From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S964972Ab1GOHyQ (ORCPT ); Fri, 15 Jul 2011 03:54:16 -0400 Received: from mga09.intel.com ([134.134.136.24]:55310 "EHLO mga09.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S964863Ab1GOHyQ (ORCPT ); Fri, 15 Jul 2011 03:54:16 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.65,534,1304319600"; d="scan'208";a="27976986" From: Andi Kleen To: Anton Blanchard Cc: dwg@au1.ibm.com, mel@csn.ul.ie, akpm@linux-foundation.org, hughd@google.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH 2/2] hugepage: Allow parallelization of the hugepage fault path References: <20110125143226.37532ea2@kryten> <20110125143414.1dbb150c@kryten> Date: Fri, 15 Jul 2011 00:52:38 -0700 In-Reply-To: <20110125143414.1dbb150c@kryten> (Anton Blanchard's message of "Tue, 25 Jan 2011 14:34:14 +1100") Message-ID: User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/23.2 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Anton Blanchard writes: > This patch improves the situation by replacing the single mutex with a > table of mutexes, selected based on a hash of the address_space and > file offset being faulted (or mm and virtual address for MAP_PRIVATE > mappings). It's unclear to me how this solves the original OOM problem. But then you can still have early oom over all the hugepages if they happen to hash to different pages, can't you? I think it would be better to move out the clearing out of the lock, and possibly take the lock only when the hugepages are about to go OOM. -Andi -- ak@linux.intel.com -- Speaking for myself only