From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1752646AbbBYVo3 (ORCPT <rfc822;w@1wt.eu>);
	Wed, 25 Feb 2015 16:44:29 -0500
Received: from mail.linuxfoundation.org ([140.211.169.12]:36725 "EHLO
	mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1752761AbbBYVo1 (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Wed, 25 Feb 2015 16:44:27 -0500
Date: Wed, 25 Feb 2015 13:44:26 -0800
From: Andrew Morton <akpm@linux-foundation.org>
To: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Michal Hocko <mhocko@suse.cz>,
        Konstantin Khlebnikov <khlebnikov@yandex-team.ru>,
        "linux-mm@kvack.org" <linux-mm@kvack.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] mm: hide per-cpu lists in output of show_mem()
Message-Id: <20150225134426.d907ecb7130d12dc8ad97c90@linux-foundation.org>
In-Reply-To: <CALYGNiO8Y3oJbPMF8m2ndtBp5=RBiw3o6rKyWsGXF0RyT9JYVQ@mail.gmail.com>
References: <20150220143942.19568.4548.stgit@buzz>
	<20150223143746.GG24272@dhcp22.suse.cz>
	<CALYGNiO8Y3oJbPMF8m2ndtBp5=RBiw3o6rKyWsGXF0RyT9JYVQ@mail.gmail.com>
X-Mailer: Sylpheed 3.4.1 (GTK+ 2.24.23; 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: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Tue, 24 Feb 2015 13:03:01 +0400 Konstantin Khlebnikov <koct9i@gmail.com> wrote:

> On Mon, Feb 23, 2015 at 5:37 PM, Michal Hocko <mhocko@suse.cz> wrote:
> > On Fri 20-02-15 17:39:42, Konstantin Khlebnikov wrote:
> >> This makes show_mem() much less verbose at huge machines. Instead of
> >> huge and almost useless dump of counters for each per-zone per-cpu
> >> lists this patch prints sum of these counters for each zone (free_pcp)
> >> and size of per-cpu list for current cpu (local_pcp).
> >
> > I like this! I do not remember when I found this information useful
> > while debugging either an allocation failure warning or OOM killer
> > report.
> >
> >> Flag SHOW_MEM_PERCPU_LISTS reverts old verbose mode.
> >
> > Nobody seems to be using this flag so why bother?
> 
> Yes. But this might be important for architectures which has asymmetrical
> memory topology, I've heard about unicorns like that.

Please provide more details about this (why important?  How would it
be used) and I'll add it to the changelog.