Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1763122Ab3DDQU3 (ORCPT ); Thu, 4 Apr 2013 12:20:29 -0400 Received: from cantor2.suse.de ([195.135.220.15]:47934 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1763102Ab3DDQUZ (ORCPT ); Thu, 4 Apr 2013 12:20:25 -0400 Date: Thu, 4 Apr 2013 18:20:23 +0200 From: Michal Hocko To: Wanpeng Li Cc: Andrew Morton , KAMEZAWA Hiroyuki , "Aneesh Kumar K.V" , Mel Gorman , Rik van Riel , Hillf Danton , linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH 0/6] mm/hugetlb: gigantic hugetlb page pools shrink supporting Message-ID: <20130404162023.GQ29911@dhcp22.suse.cz> References: <1365066554-29195-1-git-send-email-liwanp@linux.vnet.ibm.com> <20130404161746.GP29911@dhcp22.suse.cz> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20130404161746.GP29911@dhcp22.suse.cz> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1830 Lines: 37 On Thu 04-04-13 18:17:46, Michal Hocko wrote: > On Thu 04-04-13 17:09:08, Wanpeng Li wrote: > > order >= MAX_ORDER pages are only allocated at boot stage using the > > bootmem allocator with the "hugepages=xxx" option. These pages are never > > free after boot by default since it would be a one-way street(>= MAX_ORDER > > pages cannot be allocated later), but if administrator confirm not to > > use these gigantic pages any more, these pinned pages will waste memory > > since other users can't grab free pages from gigantic hugetlb pool even > > if OOM, it's not flexible. The patchset add hugetlb gigantic page pools > > shrink supporting. Administrator can enable knob exported in sysctl to > > permit to shrink gigantic hugetlb pool. > > I am not sure I see why the new knob is needed. > /sys/kernel/mm/hugepages/hugepages-*/nr_hugepages is root interface so > an additional step to allow writing to the file doesn't make much sense > to me to be honest. > > Support for shrinking gigantic huge pages makes some sense to me but I > would be interested in the real world example. GB pages are usually used > in very specific environments where the amount is usually well known. > > I could imagine nr_hugepages_mempolicy would make more sense to free > pages from particular nodes so they could be offlined for example. > Does the patchset handles this as well? Ohh, I should have checked before asking. Both knobs use the same hugetlb_sysctl_handler_common and unless there is something hardcoded in the patches then it should be supproted. -- Michal Hocko SUSE Labs -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/