563-1-git-send-email-jmarchan@redhat.com> <1382101019-23563-2-git-send-email-jmarchan@redhat.com> <20131105155319.732dcbefb162c2ee4716ef9d@linux-foundation.org> Subject: Re: [PATCH v4 2/2] mm: allow to set overcommit ratio more precisely MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit X-Originating-IP: [10.5.82.11] X-Mailer: Zimbra 8.0.3_GA_5664 (ZimbraWebClient - FF22 (Linux)/8.0.3_GA_5664) Thread-Topic: allow to set overcommit ratio more precisely Thread-Index: vmEQXa6c4meyr6nxaL+2qkPfDwXbJg== Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org ----- 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. Jerome