From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754648Ab0AMC2I (ORCPT ); Tue, 12 Jan 2010 21:28:08 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752219Ab0AMC2H (ORCPT ); Tue, 12 Jan 2010 21:28:07 -0500 Received: from hera.kernel.org ([140.211.167.34]:40434 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752131Ab0AMC2F (ORCPT ); Tue, 12 Jan 2010 21:28:05 -0500 Message-ID: <4B4D2F49.6070509@kernel.org> Date: Tue, 12 Jan 2010 18:26:17 -0800 From: Yinghai Lu User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.5) Gecko/20091130 SUSE/3.0.0-1.1.1 Thunderbird/3.0 MIME-Version: 1.0 To: Suresh Siddha CC: Linus Torvalds , "ananth@in.ibm.com" , Ingo Molnar , Thomas Gleixner , "H. Peter Anvin" , Andrew Morton , "linux-kernel@vger.kernel.org" Subject: Re: [PATCH -v2 5/5] x86: use dmi check to treat disabled cpus as hotplug cpus. References: <1263338274-6485-1-git-send-email-yinghai@kernel.org> <1263338274-6485-5-git-send-email-yinghai@kernel.org> <1263340563.2854.1011.camel@sbs-t61.sc.intel.com> <4B4D0E39.10200@kernel.org> <1263347315.2854.1296.camel@sbs-t61.sc.intel.com> <4B4D2811.7000001@kernel.org> <1263348363.2854.1360.camel@sbs-t61.sc.intel.com> <4B4D2C44.2060709@kernel.org> <1263349268.2854.1386.camel@sbs-t61.sc.intel.com> In-Reply-To: <1263349268.2854.1386.camel@sbs-t61.sc.intel.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 01/12/2010 06:21 PM, Suresh Siddha wrote: > On Tue, 2010-01-12 at 18:13 -0800, Yinghai Lu wrote: >> On 01/12/2010 06:06 PM, Suresh Siddha wrote: >>> On Tue, 2010-01-12 at 17:55 -0800, Yinghai Lu wrote: >>>> you mean this blacklist could be too long? >>> >>> yes. >>> >>>> >>>> switch to whitelist for the box can treat disabled cpus as hotplug >>>> cpus? >>> >>> Do we really need all this? Systems which support physical hotplug >>> typically have lot's of cpu's (mostly will have atleast > 8). Even if we >>> really need to identify, then perhaps we can check if ACPI has any hints >>> regarding the physical hotplug support at boot time (we should check >>> with Andi Kleen or Len Brown on this). >>> >>> For now, I think we can keep it simple by using the detected enabled >>> cpu's. >> >> sth like this ? > > Well, I was referring more to the apic model selection than the prefill > case. About this possible cpu's, will the wastage be more than few kb > for few disabled cpu's. for 8 sockets systems if only have two cpus instatalled. that disabled cpus will be 6 * 8 * 2 = 96. and per_cpu area is about per cpu 2M, so will waste about 96 x 2M YH