From mboxrd@z Thu Jan 1 00:00:00 1970 Received: with ECARTIS (v1.0.0; list linux-mips); Fri, 14 Sep 2012 01:05:20 +0200 (CEST) Received: from mail.linuxfoundation.org ([140.211.169.12]:34724 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by eddie.linux-mips.org with ESMTP id S1903384Ab2IMXFQ (ORCPT ); Fri, 14 Sep 2012 01:05:16 +0200 Received: from akpm.mtv.corp.google.com (216-239-45-4.google.com [216.239.45.4]) by mail.linuxfoundation.org (Postfix) with ESMTPSA id C8D9D9E3; Thu, 13 Sep 2012 23:05:07 +0000 (UTC) Date: Thu, 13 Sep 2012 16:05:06 -0700 From: Andrew Morton To: "Kirill A. Shutemov" Cc: linux-mm@kvack.org, Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , x86@kernel.org, Andi Kleen , Tim Chen , Alex Shi , Jan Beulich , Robert Richter , Andy Lutomirski , Andrea Arcangeli , Johannes Weiner , Hugh Dickins , KAMEZAWA Hiroyuki , Mel Gorman , linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, linux-mips@linux-mips.org, linux-sh@vger.kernel.org, sparclinux@vger.kernel.org Subject: Re: [PATCH v4 0/8] Avoid cache trashing on clearing huge/gigantic page Message-Id: <20120913160506.d394392a.akpm@linux-foundation.org> In-Reply-To: <1345470757-12005-1-git-send-email-kirill.shutemov@linux.intel.com> References: <1345470757-12005-1-git-send-email-kirill.shutemov@linux.intel.com> X-Mailer: Sylpheed 3.0.2 (GTK+ 2.20.1; x86_64-pc-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-archive-position: 34496 X-ecartis-version: Ecartis v1.0.0 Sender: linux-mips-bounce@linux-mips.org Errors-to: linux-mips-bounce@linux-mips.org X-original-sender: akpm@linux-foundation.org Precedence: bulk List-help: List-unsubscribe: List-software: Ecartis version 1.0.0 List-Id: linux-mips X-List-ID: linux-mips List-subscribe: List-owner: List-post: List-archive: X-list: linux-mips Return-Path: On Mon, 20 Aug 2012 16:52:29 +0300 "Kirill A. Shutemov" wrote: > Clearing a 2MB huge page will typically blow away several levels of CPU > caches. To avoid this only cache clear the 4K area around the fault > address and use a cache avoiding clears for the rest of the 2MB area. > > This patchset implements cache avoiding version of clear_page only for > x86. If an architecture wants to provide cache avoiding version of > clear_page it should to define ARCH_HAS_USER_NOCACHE to 1 and implement > clear_page_nocache() and clear_user_highpage_nocache(). Patchset looks nice to me, but the changelogs are terribly short of performance measurements. For this sort of change I do think it is important that pretty exhaustive testing be performed, and that the results (or a readable summary of them) be shown. And that testing should be designed to probe for slowdowns, not just the speedups! From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrew Morton Date: Thu, 13 Sep 2012 23:05:06 +0000 Subject: Re: [PATCH v4 0/8] Avoid cache trashing on clearing huge/gigantic page Message-Id: <20120913160506.d394392a.akpm@linux-foundation.org> List-Id: References: <1345470757-12005-1-git-send-email-kirill.shutemov@linux.intel.com> In-Reply-To: <1345470757-12005-1-git-send-email-kirill.shutemov@linux.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: "Kirill A. Shutemov" Cc: linux-mm@kvack.org, Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , x86@kernel.org, Andi Kleen , Tim Chen , Alex Shi , Jan Beulich , Robert Richter , Andy Lutomirski , Andrea Arcangeli , Johannes Weiner , Hugh Dickins , KAMEZAWA Hiroyuki , Mel Gorman , linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, linux-mips@linux-mips.org, linux-sh@vger.kernel.org, sparclinux@vger.kernel.org On Mon, 20 Aug 2012 16:52:29 +0300 "Kirill A. Shutemov" wrote: > Clearing a 2MB huge page will typically blow away several levels of CPU > caches. To avoid this only cache clear the 4K area around the fault > address and use a cache avoiding clears for the rest of the 2MB area. > > This patchset implements cache avoiding version of clear_page only for > x86. If an architecture wants to provide cache avoiding version of > clear_page it should to define ARCH_HAS_USER_NOCACHE to 1 and implement > clear_page_nocache() and clear_user_highpage_nocache(). Patchset looks nice to me, but the changelogs are terribly short of performance measurements. For this