From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758889Ab2FULCf (ORCPT ); Thu, 21 Jun 2012 07:02:35 -0400 Received: from mx1.redhat.com ([209.132.183.28]:51320 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758399Ab2FULCc (ORCPT ); Thu, 21 Jun 2012 07:02:32 -0400 Date: Thu, 21 Jun 2012 13:00:55 +0200 From: Alexander Gordeev To: Suresh Siddha Cc: yinghai@kernel.org, linux-kernel@vger.kernel.org, x86@kernel.org, gorcunov@openvz.org, Ingo Molnar Subject: Re: [PATCH 1/2] x86, irq: update irq_cfg domain unless the new affinity is a subset of the current domain Message-ID: <20120621110055.GE2223@dhcp-26-207.brq.redhat.com> References: <1337643880.1997.166.camel@sbsiddha-desk.sc.intel.com> <1337644682-19854-1-git-send-email-suresh.b.siddha@intel.com> <20120606172017.GA4777@dhcp-26-207.brq.redhat.com> <1339806320.3475.68.camel@sbsiddha-desk.sc.intel.com> <20120618091740.GK3383@dhcp-26-207.brq.redhat.com> <1340151523.3696.27.camel@sbsiddha-desk.sc.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1340151523.3696.27.camel@sbsiddha-desk.sc.intel.com> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Jun 19, 2012 at 05:18:42PM -0700, Suresh Siddha wrote: > On Mon, 2012-06-18 at 17:51 -0700, Suresh Siddha wrote: > BTW, there is still one open that I would like to address. How to handle > the vector pressure during boot etc (as the default vector assignment > specifies all online cpus) when there are lot interrupt sources but > fewer x2apic clusters (like one or two socket server case). > > We should be able to do something like the appended. Any better > suggestions? I don't want to add boot parameters to limit the x2apic > cluster membership etc (to fewer than 16 logical cpu's) if possible. This cpu_online_mask approach should work IMO. Although it looks little bit hacky for me. May be we could start with default_vector_allocation_domain() and explicitly switch to cluster_vector_allocation_domain() once booted? As of boot parameters, I can think of multi-pass walk thru a cpumask to find a free cluster => core => sibling. In worst case I can imagine a vector space defragmentator. But nothing really small to avoid current code reshake. Also, how heavy the vector pressure actually is? -- Regards, Alexander Gordeev agordeev@redhat.com