From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ravikiran G Thirumalai Date: Mon, 17 Apr 2006 22:02:38 +0000 Subject: Re: [PATCH 00/05] robust per_cpu allocation for modules Message-Id: <20060417220238.GD3945@localhost.localdomain> List-Id: References: <1145049535.1336.128.camel@localhost.localdomain> <4440855A.7040203@yahoo.com.au> In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Christoph Lameter Cc: Nick Piggin , Steven Rostedt , LKML , Andrew Morton , Linus Torvalds , Ingo Molnar , Thomas Gleixner , Andi Kleen , Martin Mares , bjornw@axis.com, schwidefsky@de.ibm.com, benedict.gaster@superh.com, lethal@linux-sh.org, Chris Zankel , Marc Gauthier , Joe Taylor , David Mosberger-Tang , rth@twiddle.net, spyro@f2s.com, starvik@axis.com, tony.luck@intel.com, linux-ia64@vger.kernel.org, ralf@linux-mips.org, linux-mips@linux-mips.org, grundler@parisc-linux.org, parisc-linux@parisc-linux.org, linuxppc-dev@ozlabs.org, paulus@samba.org, linux390@de.ibm.com, davem@davemloft.net On Mon, Apr 17, 2006 at 09:55:02AM -0700, Christoph Lameter wrote: > On Sat, 15 Apr 2006, Nick Piggin wrote: > > > If I'm following you correctly, this adds another dependent load > > to a per-CPU data access, and from memory that isn't node-affine. > > I am also concerned about that. Kiran has a patch to avoid allocpercpu > having to go through one level of indirection that I guess would no > longer work with this scheme. The alloc_percpu reimplementation would work regardless of changes to static per-cpu areas. But, any extra indirection as was proposed initially is bad IMHO. > > > If so, I think people with SMP and NUMA kernels would care more > > about performance and scalability than the few k of memory this > > saves. > > Right. Me too :) Kiran From mboxrd@z Thu Jan 1 00:00:00 1970 Received: with ECARTIS (v1.0.0; list linux-mips); Mon, 17 Apr 2006 22:49:25 +0100 (BST) Received: from ns1.siteground.net ([207.218.208.2]:20355 "EHLO serv01.siteground.net") by ftp.linux-mips.org with ESMTP id S8133643AbWDQVtP (ORCPT ); Mon, 17 Apr 2006 22:49:15 +0100 Received: from adsl-69-227-37-145.dsl.pltn13.pacbell.net ([69.227.37.145] helo=localhost.localdomain) by serv01.siteground.net with esmtpa (Exim 4.52) id 1FVbmp-0008Rz-R8; Mon, 17 Apr 2006 17:01:36 -0500 Date: Mon, 17 Apr 2006 15:02:38 -0700 From: Ravikiran G Thirumalai To: Christoph Lameter Cc: Nick Piggin , Steven Rostedt , LKML , Andrew Morton , Linus Torvalds , Ingo Molnar , Thomas Gleixner , Andi Kleen , Martin Mares , bjornw@axis.com, schwidefsky@de.ibm.com, benedict.gaster@superh.com, lethal@linux-sh.org, Chris Zankel , Marc Gauthier , Joe Taylor , David Mosberger-Tang , rth@twiddle.net, spyro@f2s.com, starvik@axis.com, tony.luck@intel.com, linux-ia64@vger.kernel.org, ralf@linux-mips.org, linux-mips@linux-mips.org, grundler@parisc-linux.org, parisc-linux@parisc-linux.org, linuxppc-dev@ozlabs.org, paulus@samba.org, linux390@de.ibm.com, davem@davemloft.net Subject: Re: [PATCH 00/05] robust per_cpu allocation for modules Message-ID: <20060417220238.GD3945@localhost.localdomain> References: <1145049535.1336.128.camel@localhost.localdomain> <4440855A.7040203@yahoo.com.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.4.2.1i X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - serv01.siteground.net X-AntiAbuse: Original Domain - linux-mips.org X-AntiAbuse: Originator/Caller UID/GID - [0 0] / [47 12] X-AntiAbuse: Sender Address Domain - scalex86.org X-Source: X-Source-Args: X-Source-Dir: Return-Path: X-Envelope-To: <"|/home/ecartis/ecartis -s linux-mips"> (uid 0) X-Orcpt: rfc822;linux-mips@linux-mips.org Original-Recipient: rfc822;linux-mips@linux-mips.org X-archive-position: 11146 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: kiran@scalex86.org Precedence: bulk X-list: linux-mips On Mon, Apr 17, 2006 at 09:55:02AM -0700, Christoph Lameter wrote: > On Sat, 15 Apr 2006, Nick Piggin wrote: > > > If I'm following you correctly, this adds another dependent load > > to a per-CPU data access, and from memory that isn't node-affine. > > I am also concerned about that. Kiran has a patch to avoid allocpercpu > having to go through one level of indirection that I guess would no > longer work with this scheme. The alloc_percpu reimplementation would work regardless of changes to static per-cpu areas. But, any extra indirection as was proposed initially is bad IMHO. > > > If so, I think people with SMP and NUMA kernels would care more > > about performance and scalability than the few k of memory this > > saves. > > Right. Me too :) Kiran From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from serv01.siteground.net (ns1.siteground.net [207.218.208.2]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTP id 9C94C679F0 for ; Tue, 18 Apr 2006 08:01:42 +1000 (EST) Date: Mon, 17 Apr 2006 15:02:38 -0700 From: Ravikiran G Thirumalai To: Christoph Lameter Subject: Re: [PATCH 00/05] robust per_cpu allocation for modules Message-ID: <20060417220238.GD3945@localhost.localdomain> References: <1145049535.1336.128.camel@localhost.localdomain> <4440855A.7040203@yahoo.com.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: Cc: Andrew Morton , linux-mips@linux-mips.org, David Mosberger-Tang , linux-ia64@vger.kernel.org, Martin Mares , spyro@f2s.com, Joe Taylor , Andi Kleen , linuxppc-dev@ozlabs.org, paulus@samba.org, benedict.gaster@superh.com, bjornw@axis.com, Ingo Molnar , Nick Piggin , grundler@parisc-linux.org, Steven Rostedt , starvik@axis.com, Linus Torvalds , Thomas Gleixner , rth@twiddle.net, Chris Zankel , tony.luck@intel.com, LKML , ralf@linux-mips.org, Marc Gauthier , lethal@linux-sh.org, schwidefsky@de.ibm.com, linux390@de.ibm.com, davem@davemloft.net, parisc-linux@parisc-linux.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Mon, Apr 17, 2006 at 09:55:02AM -0700, Christoph Lameter wrote: > On Sat, 15 Apr 2006, Nick Piggin wrote: > > > If I'm following you correctly, this adds another dependent load > > to a per-CPU data access, and from memory that isn't node-affine. > > I am also concerned about that. Kiran has a patch to avoid allocpercpu > having to go through one level of indirection that I guess would no > longer work with this scheme. The alloc_percpu reimplementation would work regardless of changes to static per-cpu areas. But, any extra indirection as was proposed initially is bad IMHO. > > > If so, I think people with SMP and NUMA kernels would care more > > about performance and scalability than the few k of memory this > > saves. > > Right. Me too :) Kiran