sort of change I do think it is important that pretty exhaustive testing be performed, and that the results (or a readable summary of them) be shown. And that testing should be designed to probe for slowdowns, not just the speedups! From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.linuxfoundation.org (mail.linuxfoundation.org [140.211.169.12]) by ozlabs.org (Postfix) with ESMTP id 206982C007D for ; Fri, 14 Sep 2012 09:05:09 +1000 (EST) Date: Thu, 13 Sep 2012 16:05:06 -0700 From: Andrew Morton To: "Kirill A. Shutemov" Subject: Re: [PATCH v4 0/8] Avoid cache trashing on clearing huge/gigantic page Message-Id: <20120913160506.d394392a.akpm@linux-foundation.org> In-Reply-To: <1345470757-12005-1-git-send-email-kirill.shutemov@linux.intel.com> References: <1345470757-12005-1-git-send-email-kirill.shutemov@linux.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Cc: Andrea Arcangeli , linux-mips@linux-mips.org, Andi Kleen , Alex Shi , Robert Richter , linuxppc-dev@lists.ozlabs.org, x86@kernel.org, Hugh Dickins , linux-kernel@vger.kernel.org, Jan Beulich , Andy Lutomirski , Johannes Weiner , linux-mm@kvack.org, linux-sh@vger.kernel.org, Ingo Molnar , Mel Gorman , "H. Peter Anvin" , sparclinux@vger.kernel.org, Thomas Gleixner , Tim Chen , KAMEZAWA Hiroyuki List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Mon, 20 Aug 2012 16:52:29 +0300 "Kirill A. Shutemov" wrote: > Clearing a 2MB huge page will typically blow away several levels of CPU > caches. To avoid this only cache clear the 4K area around the fault > address and use a cache avoiding clears for the rest of the 2MB area. > > This patchset implements cache avoiding version of clear_page only for > x86. If an architecture wants to provide cache avoiding version of > clear_page it should to define ARCH_HAS_USER_NOCACHE to 1 and implement > clear_page_nocache() and clear_user_highpage_nocache(). Patchset looks nice to me, but the changelogs are terribly short of performance measurements. For this sort of change I do think it is important that pretty exhaustive testing be performed, and that the results (or a readable summary of them) be shown. And that testing should be designed to probe for slowdowns, not just the speedups! From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from psmtp.com (na3sys010amx135.postini.com [74.125.245.135]) by kanga.kvack.org (Postfix) with SMTP id 5B7F46B0186 for ; Thu, 13 Sep 2012 19:05:09 -0400 (EDT) Date: Thu, 13 Sep 2012 16:05:06 -0700 From: Andrew Morton Subject: Re: [PATCH v4 0/8] Avoid cache trashing on clearing huge/gigantic page Message-Id: <20120913160506.d394392a.akpm@linux-foundation.org> In-Reply-To: <1345470757-12005-1-git-send-email-kirill.shutemov@linux.intel.com> References: <1345470757-12005-1-git-send-email-kirill.shutemov@linux.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-linux-mm@kvack.org List-ID: To: "Kirill A. Shutemov" Cc: linux-mm@kvack.org, Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , x86@kernel.org, Andi Kleen , Tim Chen , Alex Shi , Jan Beulich , Robert Richter , Andy Lutomirski , Andrea Arcangeli , Johannes Weiner , Hugh Dickins , KAMEZAWA Hiroyuki , Mel Gorman , linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, linux-mips@linux-mips.org, linux-sh@vger.kernel.org, sparclinux@vger.kernel.org On Mon, 20 Aug 2012 16:52:29 +0300 "Kirill A. Shutemov" wrote: > Clearing a 2MB huge page will typically blow away several levels of CPU > caches. To avoid this only cache clear the 4K area around the fault > address and use a cache avoiding clears for the rest of the 2MB area. > > This patchset implements cache avoiding version of clear_page only for > x86. If an architecture wants to provide cache avoiding version of > clear_page it should to define ARCH_HAS_USER_NOCACHE to 1 and implement > clear_page_nocache() and clear_user_highpage_nocache(). Patchset looks nice to me, but the changelogs are terribly short of performance measurements. For this sort of change I do think it is important that pretty exhaustive testing be performed, and that the results (or a readable summary of them) be shown. And that testing should be designed to probe for slowdowns, not just the speedups! -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org