From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933703AbXHLKVS (ORCPT ); Sun, 12 Aug 2007 06:21:18 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755298AbXHLKVK (ORCPT ); Sun, 12 Aug 2007 06:21:10 -0400 Received: from cantor2.suse.de ([195.135.220.15]:50152 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753336AbXHLKVH (ORCPT ); Sun, 12 Aug 2007 06:21:07 -0400 From: Andi Kleen To: Willy Tarreau Subject: Re: [2.6.20.16 review 08/28] x86_64: allocate sparsemem memmap above 4G Date: Sun, 12 Aug 2007 12:18:11 +0200 User-Agent: KMail/1.9.1 Cc: linux-kernel@vger.kernel.org, stable@kernel.org, Zou Nan hai , Suresh Siddha , Andrew Morton , Linus Torvalds , Chris Wright , Greg Kroah-Hartman References: <20070811184752.%N@1wt.eu> <20070811184837.%N@1wt.eu> In-Reply-To: <20070811184837.%N@1wt.eu> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200708121218.12411.ak@suse.de> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Saturday 11 August 2007 21:48, Willy Tarreau wrote: > On systems with huge amount of physical memory, VFS cache and memory memmap > may eat all available system memory under 4G, then the system may fail to > allocate swiotlb bounce buffer. > > There was a fix for this issue in arch/x86_64/mm/numa.c, but that fix dose > not cover sparsemem model. Have you checked if sparsemem even worked in 2.6.20? Irc it was quite unstable a couple of releases ago. There were times where it rarely booted on x86-64 because so few people test it. If not the patch is not needed, although relatively harmless too. -Andi