From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from psmtp.com (na3sys010amx147.postini.com [74.125.245.147]) by kanga.kvack.org (Postfix) with SMTP id 745F76B0005 for ; Sun, 24 Feb 2013 20:36:02 -0500 (EST) Received: by mail-pb0-f52.google.com with SMTP id ma3so1369997pbc.39 for ; Sun, 24 Feb 2013 17:36:01 -0800 (PST) Message-ID: <512ABFF7.9090207@gmail.com> Date: Mon, 25 Feb 2013 09:35:51 +0800 From: Will Huck MIME-Version: 1.0 Subject: Re: [Bug fix PATCH 1/2] acpi, movablemem_map: Exclude memblock.reserved ranges when parsing SRAT. References: <1361358056-1793-1-git-send-email-tangchen@cn.fujitsu.com> <1361358056-1793-2-git-send-email-tangchen@cn.fujitsu.com> <5124C22B.8030401@cn.fujitsu.com> <5124C32E.1080902@gmail.com> <3908561D78D1C84285E8C5FCA982C28F1E06B55D@ORSMSX108.amr.corp.intel.com> In-Reply-To: <3908561D78D1C84285E8C5FCA982C28F1E06B55D@ORSMSX108.amr.corp.intel.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: owner-linux-mm@kvack.org List-ID: To: "Luck, Tony" Cc: Tang Chen , "akpm@linux-foundation.org" , "jiang.liu@huawei.com" , "wujianguo@huawei.com" , "hpa@zytor.com" , "wency@cn.fujitsu.com" , "laijs@cn.fujitsu.com" , "linfeng@cn.fujitsu.com" , "yinghai@kernel.org" , "isimatu.yasuaki@jp.fujitsu.com" , "rob@landley.net" , "kosaki.motohiro@jp.fujitsu.com" , "minchan.kim@gmail.com" , "mgorman@suse.de" , "rientjes@google.com" , "guz.fnst@cn.fujitsu.com" , "rusty@rustcorp.com.au" , "lliubbo@gmail.com" , "jaegeuk.hanse@gmail.com" , "glommer@parallels.com" , "linux-kernel@vger.kernel.org" , "linux-mm@kvack.org" On 02/21/2013 06:41 AM, Luck, Tony wrote: >> What's the relationship between e820 map and SRAT? > The e820 map (or EFI memory map on some recent systems) provides > a list of memory ranges together with usage information (e.g. reserved > for BIOS, or available) and attributes (WB cacheable, uncacheable). > > The SRAT table provides topology information for address ranges. It > tells the OS which memory is close to each cpu, and which is more > distant. If there are multiple degrees of "distant" then the SLIT table > provides a matrix of relative latencies between nodes. What's the meaning of multiple degrees of "distant" here? Eg, there are ten nodes, can SRAT tell each node which memory on other node is more close or distant? If the answer is yes, why need SLIT since processes can use memory close to their nodes. SRAT and SLIT are get from firmware or UEFI? > > -Tony -- 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