From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752689AbYHRD5Q (ORCPT ); Sun, 17 Aug 2008 23:57:16 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751179AbYHRD5A (ORCPT ); Sun, 17 Aug 2008 23:57:00 -0400 Received: from casper.infradead.org ([85.118.1.10]:55416 "EHLO casper.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750947AbYHRD5A (ORCPT ); Sun, 17 Aug 2008 23:57:00 -0400 Date: Sun, 17 Aug 2008 20:56:43 -0700 From: Arjan van de Ven To: "Li, Shaohua" Cc: Ingo Molnar , lkml , "airlied@linux.ie" , Andrew Morton , Ingo Molnar , "Siddha, Suresh B" , "Pallipadi, Venkatesh" , Thomas Gleixner , "H. Peter Anvin" Subject: Re: [patch 2/2] reduce tlb/cache flush times of agpgart memory allocation Message-ID: <20080817205643.25deb89d@infradead.org> In-Reply-To: <76780B19A496DC4B80439008DAD7076C0CF9E0E1@PDSMSX501.ccr.corp.intel.com> References: <1217832690.21811.9.camel@sli10-desk.sh.intel.com> <20080815143131.GF12954@elte.hu> <20080815074033.4817f876@infradead.org> <76780B19A496DC4B80439008DAD7076C0CF9E0E1@PDSMSX501.ccr.corp.intel.com> Organization: Intel X-Mailer: Claws Mail 3.5.0 (GTK+ 2.12.11; i386-redhat-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-SRS-Rewrite: SMTP reverse-path rewritten from by casper.infradead.org See http://www.infradead.org/rpr.html Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, 18 Aug 2008 09:21:12 +0800 "Li, Shaohua" wrote: > > > > >it really needs something else instead; it needs airlied's array > >allocator > >otherwise you hit the second wall as well (the pat checks per page) > Somebody should have a measurement. In my test, the real bottleneck > is the cache flush. It appears flush cache page is slow if there are > a lot of pages, In my patch, I use a wbinvd. This can be optimized to > do wbinvd with a threshold. Maybe airlied can change his patch with > this way. it would be great if you had time to update his patch and this to it... and the logic probably should be "if there's more than X pags in the the array, just use wbinvd". Although wbinvd is very painful if you have 12Mb of cache and you wipe it for all cores in the system ;-( -- If you want to reach me at my work email, use arjan@linux.intel.com For development, discussion and tips for power savings, visit http://www.lesswatts.org