From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753315Ab1B1JxT (ORCPT ); Mon, 28 Feb 2011 04:53:19 -0500 Received: from cantor.suse.de ([195.135.220.2]:56667 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752886Ab1B1JxS (ORCPT ); Mon, 28 Feb 2011 04:53:18 -0500 Date: Mon, 28 Feb 2011 10:53:16 +0100 From: Michal Hocko To: KAMEZAWA Hiroyuki Cc: Dave Hansen , linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: Re: [RFC PATCH] page_cgroup: Reduce allocation overhead for page_cgroup array for CONFIG_SPARSEMEM v4 Message-ID: <20110228095316.GC4648@tiehlicka.suse.cz> References: <20110223151047.GA7275@tiehlicka.suse.cz> <1298485162.7236.4.camel@nimitz> <20110224134045.GA22122@tiehlicka.suse.cz> <20110225122522.8c4f1057.kamezawa.hiroyu@jp.fujitsu.com> <20110225095357.GA23241@tiehlicka.suse.cz> <20110228095347.7510b1d4.kamezawa.hiroyu@jp.fujitsu.com> <20110228091256.GA4648@tiehlicka.suse.cz> <20110228182322.a34cc1fd.kamezawa.hiroyu@jp.fujitsu.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20110228182322.a34cc1fd.kamezawa.hiroyu@jp.fujitsu.com> User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon 28-02-11 18:23:22, KAMEZAWA Hiroyuki wrote: [...] > > From 84a9555741b59cb2a0a67b023e4bd0f92c670ca1 Mon Sep 17 00:00:00 2001 > > From: Michal Hocko > > Date: Thu, 24 Feb 2011 11:25:44 +0100 > > Subject: [PATCH] page_cgroup: Reduce allocation overhead for page_cgroup array for CONFIG_SPARSEMEM > > > > Currently we are allocating a single page_cgroup array per memory > > section (stored in mem_section->base) when CONFIG_SPARSEMEM is selected. > > This is correct but memory inefficient solution because the allocated > > memory (unless we fall back to vmalloc) is not kmalloc friendly: > > - 32b - 16384 entries (20B per entry) fit into 327680B so the > > 524288B slab cache is used > > - 32b with PAE - 131072 entries with 2621440B fit into 4194304B > > - 64b - 32768 entries (40B per entry) fit into 2097152 cache > > > > This is ~37% wasted space per memory section and it sumps up for the > > whole memory. On a x86_64 machine it is something like 6MB per 1GB of > > RAM. > > > > We can reduce the internal fragmentation by using alloc_pages_exact > > which allocates PAGE_SIZE aligned blocks so we will get down to <4kB > > wasted memory per section which is much better. > > > > We still need a fallback to vmalloc because we have no guarantees that > > we will have a continuous memory of that size (order-10) later on during > > the hotplug events. > > > > Signed-off-by: Michal Hocko > > CC: Dave Hansen > > CC: KAMEZAWA Hiroyuki > > Acked-by: KAMEZAWA Hiroyuki Thanks. I will repost it with Andrew in the CC. > > But...nitpick, it may be from my fault.. [...] > > +static void free_page_cgroup(void *addr) > > +{ > > + if (is_vmalloc_addr(addr)) { > > + vfree(addr); > > + } else { > > + struct page *page = virt_to_page(addr); > > + if (!PageReserved(page)) { /* Is bootmem ? */ > > I think we never see PageReserved if we just use alloc_pages_exact()/vmalloc(). I have checked that and we really do not (unless I am missing some subtle side effects). Anyway, I think we still should at least BUG_ON on that. > Maybe my old patch was not enough and this kind of junks are remaining in > the original code. Should I incorporate it into the patch. I think that a separate one would be better for readability. --- >>From e7a897a42b526620eb4afada2d036e1c9ff9e62a Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Mon, 28 Feb 2011 10:43:12 +0100 Subject: [PATCH] page_cgroup array is never stored on reserved pages KAMEZAWA Hiroyuki noted that free_pages_cgroup doesn't have to check for PageReserved because we never store the array on reserved pages (neither alloc_pages_exact nor vmalloc use those pages). So we can replace the check by a BUG_ON. Signed-off-by: Michal Hocko CC: KAMEZAWA Hiroyuki --- mm/page_cgroup.c | 8 ++++---- 1 files changed, 4 insertions(+), 4 deletions(-) diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index eae3cd2..dd5f789 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -125,10 +125,10 @@ static void free_page_cgroup(void *addr) vfree(addr); } else { struct page *page = virt_to_page(addr); - if (!PageReserved(page)) { /* Is bootmem ? */ - size_t table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION; - free_pages_exact(addr, table_size); - } + size_t table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION; + + BUG_ON(PageReserved(page)); + free_pages_exact(addr, table_size); } } -- 1.7.2.3 -- Michal Hocko SUSE Labs SUSE LINUX s.r.o. Lihovarska 1060/12 190 00 Praha 9 Czech Republic