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 S1755434AbbCFWbF (ORCPT <rfc822;w@1wt.eu>);
	Fri, 6 Mar 2015 17:31:05 -0500
Received: from userp1040.oracle.com ([156.151.31.81]:39854 "EHLO
	userp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1754732AbbCFWbC (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Fri, 6 Mar 2015 17:31:02 -0500
Message-ID: <54FA2A8D.5090509@oracle.com>
Date: Fri, 06 Mar 2015 14:30:37 -0800
From: Mike Kravetz <mike.kravetz@oracle.com>
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.5.0
MIME-Version: 1.0
To: Andi Kleen <andi@firstfloor.org>
CC: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        Andrew Morton <akpm@linux-foundation.org>,
        Davidlohr Bueso <dave@stgolabs.net>,
        Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>,
        Joonsoo Kim <iamjoonsoo.kim@lge.com>
Subject: Re: [PATCH 0/4] hugetlbfs: optionally reserve all fs pages at mount
 time
References: <1425432106-17214-1-git-send-email-mike.kravetz@oracle.com> <87lhj9ai5u.fsf@tassilo.jf.intel.com>
In-Reply-To: <87lhj9ai5u.fsf@tassilo.jf.intel.com>
Content-Type: text/plain; charset=windows-1252; format=flowed
Content-Transfer-Encoding: 7bit
X-Source-IP: aserv0021.oracle.com [141.146.126.233]
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On 03/06/2015 02:13 PM, Andi Kleen wrote:
> Mike Kravetz <mike.kravetz@oracle.com> writes:
>
>> hugetlbfs allocates huge pages from the global pool as needed.  Even if
>> the global pool contains a sufficient number pages for the filesystem
>> size at mount time, those global pages could be grabbed for some other
>> use.  As a result, filesystem huge page allocations may fail due to lack
>> of pages.
>
>
> What's the difference of this new option to simply doing
>
> mount -t hugetlbfs none /huge
> echo XXX > /proc/sys/vm/nr_hugepages

In the above sequence, it is still possible for another user/application
to allocate some (or all) of the XXX huge pages.  There is no guarantee
that users of the filesystem will get all XXX pages.

I see the use of the reserve option to be:
# Make sure there are XXX huge pages in the global pool
echo XXX > /proc/sys/vm/nr_hugepages
# Mount/create the filesystem and reserve XXX huge pages
mount -t hugetlbfs -o size=XXX,reserve=XXX none /huge

If the mount is successful, then users of the filesystem know their are
XXX huge pages available for their use.

-- 
Mike Kravetz