From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753029AbXDIVtE (ORCPT ); Mon, 9 Apr 2007 17:49:04 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753071AbXDIVsf (ORCPT ); Mon, 9 Apr 2007 17:48:35 -0400 Received: from ebiederm.dsl.xmission.com ([166.70.28.69]:37400 "EHLO ebiederm.dsl.xmission.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753415AbXDIVsb (ORCPT ); Mon, 9 Apr 2007 17:48:31 -0400 From: ebiederm@xmission.com (Eric W. Biederman) To: Andrew Morton Cc: Ravikiran G Thirumalai , linux-kernel@vger.kernel.org Subject: Re: [patch] Pad irq_desc to internode cacheline size References: <20070409195356.GA5275@localhost.localdomain> <20070409135729.a466e9cb.akpm@linux-foundation.org> Date: Mon, 09 Apr 2007 15:47:52 -0600 In-Reply-To: <20070409135729.a466e9cb.akpm@linux-foundation.org> (Andrew Morton's message of "Mon, 9 Apr 2007 13:57:29 -0700") Message-ID: User-Agent: Gnus/5.110006 (No Gnus v0.6) Emacs/21.4 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Andrew Morton writes: > This will consume nearly 4k per irq won't it? What is the upper bound > here, across all configs and all hardware? > > Is VSMP the only arch which has ____cacheline_internodealigned_in_smp > larger than ____cacheline_aligned_in_smp? Ugh. We set internode aligned to 4k for all of x86_64. I believe this ups our worst case memory consumption for the array from 1M to 32M. Although the low end might be 2M. I can't recall if an irq_desc takes one cache line or two after we have put the cpu masks in it. My gut feel says that what we want to do is delay this until we are dynamically allocating the array members. Then we can at least have the chance of allocating the memory on the proper NUMA node, and won't need the extra NUMA alignment. I'm not at all certain I'm impressed by an architecture that has 4K aligned cache lines. That seems terribly piggy. We might as well do distributed shared memory in software on a cluster... Eric