From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756804AbcLOBoU (ORCPT ); Wed, 14 Dec 2016 20:44:20 -0500 Received: from layla.krisman.be ([176.31.208.35]:38461 "EHLO layla.krisman.be" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752925AbcLOBoT (ORCPT ); Wed, 14 Dec 2016 20:44:19 -0500 X-Greylist: delayed 2164 seconds by postgrey-1.27 at vger.kernel.org; Wed, 14 Dec 2016 20:44:18 EST From: Gabriel Krisman Bertazi To: "Guilherme G. Piccoli" Cc: tglx@linutronix.de, linux-kernel@vger.kernel.org, gabriel@krisman.be, hch@lst.de, linuxppc-dev@lists.ozlabs.org, linux-pci@vger.kernel.org Subject: Re: [PATCH] genirq/affinity: fix node generation from cpumask In-Reply-To: <1481738472-2671-1-git-send-email-gpiccoli@linux.vnet.ibm.com> (Guilherme G. Piccoli's message of "Wed, 14 Dec 2016 16:01:12 -0200") References: <1481738472-2671-1-git-send-email-gpiccoli@linux.vnet.ibm.com> User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/25.1 (gnu/linux) Date: Wed, 14 Dec 2016 23:05:51 -0200 Message-ID: <87oa0erogg.fsf@collabora.co.uk> MIME-Version: 1.0 Content-Type: text/plain Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org "Guilherme G. Piccoli" writes: > Commit 34c3d9819fda ("genirq/affinity: Provide smarter irq spreading > infrastructure") introduced a better IRQ spreading mechanism, taking > account of the available NUMA nodes in the machine. > > Problem is that the algorithm of retrieving the nodemask iterates > "linearly" based on the number of online nodes - some architectures > present non-linear node distribution among the nodemask, like PowerPC. > If this is the case, the algorithm lead to a wrong node count number > and therefore to a bad/incomplete IRQ affinity distribution. > > For example, this problem were found in a machine with 128 CPUs and two > nodes, namely nodes 0 and 8 (instead of 0 and 1, if it was linearly > distributed). This led to a wrong affinity distribution which then led to > a bad mq allocation for nvme driver. > > Finally, we take the opportunity to fix a comment regarding the affinity > distribution when we have _more_ nodes than vectors. Thanks for taking care of this so quickly, Guilherme. Reviewed-by: Gabriel Krisman Bertazi -- Gabriel Krisman Bertazi