Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755066AbZKWHcx (ORCPT ); Mon, 23 Nov 2009 02:32:53 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753173AbZKWHcw (ORCPT ); Mon, 23 Nov 2009 02:32:52 -0500 Received: from mail-pz0-f171.google.com ([209.85.222.171]:34444 "EHLO mail-pz0-f171.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753030AbZKWHcv convert rfc822-to-8bit (ORCPT ); Mon, 23 Nov 2009 02:32:51 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=VoIpT+/MxiUWbE8ts6VTAMHi2+OanM4O+QYEGXju7sjk/ihTqW398Ss3UBttNfVVwb tSmcF0btJh4Mi/yBFUPE0SdJpkhQRcta1wuiNpkfOzi8iRC6KG1Ub+CKCSn7kiTuMSVJ 9ReHFZFGgYdjKfiNfnnxbd9p45WB4LfkzYA74= MIME-Version: 1.0 In-Reply-To: <20091123064630.7385.30498.stgit@ppwaskie-hc2.jf.intel.com> References: <20091123064630.7385.30498.stgit@ppwaskie-hc2.jf.intel.com> Date: Mon, 23 Nov 2009 15:32:57 +0800 Message-ID: <2674af740911222332i65c0d066h79bf2c1ca1d5e4f0@mail.gmail.com> Subject: Re: [PATCH] irq: Add node_affinity CPU masks for smarter irqbalance hints From: Yong Zhang To: Peter P Waskiewicz Jr Cc: linux-kernel@vger.kernel.org, arjan@linux.jf.intel.com, davem@davemloft.net, netdev@vger.kernel.org Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1185 Lines: 28 On Mon, Nov 23, 2009 at 2:46 PM, Peter P Waskiewicz Jr wrote: > This patchset adds a new CPU mask for SMP systems to the irq_desc > struct.  It also exposes an API for underlying device drivers to > assist irqbalance in making smarter decisions when balancing, especially > in a NUMA environment.  For example, an ethernet driver with MSI-X may > wish to limit the CPUs that an interrupt can be balanced within to > stay on a single NUMA node.  Current irqbalance operation can move the > interrupt off the node, resulting in cross-node memory accesses and > locks. > > The API is a get/set API within the kernel, along with a /proc entry > for the interrupt. > > Signed-off-by: Peter P Waskiewicz Jr > --- 1) I think you should consider CONFIG_CPUMASK_OFFSTACK which will affect node_affinity. 2) It seems like this patch can't work with SPARSE_IRQ. Thanks, Yong -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/